diff --git a/diloco_state/anchor/adapter_config.json b/diloco_state/anchor/adapter_config.json index 9a29a2efa1c03d4d7d26ad2e365e1e24e83847f0..22f55eae397ab7782497ba3373feeaaac4a55d26 100644 --- a/diloco_state/anchor/adapter_config.json +++ b/diloco_state/anchor/adapter_config.json @@ -19,28 +19,30 @@ "lora_alpha": 64, "lora_bias": false, "lora_dropout": 0.05, + "lora_ga_config": null, "megatron_config": null, "megatron_core": "megatron.core", "modules_to_save": null, "peft_type": "LORA", - "peft_version": "0.18.1", + "peft_version": "0.19.1", "qalora_group_size": 16, "r": 32, "rank_pattern": {}, "revision": null, "target_modules": [ - "out_proj", "x_proj", - "o_proj", - "dt_proj", - "q_proj", "k_proj", + "q_proj", + "v_proj", "in_proj", - "v_proj" + "out_proj", + "dt_proj", + "o_proj" ], "target_parameters": null, "task_type": "CAUSAL_LM", "trainable_token_indices": null, + "use_bdlora": null, "use_dora": false, "use_qalora": false, "use_rslora": false diff --git a/diloco_state/anchor/adapter_model.safetensors b/diloco_state/anchor/adapter_model.safetensors index 75246c02f6b07f43059ad6e3f1e1d1e950e37d7f..c60135d75ec9e0ed13aa3b7fe94f223f838f524d 100644 --- a/diloco_state/anchor/adapter_model.safetensors +++ b/diloco_state/anchor/adapter_model.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:1c64962ca0ef34f3ac44a8e56045b0aa04c1b6e45689df221dca2994d268dde8 -size 1557071872 +oid sha256:c6203f410af11ab49298ec6ee04e05e024a713e8777d69314d1918f25dc12f4c +size 1557071904 diff --git a/diloco_state/anchor/anchor_metadata.json b/diloco_state/anchor/anchor_metadata.json new file mode 100644 index 0000000000000000000000000000000000000000..01d54963d3268e2b1f85867545b91dc3b21ad373 --- /dev/null +++ b/diloco_state/anchor/anchor_metadata.json @@ -0,0 +1,17 @@ +{ + "promoted_at": "2026-05-15T11:24:25+00:00", + "repo_id": "WeirdRunner/Ouroboros", + "source_revision": "374a9a32d81242224465b786d62aaef7564639e6", + "source_checkpoint": "runs/azure_h100_dgac/stage_10/checkpoint-0001154", + "source_local_checkpoint": null, + "anchor_prefix": "diloco_state/anchor", + "terminal_stage": 10, + "total_train_samples": 36906, + "mark_dgac_complete": true, + "reason": "Promoted completed Azure DGAC checkpoint to canonical DiLoCo anchor.", + "copied_files": { + "runs/azure_h100_dgac/stage_10/checkpoint-0001154/adapter_model/adapter_model.safetensors": "diloco_state/anchor/adapter_model.safetensors", + "runs/azure_h100_dgac/stage_10/checkpoint-0001154/adapter_model/adapter_config.json": "diloco_state/anchor/adapter_config.json", + "runs/azure_h100_dgac/stage_10/checkpoint-0001154/halt_gate.pt": "diloco_state/anchor/halt_gate.pt" + } +} diff --git a/diloco_state/anchor/halt_gate.pt b/diloco_state/anchor/halt_gate.pt index 279109f60f3191e945095dfe061035be9211a393..e3634afe97f356bf2133443fc6f977d96c625070 100644 --- a/diloco_state/anchor/halt_gate.pt +++ b/diloco_state/anchor/halt_gate.pt @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:01e3378d2f77774333576a19b81e44407e1efc6bb921c2d881dca1cf820ce3c6 -size 22453 +oid sha256:44c45b99de75bb995d1366ff90ecc8e39d87030391dd52e078d66a5ff5f92db7 +size 22052 diff --git a/diloco_state/locks/mac_dgac_fallback.json b/diloco_state/locks/mac_dgac_fallback.json deleted file mode 100644 index 37c95ae932b686162547017381091871859acaaa..0000000000000000000000000000000000000000 --- a/diloco_state/locks/mac_dgac_fallback.json +++ /dev/null @@ -1,23 +0,0 @@ -{ - "claim_id": "mac-dgac-5a1adde2cf3e", - "status": "failed", - "created_at": 1778737191.287617, - "updated_at": 1778738089.145686, - "expires_at": 1778845191.287617, - "host": "Earningss-Mac-mini.local", - "pid": 3776, - "worker_ids": [ - "A" - ], - "expected_stage_k": 10, - "expected_round_n": 3, - "expected_mode": "waiting", - "expected_total_samples_seen": 23481, - "expected_projected_shards": { - "A": 4475, - "B": 4475, - "C": 4475 - }, - "failure": "Local Mac fallback cancelled by user on 2026-05-14 after detached screen run was interrupted.", - "failed_at": 1778738089.145686 -} \ No newline at end of file diff --git a/diloco_state/round_state.json b/diloco_state/round_state.json index f277136b41ec8eee87be1bfb4c2da011f71cd41e..e7e08462875710602bd932db486cee1e0f6a3728 100644 --- a/diloco_state/round_state.json +++ b/diloco_state/round_state.json @@ -1,21 +1,13 @@ { "stage_k": 10, - "round_n": 3, - "mode": "waiting", + "round_n": 0, + "mode": "dgac-complete", "triggered_workers": [], - "attendance_workers": [ - "A", - "B", - "C" - ], - "projected_shards": { - "A": 4475, - "B": 4475, - "C": 4475 - }, + "attendance_workers": [], + "projected_shards": {}, "anchor_path": "diloco_state/anchor", "total_samples_seen": { - "10": 23481 + "10": 36906 }, "completed_stages": [ 0, @@ -30,21 +22,23 @@ 9, 10 ], - "dgac_manual_gate": false, + "dgac_manual_gate": true, "dgac_diloco": true, "pre_dgac_total_samples_seen": { "10": 36906 }, - "last_updated": 1778738089.145686, - "triggered_at": 1778735042.370384, - "last_round_workers": [ - "B" - ], - "last_round_samples": 6713, + "last_updated": 1778844265.5883918, + "triggered_at": 0.0, + "last_round_workers": [], + "last_round_samples": 36906, "seed": 42, "dispatch_failures": [], "mac_dgac_claim_id": "mac-dgac-5a1adde2cf3e", "mac_dgac_claimed_at": 1778735042.370384, "mac_dgac_failed_at": 1778738089.145686, - "mac_dgac_failure": "Local Mac fallback cancelled by user on 2026-05-14 after detached screen run was interrupted." -} \ No newline at end of file + "mac_dgac_failure": "Local Mac fallback cancelled by user on 2026-05-14 after detached screen run was interrupted.", + "dgac_round_n": 0, + "dgac_round_label": "DGAC dedicated round 000", + "next_dgac_round_n": 4, + "dgac_diloco_complete": true +} diff --git a/diloco_state/workers/A/round_0000_stage_10/adapter_config.json b/diloco_state/workers/A/round_0000_stage_10/adapter_config.json deleted file mode 100644 index 45a575d4bf16877bf09b39781376fe2597e5e27c..0000000000000000000000000000000000000000 --- a/diloco_state/workers/A/round_0000_stage_10/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "k_proj", - "o_proj", - "dt_proj", - "in_proj", - "q_proj", - "out_proj", - "x_proj", - "v_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/A/round_0000_stage_10/adapter_model.safetensors b/diloco_state/workers/A/round_0000_stage_10/adapter_model.safetensors deleted file mode 100644 index 3b02c44dc2d282075fe701f0a0444ab07294fe6f..0000000000000000000000000000000000000000 --- a/diloco_state/workers/A/round_0000_stage_10/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:a55ffb7a82b803ce4af0b9888ad9cb25b34014c5c0693f926825da9e483894ad -size 1557071904 diff --git a/diloco_state/workers/A/round_0000_stage_10/halt_gate.pt b/diloco_state/workers/A/round_0000_stage_10/halt_gate.pt deleted file mode 100644 index 25ce49203855f589824d9e31aa70405da8567574..0000000000000000000000000000000000000000 --- a/diloco_state/workers/A/round_0000_stage_10/halt_gate.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:b83448737e8031936d06797e21b7ae946e23d2a686e95a36b3d438077c620eae -size 22453 diff --git a/diloco_state/workers/A/round_0000_stage_2/adapter_config.json b/diloco_state/workers/A/round_0000_stage_2/adapter_config.json deleted file mode 100644 index 1741adf785bab3138f26e0cf8741026c1e858f4e..0000000000000000000000000000000000000000 --- a/diloco_state/workers/A/round_0000_stage_2/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "v_proj", - "x_proj", - "out_proj", - "dt_proj", - "o_proj", - "in_proj", - "q_proj", - "k_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/A/round_0000_stage_2/adapter_model.safetensors b/diloco_state/workers/A/round_0000_stage_2/adapter_model.safetensors deleted file mode 100644 index 31c49fdd240aeb7bf0c1becc797bfb63a58aebc7..0000000000000000000000000000000000000000 --- a/diloco_state/workers/A/round_0000_stage_2/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8c5904c6ff8242d05dad345b8e369fb40744b358a7c0b293f67d0895a64c4bfa -size 1557071904 diff --git a/diloco_state/workers/A/round_0000_stage_3/adapter_config.json b/diloco_state/workers/A/round_0000_stage_3/adapter_config.json deleted file mode 100644 index 3d4d2fcaecba4e018ba21f0e4dc9fcdd2c2d0ad7..0000000000000000000000000000000000000000 --- a/diloco_state/workers/A/round_0000_stage_3/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "x_proj", - "in_proj", - "q_proj", - "o_proj", - "dt_proj", - "v_proj", - "k_proj", - "out_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/A/round_0000_stage_3/adapter_model.safetensors b/diloco_state/workers/A/round_0000_stage_3/adapter_model.safetensors deleted file mode 100644 index fa0229fffdc9a6ccab55fce9294196716bac9167..0000000000000000000000000000000000000000 --- a/diloco_state/workers/A/round_0000_stage_3/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:239f3a146c4cf69353939bf554b87fb44930ec14d1b5527cadc6cf7ba5a2d1e5 -size 1557071904 diff --git a/diloco_state/workers/A/round_0000_stage_4/adapter_config.json b/diloco_state/workers/A/round_0000_stage_4/adapter_config.json deleted file mode 100644 index a1aad56b45f111c8371c422eb953d452eb31d78a..0000000000000000000000000000000000000000 --- a/diloco_state/workers/A/round_0000_stage_4/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "out_proj", - "o_proj", - "dt_proj", - "k_proj", - "q_proj", - "v_proj", - "x_proj", - "in_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/A/round_0000_stage_4/adapter_model.safetensors b/diloco_state/workers/A/round_0000_stage_4/adapter_model.safetensors deleted file mode 100644 index 834fc6fab967ee21df4af14c0943dd37392037e0..0000000000000000000000000000000000000000 --- a/diloco_state/workers/A/round_0000_stage_4/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:472ef610908129083609d87f02989fdc312d0732c790e729884aa6a09a081455 -size 1557071904 diff --git a/diloco_state/workers/A/round_0000_stage_5/adapter_config.json b/diloco_state/workers/A/round_0000_stage_5/adapter_config.json deleted file mode 100644 index 9288da7a9f4c051f385b95b04ae45777ad37db65..0000000000000000000000000000000000000000 --- a/diloco_state/workers/A/round_0000_stage_5/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "dt_proj", - "v_proj", - "out_proj", - "q_proj", - "o_proj", - "k_proj", - "in_proj", - "x_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/A/round_0000_stage_5/adapter_model.safetensors b/diloco_state/workers/A/round_0000_stage_5/adapter_model.safetensors deleted file mode 100644 index a3507f6ea2332b5a0b5e643ef17099b15db7c3a9..0000000000000000000000000000000000000000 --- a/diloco_state/workers/A/round_0000_stage_5/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:071ac904a94bc390ee479b9a52886efc44b31f1cf48517debbceacd0e98d9a8c -size 1557071904 diff --git a/diloco_state/workers/A/round_0000_stage_6/adapter_config.json b/diloco_state/workers/A/round_0000_stage_6/adapter_config.json deleted file mode 100644 index 7baff54a814907aded12da9eebe20a32afeb497d..0000000000000000000000000000000000000000 --- a/diloco_state/workers/A/round_0000_stage_6/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "out_proj", - "x_proj", - "o_proj", - "dt_proj", - "k_proj", - "q_proj", - "in_proj", - "v_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/A/round_0000_stage_6/adapter_model.safetensors b/diloco_state/workers/A/round_0000_stage_6/adapter_model.safetensors deleted file mode 100644 index 98fe2279f31513802a6a5dd327a60b26c7189328..0000000000000000000000000000000000000000 --- a/diloco_state/workers/A/round_0000_stage_6/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:611e3b4bd07f6847d366ab84447f2dcea746700feb473c6bb564c122c41ffc2c -size 1557071904 diff --git a/diloco_state/workers/A/round_0000_stage_7/adapter_config.json b/diloco_state/workers/A/round_0000_stage_7/adapter_config.json deleted file mode 100644 index 6a947a2fb4be73e03f523e9a0eae4b9ebf703912..0000000000000000000000000000000000000000 --- a/diloco_state/workers/A/round_0000_stage_7/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "k_proj", - "dt_proj", - "v_proj", - "o_proj", - "q_proj", - "out_proj", - "x_proj", - "in_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/A/round_0000_stage_7/adapter_model.safetensors b/diloco_state/workers/A/round_0000_stage_7/adapter_model.safetensors deleted file mode 100644 index 5257db45631e8ed1fda5dcc72894669ecd8915fe..0000000000000000000000000000000000000000 --- a/diloco_state/workers/A/round_0000_stage_7/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6737d9ebf2dba30b38c3962cf50f0e92cd9cbf37dd1a7e4ab7384da732251f07 -size 1557071904 diff --git a/diloco_state/workers/A/round_0000_stage_8/adapter_config.json b/diloco_state/workers/A/round_0000_stage_8/adapter_config.json deleted file mode 100644 index 11dad7a33aa9dbdd8b2ccca220408ce5721f8faf..0000000000000000000000000000000000000000 --- a/diloco_state/workers/A/round_0000_stage_8/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "x_proj", - "o_proj", - "dt_proj", - "k_proj", - "in_proj", - "v_proj", - "out_proj", - "q_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/A/round_0000_stage_8/adapter_model.safetensors b/diloco_state/workers/A/round_0000_stage_8/adapter_model.safetensors deleted file mode 100644 index 5e1d2062ac7abd86400c1e5c89f8fbdda5412712..0000000000000000000000000000000000000000 --- a/diloco_state/workers/A/round_0000_stage_8/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:ac8806330f02330231849cee989aeef8b3a20731a9449c7efb12b631df398cea -size 1557071904 diff --git a/diloco_state/workers/A/round_0000_stage_9/adapter_config.json b/diloco_state/workers/A/round_0000_stage_9/adapter_config.json deleted file mode 100644 index e3998c195108a849583c6b1716f1155c6d3126c4..0000000000000000000000000000000000000000 --- a/diloco_state/workers/A/round_0000_stage_9/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "q_proj", - "out_proj", - "o_proj", - "v_proj", - "k_proj", - "in_proj", - "x_proj", - "dt_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/A/round_0000_stage_9/adapter_model.safetensors b/diloco_state/workers/A/round_0000_stage_9/adapter_model.safetensors deleted file mode 100644 index 952802f9ab0917a36319f2e211908dea5ac3550b..0000000000000000000000000000000000000000 --- a/diloco_state/workers/A/round_0000_stage_9/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:393ccc96c77a4a07a3becac504085669c967b640fe30443b34520160f7845175 -size 1557071904 diff --git a/diloco_state/workers/A/round_0001_stage_10/adapter_config.json b/diloco_state/workers/A/round_0001_stage_10/adapter_config.json deleted file mode 100644 index bbbe4633de518b4ae920eaa102f474cf519ed868..0000000000000000000000000000000000000000 --- a/diloco_state/workers/A/round_0001_stage_10/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "dt_proj", - "q_proj", - "out_proj", - "v_proj", - "o_proj", - "x_proj", - "k_proj", - "in_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/A/round_0001_stage_10/adapter_model.safetensors b/diloco_state/workers/A/round_0001_stage_10/adapter_model.safetensors deleted file mode 100644 index 7c0fd4dc6e153ad825590d160f880f52203658cc..0000000000000000000000000000000000000000 --- a/diloco_state/workers/A/round_0001_stage_10/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8de76ed9b30e5a6083ddb03e241b66719d62d213fb8a452978bd5a117ce20e43 -size 1557071904 diff --git a/diloco_state/workers/A/round_0001_stage_10/halt_gate.pt b/diloco_state/workers/A/round_0001_stage_10/halt_gate.pt deleted file mode 100644 index 733deb6505a77da6bec5f4371398c0f66634a8bd..0000000000000000000000000000000000000000 --- a/diloco_state/workers/A/round_0001_stage_10/halt_gate.