Training in progress, step 500, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 512,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 16,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.9.0",
+  "use_cache": false,
+  "vocab_size": 50257
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 0,
+  "transformers_version": "5.9.0",
+  "use_cache": true
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01f02a6552ebf557c663261cde7e237513b533f9cc549a0a4e441821d246faa3
+size 4523108832

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9735805862fcaf445077a15d872c7a340cd7e8ea695d46738281425d99ff7bc1
+size 2911851147

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:098b29492211804ab324a36f37466821d948280bb74fce4ba895c03f13ecd878
+size 14645

last-checkpoint/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f77569c2e850b04af982cc8c1389f1430851448915c593b69e5da36ce05b71d7
+size 1383

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b61ed96b9f34f057dffa0bad8ef6959040ba1cfe848017506ba05f40fdaea76
+size 1465

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": false,
+  "local_files_only": false,
+  "max_length": 512,
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "stride": 0,
+  "tokenizer_class": "GPT2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<|endoftext|>"
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,112 @@
+{
+  "best_global_step": 500,
+  "best_metric": 1.025797724723816,
+  "best_model_checkpoint": "./sft-out/checkpoint-500",
+  "epoch": 0.8840267418089397,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08840267418089397,
+      "grad_norm": 2.867945432662964,
+      "learning_rate": 9.800000000000001e-06,
+      "loss": 1.6486561584472657,
+      "step": 50
+    },
+    {
+      "epoch": 0.17680534836178793,
+      "grad_norm": 2.9991917610168457,
+      "learning_rate": 1.98e-05,
+      "loss": 1.33203125,
+      "step": 100
+    },
+    {
+      "epoch": 0.26520802254268194,
+      "grad_norm": 2.570798635482788,
+      "learning_rate": 1.9854078984834904e-05,
+      "loss": 1.2356742858886718,
+      "step": 150
+    },
+    {
+      "epoch": 0.35361069672357587,
+      "grad_norm": 2.5860543251037598,
+      "learning_rate": 1.9408807689542257e-05,
+      "loss": 1.2118841552734374,
+      "step": 200
+    },
+    {
+      "epoch": 0.44201337090446985,
+      "grad_norm": 2.117816686630249,
+      "learning_rate": 1.8677654533689287e-05,
+      "loss": 1.1767095184326173,
+      "step": 250
+    },
+    {
+      "epoch": 0.5304160450853639,
+      "grad_norm": 2.276134729385376,
+      "learning_rate": 1.7682835235935236e-05,
+      "loss": 1.1405416870117187,
+      "step": 300
+    },
+    {
+      "epoch": 0.6188187192662578,
+      "grad_norm": 2.2516863346099854,
+      "learning_rate": 1.645457687723951e-05,
+      "loss": 1.128560562133789,
+      "step": 350
+    },
+    {
+      "epoch": 0.7072213934471517,
+      "grad_norm": 2.084246873855591,
+      "learning_rate": 1.5030199466302354e-05,
+      "loss": 1.1079308319091796,
+      "step": 400
+    },
+    {
+      "epoch": 0.7956240676280457,
+      "grad_norm": 2.195765495300293,
+      "learning_rate": 1.3452981989985347e-05,
+      "loss": 1.0333491516113282,
+      "step": 450
+    },
+    {
+      "epoch": 0.8840267418089397,
+      "grad_norm": 2.2488884925842285,
+      "learning_rate": 1.1770847403195836e-05,
+      "loss": 1.0508524322509765,
+      "step": 500
+    },
+    {
+      "epoch": 0.8840267418089397,
+      "eval_loss": 1.025797724723816,
+      "eval_runtime": 31.5114,
+      "eval_samples_per_second": 15.867,
+      "eval_steps_per_second": 1.999,
+      "step": 500
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 1000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.9429307822186496e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b09d01e394e9508be9f5db421ce912c1e3d19f75d3680c709cd862dd999d76c4
+size 5329