Add files using upload-large-folder tool

Ministral-3-3B-Instruct-2512_english_full_lf/.session_lock

@@ -0,0 +1 @@
+{"session": "f8d6c541", "utc": "2026-08-04T06:41:46.191365+00:00"}

Ministral-3-3B-Instruct-2512_english_full_lf/training_summary.json

@@ -0,0 +1,55 @@
+{
+ "run_name": "Ministral-3-3B-Instruct-2512_english_full_lf",
+ "condition": "english",
+ "model_id": "unsloth/Ministral-3-3B-Instruct-2512",
+ "dose": "full",
+ "dose_file": "/content/drive/MyDrive/Syn-SQL Spider train  BIRD train/v2/train data/english/train/spider_en_6948.jsonl",
+ "n_rows": 6948,
+ "hyperparameters": {
+  "load_in_4bit": true,
+  "max_seq_length": 4096,
+  "lora_r": 16,
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "learning_rate": 0.0002,
+  "epochs": 2.0,
+  "per_device_batch_size": 1,
+  "grad_accum": 8,
+  "warmup_ratio": 0.03,
+  "weight_decay": 0.01,
+  "lr_scheduler": "linear",
+  "seed": 3407,
+  "optim": "adamw_8bit",
+  "loss_on": "responses_only (SQL answer + end-of-turn)"
+ },
+ "prompt_version": "p1",
+ "notebook_version": "train-v3-lf3",
+ "instruction_sha256": "c7e8631a429b9e8e",
+ "framework": "llamafactory@ef2d8f9da66ef13378dc8068dabc99cfe89a9736",
+ "lf_template": "ministral3",
+ "use_unsloth_requested": true,
+ "use_unsloth_effective": true,
+ "tiny_run": false,
+ "n_rows_over_cutoff": 0,
+ "resume_note": null,
+ "trained_by": "RUN_ministral3.ipynb",
+ "render_provenance": {
+  "text_construction": "llamafactory template render (canary-verified == eval_prompt_render + SQL + EOT)",
+  "chat_template_sha256": "a81fa42ad89f88c7"
+ },
+ "train_loss": 0.013689696994557616,
+ "train_runtime_s": 9689.671,
+ "versions": {
+  "torch": "2.10.0",
+  "transformers": "5.5.0",
+  "unsloth": "2026.7.2",
+  "trl": "0.24.0",
+  "peft": "0.18.1",
+  "llamafactory": "0.9.6.dev0",
+  "bitsandbytes": "0.50.0"
+ },
+ "gpu": "NVIDIA L4",
+ "saved_utc": "2026-08-04T09:25:06.162832+00:00",
+ "adapter_path": "/content/drive/MyDrive/Syn-SQL Spider train  BIRD train/v2/fine tune models/Ministral-3-3B-Instruct-2512_english_full_lf/adapter",
+ "merged_16bit_path": null
+}

Ministral-3-3B-Instruct-2512_welsh_full_lf/.session_lock

@@ -0,0 +1 @@
+{"session": "dea84e3d", "utc": "2026-08-04T02:46:46.489969+00:00"}

Ministral-3-3B-Instruct-2512_welsh_full_lf/training_summary.json

@@ -0,0 +1,55 @@
+{
+ "run_name": "Ministral-3-3B-Instruct-2512_welsh_full_lf",
+ "condition": "welsh",
+ "model_id": "unsloth/Ministral-3-3B-Instruct-2512",
+ "dose": "full",
+ "dose_file": "/content/drive/MyDrive/Syn-SQL Spider train  BIRD train/v2/train data/welsh/train/spider_cy_6948.jsonl",
+ "n_rows": 6948,
+ "hyperparameters": {
+  "load_in_4bit": true,
+  "max_seq_length": 4096,
+  "lora_r": 16,
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "learning_rate": 0.0002,
+  "epochs": 2.0,
+  "per_device_batch_size": 1,
+  "grad_accum": 8,
+  "warmup_ratio": 0.03,
+  "weight_decay": 0.01,
+  "lr_scheduler": "linear",
+  "seed": 3407,
+  "optim": "adamw_8bit",
+  "loss_on": "responses_only (SQL answer + end-of-turn)"
+ },
+ "prompt_version": "p1",
+ "notebook_version": "train-v3-lf3",
+ "instruction_sha256": "c7e8631a429b9e8e",
+ "framework": "llamafactory@ef2d8f9da66ef13378dc8068dabc99cfe89a9736",
+ "lf_template": "ministral3",
+ "use_unsloth_requested": true,
+ "use_unsloth_effective": true,
+ "tiny_run": false,
+ "n_rows_over_cutoff": 0,
+ "resume_note": null,
+ "trained_by": "RUN_ministral3.ipynb",
+ "render_provenance": {
+  "text_construction": "llamafactory template render (canary-verified == eval_prompt_render + SQL + EOT)",
+  "chat_template_sha256": "a81fa42ad89f88c7"
+ },
+ "train_loss": 0.01085191247373888,
+ "train_runtime_s": 10995.2712,
+ "versions": {
+  "torch": "2.10.0",
+  "transformers": "5.5.0",
+  "unsloth": "2026.7.2",
+  "trl": "0.24.0",
+  "peft": "0.18.1",
+  "llamafactory": "0.9.6.dev0",
+  "bitsandbytes": "0.50.0"
+ },
+ "gpu": "NVIDIA L4",
+ "saved_utc": "2026-08-04T05:51:55.165112+00:00",
+ "adapter_path": "/content/drive/MyDrive/Syn-SQL Spider train  BIRD train/v2/fine tune models/Ministral-3-3B-Instruct-2512_welsh_full_lf/adapter",
+ "merged_16bit_path": null
+}

Ministral-3-8B-Instruct-2512_english_full_lf/.session_lock

@@ -0,0 +1 @@
+{"session": "fd1f4858", "utc": "2026-08-04T21:19:09.201118+00:00"}

Ministral-3-8B-Instruct-2512_english_full_lf/training_summary.json

@@ -0,0 +1,55 @@
+{
+ "run_name": "Ministral-3-8B-Instruct-2512_english_full_lf",
+ "condition": "english",
+ "model_id": "unsloth/Ministral-3-8B-Instruct-2512",
+ "dose": "full",
+ "dose_file": "/content/drive/MyDrive/Syn-SQL Spider train  BIRD train/v2/train data/english/train/spider_en_6948.jsonl",
+ "n_rows": 6948,
+ "hyperparameters": {
+  "load_in_4bit": true,
+  "max_seq_length": 4096,
+  "lora_r": 16,
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "learning_rate": 0.0002,
+  "epochs": 2.0,
+  "per_device_batch_size": 1,
+  "grad_accum": 8,
+  "warmup_ratio": 0.03,
+  "weight_decay": 0.01,
+  "lr_scheduler": "linear",
+  "seed": 3407,
+  "optim": "adamw_8bit",
+  "loss_on": "responses_only (SQL answer + end-of-turn)"
+ },
+ "prompt_version": "p1",
+ "notebook_version": "train-v3-lf3",
+ "instruction_sha256": "c7e8631a429b9e8e",
+ "framework": "llamafactory@ef2d8f9da66ef13378dc8068dabc99cfe89a9736",
+ "lf_template": "ministral3",
+ "use_unsloth_requested": true,
+ "use_unsloth_effective": true,
+ "tiny_run": false,
+ "n_rows_over_cutoff": 0,
+ "resume_note": null,
+ "trained_by": "RUN_ministral3.ipynb",
+ "render_provenance": {
+  "text_construction": "llamafactory template render (canary-verified == eval_prompt_render + SQL + EOT)",
+  "chat_template_sha256": "2ef2939ee9623cd5"
+ },
+ "train_loss": 0.012401104205951386,
+ "train_runtime_s": 15684.2331,
+ "versions": {
+  "torch": "2.10.0",
+  "transformers": "5.5.0",
+  "unsloth": "2026.7.2",
+  "trl": "0.24.0",
+  "peft": "0.18.1",
+  "llamafactory": "0.9.6.dev0",
+  "bitsandbytes": "0.50.0"
+ },
+ "gpu": "NVIDIA L4",
+ "saved_utc": "2026-08-05T01:42:32.087309+00:00",
+ "adapter_path": "/content/drive/MyDrive/Syn-SQL Spider train  BIRD train/v2/fine tune models/Ministral-3-8B-Instruct-2512_english_full_lf/adapter",
+ "merged_16bit_path": null
+}

Ministral-3-8B-Instruct-2512_welsh_full_lf/.session_lock

@@ -0,0 +1 @@
+{"session": "ea7a331c", "utc": "2026-08-04T14:26:32.011726+00:00"}

Ministral-3-8B-Instruct-2512_welsh_full_lf/training_summary.json

@@ -0,0 +1,55 @@
+{
+ "run_name": "Ministral-3-8B-Instruct-2512_welsh_full_lf",
+ "condition": "welsh",
+ "model_id": "unsloth/Ministral-3-8B-Instruct-2512",
+ "dose": "full",
+ "dose_file": "/content/drive/MyDrive/Syn-SQL Spider train  BIRD train/v2/train data/welsh/train/spider_cy_6948.jsonl",
+ "n_rows": 6948,
+ "hyperparameters": {
+  "load_in_4bit": true,
+  "max_seq_length": 4096,
+  "lora_r": 16,
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "learning_rate": 0.0002,
+  "epochs": 2.0,
+  "per_device_batch_size": 1,
+  "grad_accum": 8,
+  "warmup_ratio": 0.03,
+  "weight_decay": 0.01,
+  "lr_scheduler": "linear",
+  "seed": 3407,
+  "optim": "adamw_8bit",
+  "loss_on": "responses_only (SQL answer + end-of-turn)"
+ },
+ "prompt_version": "p1",
+ "notebook_version": "train-v3-lf3",
+ "instruction_sha256": "c7e8631a429b9e8e",
+ "framework": "llamafactory@ef2d8f9da66ef13378dc8068dabc99cfe89a9736",
+ "lf_template": "ministral3",
+ "use_unsloth_requested": true,
+ "use_unsloth_effective": true,
+ "tiny_run": false,
+ "n_rows_over_cutoff": 0,
+ "resume_note": null,
+ "trained_by": "RUN_ministral3.ipynb",
+ "render_provenance": {
+  "text_construction": "llamafactory template render (canary-verified == eval_prompt_render + SQL + EOT)",
+  "chat_template_sha256": "2ef2939ee9623cd5"
+ },
+ "train_loss": 0.009693514537473474,
+ "train_runtime_s": 18909.6135,
+ "versions": {
+  "torch": "2.10.0",
+  "transformers": "5.5.0",
+  "unsloth": "2026.7.2",
+  "trl": "0.24.0",
+  "peft": "0.18.1",
+  "llamafactory": "0.9.6.dev0",
+  "bitsandbytes": "0.50.0"
+ },
+ "gpu": "NVIDIA L4",
+ "saved_utc": "2026-08-04T19:43:53.607225+00:00",
+ "adapter_path": "/content/drive/MyDrive/Syn-SQL Spider train  BIRD train/v2/fine tune models/Ministral-3-8B-Instruct-2512_welsh_full_lf/adapter",
+ "merged_16bit_path": null
+}

NOTE.txt

@@ -0,0 +1 @@
+adapters from v2 runs land here. old run 1 adapter (old bundle) stays in new/fine tune models, legacy.

Qwen3.5-4B_english_full_lf/.session_lock

@@ -0,0 +1 @@
+{"session": "532e3250", "utc": "2026-08-04T14:34:31.781746+00:00"}

Qwen3.5-4B_english_full_lf/training_summary.json

@@ -0,0 +1,55 @@
+{
+ "run_name": "Qwen3.5-4B_english_full_lf",
+ "condition": "english",
+ "model_id": "unsloth/Qwen3.5-4B",
+ "dose": "full",
+ "dose_file": "/content/drive/MyDrive/Syn-SQL Spider train  BIRD train/v2/train data/english/train/spider_en_6948.jsonl",
+ "n_rows": 6948,
+ "hyperparameters": {
+  "load_in_4bit": true,
+  "max_seq_length": 4096,
+  "lora_r": 16,
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "learning_rate": 0.0002,
+  "epochs": 2.0,
+  "per_device_batch_size": 1,
+  "grad_accum": 8,
+  "warmup_ratio": 0.03,
+  "weight_decay": 0.01,
+  "lr_scheduler": "linear",
+  "seed": 3407,
+  "optim": "adamw_8bit",
+  "loss_on": "responses_only (SQL answer + end-of-turn)"
+ },
+ "prompt_version": "p1",
+ "notebook_version": "train-v3-lf3",
+ "instruction_sha256": "c7e8631a429b9e8e",
+ "framework": "llamafactory@ef2d8f9da66ef13378dc8068dabc99cfe89a9736",
+ "lf_template": "qwen3_5",
+ "use_unsloth_requested": true,
+ "use_unsloth_effective": true,
+ "tiny_run": false,
+ "n_rows_over_cutoff": 0,
+ "resume_note": null,
+ "trained_by": "RUN_qwen35.ipynb",
+ "render_provenance": {
+  "text_construction": "llamafactory template render (canary-verified == eval_prompt_render + SQL + EOT)",
+  "chat_template_sha256": "8452ca85cb1e0ff0"
+ },
+ "train_loss": 0.028501616222880378,
+ "train_runtime_s": 7712.1937,
+ "versions": {
+  "torch": "2.10.0",
+  "transformers": "5.5.0",
+  "unsloth": "2026.7.2",
+  "trl": "0.24.0",
+  "peft": "0.18.1",
+  "llamafactory": "0.9.6.dev0",
+  "bitsandbytes": "0.50.0"
+ },
+ "gpu": "NVIDIA L4",
+ "saved_utc": "2026-08-04T16:45:23.157738+00:00",
+ "adapter_path": "/content/drive/MyDrive/Syn-SQL Spider train  BIRD train/v2/fine tune models/Qwen3.5-4B_english_full_lf/adapter",
+ "merged_16bit_path": null
+}

Qwen3.5-4B_welsh_full_lf/.session_lock

@@ -0,0 +1 @@
+{"session": "249ea001", "utc": "2026-08-04T07:17:01.284881+00:00"}

Qwen3.5-4B_welsh_full_lf/training_summary.json

@@ -0,0 +1,55 @@
+{
+ "run_name": "Qwen3.5-4B_welsh_full_lf",
+ "condition": "welsh",
+ "model_id": "unsloth/Qwen3.5-4B",
+ "dose": "full",
+ "dose_file": "/content/drive/MyDrive/Syn-SQL Spider train  BIRD train/v2/train data/welsh/train/spider_cy_6948.jsonl",
+ "n_rows": 6948,
+ "hyperparameters": {
+  "load_in_4bit": true,
+  "max_seq_length": 4096,
+  "lora_r": 16,
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "learning_rate": 0.0002,
+  "epochs": 2.0,
+  "per_device_batch_size": 1,
+  "grad_accum": 8,
+  "warmup_ratio": 0.03,
+  "weight_decay": 0.01,
+  "lr_scheduler": "linear",
+  "seed": 3407,
+  "optim": "adamw_8bit",
+  "loss_on": "responses_only (SQL answer + end-of-turn)"
+ },
+ "prompt_version": "p1",
+ "notebook_version": "train-v3-lf3",
+ "instruction_sha256": "c7e8631a429b9e8e",
+ "framework": "llamafactory@ef2d8f9da66ef13378dc8068dabc99cfe89a9736",
+ "lf_template": "qwen3_5",
+ "use_unsloth_requested": true,
+ "use_unsloth_effective": true,
+ "tiny_run": false,
+ "n_rows_over_cutoff": 18,
+ "resume_note": null,
+ "trained_by": "RUN_qwen35.ipynb",
+ "render_provenance": {
+  "text_construction": "llamafactory template render (canary-verified == eval_prompt_render + SQL + EOT)",
+  "chat_template_sha256": "8452ca85cb1e0ff0"
+ },
+ "train_loss": 0.08168271676100301,
+ "train_runtime_s": 15351.4237,
+ "versions": {
+  "torch": "2.10.0",
+  "transformers": "5.5.0",
+  "unsloth": "2026.7.2",
+  "trl": "0.24.0",
+  "peft": "0.18.1",
+  "llamafactory": "0.9.6.dev0",
+  "bitsandbytes": "0.50.0"
+ },
+ "gpu": "NVIDIA L4",
+ "saved_utc": "2026-08-04T11:35:50.938648+00:00",
+ "adapter_path": "/content/drive/MyDrive/Syn-SQL Spider train  BIRD train/v2/fine tune models/Qwen3.5-4B_welsh_full_lf/adapter",
+ "merged_16bit_path": null
+}