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:39271bb538a5829fad8846f0e9f1fc7bc147dc5467d41b0405e41819e8f3ab20 -size 22453 diff --git a/diloco_state/workers/A/round_0001_stage_2/adapter_config.json b/diloco_state/workers/A/round_0001_stage_2/adapter_config.json deleted file mode 100644 index fe3776ec63af4864218802d39e81817003e72b08..0000000000000000000000000000000000000000 --- a/diloco_state/workers/A/round_0001_stage_2/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "in_proj", - "x_proj", - "out_proj", - "v_proj", - "k_proj", - "dt_proj", - "o_proj", - "q_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/A/round_0001_stage_2/adapter_model.safetensors b/diloco_state/workers/A/round_0001_stage_2/adapter_model.safetensors deleted file mode 100644 index f3589721a97575adebbae809f67a7d8511e219dd..0000000000000000000000000000000000000000 --- a/diloco_state/workers/A/round_0001_stage_2/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:bc55293414930eb58c040a6c076d86ecc4b11c55a98988e95a8a046325f29b02 -size 1557071904 diff --git a/diloco_state/workers/A/round_0001_stage_3/adapter_config.json b/diloco_state/workers/A/round_0001_stage_3/adapter_config.json deleted file mode 100644 index dd9f566b4df8caff0de63d41d14cd65d2cbc06a1..0000000000000000000000000000000000000000 --- a/diloco_state/workers/A/round_0001_stage_3/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "k_proj", - "o_proj", - "dt_proj", - "q_proj", - "x_proj", - "out_proj", - "v_proj", - "in_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/A/round_0001_stage_3/adapter_model.safetensors b/diloco_state/workers/A/round_0001_stage_3/adapter_model.safetensors deleted file mode 100644 index 77b425589cbe56c8eb72efd5e791daaa121e6287..0000000000000000000000000000000000000000 --- a/diloco_state/workers/A/round_0001_stage_3/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:87a62908ae39f9665653b2b934f1a0fdb6ad03d94a732cffd9a4cc0415c3d0c8 -size 1557071904 diff --git a/diloco_state/workers/A/round_0001_stage_8/adapter_config.json b/diloco_state/workers/A/round_0001_stage_8/adapter_config.json deleted file mode 100644 index a37b64698ad67b9000a24ee5e4166a967d2ef9fe..0000000000000000000000000000000000000000 --- a/diloco_state/workers/A/round_0001_stage_8/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "v_proj", - "in_proj", - "x_proj", - "out_proj", - "k_proj", - "o_proj", - "q_proj", - "dt_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/A/round_0001_stage_8/adapter_model.safetensors b/diloco_state/workers/A/round_0001_stage_8/adapter_model.safetensors deleted file mode 100644 index 345206acc786c42bcfae5f1b276a5b6ae119e6a9..0000000000000000000000000000000000000000 --- a/diloco_state/workers/A/round_0001_stage_8/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:48dbee134d0629ee682c34c567192adb4a6ece32999756ff04ed49f84591102a -size 1557071904 diff --git a/diloco_state/workers/A/round_0001_stage_9/adapter_config.json b/diloco_state/workers/A/round_0001_stage_9/adapter_config.json deleted file mode 100644 index 6ae1b9b9400a445e82a87cf582c610818142fe51..0000000000000000000000000000000000000000 --- a/diloco_state/workers/A/round_0001_stage_9/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "o_proj", - "x_proj", - "out_proj", - "in_proj", - "q_proj", - "v_proj", - "dt_proj", - "k_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/A/round_0001_stage_9/adapter_model.safetensors b/diloco_state/workers/A/round_0001_stage_9/adapter_model.safetensors deleted file mode 100644 index ae52007c4b7c0ddf0c2f1f9a5b0b3cb46166d65e..0000000000000000000000000000000000000000 --- a/diloco_state/workers/A/round_0001_stage_9/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:930077cd63eb849d581016e07be1e5b12fafff06c7b5d76eb675ee703da76786 -size 1557071904 diff --git a/diloco_state/workers/A/round_0002_stage_10/adapter_config.json b/diloco_state/workers/A/round_0002_stage_10/adapter_config.json deleted file mode 100644 index afe04d3e39be4d9084fb03aa2e04e61f827e160c..0000000000000000000000000000000000000000 --- a/diloco_state/workers/A/round_0002_stage_10/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "dt_proj", - "q_proj", - "v_proj", - "out_proj", - "o_proj", - "in_proj", - "x_proj", - "k_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/A/round_0002_stage_10/adapter_model.safetensors b/diloco_state/workers/A/round_0002_stage_10/adapter_model.safetensors deleted file mode 100644 index 60603b63e528a0f8cb2779dfd4c8f90f3dd33b85..0000000000000000000000000000000000000000 --- a/diloco_state/workers/A/round_0002_stage_10/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:23b66c40ab1d63e82dbc406e97b5e4fd3e9d11caf9583f3c746a4e8ea140f562 -size 1557071904 diff --git a/diloco_state/workers/A/round_0002_stage_2/adapter_config.json b/diloco_state/workers/A/round_0002_stage_2/adapter_config.json deleted file mode 100644 index a31ec18fdf80ea7e11cf50ae2edbfc9ab2c34ca5..0000000000000000000000000000000000000000 --- a/diloco_state/workers/A/round_0002_stage_2/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "v_proj", - "x_proj", - "dt_proj", - "o_proj", - "in_proj", - "k_proj", - "q_proj", - "out_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/A/round_0002_stage_2/adapter_model.safetensors b/diloco_state/workers/A/round_0002_stage_2/adapter_model.safetensors deleted file mode 100644 index 6a47eb23a2fbd5f5e192658dbc96033e04daa578..0000000000000000000000000000000000000000 --- a/diloco_state/workers/A/round_0002_stage_2/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:7d5fb9571dcff60945ef0ac2309fcd742bfbc7789cb323284bc55579e016fb64 -size 1557071904 diff --git a/diloco_state/workers/A/round_0002_stage_8/adapter_config.json b/diloco_state/workers/A/round_0002_stage_8/adapter_config.json deleted file mode 100644 index dd56fe813dce0fbc9733e27b04b0b040914320aa..0000000000000000000000000000000000000000 --- a/diloco_state/workers/A/round_0002_stage_8/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "o_proj", - "q_proj", - "dt_proj", - "v_proj", - "x_proj", - "k_proj", - "out_proj", - "in_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/A/round_0002_stage_8/adapter_model.safetensors b/diloco_state/workers/A/round_0002_stage_8/adapter_model.safetensors deleted file mode 100644 index 8c72ac9e84dac877a0b3b77171005548e6bee350..0000000000000000000000000000000000000000 --- a/diloco_state/workers/A/round_0002_stage_8/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:73e17c7979d7e147306a29dbb857d896fe79fb42fad42b8a9c3c7f631904b44d -size 1557071904 diff --git a/diloco_state/workers/A/round_0003_stage_2/adapter_config.json b/diloco_state/workers/A/round_0003_stage_2/adapter_config.json deleted file mode 100644 index 7c41bdbbe629d928da32801595cfd4f6f8d5342b..0000000000000000000000000000000000000000 --- a/diloco_state/workers/A/round_0003_stage_2/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "o_proj", - "out_proj", - "k_proj", - "v_proj", - "x_proj", - "q_proj", - "dt_proj", - "in_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/A/round_0003_stage_2/adapter_model.safetensors b/diloco_state/workers/A/round_0003_stage_2/adapter_model.safetensors deleted file mode 100644 index cf85724f978ad7e14a722a46ae016c84355a2e66..0000000000000000000000000000000000000000 --- a/diloco_state/workers/A/round_0003_stage_2/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:c2e9ffdaff42d50ee191862b860b9b5d0bbda8b583ef2b651ace06aeddc0f466 -size 1557071904 diff --git a/diloco_state/workers/A/round_0004_stage_2/adapter_config.json b/diloco_state/workers/A/round_0004_stage_2/adapter_config.json deleted file mode 100644 index 605e9c9323bc26f223f1b0d55df36be8e25e38b6..0000000000000000000000000000000000000000 --- a/diloco_state/workers/A/round_0004_stage_2/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "out_proj", - "dt_proj", - "q_proj", - "in_proj", - "v_proj", - "x_proj", - "k_proj", - "o_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/A/round_0004_stage_2/adapter_model.safetensors b/diloco_state/workers/A/round_0004_stage_2/adapter_model.safetensors deleted file mode 100644 index 66eedc5971740084d696141df1fbde979768d134..0000000000000000000000000000000000000000 --- a/diloco_state/workers/A/round_0004_stage_2/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:424c17487c5246ddbabe33a943fb446f5f7a6387f6fd47e251ad5421e5747674 -size 1557071904 diff --git a/diloco_state/workers/A/round_0004_stage_3/adapter_config.json b/diloco_state/workers/A/round_0004_stage_3/adapter_config.json deleted file mode 100644 index 505ba73b8e58b4ea549ca5d45f3a60dde4ac5e42..0000000000000000000000000000000000000000 --- a/diloco_state/workers/A/round_0004_stage_3/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "x_proj", - "o_proj", - "k_proj", - "dt_proj", - "v_proj", - "in_proj", - "q_proj", - "out_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/A/round_0004_stage_3/adapter_model.safetensors b/diloco_state/workers/A/round_0004_stage_3/adapter_model.safetensors deleted file mode 100644 index a5a4e7141aae42e4fa042e2e2ce1d105ab2132bf..0000000000000000000000000000000000000000 --- a/diloco_state/workers/A/round_0004_stage_3/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:db97c19bd2571a606e2bc7ccd0f1ba54fed4bc8fdb77e6835844ffa11ad1c20d -size 1557071904 diff --git a/diloco_state/workers/A/round_0005_stage_2/adapter_config.json b/diloco_state/workers/A/round_0005_stage_2/adapter_config.json deleted file mode 100644 index a6f825a573e3c25bac86ec00bae5863607c088b3..0000000000000000000000000000000000000000 --- a/diloco_state/workers/A/round_0005_stage_2/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "q_proj", - "v_proj", - "in_proj", - "o_proj", - "x_proj", - "out_proj", - "dt_proj", - "k_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/A/round_0005_stage_2/adapter_model.safetensors b/diloco_state/workers/A/round_0005_stage_2/adapter_model.safetensors deleted file mode 100644 index 187e446004bed273e60ecf9d7ebed7a5415fb2f4..0000000000000000000000000000000000000000 --- a/diloco_state/workers/A/round_0005_stage_2/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:d8b1c9e086a8c3eaaff6b34ba6d27cb38538fd45f9db27eb647a52068754f92d -size 1557071904 diff --git a/diloco_state/workers/A/round_0005_stage_3/adapter_config.json b/diloco_state/workers/A/round_0005_stage_3/adapter_config.json deleted file mode 100644 index 3e52e9340f4771f9a9152549d8c634fd6c686737..0000000000000000000000000000000000000000 --- a/diloco_state/workers/A/round_0005_stage_3/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "o_proj", - "in_proj", - "q_proj", - "x_proj", - "k_proj", - "out_proj", - "dt_proj", - "v_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/A/round_0005_stage_3/adapter_model.safetensors b/diloco_state/workers/A/round_0005_stage_3/adapter_model.safetensors deleted file mode 100644 index 5260c1edff248db1ae21c13c394d34f1218d5abb..0000000000000000000000000000000000000000 --- a/diloco_state/workers/A/round_0005_stage_3/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:16b6aa3a194896d2b78103b5a4c0e0eda475848dfe3f26372942a96318829516 -size 1557071904 diff --git a/diloco_state/workers/A/status.json b/diloco_state/workers/A/status.json deleted file mode 100644 index 41cb7082b7ad9cf7298519a35307da17e2c05ba8..0000000000000000000000000000000000000000 --- a/diloco_state/workers/A/status.json +++ /dev/null @@ -1,10 +0,0 @@ -{ - "worker_id": "A", - "stage_k": 10, - "round_n": 1, - "samples_seen": 8256, - "status": "done", - "timestamp": 1778607687.040924, - "weights_path": "diloco_state/workers/A/round_0001_stage_10", - "halt_gate_path": "diloco_state/workers/A/round_0001_stage_10/halt_gate.pt" -} \ No newline at end of file diff --git a/diloco_state/workers/B/round_0000_stage_10/adapter_config.json b/diloco_state/workers/B/round_0000_stage_10/adapter_config.json deleted file mode 100644 index 53f6919e59c8d039fa855a284943d906a2d52701..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/round_0000_stage_10/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "q_proj", - "in_proj", - "k_proj", - "v_proj", - "o_proj", - "x_proj", - "dt_proj", - "out_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/B/round_0000_stage_10/adapter_model.safetensors b/diloco_state/workers/B/round_0000_stage_10/adapter_model.safetensors deleted file mode 100644 index 3b02c44dc2d282075fe701f0a0444ab07294fe6f..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/round_0000_stage_10/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:a55ffb7a82b803ce4af0b9888ad9cb25b34014c5c0693f926825da9e483894ad -size 1557071904 diff --git a/diloco_state/workers/B/round_0000_stage_10/halt_gate.pt b/diloco_state/workers/B/round_0000_stage_10/halt_gate.pt deleted file mode 100644 index 25ce49203855f589824d9e31aa70405da8567574..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/round_0000_stage_10/halt_gate.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:b83448737e8031936d06797e21b7ae946e23d2a686e95a36b3d438077c620eae -size 22453 diff --git a/diloco_state/workers/B/round_0000_stage_2/adapter_config.json b/diloco_state/workers/B/round_0000_stage_2/adapter_config.json deleted file mode 100644 index 79b44e0524c6bb99db2da1eacf33d5f2e47f86d5..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/round_0000_stage_2/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "dt_proj", - "v_proj", - "k_proj", - "q_proj", - "out_proj", - "in_proj", - "x_proj", - "o_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/B/round_0000_stage_2/adapter_model.safetensors b/diloco_state/workers/B/round_0000_stage_2/adapter_model.safetensors deleted file mode 100644 index 878eaf4d52394f1e42acea4d6b4adebe3e3c386f..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/round_0000_stage_2/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:f3140886506e17504bd7e75c7ff8d43f8fb08fb30d83fa3439ee812623691298 -size 1557071904 diff --git a/diloco_state/workers/B/round_0000_stage_3/adapter_config.json b/diloco_state/workers/B/round_0000_stage_3/adapter_config.json deleted file mode 100644 index e34d70bf3ddcc7dc1318522dc015928cc1634cc4..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/round_0000_stage_3/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "in_proj", - "k_proj", - "o_proj", - "x_proj", - "dt_proj", - "out_proj", - "v_proj", - "q_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/B/round_0000_stage_3/adapter_model.safetensors b/diloco_state/workers/B/round_0000_stage_3/adapter_model.safetensors deleted file mode 100644 index 9ab22cf39bf0a51edb3ee3fce5ce13bdee257767..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/round_0000_stage_3/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:d783a2d9bceb26cc4e18646f4dec19f99ec5f4969f9f1bab87d7a2a611b8517a -size 1557071904 diff --git a/diloco_state/workers/B/round_0000_stage_4/adapter_config.json b/diloco_state/workers/B/round_0000_stage_4/adapter_config.json deleted file mode 100644 index ec19018e57d3f36e5ee7c83390fbef291c9302fb..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/round_0000_stage_4/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "k_proj", - "q_proj", - "out_proj", - "in_proj", - "x_proj", - "dt_proj", - "o_proj", - "v_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/B/round_0000_stage_4/adapter_model.safetensors b/diloco_state/workers/B/round_0000_stage_4/adapter_model.safetensors deleted file mode 100644 index a58d32f15f550ac464e03b6291a00bf579ab83ad..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/round_0000_stage_4/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:4c255928ec26705a7a51510d58eff840283c5cbf2f0bb6ae0f07425d9af3c065 -size 1557071904 diff --git a/diloco_state/workers/B/round_0000_stage_5/adapter_config.json b/diloco_state/workers/B/round_0000_stage_5/adapter_config.json deleted file mode 100644 index f5bb0c5ea60e48ccf0bc59372b1deb6dab4eaa83..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/round_0000_stage_5/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "k_proj", - "out_proj", - "q_proj", - "x_proj", - "in_proj", - "v_proj", - "o_proj", - "dt_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/B/round_0000_stage_5/adapter_model.safetensors b/diloco_state/workers/B/round_0000_stage_5/adapter_model.safetensors deleted file mode 100644 index bf0bd04cdfc4c4b345b1b9def901c26e493d9341..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/round_0000_stage_5/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:303406145c519df6fbdc2b26119d9477aa917f672889c835825baf6fd36b25c1 -size 1557071904 diff --git a/diloco_state/workers/B/round_0000_stage_6/adapter_config.json b/diloco_state/workers/B/round_0000_stage_6/adapter_config.json deleted file mode 100644 index 5fda0fb80ca4cd09c158b1165d53579c7890496b..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/round_0000_stage_6/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "in_proj", - "q_proj", - "dt_proj", - "k_proj", - "out_proj", - "v_proj", - "o_proj", - "x_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/B/round_0000_stage_6/adapter_model.safetensors b/diloco_state/workers/B/round_0000_stage_6/adapter_model.safetensors deleted file mode 100644 index 2e6f0ee7d68a0cbe9d9086f385d241f38445200c..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/round_0000_stage_6/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:9caa8a022d91590041184e94c2785132fa1de9ed62dbce1c22cd8a06f62c869f -size 1557071904 diff --git a/diloco_state/workers/B/round_0000_stage_7/adapter_config.json b/diloco_state/workers/B/round_0000_stage_7/adapter_config.json deleted file mode 100644 index 22bde83ec4df9c24d88948e9f8ff5fbdd94ac7e7..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/round_0000_stage_7/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "k_proj", - "x_proj", - "in_proj", - "v_proj", - "dt_proj", - "o_proj", - "q_proj", - "out_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/B/round_0000_stage_7/adapter_model.safetensors b/diloco_state/workers/B/round_0000_stage_7/adapter_model.safetensors deleted file mode 100644 index 0af3bc43c8ac2138349416dc04c877262f4f432a..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/round_0000_stage_7/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:f915840fda1b1a8e6cfd249b135d33751051a86dbf94c0b71bbf50aa7e42d250 -size 1557071904 diff --git a/diloco_state/workers/B/round_0000_stage_9/adapter_config.json b/diloco_state/workers/B/round_0000_stage_9/adapter_config.json deleted file mode 100644 index c53beb4da822379fb49adede471bb4494dda85d7..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/round_0000_stage_9/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "q_proj", - "k_proj", - "o_proj", - "v_proj", - "out_proj", - "x_proj", - "in_proj", - "dt_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/B/round_0000_stage_9/adapter_model.safetensors b/diloco_state/workers/B/round_0000_stage_9/adapter_model.safetensors deleted file mode 100644 index 5f58b9eba080dfa267d91bb2f3a5c94c022f36b3..