Qwen3.5-9B_english_full_lf/.session_lock

@@ -0,0 +1 @@
+{"session": "728d6342", "utc": "2026-08-03T23:32:28.496697+00:00"}

Qwen3.5-9B_english_full_lf/adapter/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3_5ForConditionalGeneration",
+    "parent_library": "transformers.models.qwen3_5.modeling_qwen3_5",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen3.5-9B",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "(?:.*?(?:language|text).*?(?:self_attn|attention|attn|mixer|mlp|feed_forward|ffn|dense|mixer).*?(?:down_proj|gate_proj|in_proj_a|in_proj_b|in_proj_qkv|in_proj_z|k_proj|o_proj|out_proj|q_proj|up_proj|v_proj))|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mixer|mlp|feed_forward|ffn|dense|mixer)\\.(?:(?:down_proj|gate_proj|in_proj_a|in_proj_b|in_proj_qkv|in_proj_z|k_proj|o_proj|out_proj|q_proj|up_proj|v_proj)))",
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

Qwen3.5-9B_english_full_lf/adapter/all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "total_flos": 4.355163012428191e+17,
+    "train_loss": 0.09656419400961681,
+    "train_runtime": 17909.8032,
+    "train_samples_per_second": 0.776,
+    "train_steps_per_second": 0.097
+}

Qwen3.5-9B_english_full_lf/training_summary.json

@@ -0,0 +1,55 @@
+{
+ "run_name": "Qwen3.5-9B_english_full_lf",
+ "condition": "english",
+ "model_id": "unsloth/Qwen3.5-9B",
+ "dose": "full",
+ "dose_file": "/content/drive/MyDrive/Syn-SQL Spider train  BIRD train/v2/train data/english/train/spider_en_6948.jsonl",
+ "n_rows": 6948,
+ "hyperparameters": {
+  "load_in_4bit": true,
+  "max_seq_length": 4096,
+  "lora_r": 16,
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "learning_rate": 0.0002,
+  "epochs": 2.0,
+  "per_device_batch_size": 1,
+  "grad_accum": 8,
+  "warmup_ratio": 0.03,
+  "weight_decay": 0.01,
+  "lr_scheduler": "linear",
+  "seed": 3407,
+  "optim": "adamw_8bit",
+  "loss_on": "responses_only (SQL answer + end-of-turn)"
+ },
+ "prompt_version": "p1",
+ "notebook_version": "train-v3-lf3",
+ "instruction_sha256": "c7e8631a429b9e8e",
+ "framework": "llamafactory@ef2d8f9da66ef13378dc8068dabc99cfe89a9736",
+ "lf_template": "qwen3_5",
+ "use_unsloth_requested": true,
+ "use_unsloth_effective": true,
+ "tiny_run": false,
+ "n_rows_over_cutoff": 0,
+ "resume_note": null,
+ "trained_by": "RUN_qwen35.ipynb",
+ "render_provenance": {
+  "text_construction": "llamafactory template render (canary-verified == eval_prompt_render + SQL + EOT)",
+  "chat_template_sha256": "8452ca85cb1e0ff0"
+ },
+ "train_loss": 0.09656419400961681,
+ "train_runtime_s": 17909.8032,
+ "versions": {
+  "torch": "2.10.0",
+  "transformers": "5.5.0",
+  "unsloth": "2026.7.2",
+  "trl": "0.24.0",
+  "peft": "0.18.1",
+  "llamafactory": "0.9.6.dev0",
+  "bitsandbytes": "0.50.0"
+ },
+ "gpu": "NVIDIA L4",
+ "saved_utc": "2026-08-04T04:33:35.439154+00:00",
+ "adapter_path": "/content/drive/MyDrive/Syn-SQL Spider train  BIRD train/v2/fine tune models/Qwen3.5-9B_english_full_lf/adapter",
+ "merged_16bit_path": null
+}

Qwen3.5-9B_welsh_full_lf/.session_lock

@@ -0,0 +1 @@
+{"session": "5a70d80d", "utc": "2026-08-01T22:56:41.599379+00:00"}

Qwen3.5-9B_welsh_full_lf/adapter/README.md

@@ -0,0 +1,62 @@
+---
+library_name: peft
+license: other
+base_model: unsloth/Qwen3.5-9B
+tags:
+- base_model:adapter:unsloth/Qwen3.5-9B
+- llama-factory
+- lora
+- transformers
+- unsloth
+pipeline_tag: text-generation
+model-index:
+- name: adapter
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# adapter
+
+This model is a fine-tuned version of [unsloth/Qwen3.5-9B](https://huggingface.co/unsloth/Qwen3.5-9B) on the spider_welsh dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 3407
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Use OptimizerNames.ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 0.03
+- num_epochs: 2.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.18.1
+- Transformers 5.5.0
+- Pytorch 2.10.0+cu128
+- Datasets 3.6.0
+- Tokenizers 0.22.2

Qwen3.5-9B_welsh_full_lf/adapter/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3_5ForConditionalGeneration",
+    "parent_library": "transformers.models.qwen3_5.modeling_qwen3_5",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen3.5-9B",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "(?:.*?(?:language|text).*?(?:self_attn|attention|attn|mixer|mlp|feed_forward|ffn|dense|mixer).*?(?:down_proj|gate_proj|in_proj_a|in_proj_b|in_proj_qkv|in_proj_z|k_proj|o_proj|out_proj|q_proj|up_proj|v_proj))|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mixer|mlp|feed_forward|ffn|dense|mixer)\\.(?:(?:down_proj|gate_proj|in_proj_a|in_proj_b|in_proj_qkv|in_proj_z|k_proj|o_proj|out_proj|q_proj|up_proj|v_proj)))",
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

Qwen3.5-9B_welsh_full_lf/adapter/all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "total_flos": 7.118946556894403e+17,
+    "train_loss": 0.07514798696934148,
+    "train_runtime": 25303.6125,
+    "train_samples_per_second": 0.549,
+    "train_steps_per_second": 0.069
+}

Qwen3.5-9B_welsh_full_lf/adapter/chat_template.jinja

@@ -0,0 +1,158 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- set num_sys = 0 %}
+{%- set merged_system = '' %}
+{%- if messages[0].role == 'system' or messages[0].role == 'developer' %}
+    {%- set first = render_content(messages[0].content, false, true)|trim %}
+    {%- if messages|length > 1 and (messages[1].role == 'system' or messages[1].role == 'developer') %}
+        {%- set second = render_content(messages[1].content, false, true)|trim %}
+        {%- set merged_system = first + '\n' + second %}
+        {%- set num_sys = 2 %}
+    {%- else %}
+        {%- set merged_system = first %}
+        {%- set num_sys = 1 %}
+    {%- endif %}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if merged_system %}
+        {{- '\n\n' + merged_system }}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if merged_system %}
+        {{- '<|im_start|>system\n' + merged_system + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if loop.index0 >= num_sys and message.role != "system" and message.role != "developer" %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is mapping %}
+                    {%- for args_name in tool_call.arguments %}
+                        {%- set args_value = tool_call.arguments[args_name] %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- else %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}
+{#- Unsloth fixes - developer role, tool calling #}

Qwen3.5-9B_welsh_full_lf/adapter/processor_config.json

@@ -0,0 +1,63 @@
+{
+  "image_processor": {
+    "data_format": "channels_first",
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Qwen2VLImageProcessor",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "merge_size": 2,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 16777216,
+      "shortest_edge": 65536
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen3VLProcessor",
+  "video_processor": {
+    "data_format": "channels_first",
+    "default_to_square": true,
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "fps": 2,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_frames": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 25165824,
+      "shortest_edge": 4096
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen3VLVideoProcessor"
+  }
+}

Qwen3.5-9B_welsh_full_lf/adapter/tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": false,
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}

Qwen3.5-9B_welsh_full_lf/adapter/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "total_flos": 7.118946556894403e+17,
+    "train_loss": 0.07514798696934148,
+    "train_runtime": 25303.6125,
+    "train_samples_per_second": 0.549,
+    "train_steps_per_second": 0.069
+}

Qwen3.5-9B_welsh_full_lf/adapter/trainer_log.jsonl

@@ -0,0 +1,174 @@
+{"current_steps": 10, "total_steps": 1738, "loss": 0.7214118957519531, "lr": 3.39622641509434e-05, "epoch": 0.011514104778353483, "percentage": 0.58, "elapsed_time": "0:04:02", "remaining_time": "11:39:26"}
+{"current_steps": 20, "total_steps": 1738, "loss": 0.40369887351989747, "lr": 7.169811320754717e-05, "epoch": 0.023028209556706966, "percentage": 1.15, "elapsed_time": "0:06:05", "remaining_time": "8:42:35"}
+{"current_steps": 30, "total_steps": 1738, "loss": 0.28697991371154785, "lr": 0.00010943396226415095, "epoch": 0.03454231433506045, "percentage": 1.73, "elapsed_time": "0:09:30", "remaining_time": "9:01:18"}
+{"current_steps": 40, "total_steps": 1738, "loss": 0.19481070041656495, "lr": 0.00014716981132075472, "epoch": 0.04605641911341393, "percentage": 2.3, "elapsed_time": "0:12:24", "remaining_time": "8:46:23"}
+{"current_steps": 50, "total_steps": 1738, "loss": 0.18217933177947998, "lr": 0.0001849056603773585, "epoch": 0.057570523891767415, "percentage": 2.88, "elapsed_time": "0:15:13", "remaining_time": "8:34:12"}
+{"current_steps": 60, "total_steps": 1738, "loss": 0.14774123430252076, "lr": 0.00019928783382789318, "epoch": 0.0690846286701209, "percentage": 3.45, "elapsed_time": "0:17:56", "remaining_time": "8:21:51"}
+{"current_steps": 70, "total_steps": 1738, "loss": 0.1435450315475464, "lr": 0.00019810089020771515, "epoch": 0.08059873344847437, "percentage": 4.03, "elapsed_time": "0:20:17", "remaining_time": "8:03:41"}
+{"current_steps": 80, "total_steps": 1738, "loss": 0.13325626850128175, "lr": 0.0001969139465875371, "epoch": 0.09211283822682786, "percentage": 4.6, "elapsed_time": "0:23:05", "remaining_time": "7:58:35"}
+{"current_steps": 90, "total_steps": 1738, "loss": 0.1322884202003479, "lr": 0.00019572700296735906, "epoch": 0.10362694300518134, "percentage": 5.18, "elapsed_time": "0:25:37", "remaining_time": "7:49:06"}
+{"current_steps": 100, "total_steps": 1738, "loss": 0.1434216618537903, "lr": 0.00019454005934718102, "epoch": 0.11514104778353483, "percentage": 5.75, "elapsed_time": "0:28:09", "remaining_time": "7:41:09"}
+{"current_steps": 110, "total_steps": 1738, "loss": 0.12563796043395997, "lr": 0.000193353115727003, "epoch": 0.1266551525618883, "percentage": 6.33, "elapsed_time": "0:30:40", "remaining_time": "7:33:59"}
+{"current_steps": 120, "total_steps": 1738, "loss": 0.10024609565734863, "lr": 0.00019216617210682493, "epoch": 0.1381692573402418, "percentage": 6.9, "elapsed_time": "0:32:44", "remaining_time": "7:21:33"}
+{"current_steps": 130, "total_steps": 1738, "loss": 0.1112401843070984, "lr": 0.0001909792284866469, "epoch": 0.1496833621185953, "percentage": 7.48, "elapsed_time": "0:35:12", "remaining_time": "7:15:24"}
+{"current_steps": 140, "total_steps": 1738, "loss": 0.14458032846450805, "lr": 0.00018979228486646886, "epoch": 0.16119746689694875, "percentage": 8.06, "elapsed_time": "0:37:29", "remaining_time": "7:08:01"}
+{"current_steps": 150, "total_steps": 1738, "loss": 0.15376924276351928, "lr": 0.0001886053412462908, "epoch": 0.17271157167530224, "percentage": 8.63, "elapsed_time": "0:39:57", "remaining_time": "7:03:00"}
+{"current_steps": 160, "total_steps": 1738, "loss": 0.12220618724822999, "lr": 0.00018741839762611277, "epoch": 0.18422567645365573, "percentage": 9.21, "elapsed_time": "0:42:27", "remaining_time": "6:58:43"}
+{"current_steps": 170, "total_steps": 1738, "loss": 0.13644108772277833, "lr": 0.00018623145400593473, "epoch": 0.19573978123200922, "percentage": 9.78, "elapsed_time": "0:44:41", "remaining_time": "6:52:08"}
+{"current_steps": 180, "total_steps": 1738, "loss": 0.12050632238388062, "lr": 0.00018504451038575667, "epoch": 0.20725388601036268, "percentage": 10.36, "elapsed_time": "0:47:21", "remaining_time": "6:49:58"}
+{"current_steps": 190, "total_steps": 1738, "loss": 0.095745050907135, "lr": 0.00018385756676557864, "epoch": 0.21876799078871617, "percentage": 10.93, "elapsed_time": "0:49:55", "remaining_time": "6:46:45"}
+{"current_steps": 200, "total_steps": 1738, "loss": 0.11167386770248414, "lr": 0.0001826706231454006, "epoch": 0.23028209556706966, "percentage": 11.51, "elapsed_time": "0:52:09", "remaining_time": "6:41:04"}
+{"current_steps": 210, "total_steps": 1738, "loss": 0.12026709318161011, "lr": 0.00018148367952522257, "epoch": 0.24179620034542315, "percentage": 12.08, "elapsed_time": "0:54:48", "remaining_time": "6:38:49"}
+{"current_steps": 220, "total_steps": 1738, "loss": 0.09432681798934936, "lr": 0.0001802967359050445, "epoch": 0.2533103051237766, "percentage": 12.66, "elapsed_time": "0:57:15", "remaining_time": "6:35:04"}
+{"current_steps": 230, "total_steps": 1738, "loss": 0.08572279810905456, "lr": 0.00017910979228486648, "epoch": 0.26482440990213013, "percentage": 13.23, "elapsed_time": "0:59:23", "remaining_time": "6:29:21"}
+{"current_steps": 240, "total_steps": 1738, "loss": 0.09878050684928893, "lr": 0.00017792284866468845, "epoch": 0.2763385146804836, "percentage": 13.81, "elapsed_time": "1:01:45", "remaining_time": "6:25:28"}
+{"current_steps": 250, "total_steps": 1738, "loss": 0.11013094186782837, "lr": 0.00017673590504451039, "epoch": 0.28785261945883706, "percentage": 14.38, "elapsed_time": "1:03:59", "remaining_time": "6:20:52"}
+{"current_steps": 260, "total_steps": 1738, "loss": 0.10203649997711181, "lr": 0.00017554896142433235, "epoch": 0.2993667242371906, "percentage": 14.96, "elapsed_time": "1:06:19", "remaining_time": "6:17:02"}
+{"current_steps": 270, "total_steps": 1738, "loss": 0.1063314437866211, "lr": 0.00017436201780415432, "epoch": 0.31088082901554404, "percentage": 15.54, "elapsed_time": "1:08:39", "remaining_time": "6:13:19"}
+{"current_steps": 280, "total_steps": 1738, "loss": 0.11133484840393067, "lr": 0.00017317507418397626, "epoch": 0.3223949337938975, "percentage": 16.11, "elapsed_time": "1:10:45", "remaining_time": "6:08:28"}
+{"current_steps": 290, "total_steps": 1738, "loss": 0.12339661121368409, "lr": 0.00017198813056379822, "epoch": 0.333909038572251, "percentage": 16.69, "elapsed_time": "1:12:54", "remaining_time": "6:04:01"}
+{"current_steps": 300, "total_steps": 1738, "loss": 0.12251745462417603, "lr": 0.0001708011869436202, "epoch": 0.3454231433506045, "percentage": 17.26, "elapsed_time": "1:15:35", "remaining_time": "6:02:21"}
+{"current_steps": 310, "total_steps": 1738, "loss": 0.08958682417869568, "lr": 0.00016961424332344213, "epoch": 0.356937248128958, "percentage": 17.84, "elapsed_time": "1:17:53", "remaining_time": "5:58:48"}
+{"current_steps": 320, "total_steps": 1738, "loss": 0.0981544315814972, "lr": 0.0001684272997032641, "epoch": 0.36845135290731146, "percentage": 18.41, "elapsed_time": "1:20:02", "remaining_time": "5:54:42"}
+{"current_steps": 330, "total_steps": 1738, "loss": 0.1052359700202942, "lr": 0.00016724035608308606, "epoch": 0.3799654576856649, "percentage": 18.99, "elapsed_time": "1:22:17", "remaining_time": "5:51:05"}
+{"current_steps": 340, "total_steps": 1738, "loss": 0.08735547065734864, "lr": 0.00016605341246290803, "epoch": 0.39147956246401844, "percentage": 19.56, "elapsed_time": "1:24:48", "remaining_time": "5:48:42"}
+{"current_steps": 350, "total_steps": 1738, "loss": 0.09380005598068238, "lr": 0.00016486646884272997, "epoch": 0.4029936672423719, "percentage": 20.14, "elapsed_time": "1:27:34", "remaining_time": "5:47:17"}
+{"current_steps": 360, "total_steps": 1738, "loss": 0.07771520018577575, "lr": 0.00016367952522255194, "epoch": 0.41450777202072536, "percentage": 20.71, "elapsed_time": "1:29:55", "remaining_time": "5:44:12"}
+{"current_steps": 370, "total_steps": 1738, "loss": 0.09400086998939514, "lr": 0.0001624925816023739, "epoch": 0.4260218767990789, "percentage": 21.29, "elapsed_time": "1:32:06", "remaining_time": "5:40:32"}
+{"current_steps": 380, "total_steps": 1738, "loss": 0.1022405743598938, "lr": 0.00016130563798219584, "epoch": 0.43753598157743234, "percentage": 21.86, "elapsed_time": "1:34:23", "remaining_time": "5:37:18"}
+{"current_steps": 390, "total_steps": 1738, "loss": 0.09805543422698974, "lr": 0.0001601186943620178, "epoch": 0.44905008635578586, "percentage": 22.44, "elapsed_time": "1:36:37", "remaining_time": "5:34:00"}
+{"current_steps": 400, "total_steps": 1738, "loss": 0.09697328805923462, "lr": 0.00015893175074183977, "epoch": 0.4605641911341393, "percentage": 23.01, "elapsed_time": "1:39:08", "remaining_time": "5:31:37"}
+{"current_steps": 410, "total_steps": 1738, "loss": 0.08837212920188904, "lr": 0.00015774480712166174, "epoch": 0.4720782959124928, "percentage": 23.59, "elapsed_time": "1:41:31", "remaining_time": "5:28:50"}
+{"current_steps": 420, "total_steps": 1738, "loss": 0.09212102890014648, "lr": 0.00015655786350148368, "epoch": 0.4835924006908463, "percentage": 24.17, "elapsed_time": "1:43:32", "remaining_time": "5:24:56"}
+{"current_steps": 430, "total_steps": 1738, "loss": 0.10352182388305664, "lr": 0.00015537091988130565, "epoch": 0.49510650546919976, "percentage": 24.74, "elapsed_time": "1:46:13", "remaining_time": "5:23:06"}
+{"current_steps": 440, "total_steps": 1738, "loss": 0.11673917770385742, "lr": 0.0001541839762611276, "epoch": 0.5066206102475532, "percentage": 25.32, "elapsed_time": "1:48:54", "remaining_time": "5:21:16"}
+{"current_steps": 450, "total_steps": 1738, "loss": 0.08048868775367737, "lr": 0.00015299703264094955, "epoch": 0.5181347150259067, "percentage": 25.89, "elapsed_time": "1:51:15", "remaining_time": "5:18:26"}
+{"current_steps": 460, "total_steps": 1738, "loss": 0.08197142481803894, "lr": 0.00015181008902077152, "epoch": 0.5296488198042603, "percentage": 26.47, "elapsed_time": "1:54:02", "remaining_time": "5:16:48"}
+{"current_steps": 470, "total_steps": 1738, "loss": 0.09152964353561402, "lr": 0.00015062314540059349, "epoch": 0.5411629245826137, "percentage": 27.04, "elapsed_time": "1:56:25", "remaining_time": "5:14:07"}
+{"current_steps": 480, "total_steps": 1738, "loss": 0.10178450345993043, "lr": 0.00014943620178041545, "epoch": 0.5526770293609672, "percentage": 27.62, "elapsed_time": "1:58:34", "remaining_time": "5:10:46"}
+{"current_steps": 490, "total_steps": 1738, "loss": 0.07893319129943847, "lr": 0.0001482492581602374, "epoch": 0.5641911341393206, "percentage": 28.19, "elapsed_time": "2:00:39", "remaining_time": "5:07:17"}
+{"current_steps": 500, "total_steps": 1738, "loss": 0.10701384544372558, "lr": 0.00014706231454005936, "epoch": 0.5757052389176741, "percentage": 28.77, "elapsed_time": "2:02:53", "remaining_time": "5:04:17"}
+{"current_steps": 510, "total_steps": 1738, "loss": 0.10969420671463012, "lr": 0.0001458753709198813, "epoch": 0.5872193436960277, "percentage": 29.34, "elapsed_time": "2:05:29", "remaining_time": "5:02:10"}
+{"current_steps": 520, "total_steps": 1738, "loss": 0.09703192114830017, "lr": 0.00014468842729970326, "epoch": 0.5987334484743811, "percentage": 29.92, "elapsed_time": "2:08:12", "remaining_time": "5:00:17"}
+{"current_steps": 530, "total_steps": 1738, "loss": 0.10334484577178955, "lr": 0.00014350148367952523, "epoch": 0.6102475532527346, "percentage": 30.49, "elapsed_time": "2:10:41", "remaining_time": "4:57:52"}
+{"current_steps": 540, "total_steps": 1738, "loss": 0.08816312551498413, "lr": 0.0001423145400593472, "epoch": 0.6217616580310881, "percentage": 31.07, "elapsed_time": "2:13:21", "remaining_time": "4:55:50"}
+{"current_steps": 550, "total_steps": 1738, "loss": 0.0984003484249115, "lr": 0.00014112759643916916, "epoch": 0.6332757628094415, "percentage": 31.65, "elapsed_time": "2:15:48", "remaining_time": "4:53:20"}
+{"current_steps": 560, "total_steps": 1738, "loss": 0.06861529350280762, "lr": 0.0001399406528189911, "epoch": 0.644789867587795, "percentage": 32.22, "elapsed_time": "2:17:57", "remaining_time": "4:50:12"}
+{"current_steps": 570, "total_steps": 1738, "loss": 0.08618277907371522, "lr": 0.00013875370919881304, "epoch": 0.6563039723661486, "percentage": 32.8, "elapsed_time": "2:20:13", "remaining_time": "4:47:19"}
+{"current_steps": 580, "total_steps": 1738, "loss": 0.0874285340309143, "lr": 0.000137566765578635, "epoch": 0.667818077144502, "percentage": 33.37, "elapsed_time": "2:22:35", "remaining_time": "4:44:41"}
+{"current_steps": 590, "total_steps": 1738, "loss": 0.08358646035194398, "lr": 0.00013637982195845698, "epoch": 0.6793321819228555, "percentage": 33.95, "elapsed_time": "2:24:50", "remaining_time": "4:41:50"}
+{"current_steps": 600, "total_steps": 1738, "loss": 0.0663270115852356, "lr": 0.00013519287833827894, "epoch": 0.690846286701209, "percentage": 34.52, "elapsed_time": "2:27:06", "remaining_time": "4:39:01"}
+{"current_steps": 610, "total_steps": 1738, "loss": 0.08234661817550659, "lr": 0.0001340059347181009, "epoch": 0.7023603914795624, "percentage": 35.1, "elapsed_time": "2:29:30", "remaining_time": "4:36:27"}
+{"current_steps": 620, "total_steps": 1738, "loss": 0.08269160985946655, "lr": 0.00013281899109792288, "epoch": 0.713874496257916, "percentage": 35.67, "elapsed_time": "2:31:51", "remaining_time": "4:33:49"}
+{"current_steps": 630, "total_steps": 1738, "loss": 0.10781055688858032, "lr": 0.00013163204747774482, "epoch": 0.7253886010362695, "percentage": 36.25, "elapsed_time": "2:34:05", "remaining_time": "4:31:01"}
+{"current_steps": 640, "total_steps": 1738, "loss": 0.08478482961654663, "lr": 0.00013044510385756675, "epoch": 0.7369027058146229, "percentage": 36.82, "elapsed_time": "2:36:37", "remaining_time": "4:28:42"}
+{"current_steps": 650, "total_steps": 1738, "loss": 0.08250377178192139, "lr": 0.00012925816023738872, "epoch": 0.7484168105929764, "percentage": 37.4, "elapsed_time": "2:38:37", "remaining_time": "4:25:31"}
+{"current_steps": 660, "total_steps": 1738, "loss": 0.09269567728042602, "lr": 0.0001280712166172107, "epoch": 0.7599309153713298, "percentage": 37.97, "elapsed_time": "2:41:26", "remaining_time": "4:23:41"}
+{"current_steps": 670, "total_steps": 1738, "loss": 0.08082546591758728, "lr": 0.00012688427299703265, "epoch": 0.7714450201496834, "percentage": 38.55, "elapsed_time": "2:44:10", "remaining_time": "4:21:41"}
+{"current_steps": 680, "total_steps": 1738, "loss": 0.07327563166618348, "lr": 0.00012569732937685462, "epoch": 0.7829591249280369, "percentage": 39.13, "elapsed_time": "2:46:54", "remaining_time": "4:19:41"}
+{"current_steps": 690, "total_steps": 1738, "loss": 0.08316924571990966, "lr": 0.00012451038575667656, "epoch": 0.7944732297063903, "percentage": 39.7, "elapsed_time": "2:48:51", "remaining_time": "4:16:28"}
+{"current_steps": 700, "total_steps": 1738, "loss": 0.06878896951675414, "lr": 0.0001233234421364985, "epoch": 0.8059873344847438, "percentage": 40.28, "elapsed_time": "2:51:22", "remaining_time": "4:14:07"}
+{"current_steps": 710, "total_steps": 1738, "loss": 0.0887125313282013, "lr": 0.00012213649851632047, "epoch": 0.8175014392630973, "percentage": 40.85, "elapsed_time": "2:54:06", "remaining_time": "4:12:05"}
+{"current_steps": 720, "total_steps": 1738, "loss": 0.06652654409408569, "lr": 0.00012094955489614243, "epoch": 0.8290155440414507, "percentage": 41.43, "elapsed_time": "2:56:16", "remaining_time": "4:09:13"}
+{"current_steps": 730, "total_steps": 1738, "loss": 0.06771059036254883, "lr": 0.0001197626112759644, "epoch": 0.8405296488198043, "percentage": 42.0, "elapsed_time": "2:58:26", "remaining_time": "4:06:24"}
+{"current_steps": 740, "total_steps": 1738, "loss": 0.07142643928527832, "lr": 0.00011857566765578637, "epoch": 0.8520437535981578, "percentage": 42.58, "elapsed_time": "3:01:02", "remaining_time": "4:04:09"}
+{"current_steps": 750, "total_steps": 1738, "loss": 0.07080649733543395, "lr": 0.00011738872403560832, "epoch": 0.8635578583765112, "percentage": 43.15, "elapsed_time": "3:03:13", "remaining_time": "4:01:21"}
+{"current_steps": 760, "total_steps": 1738, "loss": 0.08347562551498414, "lr": 0.00011620178041543029, "epoch": 0.8750719631548647, "percentage": 43.73, "elapsed_time": "3:06:03", "remaining_time": "3:59:25"}
+{"current_steps": 770, "total_steps": 1738, "loss": 0.06628671288490295, "lr": 0.00011501483679525222, "epoch": 0.8865860679332181, "percentage": 44.3, "elapsed_time": "3:08:11", "remaining_time": "3:56:35"}
+{"current_steps": 780, "total_steps": 1738, "loss": 0.062272709608078, "lr": 0.00011382789317507419, "epoch": 0.8981001727115717, "percentage": 44.88, "elapsed_time": "3:10:38", "remaining_time": "3:54:08"}
+{"current_steps": 790, "total_steps": 1738, "loss": 0.08221861720085144, "lr": 0.00011264094955489614, "epoch": 0.9096142774899252, "percentage": 45.45, "elapsed_time": "3:13:13", "remaining_time": "3:51:52"}
+{"current_steps": 800, "total_steps": 1738, "loss": 0.08009061217308044, "lr": 0.00011145400593471811, "epoch": 0.9211283822682786, "percentage": 46.03, "elapsed_time": "3:15:25", "remaining_time": "3:49:08"}
+{"current_steps": 810, "total_steps": 1738, "loss": 0.07698827385902404, "lr": 0.00011026706231454008, "epoch": 0.9326424870466321, "percentage": 46.61, "elapsed_time": "3:18:21", "remaining_time": "3:47:15"}
+{"current_steps": 820, "total_steps": 1738, "loss": 0.06156395077705383, "lr": 0.00010908011869436203, "epoch": 0.9441565918249856, "percentage": 47.18, "elapsed_time": "3:20:38", "remaining_time": "3:44:37"}
+{"current_steps": 830, "total_steps": 1738, "loss": 0.07166528105735778, "lr": 0.00010789317507418397, "epoch": 0.9556706966033391, "percentage": 47.76, "elapsed_time": "3:22:54", "remaining_time": "3:41:58"}
+{"current_steps": 840, "total_steps": 1738, "loss": 0.06146642565727234, "lr": 0.00010670623145400594, "epoch": 0.9671848013816926, "percentage": 48.33, "elapsed_time": "3:25:45", "remaining_time": "3:39:57"}
+{"current_steps": 850, "total_steps": 1738, "loss": 0.04770505428314209, "lr": 0.00010551928783382789, "epoch": 0.9786989061600461, "percentage": 48.91, "elapsed_time": "3:28:07", "remaining_time": "3:37:25"}
+{"current_steps": 860, "total_steps": 1738, "loss": 0.06332231163978577, "lr": 0.00010433234421364986, "epoch": 0.9902130109383995, "percentage": 49.48, "elapsed_time": "3:30:27", "remaining_time": "3:34:51"}
+{"current_steps": 870, "total_steps": 1738, "loss": 0.06636042594909668, "lr": 0.00010314540059347182, "epoch": 1.0011514104778354, "percentage": 50.06, "elapsed_time": "3:32:35", "remaining_time": "3:32:06"}