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/round_0000_stage_9/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:4c4e53689d3394b22fab901f3b85b7e98b2ae9d501ba3f6ae2e6cf3e84a6fd83 -size 1557071904 diff --git a/diloco_state/workers/B/round_0001_stage_10/adapter_config.json b/diloco_state/workers/B/round_0001_stage_10/adapter_config.json deleted file mode 100644 index 7667eef9445761905f26faa5f17ad0f1a3c66157..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/round_0001_stage_10/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "q_proj", - "out_proj", - "o_proj", - "dt_proj", - "in_proj", - "k_proj", - "x_proj", - "v_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/B/round_0001_stage_10/adapter_model.safetensors b/diloco_state/workers/B/round_0001_stage_10/adapter_model.safetensors deleted file mode 100644 index 3b02c44dc2d282075fe701f0a0444ab07294fe6f..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/round_0001_stage_10/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:a55ffb7a82b803ce4af0b9888ad9cb25b34014c5c0693f926825da9e483894ad -size 1557071904 diff --git a/diloco_state/workers/B/round_0001_stage_10/halt_gate.pt b/diloco_state/workers/B/round_0001_stage_10/halt_gate.pt deleted file mode 100644 index 25ce49203855f589824d9e31aa70405da8567574..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/round_0001_stage_10/halt_gate.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:b83448737e8031936d06797e21b7ae946e23d2a686e95a36b3d438077c620eae -size 22453 diff --git a/diloco_state/workers/B/round_0001_stage_2/adapter_config.json b/diloco_state/workers/B/round_0001_stage_2/adapter_config.json deleted file mode 100644 index 0c1ee27504a6df9b90c8bfe685032b0a1ff2afff..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/round_0001_stage_2/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "x_proj", - "k_proj", - "in_proj", - "v_proj", - "dt_proj", - "q_proj", - "o_proj", - "out_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/B/round_0001_stage_2/adapter_model.safetensors b/diloco_state/workers/B/round_0001_stage_2/adapter_model.safetensors deleted file mode 100644 index aaaa1cfd4ec558106717807bd5e85cddb119faea..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/round_0001_stage_2/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:596666c98621a24b2ddfb951add612a34faf2afe682d61733200420ec2565fc1 -size 1557071904 diff --git a/diloco_state/workers/B/round_0001_stage_3/adapter_config.json b/diloco_state/workers/B/round_0001_stage_3/adapter_config.json deleted file mode 100644 index 3c6598b81bbbc494e00fba144fddb45dc1c956f9..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/round_0001_stage_3/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "v_proj", - "o_proj", - "x_proj", - "q_proj", - "dt_proj", - "in_proj", - "out_proj", - "k_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/B/round_0001_stage_3/adapter_model.safetensors b/diloco_state/workers/B/round_0001_stage_3/adapter_model.safetensors deleted file mode 100644 index 90169359265606a18b9f4ccb18c40af7dd870a65..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/round_0001_stage_3/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:aedd441b4c659e3eac21aa92cd5be54b73256574e9b46849c910d300255a25b1 -size 1557071904 diff --git a/diloco_state/workers/B/round_0001_stage_8/adapter_config.json b/diloco_state/workers/B/round_0001_stage_8/adapter_config.json deleted file mode 100644 index 4b3e0dde87f78d1040b757179301dc7bf5c74a75..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/round_0001_stage_8/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "dt_proj", - "q_proj", - "v_proj", - "k_proj", - "o_proj", - "x_proj", - "in_proj", - "out_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/B/round_0001_stage_8/adapter_model.safetensors b/diloco_state/workers/B/round_0001_stage_8/adapter_model.safetensors deleted file mode 100644 index 54e100d188aed7ce6aedee2454e141f8750a71db..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/round_0001_stage_8/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:df7f2d4e0d782e6db48af2b0bdac6ef585b2e586042f49b6f85e532a4b249efc -size 1557071904 diff --git a/diloco_state/workers/B/round_0001_stage_9/adapter_config.json b/diloco_state/workers/B/round_0001_stage_9/adapter_config.json deleted file mode 100644 index 67081b9720bd77600fc46366874c81996f919075..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/round_0001_stage_9/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "dt_proj", - "k_proj", - "q_proj", - "v_proj", - "x_proj", - "o_proj", - "out_proj", - "in_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/B/round_0001_stage_9/adapter_model.safetensors b/diloco_state/workers/B/round_0001_stage_9/adapter_model.safetensors deleted file mode 100644 index 7b5ec69fa40b0ac7958d55e71a3032d58c879452..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/round_0001_stage_9/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:3ce5b763e73d96fd40c2c0d8ca61ebed135908d71b500b8b6beec3cf1e75831d -size 1557071904 diff --git a/diloco_state/workers/B/round_0002_stage_10/adapter_config.json b/diloco_state/workers/B/round_0002_stage_10/adapter_config.json deleted file mode 100644 index b1899775b710fd212db839dd8f9dc0c6832fa85e..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/round_0002_stage_10/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "v_proj", - "x_proj", - "q_proj", - "in_proj", - "dt_proj", - "o_proj", - "k_proj", - "out_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/B/round_0002_stage_10/adapter_model.safetensors b/diloco_state/workers/B/round_0002_stage_10/adapter_model.safetensors deleted file mode 100644 index 5a7552b5af05540c1ca0a3b6f4cd030357dbd83d..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/round_0002_stage_10/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:651467a17ab4a5eacf8d3d5a32466c8e18863bb8c2d1c8fbd4f3314f34e567c0 -size 1557071904 diff --git a/diloco_state/workers/B/round_0002_stage_10/halt_gate.pt b/diloco_state/workers/B/round_0002_stage_10/halt_gate.pt deleted file mode 100644 index 012b27c72a0368b6047ed18f872c456288f127f0..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/round_0002_stage_10/halt_gate.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6a83f73e9797d464490ec009f305bce1bb89099c462c246d20cde4cdaaf19f9c -size 22453 diff --git a/diloco_state/workers/B/round_0002_stage_2/adapter_config.json b/diloco_state/workers/B/round_0002_stage_2/adapter_config.json deleted file mode 100644 index 8cb7acea9f9c5fcb98f4398086830ec68f6b2ae8..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/round_0002_stage_2/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "x_proj", - "dt_proj", - "o_proj", - "out_proj", - "k_proj", - "v_proj", - "in_proj", - "q_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/B/round_0002_stage_2/adapter_model.safetensors b/diloco_state/workers/B/round_0002_stage_2/adapter_model.safetensors deleted file mode 100644 index a6a72b0fa130c40bdeb8e2d4c388e2d0b7774b97..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/round_0002_stage_2/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:de3fa668f414f7ac57de095e7a65be33282dc8ccdebd734e588d43bbf8132589 -size 1557071904 diff --git a/diloco_state/workers/B/round_0002_stage_3/adapter_config.json b/diloco_state/workers/B/round_0002_stage_3/adapter_config.json deleted file mode 100644 index 17401d3433b1535d9ad5b03ba9bc66917e721706..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/round_0002_stage_3/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "o_proj", - "in_proj", - "x_proj", - "q_proj", - "v_proj", - "dt_proj", - "out_proj", - "k_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/B/round_0002_stage_3/adapter_model.safetensors b/diloco_state/workers/B/round_0002_stage_3/adapter_model.safetensors deleted file mode 100644 index a5a4e7141aae42e4fa042e2e2ce1d105ab2132bf..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/round_0002_stage_3/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:db97c19bd2571a606e2bc7ccd0f1ba54fed4bc8fdb77e6835844ffa11ad1c20d -size 1557071904 diff --git a/diloco_state/workers/B/round_0002_stage_8/adapter_config.json b/diloco_state/workers/B/round_0002_stage_8/adapter_config.json deleted file mode 100644 index 14ac728675e648913ee477278f53ed364615c677..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/round_0002_stage_8/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "in_proj", - "v_proj", - "o_proj", - "k_proj", - "x_proj", - "dt_proj", - "out_proj", - "q_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/B/round_0002_stage_8/adapter_model.safetensors b/diloco_state/workers/B/round_0002_stage_8/adapter_model.safetensors deleted file mode 100644 index d8154241e10aae4f5e5dccf43f73c5b5cf7f3156..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/round_0002_stage_8/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:ac709d8973877c199fa5bc85c7ba7fc934e920d04862dde273cfbf6f0c4b1f86 -size 1557071904 diff --git a/diloco_state/workers/B/round_0003_stage_2/adapter_config.json b/diloco_state/workers/B/round_0003_stage_2/adapter_config.json deleted file mode 100644 index 23cce26ba4fb4148e81c604df323e2b26998269a..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/round_0003_stage_2/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "v_proj", - "x_proj", - "out_proj", - "k_proj", - "q_proj", - "dt_proj", - "o_proj", - "in_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/B/round_0003_stage_2/adapter_model.safetensors b/diloco_state/workers/B/round_0003_stage_2/adapter_model.safetensors deleted file mode 100644 index 89974e2853c2b9adc2839b48ed57e4828029a37c..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/round_0003_stage_2/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:c162b0a5787e9a358658b23885af4f68b82bb9f174bf1dffff31936a85e72fdd -size 1557071904 diff --git a/diloco_state/workers/B/round_0003_stage_3/adapter_config.json b/diloco_state/workers/B/round_0003_stage_3/adapter_config.json deleted file mode 100644 index 3ce45f83c50a45049a7151c00cd106934d58e2e4..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/round_0003_stage_3/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "k_proj", - "x_proj", - "out_proj", - "dt_proj", - "q_proj", - "o_proj", - "v_proj", - "in_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/B/round_0003_stage_3/adapter_model.safetensors b/diloco_state/workers/B/round_0003_stage_3/adapter_model.safetensors deleted file mode 100644 index a5a4e7141aae42e4fa042e2e2ce1d105ab2132bf..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/round_0003_stage_3/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:db97c19bd2571a606e2bc7ccd0f1ba54fed4bc8fdb77e6835844ffa11ad1c20d -size 1557071904 diff --git a/diloco_state/workers/B/round_0004_stage_2/adapter_config.json b/diloco_state/workers/B/round_0004_stage_2/adapter_config.json deleted file mode 100644 index 36bdd4068ba3d95738366d8091057a6262875d13..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/round_0004_stage_2/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "o_proj", - "in_proj", - "v_proj", - "dt_proj", - "out_proj", - "q_proj", - "x_proj", - "k_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/B/round_0004_stage_2/adapter_model.safetensors b/diloco_state/workers/B/round_0004_stage_2/adapter_model.safetensors deleted file mode 100644 index 9245ff879777315ac50908b2120a4e9cc7ec99e6..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/round_0004_stage_2/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:56dd4ffb404d19864ad9185723b8443008d075a118a92e4c590b9afb303a700e -size 1557071904 diff --git a/diloco_state/workers/B/round_0004_stage_3/adapter_config.json b/diloco_state/workers/B/round_0004_stage_3/adapter_config.json deleted file mode 100644 index 336cd2a9bf1c0e909504c24e1eb98b5a6365f2f7..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/round_0004_stage_3/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "dt_proj", - "o_proj", - "out_proj", - "q_proj", - "in_proj", - "k_proj", - "x_proj", - "v_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/B/round_0004_stage_3/adapter_model.safetensors b/diloco_state/workers/B/round_0004_stage_3/adapter_model.safetensors deleted file mode 100644 index a5a4e7141aae42e4fa042e2e2ce1d105ab2132bf..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/round_0004_stage_3/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:db97c19bd2571a606e2bc7ccd0f1ba54fed4bc8fdb77e6835844ffa11ad1c20d -size 1557071904 diff --git a/diloco_state/workers/B/round_0005_stage_2/adapter_config.json b/diloco_state/workers/B/round_0005_stage_2/adapter_config.json deleted file mode 100644 index e93554a8eca2feab41bfb78454d8323a1b9348b5..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/round_0005_stage_2/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "x_proj", - "v_proj", - "o_proj", - "dt_proj", - "k_proj", - "q_proj", - "in_proj", - "out_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/B/round_0005_stage_2/adapter_model.safetensors b/diloco_state/workers/B/round_0005_stage_2/adapter_model.safetensors deleted file mode 100644 index 425c6c6a8762f03aecfe67c35730b4a268dad301..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/round_0005_stage_2/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:68375186b33e19ac1859ba1becd0662985f0771a9a40707632dd8cf2fb665dee -size 1557071904 diff --git a/diloco_state/workers/B/round_0005_stage_3/adapter_config.json b/diloco_state/workers/B/round_0005_stage_3/adapter_config.json deleted file mode 100644 index 3325a71efbb022f86aa7270db2da15fbe40b10c1..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/round_0005_stage_3/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "k_proj", - "dt_proj", - "o_proj", - "out_proj", - "q_proj", - "x_proj", - "in_proj", - "v_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/B/round_0005_stage_3/adapter_model.safetensors b/diloco_state/workers/B/round_0005_stage_3/adapter_model.safetensors deleted file mode 100644 index 17469284a54994a897f2ecd082aa55e7425c9055..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/round_0005_stage_3/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6dbe86b731000226e51b56f7bd7d7cd04edb4cbed56b1fb47560a1e7d65c40f1 -size 1557071904 diff --git a/diloco_state/workers/B/status.json b/diloco_state/workers/B/status.json deleted file mode 100644 index 4fad463a09876ef2171679807ca19ad02d83bda5..0000000000000000000000000000000000000000 --- a/diloco_state/workers/B/status.json +++ /dev/null @@ -1,10 +0,0 @@ -{ - "worker_id": "B", - "stage_k": 10, - "round_n": 2, - "samples_seen": 6713, - "status": "done", - "timestamp": 1778644098.9777951, - "weights_path": "diloco_state/workers/B/round_0002_stage_10", - "halt_gate_path": "diloco_state/workers/B/round_0002_stage_10/halt_gate.pt" -} \ No newline at end of file diff --git a/diloco_state/workers/C/round_0000_stage_10/adapter_config.json b/diloco_state/workers/C/round_0000_stage_10/adapter_config.json deleted file mode 100644 index 7e9e143b3343ff1219e90ce7a618c1f1384f26e6..0000000000000000000000000000000000000000 --- a/diloco_state/workers/C/round_0000_stage_10/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "dt_proj", - "o_proj", - "out_proj", - "in_proj", - "k_proj", - "q_proj", - "v_proj", - "x_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/C/round_0000_stage_10/adapter_model.safetensors b/diloco_state/workers/C/round_0000_stage_10/adapter_model.safetensors deleted file mode 100644 index 3b02c44dc2d282075fe701f0a0444ab07294fe6f..0000000000000000000000000000000000000000 --- a/diloco_state/workers/C/round_0000_stage_10/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:a55ffb7a82b803ce4af0b9888ad9cb25b34014c5c0693f926825da9e483894ad -size 1557071904 diff --git a/diloco_state/workers/C/round_0000_stage_10/halt_gate.pt b/diloco_state/workers/C/round_0000_stage_10/halt_gate.pt deleted file mode 100644 index 25ce49203855f589824d9e31aa70405da8567574..0000000000000000000000000000000000000000 --- a/diloco_state/workers/C/round_0000_stage_10/halt_gate.