+{"current_steps": 880, "total_steps": 1738, "loss": 0.05551731586456299, "lr": 0.00010195845697329377, "epoch": 1.0126655152561888, "percentage": 50.63, "elapsed_time": "3:34:38", "remaining_time": "3:29:16"}
+{"current_steps": 890, "total_steps": 1738, "loss": 0.041544610261917116, "lr": 0.00010077151335311574, "epoch": 1.0241796200345423, "percentage": 51.21, "elapsed_time": "3:36:56", "remaining_time": "3:26:42"}
+{"current_steps": 900, "total_steps": 1738, "loss": 0.046289393305778505, "lr": 9.95845697329377e-05, "epoch": 1.035693724812896, "percentage": 51.78, "elapsed_time": "3:39:07", "remaining_time": "3:24:02"}
+{"current_steps": 910, "total_steps": 1738, "loss": 0.040427488088607785, "lr": 9.839762611275965e-05, "epoch": 1.0472078295912493, "percentage": 52.36, "elapsed_time": "3:41:14", "remaining_time": "3:21:18"}
+{"current_steps": 920, "total_steps": 1738, "loss": 0.056103754043579104, "lr": 9.72106824925816e-05, "epoch": 1.0587219343696028, "percentage": 52.93, "elapsed_time": "3:43:22", "remaining_time": "3:18:36"}
+{"current_steps": 930, "total_steps": 1738, "loss": 0.051932376623153684, "lr": 9.602373887240357e-05, "epoch": 1.0702360391479562, "percentage": 53.51, "elapsed_time": "3:45:39", "remaining_time": "3:16:03"}
+{"current_steps": 940, "total_steps": 1738, "loss": 0.06383747458457947, "lr": 9.483679525222552e-05, "epoch": 1.0817501439263097, "percentage": 54.09, "elapsed_time": "3:47:59", "remaining_time": "3:13:32"}
+{"current_steps": 950, "total_steps": 1738, "loss": 0.04659952521324158, "lr": 9.364985163204749e-05, "epoch": 1.093264248704663, "percentage": 54.66, "elapsed_time": "3:50:39", "remaining_time": "3:11:19"}
+{"current_steps": 960, "total_steps": 1738, "loss": 0.03717791140079498, "lr": 9.246290801186944e-05, "epoch": 1.1047783534830167, "percentage": 55.24, "elapsed_time": "3:53:08", "remaining_time": "3:08:56"}
+{"current_steps": 970, "total_steps": 1738, "loss": 0.041669240593910216, "lr": 9.12759643916914e-05, "epoch": 1.1162924582613702, "percentage": 55.81, "elapsed_time": "3:55:07", "remaining_time": "3:06:09"}
+{"current_steps": 980, "total_steps": 1738, "loss": 0.04851488769054413, "lr": 9.008902077151336e-05, "epoch": 1.1278065630397236, "percentage": 56.39, "elapsed_time": "3:57:39", "remaining_time": "3:03:49"}
+{"current_steps": 990, "total_steps": 1738, "loss": 0.045262986421585084, "lr": 8.890207715133531e-05, "epoch": 1.1393206678180772, "percentage": 56.96, "elapsed_time": "4:00:02", "remaining_time": "3:01:21"}
+{"current_steps": 1000, "total_steps": 1738, "loss": 0.05669504404067993, "lr": 8.771513353115728e-05, "epoch": 1.1508347725964305, "percentage": 57.54, "elapsed_time": "4:03:04", "remaining_time": "2:59:23"}
+{"current_steps": 1010, "total_steps": 1738, "loss": 0.04218461513519287, "lr": 8.652818991097923e-05, "epoch": 1.162348877374784, "percentage": 58.11, "elapsed_time": "4:05:40", "remaining_time": "2:57:04"}
+{"current_steps": 1020, "total_steps": 1738, "loss": 0.04000657498836517, "lr": 8.53412462908012e-05, "epoch": 1.1738629821531377, "percentage": 58.69, "elapsed_time": "4:07:55", "remaining_time": "2:54:31"}
+{"current_steps": 1030, "total_steps": 1738, "loss": 0.042275750637054445, "lr": 8.415430267062315e-05, "epoch": 1.185377086931491, "percentage": 59.26, "elapsed_time": "4:10:16", "remaining_time": "2:52:01"}
+{"current_steps": 1040, "total_steps": 1738, "loss": 0.050203102827072146, "lr": 8.29673590504451e-05, "epoch": 1.1968911917098446, "percentage": 59.84, "elapsed_time": "4:12:39", "remaining_time": "2:49:34"}
+{"current_steps": 1050, "total_steps": 1738, "loss": 0.05144000053405762, "lr": 8.178041543026707e-05, "epoch": 1.208405296488198, "percentage": 60.41, "elapsed_time": "4:15:13", "remaining_time": "2:47:14"}
+{"current_steps": 1060, "total_steps": 1738, "loss": 0.027037101984024047, "lr": 8.059347181008902e-05, "epoch": 1.2199194012665515, "percentage": 60.99, "elapsed_time": "4:17:17", "remaining_time": "2:44:34"}
+{"current_steps": 1070, "total_steps": 1738, "loss": 0.048537030816078186, "lr": 7.940652818991098e-05, "epoch": 1.231433506044905, "percentage": 61.57, "elapsed_time": "4:19:37", "remaining_time": "2:42:04"}
+{"current_steps": 1080, "total_steps": 1738, "loss": 0.052651751041412356, "lr": 7.821958456973294e-05, "epoch": 1.2429476108232584, "percentage": 62.14, "elapsed_time": "4:22:10", "remaining_time": "2:39:44"}
+{"current_steps": 1090, "total_steps": 1738, "loss": 0.051165294647216794, "lr": 7.70326409495549e-05, "epoch": 1.254461715601612, "percentage": 62.72, "elapsed_time": "4:24:22", "remaining_time": "2:37:10"}
+{"current_steps": 1100, "total_steps": 1738, "loss": 0.05947286486625671, "lr": 7.584569732937686e-05, "epoch": 1.2659758203799654, "percentage": 63.29, "elapsed_time": "4:26:53", "remaining_time": "2:34:47"}
+{"current_steps": 1110, "total_steps": 1738, "loss": 0.0427574098110199, "lr": 7.465875370919882e-05, "epoch": 1.277489925158319, "percentage": 63.87, "elapsed_time": "4:29:42", "remaining_time": "2:32:35"}
+{"current_steps": 1120, "total_steps": 1738, "loss": 0.039476633071899414, "lr": 7.347181008902078e-05, "epoch": 1.2890040299366725, "percentage": 64.44, "elapsed_time": "4:31:53", "remaining_time": "2:30:01"}
+{"current_steps": 1130, "total_steps": 1738, "loss": 0.052432358264923096, "lr": 7.228486646884273e-05, "epoch": 1.3005181347150259, "percentage": 65.02, "elapsed_time": "4:34:10", "remaining_time": "2:27:31"}
+{"current_steps": 1140, "total_steps": 1738, "loss": 0.04508967101573944, "lr": 7.109792284866469e-05, "epoch": 1.3120322394933794, "percentage": 65.59, "elapsed_time": "4:36:19", "remaining_time": "2:24:56"}
+{"current_steps": 1150, "total_steps": 1738, "loss": 0.04003302454948425, "lr": 6.991097922848665e-05, "epoch": 1.3235463442717328, "percentage": 66.17, "elapsed_time": "4:38:34", "remaining_time": "2:22:26"}
+{"current_steps": 1160, "total_steps": 1738, "loss": 0.0406215101480484, "lr": 6.872403560830861e-05, "epoch": 1.3350604490500864, "percentage": 66.74, "elapsed_time": "4:41:05", "remaining_time": "2:20:03"}
+{"current_steps": 1170, "total_steps": 1738, "loss": 0.04512817859649658, "lr": 6.753709198813056e-05, "epoch": 1.34657455382844, "percentage": 67.32, "elapsed_time": "4:43:36", "remaining_time": "2:17:40"}
+{"current_steps": 1180, "total_steps": 1738, "loss": 0.03435919582843781, "lr": 6.635014836795253e-05, "epoch": 1.3580886586067933, "percentage": 67.89, "elapsed_time": "4:46:02", "remaining_time": "2:15:15"}
+{"current_steps": 1190, "total_steps": 1738, "loss": 0.04768384397029877, "lr": 6.516320474777449e-05, "epoch": 1.3696027633851469, "percentage": 68.47, "elapsed_time": "4:48:42", "remaining_time": "2:12:57"}
+{"current_steps": 1200, "total_steps": 1738, "loss": 0.04078230857849121, "lr": 6.397626112759643e-05, "epoch": 1.3811168681635002, "percentage": 69.04, "elapsed_time": "4:51:02", "remaining_time": "2:10:28"}
+{"current_steps": 1210, "total_steps": 1738, "loss": 0.036511477828025815, "lr": 6.27893175074184e-05, "epoch": 1.3926309729418538, "percentage": 69.62, "elapsed_time": "4:53:22", "remaining_time": "2:08:01"}
+{"current_steps": 1220, "total_steps": 1738, "loss": 0.04176774621009827, "lr": 6.160237388724037e-05, "epoch": 1.4041450777202074, "percentage": 70.2, "elapsed_time": "4:55:30", "remaining_time": "2:05:28"}
+{"current_steps": 1230, "total_steps": 1738, "loss": 0.0369470477104187, "lr": 6.0415430267062325e-05, "epoch": 1.4156591824985607, "percentage": 70.77, "elapsed_time": "4:57:44", "remaining_time": "2:02:58"}
+{"current_steps": 1240, "total_steps": 1738, "loss": 0.03940508961677551, "lr": 5.922848664688427e-05, "epoch": 1.4271732872769143, "percentage": 71.35, "elapsed_time": "4:59:45", "remaining_time": "2:00:23"}
+{"current_steps": 1250, "total_steps": 1738, "loss": 0.06078723073005676, "lr": 5.804154302670624e-05, "epoch": 1.4386873920552676, "percentage": 71.92, "elapsed_time": "5:02:18", "remaining_time": "1:58:01"}
+{"current_steps": 1260, "total_steps": 1738, "loss": 0.053205251693725586, "lr": 5.68545994065282e-05, "epoch": 1.4502014968336212, "percentage": 72.5, "elapsed_time": "5:04:28", "remaining_time": "1:55:30"}
+{"current_steps": 1270, "total_steps": 1738, "loss": 0.05040244460105896, "lr": 5.566765578635015e-05, "epoch": 1.4617156016119748, "percentage": 73.07, "elapsed_time": "5:06:49", "remaining_time": "1:53:04"}
+{"current_steps": 1280, "total_steps": 1738, "loss": 0.03857344686985016, "lr": 5.448071216617211e-05, "epoch": 1.4732297063903281, "percentage": 73.65, "elapsed_time": "5:09:25", "remaining_time": "1:50:43"}
+{"current_steps": 1290, "total_steps": 1738, "loss": 0.03500775396823883, "lr": 5.329376854599407e-05, "epoch": 1.4847438111686817, "percentage": 74.22, "elapsed_time": "5:11:34", "remaining_time": "1:48:12"}
+{"current_steps": 1300, "total_steps": 1738, "loss": 0.0413168728351593, "lr": 5.210682492581602e-05, "epoch": 1.496257915947035, "percentage": 74.8, "elapsed_time": "5:13:51", "remaining_time": "1:45:44"}
+{"current_steps": 1310, "total_steps": 1738, "loss": 0.02512347400188446, "lr": 5.091988130563798e-05, "epoch": 1.5077720207253886, "percentage": 75.37, "elapsed_time": "5:15:59", "remaining_time": "1:43:14"}
+{"current_steps": 1320, "total_steps": 1738, "loss": 0.05228785276412964, "lr": 4.973293768545994e-05, "epoch": 1.5192861255037422, "percentage": 75.95, "elapsed_time": "5:18:09", "remaining_time": "1:40:45"}
+{"current_steps": 1330, "total_steps": 1738, "loss": 0.030683815479278564, "lr": 4.85459940652819e-05, "epoch": 1.5308002302820956, "percentage": 76.52, "elapsed_time": "5:20:08", "remaining_time": "1:38:12"}
+{"current_steps": 1340, "total_steps": 1738, "loss": 0.04171037077903748, "lr": 4.7359050445103856e-05, "epoch": 1.542314335060449, "percentage": 77.1, "elapsed_time": "5:22:21", "remaining_time": "1:35:44"}
+{"current_steps": 1350, "total_steps": 1738, "loss": 0.0462863951921463, "lr": 4.617210682492582e-05, "epoch": 1.5538284398388025, "percentage": 77.68, "elapsed_time": "5:24:27", "remaining_time": "1:33:15"}
+{"current_steps": 1360, "total_steps": 1738, "loss": 0.047386500239372256, "lr": 4.4985163204747775e-05, "epoch": 1.565342544617156, "percentage": 78.25, "elapsed_time": "5:27:13", "remaining_time": "1:30:56"}
+{"current_steps": 1370, "total_steps": 1738, "loss": 0.03228093385696411, "lr": 4.3798219584569735e-05, "epoch": 1.5768566493955096, "percentage": 78.83, "elapsed_time": "5:29:32", "remaining_time": "1:28:31"}
+{"current_steps": 1380, "total_steps": 1738, "loss": 0.04157269597053528, "lr": 4.2611275964391695e-05, "epoch": 1.588370754173863, "percentage": 79.4, "elapsed_time": "5:31:40", "remaining_time": "1:26:02"}
+{"current_steps": 1390, "total_steps": 1738, "loss": 0.03127920925617218, "lr": 4.1424332344213654e-05, "epoch": 1.5998848589522163, "percentage": 79.98, "elapsed_time": "5:34:14", "remaining_time": "1:23:40"}
+{"current_steps": 1400, "total_steps": 1738, "loss": 0.04768775999546051, "lr": 4.0237388724035614e-05, "epoch": 1.61139896373057, "percentage": 80.55, "elapsed_time": "5:36:35", "remaining_time": "1:21:15"}
+{"current_steps": 1410, "total_steps": 1738, "loss": 0.02834024131298065, "lr": 3.905044510385757e-05, "epoch": 1.6229130685089235, "percentage": 81.13, "elapsed_time": "5:38:54", "remaining_time": "1:18:50"}
+{"current_steps": 1420, "total_steps": 1738, "loss": 0.04801633358001709, "lr": 3.786350148367953e-05, "epoch": 1.634427173287277, "percentage": 81.7, "elapsed_time": "5:41:14", "remaining_time": "1:16:25"}
+{"current_steps": 1430, "total_steps": 1738, "loss": 0.041054919362068176, "lr": 3.6676557863501486e-05, "epoch": 1.6459412780656304, "percentage": 82.28, "elapsed_time": "5:43:45", "remaining_time": "1:14:02"}
+{"current_steps": 1440, "total_steps": 1738, "loss": 0.040874847769737245, "lr": 3.5489614243323446e-05, "epoch": 1.6574553828439837, "percentage": 82.85, "elapsed_time": "5:45:50", "remaining_time": "1:11:34"}
+{"current_steps": 1450, "total_steps": 1738, "loss": 0.033627331256866455, "lr": 3.43026706231454e-05, "epoch": 1.6689694876223373, "percentage": 83.43, "elapsed_time": "5:48:04", "remaining_time": "1:09:08"}
+{"current_steps": 1460, "total_steps": 1738, "loss": 0.038556909561157225, "lr": 3.311572700296736e-05, "epoch": 1.680483592400691, "percentage": 84.0, "elapsed_time": "5:50:22", "remaining_time": "1:06:42"}
+{"current_steps": 1470, "total_steps": 1738, "loss": 0.03320715129375458, "lr": 3.192878338278932e-05, "epoch": 1.6919976971790445, "percentage": 84.58, "elapsed_time": "5:52:54", "remaining_time": "1:04:20"}
+{"current_steps": 1480, "total_steps": 1738, "loss": 0.037805581092834474, "lr": 3.074183976261128e-05, "epoch": 1.7035118019573978, "percentage": 85.16, "elapsed_time": "5:55:25", "remaining_time": "1:01:57"}
+{"current_steps": 1490, "total_steps": 1738, "loss": 0.041676169633865355, "lr": 2.9554896142433235e-05, "epoch": 1.7150259067357512, "percentage": 85.73, "elapsed_time": "5:57:31", "remaining_time": "0:59:30"}
+{"current_steps": 1500, "total_steps": 1738, "loss": 0.030134257674217225, "lr": 2.836795252225519e-05, "epoch": 1.7265400115141047, "percentage": 86.31, "elapsed_time": "5:59:33", "remaining_time": "0:57:02"}
+{"current_steps": 1510, "total_steps": 1738, "loss": 0.039453747868537906, "lr": 2.7181008902077154e-05, "epoch": 1.7380541162924583, "percentage": 86.88, "elapsed_time": "6:02:37", "remaining_time": "0:54:45"}
+{"current_steps": 1520, "total_steps": 1738, "loss": 0.02459291070699692, "lr": 2.599406528189911e-05, "epoch": 1.749568221070812, "percentage": 87.46, "elapsed_time": "6:05:28", "remaining_time": "0:52:25"}
+{"current_steps": 1530, "total_steps": 1738, "loss": 0.03068529665470123, "lr": 2.480712166172107e-05, "epoch": 1.7610823258491652, "percentage": 88.03, "elapsed_time": "6:08:05", "remaining_time": "0:50:02"}
+{"current_steps": 1540, "total_steps": 1738, "loss": 0.03191893696784973, "lr": 2.362017804154303e-05, "epoch": 1.7725964306275186, "percentage": 88.61, "elapsed_time": "6:11:07", "remaining_time": "0:47:42"}
+{"current_steps": 1550, "total_steps": 1738, "loss": 0.033748915791511534, "lr": 2.2433234421364987e-05, "epoch": 1.7841105354058722, "percentage": 89.18, "elapsed_time": "6:13:54", "remaining_time": "0:45:21"}
+{"current_steps": 1560, "total_steps": 1738, "loss": 0.0300254225730896, "lr": 2.1246290801186943e-05, "epoch": 1.7956246401842257, "percentage": 89.76, "elapsed_time": "6:16:43", "remaining_time": "0:42:59"}
+{"current_steps": 1570, "total_steps": 1738, "loss": 0.03812649250030518, "lr": 2.0059347181008903e-05, "epoch": 1.8071387449625793, "percentage": 90.33, "elapsed_time": "6:19:42", "remaining_time": "0:40:37"}
+{"current_steps": 1580, "total_steps": 1738, "loss": 0.031631627678871156, "lr": 1.8872403560830862e-05, "epoch": 1.8186528497409327, "percentage": 90.91, "elapsed_time": "6:22:22", "remaining_time": "0:38:14"}
+{"current_steps": 1590, "total_steps": 1738, "loss": 0.032389625906944275, "lr": 1.7685459940652822e-05, "epoch": 1.830166954519286, "percentage": 91.48, "elapsed_time": "6:24:29", "remaining_time": "0:35:47"}
+{"current_steps": 1600, "total_steps": 1738, "loss": 0.029292455315589903, "lr": 1.649851632047478e-05, "epoch": 1.8416810592976396, "percentage": 92.06, "elapsed_time": "6:26:53", "remaining_time": "0:33:22"}
+{"current_steps": 1610, "total_steps": 1738, "loss": 0.027284839749336244, "lr": 1.5311572700296735e-05, "epoch": 1.8531951640759932, "percentage": 92.64, "elapsed_time": "6:29:08", "remaining_time": "0:30:56"}
+{"current_steps": 1620, "total_steps": 1738, "loss": 0.029107555747032166, "lr": 1.4124629080118695e-05, "epoch": 1.8647092688543467, "percentage": 93.21, "elapsed_time": "6:31:29", "remaining_time": "0:28:30"}
+{"current_steps": 1630, "total_steps": 1738, "loss": 0.027988749742507934, "lr": 1.2937685459940654e-05, "epoch": 1.8762233736327, "percentage": 93.79, "elapsed_time": "6:33:51", "remaining_time": "0:26:05"}
+{"current_steps": 1640, "total_steps": 1738, "loss": 0.027098262310028078, "lr": 1.1750741839762612e-05, "epoch": 1.8877374784110534, "percentage": 94.36, "elapsed_time": "6:36:16", "remaining_time": "0:23:40"}
+{"current_steps": 1650, "total_steps": 1738, "loss": 0.02801818251609802, "lr": 1.056379821958457e-05, "epoch": 1.899251583189407, "percentage": 94.94, "elapsed_time": "6:39:09", "remaining_time": "0:21:17"}
+{"current_steps": 1660, "total_steps": 1738, "loss": 0.0278301477432251, "lr": 9.376854599406528e-06, "epoch": 1.9107656879677606, "percentage": 95.51, "elapsed_time": "6:41:39", "remaining_time": "0:18:52"}
+{"current_steps": 1670, "total_steps": 1738, "loss": 0.03293090164661407, "lr": 8.189910979228487e-06, "epoch": 1.922279792746114, "percentage": 96.09, "elapsed_time": "6:43:46", "remaining_time": "0:16:26"}
+{"current_steps": 1680, "total_steps": 1738, "loss": 0.03201378583908081, "lr": 7.0029673590504455e-06, "epoch": 1.9337938975244675, "percentage": 96.66, "elapsed_time": "6:46:14", "remaining_time": "0:14:01"}
+{"current_steps": 1690, "total_steps": 1738, "loss": 0.028501972556114197, "lr": 5.8160237388724035e-06, "epoch": 1.9453080023028209, "percentage": 97.24, "elapsed_time": "6:49:21", "remaining_time": "0:11:37"}
+{"current_steps": 1700, "total_steps": 1738, "loss": 0.021708619594573975, "lr": 4.629080118694362e-06, "epoch": 1.9568221070811744, "percentage": 97.81, "elapsed_time": "6:51:43", "remaining_time": "0:09:12"}
+{"current_steps": 1710, "total_steps": 1738, "loss": 0.044218555092811584, "lr": 3.4421364985163205e-06, "epoch": 1.968336211859528, "percentage": 98.39, "elapsed_time": "6:54:17", "remaining_time": "0:06:47"}
+{"current_steps": 1720, "total_steps": 1738, "loss": 0.042003685235977174, "lr": 2.255192878338279e-06, "epoch": 1.9798503166378814, "percentage": 98.96, "elapsed_time": "6:57:16", "remaining_time": "0:04:22"}
+{"current_steps": 1730, "total_steps": 1738, "loss": 0.026947709918022155, "lr": 1.0682492581602374e-06, "epoch": 1.991364421416235, "percentage": 99.54, "elapsed_time": "6:59:50", "remaining_time": "0:01:56"}
+{"current_steps": 1738, "total_steps": 1738, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "7:01:43", "remaining_time": "0:00:00"}

Qwen3.5-9B_welsh_full_lf/adapter/trainer_state.json

@@ -0,0 +1,1254 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1738,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.011514104778353483,
+      "grad_norm": 1.4558032751083374,
+      "learning_rate": 3.39622641509434e-05,
+      "loss": 0.7214118957519531,
+      "step": 10
+    },
+    {
+      "epoch": 0.023028209556706966,
+      "grad_norm": 4.765519618988037,
+      "learning_rate": 7.169811320754717e-05,
+      "loss": 0.40369887351989747,
+      "step": 20
+    },
+    {
+      "epoch": 0.03454231433506045,
+      "grad_norm": 0.8812412619590759,
+      "learning_rate": 0.00010943396226415095,
+      "loss": 0.28697991371154785,
+      "step": 30
+    },
+    {
+      "epoch": 0.04605641911341393,
+      "grad_norm": 1.2945867776870728,
+      "learning_rate": 0.00014716981132075472,
+      "loss": 0.19481070041656495,
+      "step": 40
+    },
+    {
+      "epoch": 0.057570523891767415,
+      "grad_norm": 0.6869220733642578,
+      "learning_rate": 0.0001849056603773585,
+      "loss": 0.18217933177947998,
+      "step": 50
+    },
+    {
+      "epoch": 0.0690846286701209,
+      "grad_norm": 0.7667673230171204,
+      "learning_rate": 0.00019928783382789318,
+      "loss": 0.14774123430252076,
+      "step": 60
+    },
+    {
+      "epoch": 0.08059873344847437,
+      "grad_norm": 0.6553573608398438,
+      "learning_rate": 0.00019810089020771515,
+      "loss": 0.1435450315475464,
+      "step": 70
+    },
+    {
+      "epoch": 0.09211283822682786,
+      "grad_norm": 0.7137186527252197,
+      "learning_rate": 0.0001969139465875371,
+      "loss": 0.13325626850128175,
+      "step": 80
+    },
+    {
+      "epoch": 0.10362694300518134,
+      "grad_norm": 0.5576122999191284,
+      "learning_rate": 0.00019572700296735906,
+      "loss": 0.1322884202003479,
+      "step": 90
+    },
+    {
+      "epoch": 0.11514104778353483,
+      "grad_norm": 0.44553637504577637,
+      "learning_rate": 0.00019454005934718102,
+      "loss": 0.1434216618537903,
+      "step": 100
+    },
+    {
+      "epoch": 0.1266551525618883,
+      "grad_norm": 0.5558986067771912,
+      "learning_rate": 0.000193353115727003,
+      "loss": 0.12563796043395997,
+      "step": 110
+    },
+    {
+      "epoch": 0.1381692573402418,
+      "grad_norm": 0.2788373827934265,
+      "learning_rate": 0.00019216617210682493,
+      "loss": 0.10024609565734863,
+      "step": 120
+    },
+    {
+      "epoch": 0.1496833621185953,
+      "grad_norm": 0.5484940409660339,
+      "learning_rate": 0.0001909792284866469,
+      "loss": 0.1112401843070984,
+      "step": 130
+    },
+    {
+      "epoch": 0.16119746689694875,
+      "grad_norm": 0.5152013897895813,
+      "learning_rate": 0.00018979228486646886,
+      "loss": 0.14458032846450805,
+      "step": 140
+    },
+    {
+      "epoch": 0.17271157167530224,
+      "grad_norm": 0.31011199951171875,
+      "learning_rate": 0.0001886053412462908,
+      "loss": 0.15376924276351928,
+      "step": 150
+    },
+    {
+      "epoch": 0.18422567645365573,
+      "grad_norm": 0.5639772415161133,
+      "learning_rate": 0.00018741839762611277,
+      "loss": 0.12220618724822999,
+      "step": 160
+    },
+    {
+      "epoch": 0.19573978123200922,
+      "grad_norm": 0.6271322965621948,
+      "learning_rate": 0.00018623145400593473,
+      "loss": 0.13644108772277833,
+      "step": 170
+    },
+    {
+      "epoch": 0.20725388601036268,
+      "grad_norm": 0.5183396339416504,
+      "learning_rate": 0.00018504451038575667,
+      "loss": 0.12050632238388062,
+      "step": 180
+    },
+    {
+      "epoch": 0.21876799078871617,
+      "grad_norm": 0.45620793104171753,
+      "learning_rate": 0.00018385756676557864,
+      "loss": 0.095745050907135,
+      "step": 190
+    },
+    {
+      "epoch": 0.23028209556706966,
+      "grad_norm": 0.47088560461997986,
+      "learning_rate": 0.0001826706231454006,
+      "loss": 0.11167386770248414,
+      "step": 200
+    },
+    {
+      "epoch": 0.24179620034542315,
+      "grad_norm": 0.598639190196991,
+      "learning_rate": 0.00018148367952522257,
+      "loss": 0.12026709318161011,
+      "step": 210
+    },
+    {
+      "epoch": 0.2533103051237766,
+      "grad_norm": 0.33861279487609863,
+      "learning_rate": 0.0001802967359050445,
+      "loss": 0.09432681798934936,
+      "step": 220
+    },
+    {
+      "epoch": 0.26482440990213013,
+      "grad_norm": 0.7538613677024841,
+      "learning_rate": 0.00017910979228486648,
+      "loss": 0.08572279810905456,
+      "step": 230
+    },
+    {
+      "epoch": 0.2763385146804836,
+      "grad_norm": 0.2961339056491852,
+      "learning_rate": 0.00017792284866468845,
+      "loss": 0.09878050684928893,
+      "step": 240
+    },
+    {
+      "epoch": 0.28785261945883706,
+      "grad_norm": 0.32594889402389526,
+      "learning_rate": 0.00017673590504451039,
+      "loss": 0.11013094186782837,
+      "step": 250
+    },
+    {
+      "epoch": 0.2993667242371906,
+      "grad_norm": 0.569746732711792,
+      "learning_rate": 0.00017554896142433235,
+      "loss": 0.10203649997711181,
+      "step": 260
+    },
+    {
+      "epoch": 0.31088082901554404,
+      "grad_norm": 0.5933680534362793,
+      "learning_rate": 0.00017436201780415432,
+      "loss": 0.1063314437866211,
+      "step": 270
+    },
+    {
+      "epoch": 0.3223949337938975,
+      "grad_norm": 0.5610595941543579,
+      "learning_rate": 0.00017317507418397626,
+      "loss": 0.11133484840393067,
+      "step": 280
+    },
+    {
+      "epoch": 0.333909038572251,
+      "grad_norm": 0.22871655225753784,
+      "learning_rate": 0.00017198813056379822,
+      "loss": 0.12339661121368409,
+      "step": 290
+    },
+    {
+      "epoch": 0.3454231433506045,
+      "grad_norm": 0.6132893562316895,
+      "learning_rate": 0.0001708011869436202,
+      "loss": 0.12251745462417603,
+      "step": 300
+    },
+    {
+      "epoch": 0.356937248128958,
+      "grad_norm": 0.5523132085800171,
+      "learning_rate": 0.00016961424332344213,
+      "loss": 0.08958682417869568,
+      "step": 310
+    },
+    {
+      "epoch": 0.36845135290731146,
+      "grad_norm": 0.25884944200515747,
+      "learning_rate": 0.0001684272997032641,
+      "loss": 0.0981544315814972,
+      "step": 320
+    },
+    {
+      "epoch": 0.3799654576856649,
+      "grad_norm": 0.4305489957332611,
+      "learning_rate": 0.00016724035608308606,
+      "loss": 0.1052359700202942,
+      "step": 330
+    },
+    {
+      "epoch": 0.39147956246401844,
+      "grad_norm": 0.266972154378891,
+      "learning_rate": 0.00016605341246290803,
+      "loss": 0.08735547065734864,
+      "step": 340
+    },
+    {
+      "epoch": 0.4029936672423719,
+      "grad_norm": 0.3513997793197632,
+      "learning_rate": 0.00016486646884272997,
+      "loss": 0.09380005598068238,
+      "step": 350
+    },
+    {
+      "epoch": 0.41450777202072536,
+      "grad_norm": 0.399908185005188,
+      "learning_rate": 0.00016367952522255194,
+      "loss": 0.07771520018577575,
+      "step": 360
+    },
+    {
+      "epoch": 0.4260218767990789,
+      "grad_norm": 0.4173029065132141,
+      "learning_rate": 0.0001624925816023739,
+      "loss": 0.09400086998939514,
+      "step": 370
+    },
+    {
+      "epoch": 0.43753598157743234,
+      "grad_norm": 0.3607425093650818,
+      "learning_rate": 0.00016130563798219584,
+      "loss": 0.1022405743598938,
+      "step": 380
+    },
+    {
+      "epoch": 0.44905008635578586,
+      "grad_norm": 0.439272940158844,
+      "learning_rate": 0.0001601186943620178,
+      "loss": 0.09805543422698974,
+      "step": 390
+    },
+    {
+      "epoch": 0.4605641911341393,
+      "grad_norm": 0.30824899673461914,
+      "learning_rate": 0.00015893175074183977,
+      "loss": 0.09697328805923462,
+      "step": 400
+    },
+    {
+      "epoch": 0.4720782959124928,
+      "grad_norm": 0.22737231850624084,
+      "learning_rate": 0.00015774480712166174,
+      "loss": 0.08837212920188904,
+      "step": 410
+    },
+    {
+      "epoch": 0.4835924006908463,
+      "grad_norm": 0.5007696151733398,
+      "learning_rate": 0.00015655786350148368,
+      "loss": 0.09212102890014648,
+      "step": 420
+    },
+    {
+      "epoch": 0.49510650546919976,
+      "grad_norm": 0.8312163949012756,
+      "learning_rate": 0.00015537091988130565,
+      "loss": 0.10352182388305664,
+      "step": 430
+    },
+    {
+      "epoch": 0.5066206102475532,
+      "grad_norm": 0.3628128468990326,
+      "learning_rate": 0.0001541839762611276,
+      "loss": 0.11673917770385742,
+      "step": 440
+    },
+    {
+      "epoch": 0.5181347150259067,
+      "grad_norm": 0.30306267738342285,
+      "learning_rate": 0.00015299703264094955,
+      "loss": 0.08048868775367737,
+      "step": 450
+    },
+    {
+      "epoch": 0.5296488198042603,
+      "grad_norm": 0.4510067403316498,
+      "learning_rate": 0.00015181008902077152,
+      "loss": 0.08197142481803894,
+      "step": 460
+    },
+    {
+      "epoch": 0.5411629245826137,
+      "grad_norm": 0.8832160830497742,
+      "learning_rate": 0.00015062314540059349,
+      "loss": 0.09152964353561402,
+      "step": 470
+    },
+    {
+      "epoch": 0.5526770293609672,
+      "grad_norm": 0.2997573912143707,
+      "learning_rate": 0.00014943620178041545,
+      "loss": 0.10178450345993043,
+      "step": 480
+    },
+    {
+      "epoch": 0.5641911341393206,
+      "grad_norm": 0.5723673105239868,
+      "learning_rate": 0.0001482492581602374,
+      "loss": 0.07893319129943847,
+      "step": 490
+    },
+    {
+      "epoch": 0.5757052389176741,
+      "grad_norm": 0.28181231021881104,
+      "learning_rate": 0.00014706231454005936,
+      "loss": 0.10701384544372558,
+      "step": 500
+    },
+    {
+      "epoch": 0.5872193436960277,
+      "grad_norm": 0.2696997821331024,
+      "learning_rate": 0.0001458753709198813,
+      "loss": 0.10969420671463012,
+      "step": 510
+    },
+    {
+      "epoch": 0.5987334484743811,
+      "grad_norm": 0.2919272780418396,
+      "learning_rate": 0.00014468842729970326,
+      "loss": 0.09703192114830017,
+      "step": 520
+    },
+    {
+      "epoch": 0.6102475532527346,
+      "grad_norm": 0.43880972266197205,
+      "learning_rate": 0.00014350148367952523,
+      "loss": 0.10334484577178955,
+      "step": 530
+    },
+    {
+      "epoch": 0.6217616580310881,
+      "grad_norm": 0.7810805439949036,
+      "learning_rate": 0.0001423145400593472,
+      "loss": 0.08816312551498413,
+      "step": 540
+    },
+    {
+      "epoch": 0.6332757628094415,
+      "grad_norm": 0.5470167994499207,
+      "learning_rate": 0.00014112759643916916,
+      "loss": 0.0984003484249115,
+      "step": 550
+    },
+    {
+      "epoch": 0.644789867587795,
+      "grad_norm": 0.4899495542049408,
+      "learning_rate": 0.0001399406528189911,
+      "loss": 0.06861529350280762,
+      "step": 560
+    },
+    {
+      "epoch": 0.6563039723661486,
+      "grad_norm": 0.30544984340667725,
+      "learning_rate": 0.00013875370919881304,
+      "loss": 0.08618277907371522,
+      "step": 570
+    },
+    {
+      "epoch": 0.667818077144502,
+      "grad_norm": 0.30921170115470886,
+      "learning_rate": 0.000137566765578635,
+      "loss": 0.0874285340309143,
+      "step": 580
+    },
+    {
+      "epoch": 0.6793321819228555,
+      "grad_norm": 0.6284340023994446,
+      "learning_rate": 0.00013637982195845698,
+      "loss": 0.08358646035194398,
+      "step": 590
+    },
+    {
+      "epoch": 0.690846286701209,
+      "grad_norm": 0.789817750453949,
+      "learning_rate": 0.00013519287833827894,
+      "loss": 0.0663270115852356,
+      "step": 600
+    },
+    {
+      "epoch": 0.7023603914795624,
+      "grad_norm": 0.28056079149246216,
+      "learning_rate": 0.0001340059347181009,
+      "loss": 0.08234661817550659,
+      "step": 610
+    },
+    {
+      "epoch": 0.713874496257916,
+      "grad_norm": 0.21855522692203522,
+      "learning_rate": 0.00013281899109792288,
+      "loss": 0.08269160985946655,
+      "step": 620
+    },
+    {
+      "epoch": 0.7253886010362695,
+      "grad_norm": 0.31202933192253113,
+      "learning_rate": 0.00013163204747774482,
+      "loss": 0.10781055688858032,
+      "step": 630
+    },
+    {
+      "epoch": 0.7369027058146229,
+      "grad_norm": 0.3679397702217102,
+      "learning_rate": 0.00013044510385756675,
+      "loss": 0.08478482961654663,
+      "step": 640
+    },
+    {
+      "epoch": 0.7484168105929764,
+      "grad_norm": 0.5942097306251526,
+      "learning_rate": 0.00012925816023738872,
+      "loss": 0.08250377178192139,
+      "step": 650
+    },
+    {
+      "epoch": 0.7599309153713298,
+      "grad_norm": 0.5055614709854126,
+      "learning_rate": 0.0001280712166172107,
+      "loss": 0.09269567728042602,
+      "step": 660
+    },
+    {
+      "epoch": 0.7714450201496834,
+      "grad_norm": 0.2610802948474884,
+      "learning_rate": 0.00012688427299703265,
+      "loss": 0.08082546591758728,
+      "step": 670
+    },
+    {
+      "epoch": 0.7829591249280369,
+      "grad_norm": 0.6237701177597046,
+      "learning_rate": 0.00012569732937685462,
+      "loss": 0.07327563166618348,
+      "step": 680
+    },
+    {
+      "epoch": 0.7944732297063903,
+      "grad_norm": 0.26642152667045593,
+      "learning_rate": 0.00012451038575667656,
+      "loss": 0.08316924571990966,
+      "step": 690
+    },
+    {
+      "epoch": 0.8059873344847438,
+      "grad_norm": 0.21108104288578033,
+      "learning_rate": 0.0001233234421364985,
+      "loss": 0.06878896951675414,
+      "step": 700
+    },
+    {
+      "epoch": 0.8175014392630973,
+      "grad_norm": 0.4392440617084503,
+      "learning_rate": 0.00012213649851632047,
+      "loss": 0.0887125313282013,
+      "step": 710
+    },
+    {
+      "epoch": 0.8290155440414507,
+      "grad_norm": 0.320159912109375,
+      "learning_rate": 0.00012094955489614243,
+      "loss": 0.06652654409408569,
+      "step": 720
+    },
+    {
+      "epoch": 0.8405296488198043,
+      "grad_norm": 0.26460227370262146,
+      "learning_rate": 0.0001197626112759644,
+      "loss": 0.06771059036254883,
+      "step": 730
+    },
+    {
+      "epoch": 0.8520437535981578,
+      "grad_norm": 0.47004589438438416,
+      "learning_rate": 0.00011857566765578637,
+      "loss": 0.07142643928527832,
+      "step": 740
+    },
+    {
+      "epoch": 0.8635578583765112,
+      "grad_norm": 0.2473767101764679,
+      "learning_rate": 0.00011738872403560832,
+      "loss": 0.07080649733543395,
+      "step": 750
+    },
+    {
+      "epoch": 0.8750719631548647,
+      "grad_norm": 0.26875007152557373,
+      "learning_rate": 0.00011620178041543029,
+      "loss": 0.08347562551498414,
+      "step": 760
+    },
+    {
+      "epoch": 0.8865860679332181,
+      "grad_norm": 0.39182719588279724,
+      "learning_rate": 0.00011501483679525222,
+      "loss": 0.06628671288490295,
+      "step": 770
+    },
+    {
+      "epoch": 0.8981001727115717,
+      "grad_norm": 0.2714785635471344,
+      "learning_rate": 0.00011382789317507419,
+      "loss": 0.062272709608078,
+      "step": 780
+    },
+    {
+      "epoch": 0.9096142774899252,
+      "grad_norm": 0.21083220839500427,
+      "learning_rate": 0.00011264094955489614,
+      "loss": 0.08221861720085144,
+      "step": 790
+    },
+    {
+      "epoch": 0.9211283822682786,
+      "grad_norm": 0.3812112808227539,
+      "learning_rate": 0.00011145400593471811,
+      "loss": 0.08009061217308044,
+      "step": 800
+    },
+    {
+      "epoch": 0.9326424870466321,
+      "grad_norm": 0.21525849401950836,
+      "learning_rate": 0.00011026706231454008,
+      "loss": 0.07698827385902404,
+      "step": 810
+    },
+    {
+      "epoch": 0.9441565918249856,
+      "grad_norm": 0.20923684537410736,
+      "learning_rate": 0.00010908011869436203,
+      "loss": 0.06156395077705383,
+      "step": 820
+    },
+    {
+      "epoch": 0.9556706966033391,
+      "grad_norm": 0.31822460889816284,
+      "learning_rate": 0.00010789317507418397,
+      "loss": 0.07166528105735778,
+      "step": 830
+    },
+    {
+      "epoch": 0.9671848013816926,
+      "grad_norm": 0.5312325358390808,
+      "learning_rate": 0.00010670623145400594,
+      "loss": 0.06146642565727234,
+      "step": 840
+    },
+    {
+      "epoch": 0.9786989061600461,
+      "grad_norm": 0.6128759980201721,
+      "learning_rate": 0.00010551928783382789,
+      "loss": 0.04770505428314209,
+      "step": 850
+    },
+    {
+      "epoch": 0.9902130109383995,
+      "grad_norm": 0.251099169254303,
+      "learning_rate": 0.00010433234421364986,
+      "loss": 0.06332231163978577,
+      "step": 860
+    },
+    {
+      "epoch": 1.0011514104778354,
+      "grad_norm": 0.524421215057373,
+      "learning_rate": 0.00010314540059347182,
+      "loss": 0.06636042594909668,
+      "step": 870
+    },
+    {
+      "epoch": 1.0126655152561888,
+      "grad_norm": 0.4020656943321228,