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:b83448737e8031936d06797e21b7ae946e23d2a686e95a36b3d438077c620eae -size 22453 diff --git a/diloco_state/workers/C/round_0000_stage_4/adapter_config.json b/diloco_state/workers/C/round_0000_stage_4/adapter_config.json deleted file mode 100644 index 731f05ae9798fb7596ffa396341e229d09a993c2..0000000000000000000000000000000000000000 --- a/diloco_state/workers/C/round_0000_stage_4/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "in_proj", - "o_proj", - "out_proj", - "x_proj", - "v_proj", - "k_proj", - "dt_proj", - "q_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/C/round_0000_stage_4/adapter_model.safetensors b/diloco_state/workers/C/round_0000_stage_4/adapter_model.safetensors deleted file mode 100644 index 61bf2951a9881b82d6a9c365f6462bd3bf50fc80..0000000000000000000000000000000000000000 --- a/diloco_state/workers/C/round_0000_stage_4/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:0da50eead45a71901ce77c93ed7292afaf59127185cac6ead36640afbe26a626 -size 1557071904 diff --git a/diloco_state/workers/C/round_0000_stage_5/adapter_config.json b/diloco_state/workers/C/round_0000_stage_5/adapter_config.json deleted file mode 100644 index 2b3c6d3ecec1ebcaae5c598fb7beddc4fefd8c52..0000000000000000000000000000000000000000 --- a/diloco_state/workers/C/round_0000_stage_5/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "x_proj", - "o_proj", - "dt_proj", - "out_proj", - "k_proj", - "v_proj", - "q_proj", - "in_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/C/round_0000_stage_5/adapter_model.safetensors b/diloco_state/workers/C/round_0000_stage_5/adapter_model.safetensors deleted file mode 100644 index a502c4178fa560bbfeba62587dc90963ea6586d6..0000000000000000000000000000000000000000 --- a/diloco_state/workers/C/round_0000_stage_5/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:4a17d206c6b359769bd9148a161ccb86d92852a853c5f5ac156a99b65decb476 -size 1557071904 diff --git a/diloco_state/workers/C/round_0000_stage_6/adapter_config.json b/diloco_state/workers/C/round_0000_stage_6/adapter_config.json deleted file mode 100644 index d68b9b46d1d164b1c11d316038d50918835e8652..0000000000000000000000000000000000000000 --- a/diloco_state/workers/C/round_0000_stage_6/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "q_proj", - "v_proj", - "x_proj", - "out_proj", - "o_proj", - "k_proj", - "dt_proj", - "in_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/C/round_0000_stage_6/adapter_model.safetensors b/diloco_state/workers/C/round_0000_stage_6/adapter_model.safetensors deleted file mode 100644 index 6d3e5606b5884a7cd5f9eb8937ea7d8cc4dbc37a..0000000000000000000000000000000000000000 --- a/diloco_state/workers/C/round_0000_stage_6/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:d08221fc21e4b77e772ea0d598f8ce732dcf0ed8bf6bb2a7686b7e65838fdd4d -size 1557071904 diff --git a/diloco_state/workers/C/round_0000_stage_7/adapter_config.json b/diloco_state/workers/C/round_0000_stage_7/adapter_config.json deleted file mode 100644 index 2fe7f949d1b82834df37aebfa431e34634e758e9..0000000000000000000000000000000000000000 --- a/diloco_state/workers/C/round_0000_stage_7/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "dt_proj", - "k_proj", - "o_proj", - "x_proj", - "in_proj", - "out_proj", - "v_proj", - "q_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/C/round_0000_stage_7/adapter_model.safetensors b/diloco_state/workers/C/round_0000_stage_7/adapter_model.safetensors deleted file mode 100644 index a386fccefcb597a261a03f8dd5935eb8957db099..0000000000000000000000000000000000000000 --- a/diloco_state/workers/C/round_0000_stage_7/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:d12dffa75ae3ad57f61a9993dc64a962e54ca769bd3e46cf6e69c36b0174feb7 -size 1557071904 diff --git a/diloco_state/workers/C/round_0000_stage_9/adapter_config.json b/diloco_state/workers/C/round_0000_stage_9/adapter_config.json deleted file mode 100644 index d7920f2b66a50ea576a3d8d38f29d32b1ca4ebbc..0000000000000000000000000000000000000000 --- a/diloco_state/workers/C/round_0000_stage_9/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "k_proj", - "in_proj", - "x_proj", - "q_proj", - "out_proj", - "dt_proj", - "v_proj", - "o_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/C/round_0000_stage_9/adapter_model.safetensors b/diloco_state/workers/C/round_0000_stage_9/adapter_model.safetensors deleted file mode 100644 index ad4fa4a541f9ad93cb98400c643265bbb01a32ff..0000000000000000000000000000000000000000 --- a/diloco_state/workers/C/round_0000_stage_9/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:1b033d787753dd9dcd5ed085391af8420460a5665c4450318566479c5b5988bd -size 1557071904 diff --git a/diloco_state/workers/C/round_0001_stage_10/adapter_config.json b/diloco_state/workers/C/round_0001_stage_10/adapter_config.json deleted file mode 100644 index d56bdd33d495e34efa9154436e20686b6303842a..0000000000000000000000000000000000000000 --- a/diloco_state/workers/C/round_0001_stage_10/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "v_proj", - "out_proj", - "q_proj", - "in_proj", - "x_proj", - "k_proj", - "o_proj", - "dt_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/C/round_0001_stage_10/adapter_model.safetensors b/diloco_state/workers/C/round_0001_stage_10/adapter_model.safetensors deleted file mode 100644 index ea7cd8a9b2a75980babc4a6d51d6ec74aa5b053c..0000000000000000000000000000000000000000 --- a/diloco_state/workers/C/round_0001_stage_10/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:2cf6c443f81d701bdc225608eb5a3ac89b0f3c238f9bac667a2769bc635f2c0c -size 1557071904 diff --git a/diloco_state/workers/C/round_0001_stage_10/halt_gate.pt b/diloco_state/workers/C/round_0001_stage_10/halt_gate.pt deleted file mode 100644 index 1548da539f5abd2bee18a16acaf28a44e0e38f5a..0000000000000000000000000000000000000000 --- a/diloco_state/workers/C/round_0001_stage_10/halt_gate.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:397b522db5c278c55075fd31a9fde80a22232769a14198181e69d5db75af6ea0 -size 22453 diff --git a/diloco_state/workers/C/round_0001_stage_8/adapter_config.json b/diloco_state/workers/C/round_0001_stage_8/adapter_config.json deleted file mode 100644 index fc6c583f2161aceb56768200681133a5d3d863bc..0000000000000000000000000000000000000000 --- a/diloco_state/workers/C/round_0001_stage_8/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "out_proj", - "k_proj", - "x_proj", - "in_proj", - "v_proj", - "dt_proj", - "q_proj", - "o_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/C/round_0001_stage_8/adapter_model.safetensors b/diloco_state/workers/C/round_0001_stage_8/adapter_model.safetensors deleted file mode 100644 index 718d3c15d4d7c2f11fe72ad6c629155fb5f5dddd..0000000000000000000000000000000000000000 --- a/diloco_state/workers/C/round_0001_stage_8/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:0fe0d367a0d2dfd7027a951caf4199b7049d8e9187094151e736a45424cec889 -size 1557071904 diff --git a/diloco_state/workers/C/round_0001_stage_9/adapter_config.json b/diloco_state/workers/C/round_0001_stage_9/adapter_config.json deleted file mode 100644 index 002303ced0a0a695524ff619159f824d5f917b3c..0000000000000000000000000000000000000000 --- a/diloco_state/workers/C/round_0001_stage_9/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "q_proj", - "o_proj", - "k_proj", - "out_proj", - "in_proj", - "x_proj", - "dt_proj", - "v_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/C/round_0001_stage_9/adapter_model.safetensors b/diloco_state/workers/C/round_0001_stage_9/adapter_model.safetensors deleted file mode 100644 index 2cdb6fd293b0e95abdde949aa56fe1b7e521b32a..0000000000000000000000000000000000000000 --- a/diloco_state/workers/C/round_0001_stage_9/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:c197f02ce449bd7eeed35b9b32bd7ba0d8d48660f40ffae8db83b43e9434bd7d -size 1557071904 diff --git a/diloco_state/workers/C/round_0002_stage_10/adapter_config.json b/diloco_state/workers/C/round_0002_stage_10/adapter_config.json deleted file mode 100644 index 6e89d45f3587f249715da960c4bc1354cb575359..0000000000000000000000000000000000000000 --- a/diloco_state/workers/C/round_0002_stage_10/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "dt_proj", - "k_proj", - "o_proj", - "out_proj", - "q_proj", - "v_proj", - "x_proj", - "in_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/C/round_0002_stage_10/adapter_model.safetensors b/diloco_state/workers/C/round_0002_stage_10/adapter_model.safetensors deleted file mode 100644 index 074cd602143a1f2775611260abe2a50e4cbb9180..0000000000000000000000000000000000000000 --- a/diloco_state/workers/C/round_0002_stage_10/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:831d7f86414e62aac6d482f8053b2e501301bd9731464edd1bf8186e481e33ff -size 1557071904 diff --git a/diloco_state/workers/C/round_0002_stage_8/adapter_config.json b/diloco_state/workers/C/round_0002_stage_8/adapter_config.json deleted file mode 100644 index b00414eea0fa7ccc55a028f5e5a16294f3076429..0000000000000000000000000000000000000000 --- a/diloco_state/workers/C/round_0002_stage_8/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "k_proj", - "out_proj", - "v_proj", - "o_proj", - "in_proj", - "x_proj", - "q_proj", - "dt_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/C/round_0002_stage_8/adapter_model.safetensors b/diloco_state/workers/C/round_0002_stage_8/adapter_model.safetensors deleted file mode 100644 index c7446da9189e96b4195db99497c2b2a895a35c5c..0000000000000000000000000000000000000000 --- a/diloco_state/workers/C/round_0002_stage_8/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:756f35d07427af3a1eae54e38b5fc0645bd6baf4228be1ea542e14462318e397 -size 1557071904 diff --git a/diloco_state/workers/C/round_0005_stage_3/adapter_config.json b/diloco_state/workers/C/round_0005_stage_3/adapter_config.json deleted file mode 100644 index 2846dd51e8b47101c683e067eadb04a615cd1697..0000000000000000000000000000000000000000 --- a/diloco_state/workers/C/round_0005_stage_3/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "out_proj", - "x_proj", - "in_proj", - "q_proj", - "o_proj", - "k_proj", - "dt_proj", - "v_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/diloco_state/workers/C/round_0005_stage_3/adapter_model.safetensors b/diloco_state/workers/C/round_0005_stage_3/adapter_model.safetensors deleted file mode 100644 index 6e7a7f613feff326995c499696836861315f74c4..0000000000000000000000000000000000000000 --- a/diloco_state/workers/C/round_0005_stage_3/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:cd68fe600d597d5a4c3ca2f3a6f30b41685787345b0a1eb7550006808364eafc -size 1557071904 diff --git a/diloco_state/workers/C/status.json b/diloco_state/workers/C/status.json deleted file mode 100644 index 266b112f1c395bb377f57e106504fbab829e5935..0000000000000000000000000000000000000000 --- a/diloco_state/workers/C/status.json +++ /dev/null @@ -1,10 +0,0 @@ -{ - "worker_id": "C", - "stage_k": 10, - "round_n": 1, - "samples_seen": 8512, - "status": "done", - "timestamp": 1778607734.2362878, - "weights_path": "diloco_state/workers/C/round_0001_stage_10", - "halt_gate_path": "diloco_state/workers/C/round_0001_stage_10/halt_gate.pt" -} \ No newline at end of file diff --git a/runs/azure_h100_dgac/stage_10/checkpoint-0001154/adapter_model/README.md b/runs/azure_h100_dgac/stage_10/checkpoint-0001154/adapter_model/README.md deleted file mode 100644 index c33acad28337b6b4ad0a71b841e3314ffbfcc09e..0000000000000000000000000000000000000000 --- a/runs/azure_h100_dgac/stage_10/checkpoint-0001154/adapter_model/README.md +++ /dev/null @@ -1,207 +0,0 @@ ---- -base_model: ai21labs/AI21-Jamba-Reasoning-3B -library_name: peft -pipeline_tag: text-generation -tags: -- base_model:adapter:ai21labs/AI21-Jamba-Reasoning-3B -- lora -- transformers ---- - -# Model Card for Model ID - - - - - -## Model Details - -### Model Description - - - - - -- **Developed by:** [More Information Needed] -- **Funded by [optional]:** [More Information Needed] -- **Shared by [optional]:** [More Information Needed] -- **Model type:** [More Information Needed] -- **Language(s) (NLP):** [More Information Needed] -- **License:** [More Information Needed] -- **Finetuned from model [optional]:** [More Information Needed] - -### Model Sources [optional] - - - -- **Repository:** [More Information Needed] -- **Paper [optional]:** [More Information Needed] -- **Demo [optional]:** [More Information Needed] - -## Uses - - - -### Direct Use - - - -[More Information Needed] - -### Downstream Use [optional] - - - -[More Information Needed] - -### Out-of-Scope Use - - - -[More Information Needed] - -## Bias, Risks, and Limitations - - - -[More Information Needed] - -### Recommendations - - - -Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. - -## How to Get Started with the Model - -Use the code below to get started with the model. - -[More Information Needed] - -## Training Details - -### Training Data - - - -[More Information Needed] - -### Training Procedure - - - -#### Preprocessing [optional] - -[More Information Needed] - - -#### Training Hyperparameters - -- **Training regime:** [More Information Needed] - -#### Speeds, Sizes, Times [optional] - - - -[More Information Needed] - -## Evaluation - - - -### Testing Data, Factors & Metrics - -#### Testing Data - - - -[More Information Needed] - -#### Factors - - - -[More Information Needed] - -#### Metrics - - - -[More Information Needed] - -### Results - -[More Information Needed] - -#### Summary - - - -## Model Examination [optional] - - - -[More Information Needed] - -## Environmental Impact - - - -Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - -- **Hardware Type:** [More Information Needed] -- **Hours used:** [More Information Needed] -- **Cloud Provider:** [More Information Needed] -- **Compute Region:** [More Information Needed] -- **Carbon Emitted:** [More Information Needed] - -## Technical Specifications [optional] - -### Model Architecture and Objective - -[More Information Needed] - -### Compute Infrastructure - -[More Information Needed] - -#### Hardware - -[More Information Needed] - -#### Software - -[More Information Needed] - -## Citation [optional] - - - -**BibTeX:** - -[More Information Needed] - -**APA:** - -[More Information Needed] - -## Glossary [optional] - - - -[More Information Needed] - -## More Information [optional] - -[More Information Needed] - -## Model Card Authors [optional] - -[More Information Needed] - -## Model Card Contact - -[More Information Needed] -### Framework versions - -- PEFT 0.19.1 \ No newline at end of file diff --git a/runs/azure_h100_dgac/stage_10/checkpoint-0001154/adapter_model/adapter_config.json b/runs/azure_h100_dgac/stage_10/checkpoint-0001154/adapter_model/adapter_config.json deleted file mode 100644 index 22f55eae397ab7782497ba3373feeaaac4a55d26..0000000000000000000000000000000000000000 --- a/runs/azure_h100_dgac/stage_10/checkpoint-0001154/adapter_model/adapter_config.json +++ /dev/null @@ -1,49 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "lora_ga_config": null, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.19.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "x_proj", - "k_proj", - "q_proj", - "v_proj", - "in_proj", - "out_proj", - "dt_proj", - "o_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_bdlora": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/runs/azure_h100_dgac/stage_10/checkpoint-0001154/adapter_model/adapter_model.safetensors b/runs/azure_h100_dgac/stage_10/checkpoint-0001154/adapter_model/adapter_model.safetensors deleted file mode 100644 index c60135d75ec9e0ed13aa3b7fe94f223f838f524d..0000000000000000000000000000000000000000 --- a/runs/azure_h100_dgac/stage_10/checkpoint-0001154/adapter_model/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:c6203f410af11ab49298ec6ee04e05e024a713e8777d69314d1918f25dc12f4c -size 1557071904 diff --git a/runs/azure_h100_dgac/stage_10/checkpoint-0001154/halt_gate.pt b/runs/azure_h100_dgac/stage_10/checkpoint-0001154/halt_gate.pt deleted file mode 100644 index e3634afe97f356bf2133443fc6f977d96c625070..0000000000000000000000000000000000000000 --- a/runs/azure_h100_dgac/stage_10/checkpoint-0001154/halt_gate.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:44c45b99de75bb995d1366ff90ecc8e39d87030391dd52e078d66a5ff5f92db7 -size 22052 diff --git a/runs/azure_h100_dgac/stage_10/checkpoint-0001154/training_state.pt b/runs/azure_h100_dgac/stage_10/checkpoint-0001154/training_state.pt deleted file mode 100644 index 3e1e74286e2479a19c2fa514e6cbb9df186693c5..0000000000000000000000000000000000000000 --- a/runs/azure_h100_dgac/stage_10/checkpoint-0001154/training_state.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:775ec3c0400dd1cba884fa0ed58fb6c889a3f5c37756c7683240bd6bd32ff651 -size 215045644 diff --git a/runs/stage1/checkpoint-0004000/resolved_backbone_config.json b/runs/stage1/checkpoint-0004000/resolved_backbone_config.json deleted file mode 100644 index d9fd7084584b6db16d0dcfae05d56a05a5db9185..0000000000000000000000000000000000000000 --- a/runs/stage1/checkpoint-0004000/resolved_backbone_config.json +++ /dev/null @@ -1,18 +0,0 @@ -{ - "vocab_size": 151680, - "d_model": 512, - "n_groups": 1, - "mamba_per_group": 7, - "n_heads": 8, - "n_kv_heads": 4, - "rope_theta": 1000000.0, - "mamba_d_state": 16, - "mamba_d_conv": 4, - "mamba_expand": 2, - "max_seq_len": 1024, - "dropout": 0.0, - "rms_norm_eps": 1e-05, - "tie_embeddings": true, - "head_dim": 64, - "mlp_hidden": 1408 -} \ No newline at end of file diff --git a/runs/stage1/checkpoint-0004000/training_state.pt b/runs/stage1/checkpoint-0004000/training_state.pt deleted file mode 100644 index fb288446197fb17dea04d403c80ba6a3087b5adc..0000000000000000000000000000000000000000 --- a/runs/stage1/checkpoint-0004000/training_state.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:3a5dc7edf505034687d5262050fd54ea4d94acc5a3b106fe74edd66bd3fa5d0d -size 739953938 diff --git a/runs/stage1/checkpoint-0005000/resolved_backbone_config.json b/runs/stage1/checkpoint-0005000/resolved_backbone_config.json deleted file mode 100644 index d9fd7084584b6db16d0dcfae05d56a05a5db9185..0000000000000000000000000000000000000000 --- a/runs/stage1/checkpoint-0005000/resolved_backbone_config.json +++ /dev/null @@ -1,18 +0,0 @@ -{ - "vocab_size": 151680, - "d_model": 512, - "n_groups": 1, - "mamba_per_group": 7, - "n_heads": 8, - "n_kv_heads": 4, - "rope_theta": 1000000.0, - "mamba_d_state": 16, - "mamba_d_conv": 4, - "mamba_expand": 2, - "max_seq_len": 1024, - "dropout": 0.0, - "rms_norm_eps": 1e-05, - "tie_embeddings": true, - "head_dim": 64, - "mlp_hidden": 1408 -} \ No newline at end of file diff --git a/runs/stage1/checkpoint-0005000/training_state.pt b/runs/stage1/checkpoint-0005000/training_state.pt deleted file mode 100644 index 3f8d35349de4e5f4b05e985c4c3ec96fa0cd7901..0000000000000000000000000000000000000000 --- a/runs/stage1/checkpoint-0005000/training_state.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:adb6dbfeabe9867571a4b0dd570e5a41c08928f4eda30bd83ee3b6adf7d0ef41 -size 739953938 diff --git a/runs/stage1/checkpoint-0006000/resolved_backbone_config.json b/runs/stage1/checkpoint-0006000/resolved_backbone_config.json deleted file mode 100644 index d9fd7084584b6db16d0dcfae05d56a05a5db9185..0000000000000000000000000000000000000000 --- a/runs/stage1/checkpoint-0006000/resolved_backbone_config.json +++ /dev/null @@ -1,18 +0,0 @@ -{ - "vocab_size": 151680, - "d_model": 512, - "n_groups": 1, - "mamba_per_group": 7, - "n_heads": 8, - "n_kv_heads": 4, - "rope_theta": 1000000.0, - "mamba_d_state": 16, - "mamba_d_conv": 4, - "mamba_expand": 2, - "max_seq_len": 1024, - "dropout": 0.0, - "rms_norm_eps": 1e-05, - "tie_embeddings": true, - "head_dim": 64, - "mlp_hidden": 1408 -} \ No newline at end of file diff --git a/runs/stage1/checkpoint-0006000/training_state.pt b/runs/stage1/checkpoint-0006000/training_state.pt deleted file mode 100644 index c936138d820b3b4bc01b799586ca958990685e3c..0000000000000000000000000000000000000000 --- a/runs/stage1/checkpoint-0006000/training_state.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:c31aa978492fb43e0269312319ae3b8357ac4d25ff9f6619013104cda0514092 -size 739953938 diff --git a/runs/stage1/checkpoint-0007000/resolved_backbone_config.json b/runs/stage1/checkpoint-0007000/resolved_backbone_config.json deleted file mode 100644 index d9fd7084584b6db16d0dcfae05d56a05a5db9185..0000000000000000000000000000000000000000 --- a/runs/stage1/checkpoint-0007000/resolved_backbone_config.json +++ /dev/null @@ -1,18 +0,0 @@ -{ - "vocab_size": 151680, - "d_model": 512, - "n_groups": 1, - "mamba_per_group": 7, - "n_heads": 8, - "n_kv_heads": 4, - "rope_theta": 1000000.0, - "mamba_d_state": 16, - "mamba_d_conv": 4, - "mamba_expand": 2, - "max_seq_len": 1024, - "dropout": 0.0, - "rms_norm_eps": 1e-05, - "tie_embeddings": true, - "head_dim": 64, - "mlp_hidden": 1408 -} \ No newline at end of file diff --git a/runs/stage1/checkpoint-0007000/training_state.pt b/runs/stage1/checkpoint-0007000/training_state.pt deleted file mode 100644 index a6f8aa82ac2a92b08af279a768fa9c556c3fa57c..0000000000000000000000000000000000000000 --- a/runs/stage1/checkpoint-0007000/training_state.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:5d2a203f6f546f69f7a3ad08801e70d437b554a6ca1f0a5752e07be134514c31 -size 739953938 diff --git a/runs/stage1/checkpoint-0008000/resolved_backbone_config.json b/runs/stage1/checkpoint-0008000/resolved_backbone_config.json deleted file mode 100644 index d9fd7084584b6db16d0dcfae05d56a05a5db9185..0000000000000000000000000000000000000000 --- a/runs/stage1/checkpoint-0008000/resolved_backbone_config.json +++ /dev/null @@ -1,18 +0,0 @@ -{ - "vocab_size": 151680, - "d_model": 512, - "n_groups": 1, - "mamba_per_group": 7, - "n_heads": 8, - "n_kv_heads": 4, - "rope_theta": 1000000.0, - "mamba_d_state": 16, - "mamba_d_conv": 4, - "mamba_expand": 2, - "max_seq_len": 1024, - "dropout": 0.0, - "rms_norm_eps": 1e-05, - "tie_embeddings": true, - "head_dim": 64, - "mlp_hidden": 1408 -} \ No newline at end of file diff --git a/runs/stage1/checkpoint-0008000/training_state.pt b/runs/stage1/checkpoint-0008000/training_state.pt deleted file mode 100644 index d88bc8920b8d80ea0f78b9e2cb7433e107a89d6e..0000000000000000000000000000000000000000 --- a/runs/stage1/checkpoint-0008000/training_state.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:4d1b24b193c1c2fefae942dc82787e2a7ce9256e77a5d554d58530be2b069378 -size 739953938 diff --git a/runs/stage1/checkpoint-0009000/resolved_backbone_config.json b/runs/stage1/checkpoint-0009000/resolved_backbone_config.json deleted file mode 100644 index d9fd7084584b6db16d0dcfae05d56a05a5db9185..0000000000000000000000000000000000000000 --- a/runs/stage1/checkpoint-0009000/resolved_backbone_config.json +++ /dev/null @@ -1,18 +0,0 @@ -{ - "vocab_size": 151680, - "d_model": 512, - "n_groups": 1, - "mamba_per_group": 7, - "n_heads": 8, - "n_kv_heads": 4, - "rope_theta": 1000000.0, - "mamba_d_state": 16, - "mamba_d_conv": 4, - "mamba_expand": 2, - "max_seq_len": 1024, - "dropout": 0.0, - "rms_norm_eps": 1e-05, - "tie_embeddings": true, - "head_dim": 64, - "mlp_hidden": 1408 -} \ No newline at end of file diff --git a/runs/stage1/checkpoint-0009000/training_state.pt b/runs/stage1/checkpoint-0009000/training_state.pt deleted file mode 100644 index 8b484150a9fb08ff479299b0ce4faea44fde3f3d..0000000000000000000000000000000000000000 --- a/runs/stage1/checkpoint-0009000/training_state.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:969575929adac2e8e61e57db6163abe115bd30bb06a122d2a1175de24f4a019e -size 739954002 diff --git a/runs/stage1/checkpoint-0010000/resolved_backbone_config.json b/runs/stage1/checkpoint-0010000/resolved_backbone_config.json deleted file mode 100644 index d9fd7084584b6db16d0dcfae05d56a05a5db9185..0000000000000000000000000000000000000000 --- a/runs/stage1/checkpoint-0010000/resolved_backbone_config.json +++ /dev/null @@ -1,18 +0,0 @@ -{ - "vocab_size": 151680, - "d_model": 512, - "n_groups": 1, - "mamba_per_group": 7, - "n_heads": 8, - "n_kv_heads": 4, - "rope_theta": 1000000.0, - "mamba_d_state": 16, - "mamba_d_conv": 4, - "mamba_expand": 2, - "max_seq_len": 1024, - "dropout": 0.0, - "rms_norm_eps": 1e-05, - "tie_embeddings": true, - "head_dim": 64, - "mlp_hidden": 1408 -} \ No newline at end of file diff --git a/runs/stage1/checkpoint-0010000/training_state.pt b/runs/stage1/checkpoint-0010000/training_state.pt deleted file mode 100644 index a705405d5754b2af67b95360462e87d3d4909fb9..0000000000000000000000000000000000000000 --- a/runs/stage1/checkpoint-0010000/training_state.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:af2e6e59f117a54873affad6f123316734acde577348b586971c4231991069a6 -size 739954002 diff --git a/runs/stage1/checkpoint-0011000/resolved_backbone_config.json b/runs/stage1/checkpoint-0011000/resolved_backbone_config.json deleted file mode 100644 index d9fd7084584b6db16d0dcfae05d56a05a5db9185..0000000000000000000000000000000000000000 --- a/runs/stage1/checkpoint-0011000/resolved_backbone_config.json +++ /dev/null @@ -1,18 +0,0 @@ -{ - "vocab_size": 151680, - "d_model": 512, - "n_groups": 1, - "mamba_per_group": 7, - "n_heads": 8, - "n_kv_heads": 4, - "rope_theta": 1000000.0, - "mamba_d_state": 16, - "mamba_d_conv": 4, - "mamba_expand": 2, - "max_seq_len": 1024, - "dropout": 0.0, - "rms_norm_eps": 1e-05, - "tie_embeddings": true, - "head_dim": 64, - "mlp_hidden": 1408 -} \ No newline at end of file diff --git a/runs/stage1/checkpoint-0011000/training_state.pt b/runs/stage1/checkpoint-0011000/training_state.pt deleted file mode 100644 index 4cd3915ef17349795fff0f9565ee644463b2e0b5..0000000000000000000000000000000000000000 --- a/runs/stage1/checkpoint-0011000/training_state.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:71b655fcb792efea1f57c8d112c0e771d3e4ae55cf96a9577fce5bb286d090c2 -size 739954002 diff --git a/runs/stage1/checkpoint-0012000/resolved_backbone_config.json b/runs/stage1/checkpoint-0012000/resolved_backbone_config.json deleted file mode 100644 index d9fd7084584b6db16d0dcfae05d56a05a5db9185..0000000000000000000000000000000000000000 --- a/runs/stage1/checkpoint-0012000/resolved_backbone_config.json +++ /dev/null @@ -1,18 +0,0 @@ -{ - "vocab_size": 151680, - "d_model": 512, - "n_groups": 1, - "mamba_per_group": 7, - "n_heads": 8, - "n_kv_heads": 4, - "rope_theta": 1000000.0, - "mamba_d_state": 16, - "mamba_d_conv": 4, - "mamba_expand": 2, - "max_seq_len": 1024, - "dropout": 0.0, - "rms_norm_eps": 1e-05, - "tie_embeddings": true, - "head_dim": 64, - "mlp_hidden": 1408 -} \ No newline at end of file diff --git a/runs/stage1/checkpoint-0012000/training_state.pt b/runs/stage1/checkpoint-0012000/training_state.pt deleted file mode 100644 index 0805aed1f7af9420e8d7509ae1f70a46e000148f..0000000000000000000000000000000000000000 --- a/runs/stage1/checkpoint-0012000/training_state.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8480de487d7e73c127ec4bbe31e82dbdd3e083e4989fd0b8bfecb5edddac4d36 -size 739954002 diff --git a/runs/stage1/checkpoint-0013000/resolved_backbone_config.json b/runs/stage1/checkpoint-0013000/resolved_backbone_config.json deleted file mode 100644 index d9fd7084584b6db16d0dcfae05d56a05a5db9185..0000000000000000000000000000000000000000 --- a/runs/stage1/checkpoint-0013000/resolved_backbone_config.json +++ /dev/null @@ -1,18 +0,0 @@ -{ - "vocab_size": 151680, - "d_model": 512, - "n_groups": 1, - "mamba_per_group": 7, - "n_heads": 8, - "n_kv_heads": 4, - "rope_theta": 1000000.0, - "mamba_d_state": 16, - "mamba_d_conv": 4, - "mamba_expand": 2, - "max_seq_len": 1024, - "dropout": 0.0, - "rms_norm_eps": 1e-05, - "tie_embeddings": true, - "head_dim": 64, - "mlp_hidden": 1408 -} \ No newline at end of file diff --git a/runs/stage1/checkpoint-0013000/training_state.pt b/runs/stage1/checkpoint-0013000/training_state.pt deleted file mode 100644 index 68d90811a1de58155c5ca5c8e6794e61c2300f4a..0000000000000000000000000000000000000000 --- a/runs/stage1/checkpoint-0013000/training_state.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:a0902d9f6b6393f1dc209c79f9b504a8c698c50933fe314aa431e55f16ce12fc -size 739954002 diff --git a/runs/stage1/checkpoint-0014000/resolved_backbone_config.json b/runs/stage1/checkpoint-0014000/resolved_backbone_config.json deleted file mode 100644 index d9fd7084584b6db16d0dcfae05d56a05a5db9185..0000000000000000000000000000000000000000 --- a/runs/stage1/checkpoint-0014000/resolved_backbone_config.json +++ /dev/null @@ -1,18 +0,0 @@ -{ - "vocab_size": 151680, - "d_model": 512, - "n_groups": 1, - "mamba_per_group": 7, - "n_heads": 8, - "n_kv_heads": 4, - "rope_theta": 1000000.0, - "mamba_d_state": 16, - "mamba_d_conv": 4, - "mamba_expand": 2, - "max_seq_len": 1024, - "dropout": 0.0, - "rms_norm_eps": 1e-05, - "tie_embeddings": true, - "head_dim": 64, - "mlp_hidden": 1408 -} \ No newline at end of file diff --git a/runs/stage1/checkpoint-0014000/training_state.pt b/runs/stage1/checkpoint-0014000/training_state.pt deleted file mode 100644 index 783b3b039ee7c8e38962da52e45f1753a37a299a..0000000000000000000000000000000000000000 --- a/runs/stage1/checkpoint-0014000/training_state.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:b7d9bb8caf52bade2bc85cd92fb73c5dda4adf9b26707ad6ea95cec09cce121c -size 739954002 diff --git a/runs/stage1/checkpoint-0015000/resolved_backbone_config.json b/runs/stage1/checkpoint-0015000/resolved_backbone_config.json deleted file mode 100644 index d9fd7084584b6db16d0dcfae05d56a05a5db9185..0000000000000000000000000000000000000000 --- a/runs/stage1/checkpoint-0015000/resolved_backbone_config.json +++ /dev/null @@ -1,18 +0,0 @@ -{ - "vocab_size": 151680, - "d_model": 512, - "n_groups": 1, - "mamba_per_group": 7, - "n_heads": 8, - "n_kv_heads": 4, - "rope_theta": 1000000.0, - "mamba_d_state": 16, - "mamba_d_conv": 4, - "mamba_expand": 2, - "max_seq_len": 1024, - "dropout": 0.0, - "rms_norm_eps": 1e-05, - "tie_embeddings": true, - "head_dim": 64, - "mlp_hidden": 1408 -} \ No newline at end of file diff --git a/runs/stage1/checkpoint-0015000/training_state.pt b/runs/stage1/checkpoint-0015000/training_state.pt deleted file mode 100644 index 45bb31c3910951808c0d5d748f624febe1f2e1e3..0000000000000000000000000000000000000000 --- a/runs/stage1/checkpoint-0015000/training_state.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:e18717cb2f7c2c1a605c32dc567f10bbbc75a1b054e7af017369ade9c301f22f -size 739954002 diff --git a/runs/stage1/checkpoint-0016000/resolved_backbone_config.json b/runs/stage1/checkpoint-0016000/resolved_backbone_config.json deleted file mode 100644 index d9fd7084584b6db16d0dcfae05d56a05a5db9185..0000000000000000000000000000000000000000 --- a/runs/stage1/checkpoint-0016000/resolved_backbone_config.json +++ /dev/null @@ -1,18 +0,0 @@ -{ - "vocab_size": 151680, - "d_model": 512, - "n_groups": 1, - "mamba_per_group": 7, - "n_heads": 8, - "n_kv_heads": 4, - "rope_theta": 1000000.0, - "mamba_d_state": 16, - "mamba_d_conv": 4, - "mamba_expand": 2, - "max_seq_len": 1024, - "dropout": 0.0, - "rms_norm_eps": 1e-05, - "tie_embeddings": true, - "head_dim": 64, - "mlp_hidden": 1408 -} \ No newline at end of file diff --git a/runs/stage1/checkpoint-0016000/training_state.pt b/runs/stage1/checkpoint-0016000/training_state.pt deleted file mode 100644 index 15364dc79a57b339a024d5df8648ee3f3ca67cf1..0000000000000000000000000000000000000000 --- a/runs/stage1/checkpoint-0016000/training_state.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:3e3bd55c4d0a0ff1818c60a42ae1b5b8953465f1b0c93f7f962b7b2edece52e1 -size 739954002 diff --git a/runs/stage1/checkpoint-0017000/resolved_backbone_config.json b/runs/stage1/checkpoint-0017000/resolved_backbone_config.json deleted file mode 100644 index d9fd7084584b6db16d0dcfae05d56a05a5db9185..0000000000000000000000000000000000000000 --- a/runs/stage1/checkpoint-0017000/resolved_backbone_config.json +++ /dev/null @@ -1,18 +0,0 @@ -{ - "vocab_size": 151680, - "d_model": 512, - "n_groups": 1, - "mamba_per_group": 7, - "n_heads": 8, - "n_kv_heads": 4, - "rope_theta": 1000000.0, - "mamba_d_state": 16, - "mamba_d_conv": 4, - "mamba_expand": 2, - "max_seq_len": 1024, - "dropout": 0.0, - "rms_norm_eps": 1e-05, - "tie_embeddings": true, - "head_dim": 64, - "mlp_hidden": 1408 -} \ No newline at end of file diff --git a/runs/stage1/checkpoint-0017000/training_state.pt b/runs/stage1/checkpoint-0017000/training_state.pt deleted file mode 100644 index 6fa724eb32bccfc4e2407bd1fae9f938415cc465..0000000000000000000000000000000000000000 --- a/runs/stage1/checkpoint-0017000/training_state.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:d6ee87a7b7c257323921c3ec74a26d2e7b6dcc59c28520da4b8ee09e1d266ea5 -size 739954002 diff --git a/runs/stage1/checkpoint-0018000/resolved_backbone_config.json b/runs/stage1/checkpoint-0018000/resolved_backbone_config.json deleted file mode 100644 index d9fd7084584b6db16d0dcfae05d56a05a5db9185..0000000000000000000000000000000000000000 --- a/runs/stage1/checkpoint-0018000/resolved_backbone_config.json +++ /dev/null @@ -1,18 +0,0 @@ -{ - "vocab_size": 151680, - "d_model": 512, - "n_groups": 1, - "mamba_per_group": 7, - "n_heads": 8, - "n_kv_heads": 4, - "rope_theta": 1000000.0, - "mamba_d_state": 16, - "mamba_d_conv": 4, - "mamba_expand": 2, - "max_seq_len": 1024, - "dropout": 0.0, - "rms_norm_eps": 1e-05, - "tie_embeddings": true, - "head_dim": 64, - "mlp_hidden": 1408 -} \ No newline at end of file diff --git a/runs/stage1/checkpoint-0018000/training_state.pt b/runs/stage1/checkpoint-0018000/training_state.pt deleted file mode 100644 index fff5a7bf60b94d3048e7380b2ba27b2d91a13f59..0000000000000000000000000000000000000000 --- a/runs/stage1/checkpoint-0018000/training_state.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:a71c4519158bfd283d8f846a1e1bc26d2d774bc122076b15770b6368f46cdb70 -size 739954002 diff --git a/runs/stage1/checkpoint-0019000/resolved_backbone_config.json b/runs/stage1/checkpoint-0019000/resolved_backbone_config.json deleted file mode 100644 index d9fd7084584b6db16d0dcfae05d56a05a5db9185..0000000000000000000000000000000000000000 --- a/runs/stage1/checkpoint-0019000/resolved_backbone_config.json +++ /dev/null @@ -1,18 +0,0 @@ -{ - "vocab_size": 151680, - "d_model": 512, - "n_groups": 1, - "mamba_per_group": 7, - "n_heads": 8, - "n_kv_heads": 4, - "rope_theta": 1000000.0, - "mamba_d_state": 16, - "mamba_d_conv": 4, - "mamba_expand": 2, - "max_seq_len": 1024, - "dropout": 0.0, - "rms_norm_eps": 1e-05, - "tie_embeddings": true, - "head_dim": 64, - "mlp_hidden": 1408 -} \ No newline at end of file diff --git a/runs/stage1/checkpoint-0019000/training_state.pt b/runs/stage1/checkpoint-0019000/training_state.pt deleted file mode 100644 index 29c0edf61bc5094279f043cdf549c19056f0286f..0000000000000000000000000000000000000000 --- a/runs/stage1/checkpoint-0019000/training_state.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:a21066ef55c77194bc0e938cc3981956c9781c8b0444a3664ccbffdb277f5223 -size 739954002 diff --git a/runs/stage1/checkpoint-0020000/resolved_backbone_config.json b/runs/stage1/checkpoint-0020000/resolved_backbone_config.json deleted file mode 100644 index d9fd7084584b6db16d0dcfae05d56a05a5db9185..0000000000000000000000000000000000000000 --- a/runs/stage1/checkpoint-0020000/resolved_backbone_config.json +++ /dev/null @@ -1,18 +0,0 @@ -{ - "vocab_size": 151680, - "d_model": 512, - "n_groups": 1, - "mamba_per_group": 7, - "n_heads": 8, - "n_kv_heads": 4, - "rope_theta": 1000000.0, - "mamba_d_state": 16, - "mamba_d_conv": 4, - "mamba_expand": 2, - "max_seq_len": 1024, - "dropout": 0.0, - "rms_norm_eps": 1e-05, - "tie_embeddings": true, - "head_dim": 64, - "mlp_hidden": 1408 -} \ No newline at end of file diff --git a/runs/stage1/checkpoint-0020000/training_state.pt b/runs/stage1/checkpoint-0020000/training_state.pt deleted file mode 100644 index 882989797ad454af4bf5dcccb2ff09d1613b9ea9..0000000000000000000000000000000000000000 --- a/runs/stage1/checkpoint-0020000/training_state.