+      "learning_rate": 0.00010195845697329377,
+      "loss": 0.05551731586456299,
+      "step": 880
+    },
+    {
+      "epoch": 1.0241796200345423,
+      "grad_norm": 0.21171116828918457,
+      "learning_rate": 0.00010077151335311574,
+      "loss": 0.041544610261917116,
+      "step": 890
+    },
+    {
+      "epoch": 1.035693724812896,
+      "grad_norm": 0.24785779416561127,
+      "learning_rate": 9.95845697329377e-05,
+      "loss": 0.046289393305778505,
+      "step": 900
+    },
+    {
+      "epoch": 1.0472078295912493,
+      "grad_norm": 0.32275211811065674,
+      "learning_rate": 9.839762611275965e-05,
+      "loss": 0.040427488088607785,
+      "step": 910
+    },
+    {
+      "epoch": 1.0587219343696028,
+      "grad_norm": 0.35576608777046204,
+      "learning_rate": 9.72106824925816e-05,
+      "loss": 0.056103754043579104,
+      "step": 920
+    },
+    {
+      "epoch": 1.0702360391479562,
+      "grad_norm": 0.36621224880218506,
+      "learning_rate": 9.602373887240357e-05,
+      "loss": 0.051932376623153684,
+      "step": 930
+    },
+    {
+      "epoch": 1.0817501439263097,
+      "grad_norm": 0.39907899498939514,
+      "learning_rate": 9.483679525222552e-05,
+      "loss": 0.06383747458457947,
+      "step": 940
+    },
+    {
+      "epoch": 1.093264248704663,
+      "grad_norm": 0.3571564257144928,
+      "learning_rate": 9.364985163204749e-05,
+      "loss": 0.04659952521324158,
+      "step": 950
+    },
+    {
+      "epoch": 1.1047783534830167,
+      "grad_norm": 0.48820701241493225,
+      "learning_rate": 9.246290801186944e-05,
+      "loss": 0.03717791140079498,
+      "step": 960
+    },
+    {
+      "epoch": 1.1162924582613702,
+      "grad_norm": 1.1392631530761719,
+      "learning_rate": 9.12759643916914e-05,
+      "loss": 0.041669240593910216,
+      "step": 970
+    },
+    {
+      "epoch": 1.1278065630397236,
+      "grad_norm": 0.4742698073387146,
+      "learning_rate": 9.008902077151336e-05,
+      "loss": 0.04851488769054413,
+      "step": 980
+    },
+    {
+      "epoch": 1.1393206678180772,
+      "grad_norm": 0.42412784695625305,
+      "learning_rate": 8.890207715133531e-05,
+      "loss": 0.045262986421585084,
+      "step": 990
+    },
+    {
+      "epoch": 1.1508347725964305,
+      "grad_norm": 0.3542984127998352,
+      "learning_rate": 8.771513353115728e-05,
+      "loss": 0.05669504404067993,
+      "step": 1000
+    },
+    {
+      "epoch": 1.162348877374784,
+      "grad_norm": 0.33334553241729736,
+      "learning_rate": 8.652818991097923e-05,
+      "loss": 0.04218461513519287,
+      "step": 1010
+    },
+    {
+      "epoch": 1.1738629821531377,
+      "grad_norm": 0.23639903962612152,
+      "learning_rate": 8.53412462908012e-05,
+      "loss": 0.04000657498836517,
+      "step": 1020
+    },
+    {
+      "epoch": 1.185377086931491,
+      "grad_norm": 0.40800777077674866,
+      "learning_rate": 8.415430267062315e-05,
+      "loss": 0.042275750637054445,
+      "step": 1030
+    },
+    {
+      "epoch": 1.1968911917098446,
+      "grad_norm": 0.3577110767364502,
+      "learning_rate": 8.29673590504451e-05,
+      "loss": 0.050203102827072146,
+      "step": 1040
+    },
+    {
+      "epoch": 1.208405296488198,
+      "grad_norm": 0.25555360317230225,
+      "learning_rate": 8.178041543026707e-05,
+      "loss": 0.05144000053405762,
+      "step": 1050
+    },
+    {
+      "epoch": 1.2199194012665515,
+      "grad_norm": 0.14299063384532928,
+      "learning_rate": 8.059347181008902e-05,
+      "loss": 0.027037101984024047,
+      "step": 1060
+    },
+    {
+      "epoch": 1.231433506044905,
+      "grad_norm": 0.6325031518936157,
+      "learning_rate": 7.940652818991098e-05,
+      "loss": 0.048537030816078186,
+      "step": 1070
+    },
+    {
+      "epoch": 1.2429476108232584,
+      "grad_norm": 0.44334766268730164,
+      "learning_rate": 7.821958456973294e-05,
+      "loss": 0.052651751041412356,
+      "step": 1080
+    },
+    {
+      "epoch": 1.254461715601612,
+      "grad_norm": 0.18431749939918518,
+      "learning_rate": 7.70326409495549e-05,
+      "loss": 0.051165294647216794,
+      "step": 1090
+    },
+    {
+      "epoch": 1.2659758203799654,
+      "grad_norm": 0.3941076695919037,
+      "learning_rate": 7.584569732937686e-05,
+      "loss": 0.05947286486625671,
+      "step": 1100
+    },
+    {
+      "epoch": 1.277489925158319,
+      "grad_norm": 0.4393896460533142,
+      "learning_rate": 7.465875370919882e-05,
+      "loss": 0.0427574098110199,
+      "step": 1110
+    },
+    {
+      "epoch": 1.2890040299366725,
+      "grad_norm": 0.17205744981765747,
+      "learning_rate": 7.347181008902078e-05,
+      "loss": 0.039476633071899414,
+      "step": 1120
+    },
+    {
+      "epoch": 1.3005181347150259,
+      "grad_norm": 0.47802436351776123,
+      "learning_rate": 7.228486646884273e-05,
+      "loss": 0.052432358264923096,
+      "step": 1130
+    },
+    {
+      "epoch": 1.3120322394933794,
+      "grad_norm": 0.300777792930603,
+      "learning_rate": 7.109792284866469e-05,
+      "loss": 0.04508967101573944,
+      "step": 1140
+    },
+    {
+      "epoch": 1.3235463442717328,
+      "grad_norm": 0.3595801293849945,
+      "learning_rate": 6.991097922848665e-05,
+      "loss": 0.04003302454948425,
+      "step": 1150
+    },
+    {
+      "epoch": 1.3350604490500864,
+      "grad_norm": 0.4657699465751648,
+      "learning_rate": 6.872403560830861e-05,
+      "loss": 0.0406215101480484,
+      "step": 1160
+    },
+    {
+      "epoch": 1.34657455382844,
+      "grad_norm": 0.39386045932769775,
+      "learning_rate": 6.753709198813056e-05,
+      "loss": 0.04512817859649658,
+      "step": 1170
+    },
+    {
+      "epoch": 1.3580886586067933,
+      "grad_norm": 0.31093859672546387,
+      "learning_rate": 6.635014836795253e-05,
+      "loss": 0.03435919582843781,
+      "step": 1180
+    },
+    {
+      "epoch": 1.3696027633851469,
+      "grad_norm": 0.2486288994550705,
+      "learning_rate": 6.516320474777449e-05,
+      "loss": 0.04768384397029877,
+      "step": 1190
+    },
+    {
+      "epoch": 1.3811168681635002,
+      "grad_norm": 0.3453502058982849,
+      "learning_rate": 6.397626112759643e-05,
+      "loss": 0.04078230857849121,
+      "step": 1200
+    },
+    {
+      "epoch": 1.3926309729418538,
+      "grad_norm": 0.1968221515417099,
+      "learning_rate": 6.27893175074184e-05,
+      "loss": 0.036511477828025815,
+      "step": 1210
+    },
+    {
+      "epoch": 1.4041450777202074,
+      "grad_norm": 0.3216422200202942,
+      "learning_rate": 6.160237388724037e-05,
+      "loss": 0.04176774621009827,
+      "step": 1220
+    },
+    {
+      "epoch": 1.4156591824985607,
+      "grad_norm": 0.2759150266647339,
+      "learning_rate": 6.0415430267062325e-05,
+      "loss": 0.0369470477104187,
+      "step": 1230
+    },
+    {
+      "epoch": 1.4271732872769143,
+      "grad_norm": 0.18846890330314636,
+      "learning_rate": 5.922848664688427e-05,
+      "loss": 0.03940508961677551,
+      "step": 1240
+    },
+    {
+      "epoch": 1.4386873920552676,
+      "grad_norm": 0.33738717436790466,
+      "learning_rate": 5.804154302670624e-05,
+      "loss": 0.06078723073005676,
+      "step": 1250
+    },
+    {
+      "epoch": 1.4502014968336212,
+      "grad_norm": 0.2819264233112335,
+      "learning_rate": 5.68545994065282e-05,
+      "loss": 0.053205251693725586,
+      "step": 1260
+    },
+    {
+      "epoch": 1.4617156016119748,
+      "grad_norm": 0.3969738781452179,
+      "learning_rate": 5.566765578635015e-05,
+      "loss": 0.05040244460105896,
+      "step": 1270
+    },
+    {
+      "epoch": 1.4732297063903281,
+      "grad_norm": 0.2037401795387268,
+      "learning_rate": 5.448071216617211e-05,
+      "loss": 0.03857344686985016,
+      "step": 1280
+    },
+    {
+      "epoch": 1.4847438111686817,
+      "grad_norm": 0.3159101605415344,
+      "learning_rate": 5.329376854599407e-05,
+      "loss": 0.03500775396823883,
+      "step": 1290
+    },
+    {
+      "epoch": 1.496257915947035,
+      "grad_norm": 0.4511728286743164,
+      "learning_rate": 5.210682492581602e-05,
+      "loss": 0.0413168728351593,
+      "step": 1300
+    },
+    {
+      "epoch": 1.5077720207253886,
+      "grad_norm": 0.535791277885437,
+      "learning_rate": 5.091988130563798e-05,
+      "loss": 0.02512347400188446,
+      "step": 1310
+    },
+    {
+      "epoch": 1.5192861255037422,
+      "grad_norm": 0.1492532640695572,
+      "learning_rate": 4.973293768545994e-05,
+      "loss": 0.05228785276412964,
+      "step": 1320
+    },
+    {
+      "epoch": 1.5308002302820956,
+      "grad_norm": 0.09458675235509872,
+      "learning_rate": 4.85459940652819e-05,
+      "loss": 0.030683815479278564,
+      "step": 1330
+    },
+    {
+      "epoch": 1.542314335060449,
+      "grad_norm": 0.8175351619720459,
+      "learning_rate": 4.7359050445103856e-05,
+      "loss": 0.04171037077903748,
+      "step": 1340
+    },
+    {
+      "epoch": 1.5538284398388025,
+      "grad_norm": 0.6590670347213745,
+      "learning_rate": 4.617210682492582e-05,
+      "loss": 0.0462863951921463,
+      "step": 1350
+    },
+    {
+      "epoch": 1.565342544617156,
+      "grad_norm": 0.29340294003486633,
+      "learning_rate": 4.4985163204747775e-05,
+      "loss": 0.047386500239372256,
+      "step": 1360
+    },
+    {
+      "epoch": 1.5768566493955096,
+      "grad_norm": 0.1729775071144104,
+      "learning_rate": 4.3798219584569735e-05,
+      "loss": 0.03228093385696411,
+      "step": 1370
+    },
+    {
+      "epoch": 1.588370754173863,
+      "grad_norm": 0.3740657866001129,
+      "learning_rate": 4.2611275964391695e-05,
+      "loss": 0.04157269597053528,
+      "step": 1380
+    },
+    {
+      "epoch": 1.5998848589522163,
+      "grad_norm": 0.3295336961746216,
+      "learning_rate": 4.1424332344213654e-05,
+      "loss": 0.03127920925617218,
+      "step": 1390
+    },
+    {
+      "epoch": 1.61139896373057,
+      "grad_norm": 0.21351835131645203,
+      "learning_rate": 4.0237388724035614e-05,
+      "loss": 0.04768775999546051,
+      "step": 1400
+    },
+    {
+      "epoch": 1.6229130685089235,
+      "grad_norm": 0.1875276416540146,
+      "learning_rate": 3.905044510385757e-05,
+      "loss": 0.02834024131298065,
+      "step": 1410
+    },
+    {
+      "epoch": 1.634427173287277,
+      "grad_norm": 0.3403257131576538,
+      "learning_rate": 3.786350148367953e-05,
+      "loss": 0.04801633358001709,
+      "step": 1420
+    },
+    {
+      "epoch": 1.6459412780656304,
+      "grad_norm": 0.9062486886978149,
+      "learning_rate": 3.6676557863501486e-05,
+      "loss": 0.041054919362068176,
+      "step": 1430
+    },
+    {
+      "epoch": 1.6574553828439837,
+      "grad_norm": 0.5807716250419617,
+      "learning_rate": 3.5489614243323446e-05,
+      "loss": 0.040874847769737245,
+      "step": 1440
+    },
+    {
+      "epoch": 1.6689694876223373,
+      "grad_norm": 0.30800801515579224,
+      "learning_rate": 3.43026706231454e-05,
+      "loss": 0.033627331256866455,
+      "step": 1450
+    },
+    {
+      "epoch": 1.680483592400691,
+      "grad_norm": 0.2765117585659027,
+      "learning_rate": 3.311572700296736e-05,
+      "loss": 0.038556909561157225,
+      "step": 1460
+    },
+    {
+      "epoch": 1.6919976971790445,
+      "grad_norm": 0.4241560399532318,
+      "learning_rate": 3.192878338278932e-05,
+      "loss": 0.03320715129375458,
+      "step": 1470
+    },
+    {
+      "epoch": 1.7035118019573978,
+      "grad_norm": 0.22165395319461823,
+      "learning_rate": 3.074183976261128e-05,
+      "loss": 0.037805581092834474,
+      "step": 1480
+    },
+    {
+      "epoch": 1.7150259067357512,
+      "grad_norm": 0.7209855318069458,
+      "learning_rate": 2.9554896142433235e-05,
+      "loss": 0.041676169633865355,
+      "step": 1490
+    },
+    {
+      "epoch": 1.7265400115141047,
+      "grad_norm": 0.25309354066848755,
+      "learning_rate": 2.836795252225519e-05,
+      "loss": 0.030134257674217225,
+      "step": 1500
+    },
+    {
+      "epoch": 1.7380541162924583,
+      "grad_norm": 0.7028369903564453,
+      "learning_rate": 2.7181008902077154e-05,
+      "loss": 0.039453747868537906,
+      "step": 1510
+    },
+    {
+      "epoch": 1.749568221070812,
+      "grad_norm": 0.37315866351127625,
+      "learning_rate": 2.599406528189911e-05,
+      "loss": 0.02459291070699692,
+      "step": 1520
+    },
+    {
+      "epoch": 1.7610823258491652,
+      "grad_norm": 0.2048654407262802,
+      "learning_rate": 2.480712166172107e-05,
+      "loss": 0.03068529665470123,
+      "step": 1530
+    },
+    {
+      "epoch": 1.7725964306275186,
+      "grad_norm": 0.35909903049468994,
+      "learning_rate": 2.362017804154303e-05,
+      "loss": 0.03191893696784973,
+      "step": 1540
+    },
+    {
+      "epoch": 1.7841105354058722,
+      "grad_norm": 0.51167893409729,
+      "learning_rate": 2.2433234421364987e-05,
+      "loss": 0.033748915791511534,
+      "step": 1550
+    },
+    {
+      "epoch": 1.7956246401842257,
+      "grad_norm": 0.23251453042030334,
+      "learning_rate": 2.1246290801186943e-05,
+      "loss": 0.0300254225730896,
+      "step": 1560
+    },
+    {
+      "epoch": 1.8071387449625793,
+      "grad_norm": 0.42090904712677,
+      "learning_rate": 2.0059347181008903e-05,
+      "loss": 0.03812649250030518,
+      "step": 1570
+    },
+    {
+      "epoch": 1.8186528497409327,
+      "grad_norm": 0.24246828258037567,
+      "learning_rate": 1.8872403560830862e-05,
+      "loss": 0.031631627678871156,
+      "step": 1580
+    },
+    {
+      "epoch": 1.830166954519286,
+      "grad_norm": 0.35859379172325134,
+      "learning_rate": 1.7685459940652822e-05,
+      "loss": 0.032389625906944275,
+      "step": 1590
+    },
+    {
+      "epoch": 1.8416810592976396,
+      "grad_norm": 0.24687489867210388,
+      "learning_rate": 1.649851632047478e-05,
+      "loss": 0.029292455315589903,
+      "step": 1600
+    },
+    {
+      "epoch": 1.8531951640759932,
+      "grad_norm": 0.46190133690834045,
+      "learning_rate": 1.5311572700296735e-05,
+      "loss": 0.027284839749336244,
+      "step": 1610
+    },
+    {
+      "epoch": 1.8647092688543467,
+      "grad_norm": 0.21108290553092957,
+      "learning_rate": 1.4124629080118695e-05,
+      "loss": 0.029107555747032166,
+      "step": 1620
+    },
+    {
+      "epoch": 1.8762233736327,
+      "grad_norm": 0.33688458800315857,
+      "learning_rate": 1.2937685459940654e-05,
+      "loss": 0.027988749742507934,
+      "step": 1630
+    },
+    {
+      "epoch": 1.8877374784110534,
+      "grad_norm": 0.6299461126327515,
+      "learning_rate": 1.1750741839762612e-05,
+      "loss": 0.027098262310028078,
+      "step": 1640
+    },
+    {
+      "epoch": 1.899251583189407,
+      "grad_norm": 0.4760795533657074,
+      "learning_rate": 1.056379821958457e-05,
+      "loss": 0.02801818251609802,
+      "step": 1650
+    },
+    {
+      "epoch": 1.9107656879677606,
+      "grad_norm": 0.3895326256752014,
+      "learning_rate": 9.376854599406528e-06,
+      "loss": 0.0278301477432251,
+      "step": 1660
+    },
+    {
+      "epoch": 1.922279792746114,
+      "grad_norm": 0.38368672132492065,
+      "learning_rate": 8.189910979228487e-06,
+      "loss": 0.03293090164661407,
+      "step": 1670
+    },
+    {
+      "epoch": 1.9337938975244675,
+      "grad_norm": 0.47976401448249817,
+      "learning_rate": 7.0029673590504455e-06,
+      "loss": 0.03201378583908081,
+      "step": 1680
+    },
+    {
+      "epoch": 1.9453080023028209,
+      "grad_norm": 0.2510550022125244,
+      "learning_rate": 5.8160237388724035e-06,
+      "loss": 0.028501972556114197,
+      "step": 1690
+    },
+    {
+      "epoch": 1.9568221070811744,
+      "grad_norm": 0.2520145773887634,
+      "learning_rate": 4.629080118694362e-06,
+      "loss": 0.021708619594573975,
+      "step": 1700
+    },
+    {
+      "epoch": 1.968336211859528,
+      "grad_norm": 0.16273872554302216,
+      "learning_rate": 3.4421364985163205e-06,
+      "loss": 0.044218555092811584,
+      "step": 1710
+    },
+    {
+      "epoch": 1.9798503166378814,
+      "grad_norm": 0.39117512106895447,
+      "learning_rate": 2.255192878338279e-06,
+      "loss": 0.042003685235977174,
+      "step": 1720
+    },
+    {
+      "epoch": 1.991364421416235,
+      "grad_norm": 0.5790410041809082,
+      "learning_rate": 1.0682492581602374e-06,
+      "loss": 0.026947709918022155,
+      "step": 1730
+    },
+    {
+      "epoch": 2.0,
+      "step": 1738,
+      "total_flos": 7.118946556894403e+17,
+      "train_loss": 0.07514798696934148,
+      "train_runtime": 25303.6125,
+      "train_samples_per_second": 0.549,
+      "train_steps_per_second": 0.069
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1738,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.118946556894403e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

Qwen3.5-9B_welsh_full_lf/training_summary.json

@@ -0,0 +1,55 @@
+{
+ "run_name": "Qwen3.5-9B_welsh_full_lf",
+ "condition": "welsh",
+ "model_id": "unsloth/Qwen3.5-9B",
+ "dose": "full",
+ "dose_file": "/content/drive/MyDrive/Syn-SQL Spider train  BIRD train/v2/train data/welsh/train/spider_cy_6948.jsonl",
+ "n_rows": 6948,
+ "hyperparameters": {
+  "load_in_4bit": true,
+  "max_seq_length": 4096,
+  "lora_r": 16,
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "learning_rate": 0.0002,
+  "epochs": 2.0,
+  "per_device_batch_size": 2,
+  "grad_accum": 4,
+  "warmup_ratio": 0.03,
+  "weight_decay": 0.01,
+  "lr_scheduler": "linear",
+  "seed": 3407,
+  "optim": "adamw_8bit",
+  "loss_on": "responses_only (SQL answer + end-of-turn)"
+ },
+ "prompt_version": "p1",
+ "notebook_version": "train-v3-lf3",
+ "instruction_sha256": "c7e8631a429b9e8e",
+ "framework": "llamafactory@ef2d8f9da66ef13378dc8068dabc99cfe89a9736",
+ "lf_template": "qwen3_5",
+ "use_unsloth_requested": true,
+ "use_unsloth_effective": true,
+ "tiny_run": false,
+ "n_rows_over_cutoff": 18,
+ "resume_note": null,
+ "trained_by": "RUN_qwen35.ipynb",
+ "render_provenance": {
+  "text_construction": "llamafactory template render (canary-verified == eval_prompt_render + SQL + EOT)",
+  "chat_template_sha256": "8452ca85cb1e0ff0"
+ },
+ "train_loss": 0.07514798696934148,
+ "train_runtime_s": 25303.6125,
+ "versions": {
+  "torch": "2.10.0",
+  "transformers": "5.5.0",
+  "unsloth": "2026.7.2",
+  "trl": "0.24.0",
+  "peft": "0.18.1",
+  "llamafactory": "0.9.6.dev0",
+  "bitsandbytes": "0.50.0"
+ },
+ "gpu": "NVIDIA L4",
+ "saved_utc": "2026-08-02T06:10:11.559884+00:00",
+ "adapter_path": "/content/drive/MyDrive/Syn-SQL Spider train  BIRD train/v2/fine tune models/Qwen3.5-9B_welsh_full_lf/adapter",
+ "merged_16bit_path": null
+}

README.md

@@ -0,0 +1,19 @@
+---
+tags:
+- text-to-sql
+- welsh
+- qlora
+- lora
+---
+
+# Welsh text-to-SQL SLM adapters
+
+QLoRA adapters from "Testing Welsh Text-to-SQL via SLMs (a comparative analysis)". Twelve runs: six base models (gemma-3-4b-it, gemma-3-12b-it, Qwen3.5-4B, Qwen3.5-9B, Ministral-3-3B-Instruct-2512, Ministral-3-8B-Instruct-2512), each fine-tuned once on the Welsh condition and once on the English condition of the same text-to-SQL training set.
+
+Training: LLaMA-Factory on Colab, 4-bit NF4 base loading, bf16 training arithmetic, seed 3407. One folder per run holding the final adapter, tokenizer files, train_log.txt and training_summary.json. Intermediate checkpoints are not uploaded.
+
+extras/ holds one oversized artifact from the machine translation pipeline: the Welsh-renamed soccer database used as alignment source.
+
+Code, data, benchmarks and results: https://github.com/AledCaioRow/welsh-text2sql-slms
+
+Working archive for a dissertation in progress. Aled Rowlands, 2026.