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:2495aab5f67fa89bb5ac7301680fed8cb0ed560474d3f9e5aeabca3cb660b460 -size 739954002 diff --git a/runs/stage1/checkpoint-0021000/resolved_backbone_config.json b/runs/stage1/checkpoint-0021000/resolved_backbone_config.json deleted file mode 100644 index d9fd7084584b6db16d0dcfae05d56a05a5db9185..0000000000000000000000000000000000000000 --- a/runs/stage1/checkpoint-0021000/resolved_backbone_config.json +++ /dev/null @@ -1,18 +0,0 @@ -{ - "vocab_size": 151680, - "d_model": 512, - "n_groups": 1, - "mamba_per_group": 7, - "n_heads": 8, - "n_kv_heads": 4, - "rope_theta": 1000000.0, - "mamba_d_state": 16, - "mamba_d_conv": 4, - "mamba_expand": 2, - "max_seq_len": 1024, - "dropout": 0.0, - "rms_norm_eps": 1e-05, - "tie_embeddings": true, - "head_dim": 64, - "mlp_hidden": 1408 -} \ No newline at end of file diff --git a/runs/stage1/checkpoint-0021000/training_state.pt b/runs/stage1/checkpoint-0021000/training_state.pt deleted file mode 100644 index 75d6628251de020018fb58ced81a9c0fa0cfe85d..0000000000000000000000000000000000000000 --- a/runs/stage1/checkpoint-0021000/training_state.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:bb98e3e3b2d2bf12066b4bf1ba53f4252c0b6c2ce97356fe67b132c6b850da24 -size 739954002 diff --git a/runs/stage2/checkpoint-0000500/resolved_backbone_config.json b/runs/stage2/checkpoint-0000500/resolved_backbone_config.json deleted file mode 100644 index 3196033abee3e5a26b5c30b3786104e73e5a7f2b..0000000000000000000000000000000000000000 --- a/runs/stage2/checkpoint-0000500/resolved_backbone_config.json +++ /dev/null @@ -1,18 +0,0 @@ -{ - "vocab_size": 151680, - "d_model": 512, - "n_groups": 1, - "mamba_per_group": 7, - "n_heads": 8, - "n_kv_heads": 4, - "rope_theta": 1000000.0, - "mamba_d_state": 16, - "mamba_d_conv": 4, - "mamba_expand": 2, - "max_seq_len": 2048, - "dropout": 0.0, - "rms_norm_eps": 1e-05, - "tie_embeddings": true, - "head_dim": 64, - "mlp_hidden": 1408 -} \ No newline at end of file diff --git a/runs/stage2/checkpoint-0000500/training_state.pt b/runs/stage2/checkpoint-0000500/training_state.pt deleted file mode 100644 index 869dab55d03899414a6e462e9d0f4b4c61401185..0000000000000000000000000000000000000000 --- a/runs/stage2/checkpoint-0000500/training_state.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:d688a5c4aad347c21b1ebb1eda59d3dcd6d27bc3e73ab8e46020f12aceffed70 -size 739953938 diff --git a/runs/stage2/checkpoint-0001000/resolved_backbone_config.json b/runs/stage2/checkpoint-0001000/resolved_backbone_config.json deleted file mode 100644 index 3196033abee3e5a26b5c30b3786104e73e5a7f2b..0000000000000000000000000000000000000000 --- a/runs/stage2/checkpoint-0001000/resolved_backbone_config.json +++ /dev/null @@ -1,18 +0,0 @@ -{ - "vocab_size": 151680, - "d_model": 512, - "n_groups": 1, - "mamba_per_group": 7, - "n_heads": 8, - "n_kv_heads": 4, - "rope_theta": 1000000.0, - "mamba_d_state": 16, - "mamba_d_conv": 4, - "mamba_expand": 2, - "max_seq_len": 2048, - "dropout": 0.0, - "rms_norm_eps": 1e-05, - "tie_embeddings": true, - "head_dim": 64, - "mlp_hidden": 1408 -} \ No newline at end of file diff --git a/runs/stage2/checkpoint-0001000/training_state.pt b/runs/stage2/checkpoint-0001000/training_state.pt deleted file mode 100644 index 38f35e582b2d808f9202cf5ffbd746002ce966f9..0000000000000000000000000000000000000000 --- a/runs/stage2/checkpoint-0001000/training_state.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:cc3252c2d5eea0df7ba322c8376242a648a881f93da203352d4b73c49716a63a -size 739953938 diff --git a/runs/stage2/checkpoint-0001500/resolved_backbone_config.json b/runs/stage2/checkpoint-0001500/resolved_backbone_config.json deleted file mode 100644 index 3196033abee3e5a26b5c30b3786104e73e5a7f2b..0000000000000000000000000000000000000000 --- a/runs/stage2/checkpoint-0001500/resolved_backbone_config.json +++ /dev/null @@ -1,18 +0,0 @@ -{ - "vocab_size": 151680, - "d_model": 512, - "n_groups": 1, - "mamba_per_group": 7, - "n_heads": 8, - "n_kv_heads": 4, - "rope_theta": 1000000.0, - "mamba_d_state": 16, - "mamba_d_conv": 4, - "mamba_expand": 2, - "max_seq_len": 2048, - "dropout": 0.0, - "rms_norm_eps": 1e-05, - "tie_embeddings": true, - "head_dim": 64, - "mlp_hidden": 1408 -} \ No newline at end of file diff --git a/runs/stage2/checkpoint-0001500/training_state.pt b/runs/stage2/checkpoint-0001500/training_state.pt deleted file mode 100644 index 87b12f57a2f8df8e9ba8f7b015be72527cd2207e..0000000000000000000000000000000000000000 --- a/runs/stage2/checkpoint-0001500/training_state.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:2f48c4e8a6f931acafb1dab127375cf5265e476a906cd136da8f9da9f0d606b3 -size 739953938 diff --git a/runs/stage2/checkpoint-0002000/resolved_backbone_config.json b/runs/stage2/checkpoint-0002000/resolved_backbone_config.json deleted file mode 100644 index 3196033abee3e5a26b5c30b3786104e73e5a7f2b..0000000000000000000000000000000000000000 --- a/runs/stage2/checkpoint-0002000/resolved_backbone_config.json +++ /dev/null @@ -1,18 +0,0 @@ -{ - "vocab_size": 151680, - "d_model": 512, - "n_groups": 1, - "mamba_per_group": 7, - "n_heads": 8, - "n_kv_heads": 4, - "rope_theta": 1000000.0, - "mamba_d_state": 16, - "mamba_d_conv": 4, - "mamba_expand": 2, - "max_seq_len": 2048, - "dropout": 0.0, - "rms_norm_eps": 1e-05, - "tie_embeddings": true, - "head_dim": 64, - "mlp_hidden": 1408 -} \ No newline at end of file diff --git a/runs/stage2/checkpoint-0002000/training_state.pt b/runs/stage2/checkpoint-0002000/training_state.pt deleted file mode 100644 index 01c660a80c36c044abd28ac1192a86a63146af9e..0000000000000000000000000000000000000000 --- a/runs/stage2/checkpoint-0002000/training_state.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:9bbc16904bb862202671f5a411515f1c972b9676e4058e26dfc8b9f67546893d -size 739953810 diff --git a/runs/stage2/checkpoint-0002500/resolved_backbone_config.json b/runs/stage2/checkpoint-0002500/resolved_backbone_config.json deleted file mode 100644 index 3196033abee3e5a26b5c30b3786104e73e5a7f2b..0000000000000000000000000000000000000000 --- a/runs/stage2/checkpoint-0002500/resolved_backbone_config.json +++ /dev/null @@ -1,18 +0,0 @@ -{ - "vocab_size": 151680, - "d_model": 512, - "n_groups": 1, - "mamba_per_group": 7, - "n_heads": 8, - "n_kv_heads": 4, - "rope_theta": 1000000.0, - "mamba_d_state": 16, - "mamba_d_conv": 4, - "mamba_expand": 2, - "max_seq_len": 2048, - "dropout": 0.0, - "rms_norm_eps": 1e-05, - "tie_embeddings": true, - "head_dim": 64, - "mlp_hidden": 1408 -} \ No newline at end of file diff --git a/runs/stage2/checkpoint-0002500/training_state.pt b/runs/stage2/checkpoint-0002500/training_state.pt deleted file mode 100644 index 6de8a84e480dd47e43811a8e9c7f95b86745328b..0000000000000000000000000000000000000000 --- a/runs/stage2/checkpoint-0002500/training_state.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:bc40fa7ed4bed4d125c2e965cdcf10a5e3f6efac9f98cb9f4b31d1cdb17996da -size 739953938 diff --git a/runs/stage2/checkpoint-0003000/resolved_backbone_config.json b/runs/stage2/checkpoint-0003000/resolved_backbone_config.json deleted file mode 100644 index 3196033abee3e5a26b5c30b3786104e73e5a7f2b..0000000000000000000000000000000000000000 --- a/runs/stage2/checkpoint-0003000/resolved_backbone_config.json +++ /dev/null @@ -1,18 +0,0 @@ -{ - "vocab_size": 151680, - "d_model": 512, - "n_groups": 1, - "mamba_per_group": 7, - "n_heads": 8, - "n_kv_heads": 4, - "rope_theta": 1000000.0, - "mamba_d_state": 16, - "mamba_d_conv": 4, - "mamba_expand": 2, - "max_seq_len": 2048, - "dropout": 0.0, - "rms_norm_eps": 1e-05, - "tie_embeddings": true, - "head_dim": 64, - "mlp_hidden": 1408 -} \ No newline at end of file diff --git a/runs/stage2/checkpoint-0003000/training_state.pt b/runs/stage2/checkpoint-0003000/training_state.pt deleted file mode 100644 index fdef980e3f43221df36021a6dde778866213f475..0000000000000000000000000000000000000000 --- a/runs/stage2/checkpoint-0003000/training_state.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:82c2390212f7409d77518455b6a48b4fab78a720cefc4300cc982cf8bcb3dbce -size 739953938 diff --git a/runs/stage2/checkpoint-0003500/resolved_backbone_config.json b/runs/stage2/checkpoint-0003500/resolved_backbone_config.json deleted file mode 100644 index 3196033abee3e5a26b5c30b3786104e73e5a7f2b..0000000000000000000000000000000000000000 --- a/runs/stage2/checkpoint-0003500/resolved_backbone_config.json +++ /dev/null @@ -1,18 +0,0 @@ -{ - "vocab_size": 151680, - "d_model": 512, - "n_groups": 1, - "mamba_per_group": 7, - "n_heads": 8, - "n_kv_heads": 4, - "rope_theta": 1000000.0, - "mamba_d_state": 16, - "mamba_d_conv": 4, - "mamba_expand": 2, - "max_seq_len": 2048, - "dropout": 0.0, - "rms_norm_eps": 1e-05, - "tie_embeddings": true, - "head_dim": 64, - "mlp_hidden": 1408 -} \ No newline at end of file diff --git a/runs/stage2/checkpoint-0003500/training_state.pt b/runs/stage2/checkpoint-0003500/training_state.pt deleted file mode 100644 index d35ca3d8ef4de8d8c0472d22afdac406c2cd947a..0000000000000000000000000000000000000000 --- a/runs/stage2/checkpoint-0003500/training_state.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:7ad125f6722ff684cba67b4c6a4c0693036d5feea09a52bcb008e84485d756e8 -size 739953938 diff --git a/runs/stage2/checkpoint-0004000/resolved_backbone_config.json b/runs/stage2/checkpoint-0004000/resolved_backbone_config.json deleted file mode 100644 index 3196033abee3e5a26b5c30b3786104e73e5a7f2b..0000000000000000000000000000000000000000 --- a/runs/stage2/checkpoint-0004000/resolved_backbone_config.json +++ /dev/null @@ -1,18 +0,0 @@ -{ - "vocab_size": 151680, - "d_model": 512, - "n_groups": 1, - "mamba_per_group": 7, - "n_heads": 8, - "n_kv_heads": 4, - "rope_theta": 1000000.0, - "mamba_d_state": 16, - "mamba_d_conv": 4, - "mamba_expand": 2, - "max_seq_len": 2048, - "dropout": 0.0, - "rms_norm_eps": 1e-05, - "tie_embeddings": true, - "head_dim": 64, - "mlp_hidden": 1408 -} \ No newline at end of file diff --git a/runs/stage2/checkpoint-0004000/training_state.pt b/runs/stage2/checkpoint-0004000/training_state.pt deleted file mode 100644 index 69ef9f94e6ab7c4f2acd932988be9ba9721e3923..0000000000000000000000000000000000000000 --- a/runs/stage2/checkpoint-0004000/training_state.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:48594c3922dfc55b6c60e6e6c254de3757c23ccf863dbd5bdcf44a51e96cbdb3 -size 739954258 diff --git a/runs/stage2/checkpoint-0004500/resolved_backbone_config.json b/runs/stage2/checkpoint-0004500/resolved_backbone_config.json deleted file mode 100644 index 3196033abee3e5a26b5c30b3786104e73e5a7f2b..0000000000000000000000000000000000000000 --- a/runs/stage2/checkpoint-0004500/resolved_backbone_config.json +++ /dev/null @@ -1,18 +0,0 @@ -{ - "vocab_size": 151680, - "d_model": 512, - "n_groups": 1, - "mamba_per_group": 7, - "n_heads": 8, - "n_kv_heads": 4, - "rope_theta": 1000000.0, - "mamba_d_state": 16, - "mamba_d_conv": 4, - "mamba_expand": 2, - "max_seq_len": 2048, - "dropout": 0.0, - "rms_norm_eps": 1e-05, - "tie_embeddings": true, - "head_dim": 64, - "mlp_hidden": 1408 -} \ No newline at end of file diff --git a/runs/stage2/checkpoint-0004500/training_state.pt b/runs/stage2/checkpoint-0004500/training_state.pt deleted file mode 100644 index 7ce3cf07967a584f478964d2a7ef54e6cce6cf81..0000000000000000000000000000000000000000 --- a/runs/stage2/checkpoint-0004500/training_state.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:97abb14be96912e13145cca345741011eaa30bd2d0c3771131a0a436595b45fd -size 739954258 diff --git a/runs/stage2/checkpoint-0004920/resolved_backbone_config.json b/runs/stage2/checkpoint-0004920/resolved_backbone_config.json deleted file mode 100644 index 3196033abee3e5a26b5c30b3786104e73e5a7f2b..0000000000000000000000000000000000000000 --- a/runs/stage2/checkpoint-0004920/resolved_backbone_config.json +++ /dev/null @@ -1,18 +0,0 @@ -{ - "vocab_size": 151680, - "d_model": 512, - "n_groups": 1, - "mamba_per_group": 7, - "n_heads": 8, - "n_kv_heads": 4, - "rope_theta": 1000000.0, - "mamba_d_state": 16, - "mamba_d_conv": 4, - "mamba_expand": 2, - "max_seq_len": 2048, - "dropout": 0.0, - "rms_norm_eps": 1e-05, - "tie_embeddings": true, - "head_dim": 64, - "mlp_hidden": 1408 -} \ No newline at end of file diff --git a/runs/stage2/checkpoint-0004920/training_state.pt b/runs/stage2/checkpoint-0004920/training_state.pt deleted file mode 100644 index 3cd76001474abbc1ac6ebda10ffc9a89882bbc32..0000000000000000000000000000000000000000 --- a/runs/stage2/checkpoint-0004920/training_state.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:aa54f0aa09e5b5ec85816cad1cca9a09627c4b952a7934e1b9045f24b6fcc179 -size 739954258 diff --git a/runs/stage3/best/adapter_model/README.md b/runs/stage3/best/adapter_model/README.md deleted file mode 100644 index 0faa9ea1f80a3dcf3a2dce68a301458dcc28d5d1..0000000000000000000000000000000000000000 --- a/runs/stage3/best/adapter_model/README.md +++ /dev/null @@ -1,207 +0,0 @@ ---- -base_model: ai21labs/AI21-Jamba-Reasoning-3B -library_name: peft -pipeline_tag: text-generation -tags: -- base_model:adapter:ai21labs/AI21-Jamba-Reasoning-3B -- lora -- transformers ---- - -# Model Card for Model ID - - - - - -## Model Details - -### Model Description - - - - - -- **Developed by:** [More Information Needed] -- **Funded by [optional]:** [More Information Needed] -- **Shared by [optional]:** [More Information Needed] -- **Model type:** [More Information Needed] -- **Language(s) (NLP):** [More Information Needed] -- **License:** [More Information Needed] -- **Finetuned from model [optional]:** [More Information Needed] - -### Model Sources [optional] - - - -- **Repository:** [More Information Needed] -- **Paper [optional]:** [More Information Needed] -- **Demo [optional]:** [More Information Needed] - -## Uses - - - -### Direct Use - - - -[More Information Needed] - -### Downstream Use [optional] - - - -[More Information Needed] - -### Out-of-Scope Use - - - -[More Information Needed] - -## Bias, Risks, and Limitations - - - -[More Information Needed] - -### Recommendations - - - -Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. - -## How to Get Started with the Model - -Use the code below to get started with the model. - -[More Information Needed] - -## Training Details - -### Training Data - - - -[More Information Needed] - -### Training Procedure - - - -#### Preprocessing [optional] - -[More Information Needed] - - -#### Training Hyperparameters - -- **Training regime:** [More Information Needed] - -#### Speeds, Sizes, Times [optional] - - - -[More Information Needed] - -## Evaluation - - - -### Testing Data, Factors & Metrics - -#### Testing Data - - - -[More Information Needed] - -#### Factors - - - -[More Information Needed] - -#### Metrics - - - -[More Information Needed] - -### Results - -[More Information Needed] - -#### Summary - - - -## Model Examination [optional] - - - -[More Information Needed] - -## Environmental Impact - - - -Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - -- **Hardware Type:** [More Information Needed] -- **Hours used:** [More Information Needed] -- **Cloud Provider:** [More Information Needed] -- **Compute Region:** [More Information Needed] -- **Carbon Emitted:** [More Information Needed] - -## Technical Specifications [optional] - -### Model Architecture and Objective - -[More Information Needed] - -### Compute Infrastructure - -[More Information Needed] - -#### Hardware - -[More Information Needed] - -#### Software - -[More Information Needed] - -## Citation [optional] - - - -**BibTeX:** - -[More Information Needed] - -**APA:** - -[More Information Needed] - -## Glossary [optional] - - - -[More Information Needed] - -## More Information [optional] - -[More Information Needed] - -## Model Card Authors [optional] - -[More Information Needed] - -## Model Card Contact - -[More Information Needed] -### Framework versions - -- PEFT 0.18.1 \ No newline at end of file diff --git a/runs/stage3/best/adapter_model/adapter_config.json b/runs/stage3/best/adapter_model/adapter_config.json deleted file mode 100644 index 9a29a2efa1c03d4d7d26ad2e365e1e24e83847f0..0000000000000000000000000000000000000000 --- a/runs/stage3/best/adapter_model/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "out_proj", - "x_proj", - "o_proj", - "dt_proj", - "q_proj", - "k_proj", - "in_proj", - "v_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/runs/stage3/best/adapter_model/adapter_model.safetensors b/runs/stage3/best/adapter_model/adapter_model.safetensors deleted file mode 100644 index ef5e6270c8fcb806941544abea6cae61a92790ff..0000000000000000000000000000000000000000 --- a/runs/stage3/best/adapter_model/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6cf0bd66f3786a74e78decc225cd5f90602937ead68942df0bcb09722faa643d -size 1449633736 diff --git a/runs/stage3/best/training_state.pt b/runs/stage3/best/training_state.pt deleted file mode 100644 index 61a6a7bfac630676ecb4c4f10d617c16b16c1214..0000000000000000000000000000000000000000 --- a/runs/stage3/best/training_state.