gemma-3-12b-it_english_full_lf/.session_lock

@@ -0,0 +1 @@
+{"session": "c7a87e03", "utc": "2026-08-02T14:32:13.905013+00:00"}

gemma-3-12b-it_english_full_lf/training_summary.json

@@ -0,0 +1,55 @@
+{
+ "run_name": "gemma-3-12b-it_english_full_lf",
+ "condition": "english",
+ "model_id": "unsloth/gemma-3-12b-it",
+ "dose": "full",
+ "dose_file": "/content/drive/MyDrive/Syn-SQL Spider train  BIRD train/v2/train data/english/train/spider_en_6948.jsonl",
+ "n_rows": 6948,
+ "hyperparameters": {
+  "load_in_4bit": true,
+  "max_seq_length": 4096,
+  "lora_r": 16,
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "learning_rate": 0.0002,
+  "epochs": 2.0,
+  "per_device_batch_size": 1,
+  "grad_accum": 8,
+  "warmup_ratio": 0.03,
+  "weight_decay": 0.01,
+  "lr_scheduler": "linear",
+  "seed": 3407,
+  "optim": "adamw_8bit",
+  "loss_on": "responses_only (SQL answer + end-of-turn)"
+ },
+ "prompt_version": "p1",
+ "notebook_version": "train-v3-lf3",
+ "instruction_sha256": "c7e8631a429b9e8e",
+ "framework": "llamafactory@ef2d8f9da66ef13378dc8068dabc99cfe89a9736",
+ "lf_template": "gemma3",
+ "use_unsloth_requested": true,
+ "use_unsloth_effective": true,
+ "tiny_run": false,
+ "n_rows_over_cutoff": 0,
+ "resume_note": null,
+ "trained_by": "RUN_gemma3.ipynb",
+ "render_provenance": {
+  "text_construction": "llamafactory template render (canary-verified == eval_prompt_render + SQL + EOT)",
+  "chat_template_sha256": "7de1c58e208eda46"
+ },
+ "train_loss": 0.09662253164415117,
+ "train_runtime_s": 21177.3168,
+ "versions": {
+  "torch": "2.10.0",
+  "transformers": "5.5.0",
+  "unsloth": "2026.7.2",
+  "trl": "0.24.0",
+  "peft": "0.18.1",
+  "llamafactory": "0.9.6.dev0",
+  "bitsandbytes": "0.50.0"
+ },
+ "gpu": "NVIDIA A100-SXM4-40GB",
+ "saved_utc": "2026-08-02T20:27:50.324092+00:00",
+ "adapter_path": "/content/drive/MyDrive/Syn-SQL Spider train  BIRD train/v2/fine tune models/gemma-3-12b-it_english_full_lf/adapter",
+ "merged_16bit_path": null
+}

gemma-3-12b-it_welsh_full_lf/.session_lock

@@ -0,0 +1 @@
+{"session": "fd5c0648", "utc": "2026-08-02T08:02:02.519953+00:00"}

gemma-3-12b-it_welsh_full_lf/training_summary.json

@@ -0,0 +1,55 @@
+{
+ "run_name": "gemma-3-12b-it_welsh_full_lf",
+ "condition": "welsh",
+ "model_id": "unsloth/gemma-3-12b-it",
+ "dose": "full",
+ "dose_file": "/content/drive/MyDrive/Syn-SQL Spider train  BIRD train/v2/train data/welsh/train/spider_cy_6948.jsonl",
+ "n_rows": 6948,
+ "hyperparameters": {
+  "load_in_4bit": true,
+  "max_seq_length": 4096,
+  "lora_r": 16,
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "learning_rate": 0.0002,
+  "epochs": 2.0,
+  "per_device_batch_size": 1,
+  "grad_accum": 8,
+  "warmup_ratio": 0.03,
+  "weight_decay": 0.01,
+  "lr_scheduler": "linear",
+  "seed": 3407,
+  "optim": "adamw_8bit",
+  "loss_on": "responses_only (SQL answer + end-of-turn)"
+ },
+ "prompt_version": "p1",
+ "notebook_version": "train-v3-lf3",
+ "instruction_sha256": "c7e8631a429b9e8e",
+ "framework": "llamafactory@ef2d8f9da66ef13378dc8068dabc99cfe89a9736",
+ "lf_template": "gemma3",
+ "use_unsloth_requested": true,
+ "use_unsloth_effective": true,
+ "tiny_run": false,
+ "n_rows_over_cutoff": 82,
+ "resume_note": null,
+ "trained_by": "RUN_gemma3.ipynb",
+ "render_provenance": {
+  "text_construction": "llamafactory template render (canary-verified == eval_prompt_render + SQL + EOT)",
+  "chat_template_sha256": "7de1c58e208eda46"
+ },
+ "train_loss": 0.07838781196859819,
+ "train_runtime_s": 23238.3083,
+ "versions": {
+  "torch": "2.10.0",
+  "transformers": "5.5.0",
+  "unsloth": "2026.7.2",
+  "trl": "0.24.0",
+  "peft": "0.18.1",
+  "llamafactory": "0.9.6.dev0",
+  "bitsandbytes": "0.50.0"
+ },
+ "gpu": "NVIDIA A100-SXM4-40GB",
+ "saved_utc": "2026-08-02T14:32:09.036614+00:00",
+ "adapter_path": "/content/drive/MyDrive/Syn-SQL Spider train  BIRD train/v2/fine tune models/gemma-3-12b-it_welsh_full_lf/adapter",
+ "merged_16bit_path": null
+}

gemma-3-4b-it_english_full_lf/.session_lock

@@ -0,0 +1 @@
+{"session": "87ded0d7", "utc": "2026-08-03T00:46:03.504158+00:00"}

gemma-3-4b-it_english_full_lf/training_summary.json

@@ -0,0 +1,55 @@
+{
+ "run_name": "gemma-3-4b-it_english_full_lf",
+ "condition": "english",
+ "model_id": "unsloth/gemma-3-4b-it",
+ "dose": "full",
+ "dose_file": "/content/drive/MyDrive/Syn-SQL Spider train  BIRD train/v2/train data/english/train/spider_en_6948.jsonl",
+ "n_rows": 6948,
+ "hyperparameters": {
+  "load_in_4bit": true,
+  "max_seq_length": 4096,
+  "lora_r": 16,
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "learning_rate": 0.0002,
+  "epochs": 2.0,
+  "per_device_batch_size": 1,
+  "grad_accum": 8,
+  "warmup_ratio": 0.03,
+  "weight_decay": 0.01,
+  "lr_scheduler": "linear",
+  "seed": 3407,
+  "optim": "adamw_8bit",
+  "loss_on": "responses_only (SQL answer + end-of-turn)"
+ },
+ "prompt_version": "p1",
+ "notebook_version": "train-v3-lf3",
+ "instruction_sha256": "c7e8631a429b9e8e",
+ "framework": "llamafactory@ef2d8f9da66ef13378dc8068dabc99cfe89a9736",
+ "lf_template": "gemma3",
+ "use_unsloth_requested": true,
+ "use_unsloth_effective": true,
+ "tiny_run": false,
+ "n_rows_over_cutoff": 0,
+ "resume_note": null,
+ "trained_by": "RUN_gemma3.ipynb",
+ "render_provenance": {
+  "text_construction": "llamafactory template render (canary-verified == eval_prompt_render + SQL + EOT)",
+  "chat_template_sha256": "7de1c58e208eda46"
+ },
+ "train_loss": 0.09057024988947035,
+ "train_runtime_s": 14576.0077,
+ "versions": {
+  "torch": "2.10.0",
+  "transformers": "5.5.0",
+  "unsloth": "2026.7.2",
+  "trl": "0.24.0",
+  "peft": "0.18.1",
+  "llamafactory": "0.9.6.dev0",
+  "bitsandbytes": "0.50.0"
+ },
+ "gpu": "NVIDIA A100-SXM4-40GB",
+ "saved_utc": "2026-08-03T04:51:18.551457+00:00",
+ "adapter_path": "/content/drive/MyDrive/Syn-SQL Spider train  BIRD train/v2/fine tune models/gemma-3-4b-it_english_full_lf/adapter",
+ "merged_16bit_path": null
+}

gemma-3-4b-it_welsh_full_lf/.session_lock

@@ -0,0 +1 @@
+{"session": "0358761e", "utc": "2026-08-02T20:27:53.414724+00:00"}

gemma-3-4b-it_welsh_full_lf/training_summary.json

@@ -0,0 +1,55 @@
+{
+ "run_name": "gemma-3-4b-it_welsh_full_lf",
+ "condition": "welsh",
+ "model_id": "unsloth/gemma-3-4b-it",
+ "dose": "full",
+ "dose_file": "/content/drive/MyDrive/Syn-SQL Spider train  BIRD train/v2/train data/welsh/train/spider_cy_6948.jsonl",
+ "n_rows": 6948,
+ "hyperparameters": {
+  "load_in_4bit": true,
+  "max_seq_length": 4096,
+  "lora_r": 16,
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "learning_rate": 0.0002,
+  "epochs": 2.0,
+  "per_device_batch_size": 1,
+  "grad_accum": 8,
+  "warmup_ratio": 0.03,
+  "weight_decay": 0.01,
+  "lr_scheduler": "linear",
+  "seed": 3407,
+  "optim": "adamw_8bit",
+  "loss_on": "responses_only (SQL answer + end-of-turn)"
+ },
+ "prompt_version": "p1",
+ "notebook_version": "train-v3-lf3",
+ "instruction_sha256": "c7e8631a429b9e8e",
+ "framework": "llamafactory@ef2d8f9da66ef13378dc8068dabc99cfe89a9736",
+ "lf_template": "gemma3",
+ "use_unsloth_requested": true,
+ "use_unsloth_effective": true,
+ "tiny_run": false,
+ "n_rows_over_cutoff": 82,
+ "resume_note": null,
+ "trained_by": "RUN_gemma3.ipynb",
+ "render_provenance": {
+  "text_construction": "llamafactory template render (canary-verified == eval_prompt_render + SQL + EOT)",
+  "chat_template_sha256": "7de1c58e208eda46"
+ },
+ "train_loss": 0.1089309345592152,
+ "train_runtime_s": 15358.9555,
+ "versions": {
+  "torch": "2.10.0",
+  "transformers": "5.5.0",
+  "unsloth": "2026.7.2",
+  "trl": "0.24.0",
+  "peft": "0.18.1",
+  "llamafactory": "0.9.6.dev0",
+  "bitsandbytes": "0.50.0"
+ },
+ "gpu": "NVIDIA A100-SXM4-40GB",
+ "saved_utc": "2026-08-03T00:46:01.638741+00:00",
+ "adapter_path": "/content/drive/MyDrive/Syn-SQL Spider train  BIRD train/v2/fine tune models/gemma-3-4b-it_welsh_full_lf/adapter",
+ "merged_16bit_path": null
+}

training_summary.csv

@@ -0,0 +1,13 @@
+run_name,condition,model_id,dose,n_rows,epochs,learning_rate,lora_r,load_in_4bit,train_loss,train_runtime_s,saved_utc,adapter_path,merged_16bit,notebook_version
+Ministral-3-3B-Instruct-2512_english_full_lf,english,unsloth/Ministral-3-3B-Instruct-2512,full,6948,2.0,0.0002,16,True,0.013689696994557616,9689.671,2026-08-04T09:25:06.162832+00:00,/content/drive/MyDrive/Syn-SQL Spider train  BIRD train/v2/fine tune models/Ministral-3-3B-Instruct-2512_english_full_lf/adapter,,train-v3-lf3
+Ministral-3-3B-Instruct-2512_welsh_full_lf,welsh,unsloth/Ministral-3-3B-Instruct-2512,full,6948,2.0,0.0002,16,True,0.01085191247373888,10995.2712,2026-08-04T05:51:55.165112+00:00,/content/drive/MyDrive/Syn-SQL Spider train  BIRD train/v2/fine tune models/Ministral-3-3B-Instruct-2512_welsh_full_lf/adapter,,train-v3-lf3
+Ministral-3-8B-Instruct-2512_english_full_lf,english,unsloth/Ministral-3-8B-Instruct-2512,full,6948,2.0,0.0002,16,True,0.012401104205951386,15684.2331,2026-08-05T01:42:32.087309+00:00,/content/drive/MyDrive/Syn-SQL Spider train  BIRD train/v2/fine tune models/Ministral-3-8B-Instruct-2512_english_full_lf/adapter,,train-v3-lf3
+Ministral-3-8B-Instruct-2512_welsh_full_lf,welsh,unsloth/Ministral-3-8B-Instruct-2512,full,6948,2.0,0.0002,16,True,0.009693514537473474,18909.6135,2026-08-04T19:43:53.607225+00:00,/content/drive/MyDrive/Syn-SQL Spider train  BIRD train/v2/fine tune models/Ministral-3-8B-Instruct-2512_welsh_full_lf/adapter,,train-v3-lf3
+Qwen3.5-4B_english_full_lf,english,unsloth/Qwen3.5-4B,full,6948,2.0,0.0002,16,True,0.028501616222880378,7712.1937,2026-08-04T16:45:23.157738+00:00,/content/drive/MyDrive/Syn-SQL Spider train  BIRD train/v2/fine tune models/Qwen3.5-4B_english_full_lf/adapter,,train-v3-lf3
+Qwen3.5-4B_welsh_full_lf,welsh,unsloth/Qwen3.5-4B,full,6948,2.0,0.0002,16,True,0.08168271676100301,15351.4237,2026-08-04T11:35:50.938648+00:00,/content/drive/MyDrive/Syn-SQL Spider train  BIRD train/v2/fine tune models/Qwen3.5-4B_welsh_full_lf/adapter,,train-v3-lf3
+Qwen3.5-9B_english_full_lf,english,unsloth/Qwen3.5-9B,full,6948,2.0,0.0002,16,True,0.09656419400961681,17909.8032,2026-08-04T04:33:35.439154+00:00,/content/drive/MyDrive/Syn-SQL Spider train  BIRD train/v2/fine tune models/Qwen3.5-9B_english_full_lf/adapter,,train-v3-lf3
+Qwen3.5-9B_welsh_full_lf,welsh,unsloth/Qwen3.5-9B,full,6948,2.0,0.0002,16,True,0.07514798696934148,25303.6125,2026-08-02T06:10:11.559884+00:00,/content/drive/MyDrive/Syn-SQL Spider train  BIRD train/v2/fine tune models/Qwen3.5-9B_welsh_full_lf/adapter,,train-v3-lf3
+gemma-3-12b-it_english_full_lf,english,unsloth/gemma-3-12b-it,full,6948,2.0,0.0002,16,True,0.09662253164415117,21177.3168,2026-08-02T20:27:50.324092+00:00,/content/drive/MyDrive/Syn-SQL Spider train  BIRD train/v2/fine tune models/gemma-3-12b-it_english_full_lf/adapter,,train-v3-lf3
+gemma-3-12b-it_welsh_full_lf,welsh,unsloth/gemma-3-12b-it,full,6948,2.0,0.0002,16,True,0.07838781196859819,23238.3083,2026-08-02T14:32:09.036614+00:00,/content/drive/MyDrive/Syn-SQL Spider train  BIRD train/v2/fine tune models/gemma-3-12b-it_welsh_full_lf/adapter,,train-v3-lf3
+gemma-3-4b-it_english_full_lf,english,unsloth/gemma-3-4b-it,full,6948,2.0,0.0002,16,True,0.09057024988947035,14576.0077,2026-08-03T04:51:18.551457+00:00,/content/drive/MyDrive/Syn-SQL Spider train  BIRD train/v2/fine tune models/gemma-3-4b-it_english_full_lf/adapter,,train-v3-lf3
+gemma-3-4b-it_welsh_full_lf,welsh,unsloth/gemma-3-4b-it,full,6948,2.0,0.0002,16,True,0.1089309345592152,15358.9555,2026-08-03T00:46:01.638741+00:00,/content/drive/MyDrive/Syn-SQL Spider train  BIRD train/v2/fine tune models/gemma-3-4b-it_welsh_full_lf/adapter,,train-v3-lf3