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:dd0c4571fca8ab7c2087ef33a5131b3c8ae060acd83f87806b20e957dd241f8f -size 215006601 diff --git a/runs/stage3/stage_0/best/adapter_model/README.md b/runs/stage3/stage_0/best/adapter_model/README.md deleted file mode 100644 index 0faa9ea1f80a3dcf3a2dce68a301458dcc28d5d1..0000000000000000000000000000000000000000 --- a/runs/stage3/stage_0/best/adapter_model/README.md +++ /dev/null @@ -1,207 +0,0 @@ ---- -base_model: ai21labs/AI21-Jamba-Reasoning-3B -library_name: peft -pipeline_tag: text-generation -tags: -- base_model:adapter:ai21labs/AI21-Jamba-Reasoning-3B -- lora -- transformers ---- - -# Model Card for Model ID - - - - - -## Model Details - -### Model Description - - - - - -- **Developed by:** [More Information Needed] -- **Funded by [optional]:** [More Information Needed] -- **Shared by [optional]:** [More Information Needed] -- **Model type:** [More Information Needed] -- **Language(s) (NLP):** [More Information Needed] -- **License:** [More Information Needed] -- **Finetuned from model [optional]:** [More Information Needed] - -### Model Sources [optional] - - - -- **Repository:** [More Information Needed] -- **Paper [optional]:** [More Information Needed] -- **Demo [optional]:** [More Information Needed] - -## Uses - - - -### Direct Use - - - -[More Information Needed] - -### Downstream Use [optional] - - - -[More Information Needed] - -### Out-of-Scope Use - - - -[More Information Needed] - -## Bias, Risks, and Limitations - - - -[More Information Needed] - -### Recommendations - - - -Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. - -## How to Get Started with the Model - -Use the code below to get started with the model. - -[More Information Needed] - -## Training Details - -### Training Data - - - -[More Information Needed] - -### Training Procedure - - - -#### Preprocessing [optional] - -[More Information Needed] - - -#### Training Hyperparameters - -- **Training regime:** [More Information Needed] - -#### Speeds, Sizes, Times [optional] - - - -[More Information Needed] - -## Evaluation - - - -### Testing Data, Factors & Metrics - -#### Testing Data - - - -[More Information Needed] - -#### Factors - - - -[More Information Needed] - -#### Metrics - - - -[More Information Needed] - -### Results - -[More Information Needed] - -#### Summary - - - -## Model Examination [optional] - - - -[More Information Needed] - -## Environmental Impact - - - -Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - -- **Hardware Type:** [More Information Needed] -- **Hours used:** [More Information Needed] -- **Cloud Provider:** [More Information Needed] -- **Compute Region:** [More Information Needed] -- **Carbon Emitted:** [More Information Needed] - -## Technical Specifications [optional] - -### Model Architecture and Objective - -[More Information Needed] - -### Compute Infrastructure - -[More Information Needed] - -#### Hardware - -[More Information Needed] - -#### Software - -[More Information Needed] - -## Citation [optional] - - - -**BibTeX:** - -[More Information Needed] - -**APA:** - -[More Information Needed] - -## Glossary [optional] - - - -[More Information Needed] - -## More Information [optional] - -[More Information Needed] - -## Model Card Authors [optional] - -[More Information Needed] - -## Model Card Contact - -[More Information Needed] -### Framework versions - -- PEFT 0.18.1 \ No newline at end of file diff --git a/runs/stage3/stage_0/best/adapter_model/adapter_config.json b/runs/stage3/stage_0/best/adapter_model/adapter_config.json deleted file mode 100644 index a8cfa7572e39bed4a7f9e06397495762151325dd..0000000000000000000000000000000000000000 --- a/runs/stage3/stage_0/best/adapter_model/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "x_proj", - "in_proj", - "o_proj", - "q_proj", - "k_proj", - "out_proj", - "dt_proj", - "v_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/runs/stage3/stage_0/best/adapter_model/adapter_model.safetensors b/runs/stage3/stage_0/best/adapter_model/adapter_model.safetensors deleted file mode 100644 index 2f8ee8818b7d9f5441d4a51c9762ceaa021fa743..0000000000000000000000000000000000000000 --- a/runs/stage3/stage_0/best/adapter_model/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:f31c348c1f4a0888da59ae9a2fefb8f6cd5699fdeaa72f882c005106a86714da -size 1449633736 diff --git a/runs/stage3/stage_0/best/training_state.pt b/runs/stage3/stage_0/best/training_state.pt deleted file mode 100644 index 93b9998309e5e1232f23e10f4e552f634ffc3007..0000000000000000000000000000000000000000 --- a/runs/stage3/stage_0/best/training_state.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:179c81186c187318faee60993391119b5dbbdc5782adcb27a23738b9900558a7 -size 215006601 diff --git a/runs/stage3/stage_0/checkpoint-0000894/adapter_model/README.md b/runs/stage3/stage_0/checkpoint-0000894/adapter_model/README.md deleted file mode 100644 index 0faa9ea1f80a3dcf3a2dce68a301458dcc28d5d1..0000000000000000000000000000000000000000 --- a/runs/stage3/stage_0/checkpoint-0000894/adapter_model/README.md +++ /dev/null @@ -1,207 +0,0 @@ ---- -base_model: ai21labs/AI21-Jamba-Reasoning-3B -library_name: peft -pipeline_tag: text-generation -tags: -- base_model:adapter:ai21labs/AI21-Jamba-Reasoning-3B -- lora -- transformers ---- - -# Model Card for Model ID - - - - - -## Model Details - -### Model Description - - - - - -- **Developed by:** [More Information Needed] -- **Funded by [optional]:** [More Information Needed] -- **Shared by [optional]:** [More Information Needed] -- **Model type:** [More Information Needed] -- **Language(s) (NLP):** [More Information Needed] -- **License:** [More Information Needed] -- **Finetuned from model [optional]:** [More Information Needed] - -### Model Sources [optional] - - - -- **Repository:** [More Information Needed] -- **Paper [optional]:** [More Information Needed] -- **Demo [optional]:** [More Information Needed] - -## Uses - - - -### Direct Use - - - -[More Information Needed] - -### Downstream Use [optional] - - - -[More Information Needed] - -### Out-of-Scope Use - - - -[More Information Needed] - -## Bias, Risks, and Limitations - - - -[More Information Needed] - -### Recommendations - - - -Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. - -## How to Get Started with the Model - -Use the code below to get started with the model. - -[More Information Needed] - -## Training Details - -### Training Data - - - -[More Information Needed] - -### Training Procedure - - - -#### Preprocessing [optional] - -[More Information Needed] - - -#### Training Hyperparameters - -- **Training regime:** [More Information Needed] - -#### Speeds, Sizes, Times [optional] - - - -[More Information Needed] - -## Evaluation - - - -### Testing Data, Factors & Metrics - -#### Testing Data - - - -[More Information Needed] - -#### Factors - - - -[More Information Needed] - -#### Metrics - - - -[More Information Needed] - -### Results - -[More Information Needed] - -#### Summary - - - -## Model Examination [optional] - - - -[More Information Needed] - -## Environmental Impact - - - -Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - -- **Hardware Type:** [More Information Needed] -- **Hours used:** [More Information Needed] -- **Cloud Provider:** [More Information Needed] -- **Compute Region:** [More Information Needed] -- **Carbon Emitted:** [More Information Needed] - -## Technical Specifications [optional] - -### Model Architecture and Objective - -[More Information Needed] - -### Compute Infrastructure - -[More Information Needed] - -#### Hardware - -[More Information Needed] - -#### Software - -[More Information Needed] - -## Citation [optional] - - - -**BibTeX:** - -[More Information Needed] - -**APA:** - -[More Information Needed] - -## Glossary [optional] - - - -[More Information Needed] - -## More Information [optional] - -[More Information Needed] - -## Model Card Authors [optional] - -[More Information Needed] - -## Model Card Contact - -[More Information Needed] -### Framework versions - -- PEFT 0.18.1 \ No newline at end of file diff --git a/runs/stage3/stage_0/checkpoint-0000894/adapter_model/adapter_config.json b/runs/stage3/stage_0/checkpoint-0000894/adapter_model/adapter_config.json deleted file mode 100644 index 48f54cd01f8ca3f7044a174b1dd3204570e65a42..0000000000000000000000000000000000000000 --- a/runs/stage3/stage_0/checkpoint-0000894/adapter_model/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "dt_proj", - "in_proj", - "q_proj", - "k_proj", - "v_proj", - "out_proj", - "o_proj", - "x_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/runs/stage3/stage_0/checkpoint-0000894/adapter_model/adapter_model.safetensors b/runs/stage3/stage_0/checkpoint-0000894/adapter_model/adapter_model.safetensors deleted file mode 100644 index b34da32918c6117f1250c5eb563e69697f6d0293..0000000000000000000000000000000000000000 --- a/runs/stage3/stage_0/checkpoint-0000894/adapter_model/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:60d625e6d15ffa9c44d1e65d0118ac4cf34dcce7adb2bcc51dbb0537b160c365 -size 1449633736 diff --git a/runs/stage3/stage_0/checkpoint-0000894/training_state.pt b/runs/stage3/stage_0/checkpoint-0000894/training_state.pt deleted file mode 100644 index 5b36b5ce405b4bebc4d29453667b2acf875c8e34..0000000000000000000000000000000000000000 --- a/runs/stage3/stage_0/checkpoint-0000894/training_state.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:9261bfa114c9383fa4ec1cbc307144446bda1e11ee685f9a294c4c4e82c0928b -size 215006601 diff --git a/runs/stage3/stage_0/checkpoint-0001154/adapter_model/README.md b/runs/stage3/stage_0/checkpoint-0001154/adapter_model/README.md deleted file mode 100644 index 0faa9ea1f80a3dcf3a2dce68a301458dcc28d5d1..0000000000000000000000000000000000000000 --- a/runs/stage3/stage_0/checkpoint-0001154/adapter_model/README.md +++ /dev/null @@ -1,207 +0,0 @@ ---- -base_model: ai21labs/AI21-Jamba-Reasoning-3B -library_name: peft -pipeline_tag: text-generation -tags: -- base_model:adapter:ai21labs/AI21-Jamba-Reasoning-3B -- lora -- transformers ---- - -# Model Card for Model ID - - - - - -## Model Details - -### Model Description - - - - - -- **Developed by:** [More Information Needed] -- **Funded by [optional]:** [More Information Needed] -- **Shared by [optional]:** [More Information Needed] -- **Model type:** [More Information Needed] -- **Language(s) (NLP):** [More Information Needed] -- **License:** [More Information Needed] -- **Finetuned from model [optional]:** [More Information Needed] - -### Model Sources [optional] - - - -- **Repository:** [More Information Needed] -- **Paper [optional]:** [More Information Needed] -- **Demo [optional]:** [More Information Needed] - -## Uses - - - -### Direct Use - - - -[More Information Needed] - -### Downstream Use [optional] - - - -[More Information Needed] - -### Out-of-Scope Use - - - -[More Information Needed] - -## Bias, Risks, and Limitations - - - -[More Information Needed] - -### Recommendations - - - -Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. - -## How to Get Started with the Model - -Use the code below to get started with the model. - -[More Information Needed] - -## Training Details - -### Training Data - - - -[More Information Needed] - -### Training Procedure - - - -#### Preprocessing [optional] - -[More Information Needed] - - -#### Training Hyperparameters - -- **Training regime:** [More Information Needed] - -#### Speeds, Sizes, Times [optional] - - - -[More Information Needed] - -## Evaluation - - - -### Testing Data, Factors & Metrics - -#### Testing Data - - - -[More Information Needed] - -#### Factors - - - -[More Information Needed] - -#### Metrics - - - -[More Information Needed] - -### Results - -[More Information Needed] - -#### Summary - - - -## Model Examination [optional] - - - -[More Information Needed] - -## Environmental Impact - - - -Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - -- **Hardware Type:** [More Information Needed] -- **Hours used:** [More Information Needed] -- **Cloud Provider:** [More Information Needed] -- **Compute Region:** [More Information Needed] -- **Carbon Emitted:** [More Information Needed] - -## Technical Specifications [optional] - -### Model Architecture and Objective - -[More Information Needed] - -### Compute Infrastructure - -[More Information Needed] - -#### Hardware - -[More Information Needed] - -#### Software - -[More Information Needed] - -## Citation [optional] - - - -**BibTeX:** - -[More Information Needed] - -**APA:** - -[More Information Needed] - -## Glossary [optional] - - - -[More Information Needed] - -## More Information [optional] - -[More Information Needed] - -## Model Card Authors [optional] - -[More Information Needed] - -## Model Card Contact - -[More Information Needed] -### Framework versions - -- PEFT 0.18.1 \ No newline at end of file diff --git a/runs/stage3/stage_0/checkpoint-0001154/adapter_model/adapter_config.json b/runs/stage3/stage_0/checkpoint-0001154/adapter_model/adapter_config.json deleted file mode 100644 index a8cfa7572e39bed4a7f9e06397495762151325dd..0000000000000000000000000000000000000000 --- a/runs/stage3/stage_0/checkpoint-0001154/adapter_model/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "x_proj", - "in_proj", - "o_proj", - "q_proj", - "k_proj", - "out_proj", - "dt_proj", - "v_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/runs/stage3/stage_0/checkpoint-0001154/adapter_model/adapter_model.safetensors b/runs/stage3/stage_0/checkpoint-0001154/adapter_model/adapter_model.safetensors deleted file mode 100644 index 2f8ee8818b7d9f5441d4a51c9762ceaa021fa743..0000000000000000000000000000000000000000 --- a/runs/stage3/stage_0/checkpoint-0001154/adapter_model/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:f31c348c1f4a0888da59ae9a2fefb8f6cd5699fdeaa72f882c005106a86714da -size 1449633736 diff --git a/runs/stage3/stage_0/checkpoint-0001154/training_state.pt b/runs/stage3/stage_0/checkpoint-0001154/training_state.pt deleted file mode 100644 index 93b9998309e5e1232f23e10f4e552f634ffc3007..0000000000000000000000000000000000000000 --- a/runs/stage3/stage_0/checkpoint-0001154/training_state.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:179c81186c187318faee60993391119b5dbbdc5782adcb27a23738b9900558a7 -size 215006601 diff --git a/runs/stage3/stage_1/checkpoint-0001338/adapter_model/README.md b/runs/stage3/stage_1/checkpoint-0001338/adapter_model/README.md deleted file mode 100644 index 0faa9ea1f80a3dcf3a2dce68a301458dcc28d5d1..0000000000000000000000000000000000000000 --- a/runs/stage3/stage_1/checkpoint-0001338/adapter_model/README.md +++ /dev/null @@ -1,207 +0,0 @@ ---- -base_model: ai21labs/AI21-Jamba-Reasoning-3B -library_name: peft -pipeline_tag: text-generation -tags: -- base_model:adapter:ai21labs/AI21-Jamba-Reasoning-3B -- lora -- transformers ---- - -# Model Card for Model ID - - - - - -## Model Details - -### Model Description - - - - - -- **Developed by:** [More Information Needed] -- **Funded by [optional]:** [More Information Needed] -- **Shared by [optional]:** [More Information Needed] -- **Model type:** [More Information Needed] -- **Language(s) (NLP):** [More Information Needed] -- **License:** [More Information Needed] -- **Finetuned from model [optional]:** [More Information Needed] - -### Model Sources [optional] - - - -- **Repository:** [More Information Needed] -- **Paper [optional]:** [More Information Needed] -- **Demo [optional]:** [More Information Needed] - -## Uses - - - -### Direct Use - - - -[More Information Needed] - -### Downstream Use [optional] - - - -[More Information Needed] - -### Out-of-Scope Use - - - -[More Information Needed] - -## Bias, Risks, and Limitations - - - -[More Information Needed] - -### Recommendations - - - -Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. - -## How to Get Started with the Model - -Use the code below to get started with the model. - -[More Information Needed] - -## Training Details - -### Training Data - - - -[More Information Needed] - -### Training Procedure - - - -#### Preprocessing [optional] - -[More Information Needed] - - -#### Training Hyperparameters - -- **Training regime:** [More Information Needed] - -#### Speeds, Sizes, Times [optional] - - - -[More Information Needed] - -## Evaluation - - - -### Testing Data, Factors & Metrics - -#### Testing Data - - - -[More Information Needed] - -#### Factors - - - -[More Information Needed] - -#### Metrics - - - -[More Information Needed] - -### Results - -[More Information Needed] - -#### Summary - - - -## Model Examination [optional] - - - -[More Information Needed] - -## Environmental Impact - - - -Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - -- **Hardware Type:** [More Information Needed] -- **Hours used:** [More Information Needed] -- **Cloud Provider:** [More Information Needed] -- **Compute Region:** [More Information Needed] -- **Carbon Emitted:** [More Information Needed] - -## Technical Specifications [optional] - -### Model Architecture and Objective - -[More Information Needed] - -### Compute Infrastructure - -[More Information Needed] - -#### Hardware - -[More Information Needed] - -#### Software - -[More Information Needed] - -## Citation [optional] - - - -**BibTeX:** - -[More Information Needed] - -**APA:** - -[More Information Needed] - -## Glossary [optional] - - - -[More Information Needed] - -## More Information [optional] - -[More Information Needed] - -## Model Card Authors [optional] - -[More Information Needed] - -## Model Card Contact - -[More Information Needed] -### Framework versions - -- PEFT 0.18.1 \ No newline at end of file diff --git a/runs/stage3/stage_1/checkpoint-0001338/adapter_model/adapter_config.json b/runs/stage3/stage_1/checkpoint-0001338/adapter_model/adapter_config.json deleted file mode 100644 index a8cfa7572e39bed4a7f9e06397495762151325dd..0000000000000000000000000000000000000000 --- a/runs/stage3/stage_1/checkpoint-0001338/adapter_model/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "x_proj", - "in_proj", - "o_proj", - "q_proj", - "k_proj", - "out_proj", - "dt_proj", - "v_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/runs/stage3/stage_1/checkpoint-0001338/adapter_model/adapter_model.safetensors b/runs/stage3/stage_1/checkpoint-0001338/adapter_model/adapter_model.safetensors deleted file mode 100644 index 6370a9c4a97412162280450901781bf9b6039dee..0000000000000000000000000000000000000000 --- a/runs/stage3/stage_1/checkpoint-0001338/adapter_model/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:283c43ec7d9431d528da3a758339f3cf4601b28de711242479e01866048408b4 -size 1449633736 diff --git a/runs/stage3/stage_1/checkpoint-0001338/training_state.pt b/runs/stage3/stage_1/checkpoint-0001338/training_state.pt deleted file mode 100644 index 15af2f6c08e83f1469d07609c6f328d24910a8f8..0000000000000000000000000000000000000000 --- a/runs/stage3/stage_1/checkpoint-0001338/training_state.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:ae729872096c4ce10142fa04838cd6b9f2f36e4defcfc23e1e41feafcdbc03db -size 215003465 diff --git a/runs/stage3/stage_1/checkpoint-0002293/adapter_model/README.md b/runs/stage3/stage_1/checkpoint-0002293/adapter_model/README.md deleted file mode 100644 index 0faa9ea1f80a3dcf3a2dce68a301458dcc28d5d1..0000000000000000000000000000000000000000 --- a/runs/stage3/stage_1/checkpoint-0002293/adapter_model/README.md +++ /dev/null @@ -1,207 +0,0 @@ ---- -base_model: ai21labs/AI21-Jamba-Reasoning-3B -library_name: peft -pipeline_tag: text-generation -tags: -- base_model:adapter:ai21labs/AI21-Jamba-Reasoning-3B -- lora -- transformers ---- - -# Model Card for Model ID - - - - - -## Model Details - -### Model Description - - - - - -- **Developed by:** [More Information Needed] -- **Funded by [optional]:** [More Information Needed] -- **Shared by [optional]:** [More Information Needed] -- **Model type:** [More Information Needed] -- **Language(s) (NLP):** [More Information Needed] -- **License:** [More Information Needed] -- **Finetuned from model [optional]:** [More Information Needed] - -### Model Sources [optional] - - - -- **Repository:** [More Information Needed] -- **Paper [optional]:** [More Information Needed] -- **Demo [optional]:** [More Information Needed] - -## Uses - - - -### Direct Use - - - -[More Information Needed] - -### Downstream Use [optional] - - - -[More Information Needed] - -### Out-of-Scope Use - - - -[More Information Needed] - -## Bias, Risks, and Limitations - - - -[More Information Needed] - -### Recommendations - - - -Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. - -## How to Get Started with the Model - -Use the code below to get started with the model. - -[More Information Needed] - -## Training Details - -### Training Data - - - -[More Information Needed] - -### Training Procedure - - - -#### Preprocessing [optional] - -[More Information Needed] - - -#### Training Hyperparameters - -- **Training regime:** [More Information Needed] - -#### Speeds, Sizes, Times [optional] - - - -[More Information Needed] - -## Evaluation - - - -### Testing Data, Factors & Metrics - -#### Testing Data - - - -[More Information Needed] - -#### Factors - - - -[More Information Needed] - -#### Metrics - - - -[More Information Needed] - -### Results - -[More Information Needed] - -#### Summary - - - -## Model Examination [optional] - - - -[More Information Needed] - -## Environmental Impact - - - -Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - -- **Hardware Type:** [More Information Needed] -- **Hours used:** [More Information Needed] -- **Cloud Provider:** [More Information Needed] -- **Compute Region:** [More Information Needed] -- **Carbon Emitted:** [More Information Needed] - -## Technical Specifications [optional] - -### Model Architecture and Objective - -[More Information Needed] - -### Compute Infrastructure - -[More Information Needed] - -#### Hardware - -[More Information Needed] - -#### Software - -[More Information Needed] - -## Citation [optional] - - - -**BibTeX:** - -[More Information Needed] - -**APA:** - -[More Information Needed] - -## Glossary [optional] - - - -[More Information Needed] - -## More Information [optional] - -[More Information Needed] - -## Model Card Authors [optional] - -[More Information Needed] - -## Model Card Contact - -[More Information Needed] -### Framework versions - -- PEFT 0.18.1 \ No newline at end of file diff --git a/runs/stage3/stage_1/checkpoint-0002293/adapter_model/adapter_config.json b/runs/stage3/stage_1/checkpoint-0002293/adapter_model/adapter_config.json deleted file mode 100644 index d03fda0a9d5c44750c5c38e00aa9bd57e46f8254..0000000000000000000000000000000000000000 --- a/runs/stage3/stage_1/checkpoint-0002293/adapter_model/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "in_proj", - "q_proj", - "out_proj", - "o_proj", - "v_proj", - "x_proj", - "k_proj", - "dt_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/runs/stage3/stage_1/checkpoint-0002293/adapter_model/adapter_model.safetensors b/runs/stage3/stage_1/checkpoint-0002293/adapter_model/adapter_model.safetensors deleted file mode 100644 index ab8699a20877b07aca6a9055e9a52197124cee66..0000000000000000000000000000000000000000 --- a/runs/stage3/stage_1/checkpoint-0002293/adapter_model/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:29f96b3c19c4f1b591b8c4f517263d2b468e3b180221c5a97590783240fe3741 -size 1449633736 diff --git a/runs/stage3/stage_1/checkpoint-0002293/training_state.pt b/runs/stage3/stage_1/checkpoint-0002293/training_state.pt deleted file mode 100644 index bf3e89d1425654d34f49b516213a7692f916ada7..0000000000000000000000000000000000000000 --- a/runs/stage3/stage_1/checkpoint-0002293/training_state.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:4fafb5f7b92a4959e60f804f80a2ead6bbff8b3b190289736da0f15c4c11f1ca -size 215006601 diff --git a/runs/stage3/stage_1/checkpoint-0002308/adapter_model/README.md b/runs/stage3/stage_1/checkpoint-0002308/adapter_model/README.md deleted file mode 100644 index 0faa9ea1f80a3dcf3a2dce68a301458dcc28d5d1..0000000000000000000000000000000000000000 --- a/runs/stage3/stage_1/checkpoint-0002308/adapter_model/README.md +++ /dev/null @@ -1,207 +0,0 @@ ---- -base_model: ai21labs/AI21-Jamba-Reasoning-3B -library_name: peft -pipeline_tag: text-generation -tags: -- base_model:adapter:ai21labs/AI21-Jamba-Reasoning-3B -- lora -- transformers ---- - -# Model Card for Model ID - - - - - -## Model Details - -### Model Description - - - - - -- **Developed by:** [More Information Needed] -- **Funded by [optional]:** [More Information Needed] -- **Shared by [optional]:** [More Information Needed] -- **Model type:** [More Information Needed] -- **Language(s) (NLP):** [More Information Needed] -- **License:** [More Information Needed] -- **Finetuned from model [optional]:** [More Information Needed] - -### Model Sources [optional] - - - -- **Repository:** [More Information Needed] -- **Paper [optional]:** [More Information Needed] -- **Demo [optional]:** [More Information Needed] - -## Uses - - - -### Direct Use - - - -[More Information Needed] - -### Downstream Use [optional] - - - -[More Information Needed] - -### Out-of-Scope Use - - - -[More Information Needed] - -## Bias, Risks, and Limitations - - - -[More Information Needed] - -### Recommendations - - - -Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. - -## How to Get Started with the Model - -Use the code below to get started with the model. - -[More Information Needed] - -## Training Details - -### Training Data - - - -[More Information Needed] - -### Training Procedure - - - -#### Preprocessing [optional] - -[More Information Needed] - - -#### Training Hyperparameters - -- **Training regime:** [More Information Needed] - -#### Speeds, Sizes, Times [optional] - - - -[More Information Needed] - -## Evaluation - - - -### Testing Data, Factors & Metrics - -#### Testing Data - - - -[More Information Needed] - -#### Factors - - - -[More Information Needed] - -#### Metrics - - - -[More Information Needed] - -### Results - -[More Information Needed] - -#### Summary - - - -## Model Examination [optional] - - - -[More Information Needed] - -## Environmental Impact - - - -Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - -- **Hardware Type:** [More Information Needed] -- **Hours used:** [More Information Needed] -- **Cloud Provider:** [More Information Needed] -- **Compute Region:** [More Information Needed] -- **Carbon Emitted:** [More Information Needed] - -## Technical Specifications [optional] - -### Model Architecture and Objective - -[More Information Needed] - -### Compute Infrastructure - -[More Information Needed] - -#### Hardware - -[More Information Needed] - -#### Software - -[More Information Needed] - -## Citation [optional] - - - -**BibTeX:** - -[More Information Needed] - -**APA:** - -[More Information Needed] - -## Glossary [optional] - - - -[More Information Needed] - -## More Information [optional] - -[More Information Needed] - -## Model Card Authors [optional] - -[More Information Needed] - -## Model Card Contact - -[More Information Needed] -### Framework versions - -- PEFT 0.18.1 \ No newline at end of file diff --git a/runs/stage3/stage_1/checkpoint-0002308/adapter_model/adapter_config.json b/runs/stage3/stage_1/checkpoint-0002308/adapter_model/adapter_config.json deleted file mode 100644 index 9a29a2efa1c03d4d7d26ad2e365e1e24e83847f0..0000000000000000000000000000000000000000 --- a/runs/stage3/stage_1/checkpoint-0002308/adapter_model/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "out_proj", - "x_proj", - "o_proj", - "dt_proj", - "q_proj", - "k_proj", - "in_proj", - "v_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/runs/stage3/stage_1/checkpoint-0002308/adapter_model/adapter_model.safetensors b/runs/stage3/stage_1/checkpoint-0002308/adapter_model/adapter_model.safetensors deleted file mode 100644 index ef5e6270c8fcb806941544abea6cae61a92790ff..0000000000000000000000000000000000000000 --- a/runs/stage3/stage_1/checkpoint-0002308/adapter_model/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6cf0bd66f3786a74e78decc225cd5f90602937ead68942df0bcb09722faa643d -size 1449633736 diff --git a/runs/stage3/stage_1/checkpoint-0002308/training_state.pt b/runs/stage3/stage_1/checkpoint-0002308/training_state.pt deleted file mode 100644 index 61a6a7bfac630676ecb4c4f10d617c16b16c1214..0000000000000000000000000000000000000000 --- a/runs/stage3/stage_1/checkpoint-0002308/training_state.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:dd0c4571fca8ab7c2087ef33a5131b3c8ae060acd83f87806b20e957dd241f8f -size 215006601 diff --git a/runs/stage3/stage_2/checkpoint-0002987/adapter_model/README.md b/runs/stage3/stage_2/checkpoint-0002987/adapter_model/README.md deleted file mode 100644 index 0faa9ea1f80a3dcf3a2dce68a301458dcc28d5d1..0000000000000000000000000000000000000000 --- a/runs/stage3/stage_2/checkpoint-0002987/adapter_model/README.md +++ /dev/null @@ -1,207 +0,0 @@ ---- -base_model: ai21labs/AI21-Jamba-Reasoning-3B -library_name: peft -pipeline_tag: text-generation -tags: -- base_model:adapter:ai21labs/AI21-Jamba-Reasoning-3B -- lora -- transformers ---- - -# Model Card for Model ID - - - - - -## Model Details - -### Model Description - - - - - -- **Developed by:** [More Information Needed] -- **Funded by [optional]:** [More Information Needed] -- **Shared by [optional]:** [More Information Needed] -- **Model type:** [More Information Needed] -- **Language(s) (NLP):** [More Information Needed] -- **License:** [More Information Needed] -- **Finetuned from model [optional]:** [More Information Needed] - -### Model Sources [optional] - - - -- **Repository:** [More Information Needed] -- **Paper [optional]:** [More Information Needed] -- **Demo [optional]:** [More Information Needed] - -## Uses - - - -### Direct Use - - - -[More Information Needed] - -### Downstream Use [optional] - - - -[More Information Needed] - -### Out-of-Scope Use - - - -[More Information Needed] - -## Bias, Risks, and Limitations - - - -[More Information Needed] - -### Recommendations - - - -Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. - -## How to Get Started with the Model - -Use the code below to get started with the model. - -[More Information Needed] - -## Training Details - -### Training Data - - - -[More Information Needed] - -### Training Procedure - - - -#### Preprocessing [optional] - -[More Information Needed] - - -#### Training Hyperparameters - -- **Training regime:** [More Information Needed] - -#### Speeds, Sizes, Times [optional] - - - -[More Information Needed] - -## Evaluation - - - -### Testing Data, Factors & Metrics - -#### Testing Data - - - -[More Information Needed] - -#### Factors - - - -[More Information Needed] - -#### Metrics - - - -[More Information Needed] - -### Results - -[More Information Needed] - -#### Summary - - - -## Model Examination [optional] - - - -[More Information Needed] - -## Environmental Impact - - - -Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - -- **Hardware Type:** [More Information Needed] -- **Hours used:** [More Information Needed] -- **Cloud Provider:** [More Information Needed] -- **Compute Region:** [More Information Needed] -- **Carbon Emitted:** [More Information Needed] - -## Technical Specifications [optional] - -### Model Architecture and Objective - -[More Information Needed] - -### Compute Infrastructure - -[More Information Needed] - -#### Hardware - -[More Information Needed] - -#### Software - -[More Information Needed] - -## Citation [optional] - - - -**BibTeX:** - -[More Information Needed] - -**APA:** - -[More Information Needed] - -## Glossary [optional] - - - -[More Information Needed] - -## More Information [optional] - -[More Information Needed] - -## Model Card Authors [optional] - -[More Information Needed] - -## Model Card Contact - -[More Information Needed] -### Framework versions - -- PEFT 0.18.1 \ No newline at end of file diff --git a/runs/stage3/stage_2/checkpoint-0002987/adapter_model/adapter_config.json b/runs/stage3/stage_2/checkpoint-0002987/adapter_model/adapter_config.json deleted file mode 100644 index 9a29a2efa1c03d4d7d26ad2e365e1e24e83847f0..0000000000000000000000000000000000000000 --- a/runs/stage3/stage_2/checkpoint-0002987/adapter_model/adapter_config.json +++ /dev/null @@ -1,47 +0,0 @@ -{ - "alora_invocation_tokens": null, - "alpha_pattern": {}, - "arrow_config": null, - "auto_mapping": null, - "base_model_name_or_path": "ai21labs/AI21-Jamba-Reasoning-3B", - "bias": "none", - "corda_config": null, - "ensure_weight_tying": false, - "eva_config": null, - "exclude_modules": null, - "fan_in_fan_out": false, - "inference_mode": true, - "init_lora_weights": true, - "layer_replication": null, - "layers_pattern": null, - "layers_to_transform": null, - "loftq_config": {}, - "lora_alpha": 64, - "lora_bias": false, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": null, - "peft_type": "LORA", - "peft_version": "0.18.1", - "qalora_group_size": 16, - "r": 32, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "out_proj", - "x_proj", - "o_proj", - "dt_proj", - "q_proj", - "k_proj", - "in_proj", - "v_proj" - ], - "target_parameters": null, - "task_type": "CAUSAL_LM", - "trainable_token_indices": null, - "use_dora": false, - "use_qalora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/runs/stage3/stage_2/checkpoint-0002987/adapter_model/adapter_model.safetensors b/runs/stage3/stage_2/checkpoint-0002987/adapter_model/adapter_model.safetensors deleted file mode 100644 index 406651be899b1be40426c51b9775aac7559c0492..0000000000000000000000000000000000000000 --- a/runs/stage3/stage_2/checkpoint-0002987/adapter_model/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:0be8371295e24be0c54dfb19bd080916c5ffdbf857cf39edc81a69aa3ef336e9 -size 1449633736 diff --git a/runs/stage3/stage_2/checkpoint-0002987/training_state.pt b/runs/stage3/stage_2/checkpoint-0002987/training_state.pt deleted file mode 100644 index b740e18d8e6eb5d15788bc3077e35c0d403baf0f..0000000000000000000000000000000000000000 --- a/runs/stage3/stage_2/checkpoint-0002987/training_state.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:110b524fc2923d18e4cae2accebb68a0a07a337b3706137095a2fe5792b1cec1 -size 215003465