Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,65 @@
----
-license: mit
----
+---
+base_model: Qwen/Qwen2.5-0.5B
+library_name: peft
+license: other
+metrics:
+- accuracy
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: qwen2.5-0.5b-v1
+  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. -->
+
+# qwen2.5-0.5b-v1
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-0.5B](https://huggingface.co/Qwen/Qwen2.5-0.5B) on the /network-volume/data/SFT_glaive_toolcall_en/greennode_glaive_toolcall_en.json dataset.
+It achieves the following results on the evaluation set:
+- Loss: nan
+- Accuracy: nan
+
+## 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: 1e-05
+- train_batch_size: 2
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.05
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.45.0
+- Pytorch 2.4.0a0+3bcc3cddb5.nv24.07
+- Datasets 2.21.0
+- Tokenizers 0.20.0

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-0.5B",
+  "bias": "none",
+  "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_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj",
+    "down_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd65e55d52fe4cb4bf1d01ec9b3d0f4854b527dd34efddbcb69db221f129e101
+size 17640136

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 2.993684210526316,
+    "eval_accuracy": NaN,
+    "eval_loss": NaN,
+    "eval_runtime": 4.3283,
+    "eval_samples_per_second": 11.552,
+    "eval_steps_per_second": 11.552,
+    "total_flos": 49457916387328.0,
+    "train_loss": 5.2246711257473155,
+    "train_runtime": 535.0123,
+    "train_samples_per_second": 5.327,
+    "train_steps_per_second": 1.329
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.993684210526316,
+    "eval_accuracy": NaN,
+    "eval_loss": NaN,
+    "eval_runtime": 4.3283,
+    "eval_samples_per_second": 11.552,
+    "eval_steps_per_second": 11.552
+}

runs/Apr16_07-35-24_fj-1c10e033-0406-4323-9f87-f201ff27b62b-master-0/events.out.tfevents.1744788932.fj-1c10e033-0406-4323-9f87-f201ff27b62b-master-0.32.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79242105dc5a3ea1e3c9b9e89bceef7add48f19b1212237a115c7f40bec7260a
+size 20568

runs/Apr16_07-35-24_fj-1c10e033-0406-4323-9f87-f201ff27b62b-master-0/events.out.tfevents.1744789472.fj-1c10e033-0406-4323-9f87-f201ff27b62b-master-0.32.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c05c12589b02f280390c5f300edb5e49d8c031bbd87dfdde104a6d1aed5cc7e
+size 363

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.993684210526316,
+    "total_flos": 49457916387328.0,
+    "train_loss": 5.2246711257473155,
+    "train_runtime": 535.0123,
+    "train_samples_per_second": 5.327,
+    "train_steps_per_second": 1.329
+}

trainer_log.jsonl

@@ -0,0 +1,72 @@
+{"current_steps": 10, "total_steps": 711, "loss": 11.5876, "learning_rate": 2.7777777777777783e-06, "epoch": 0.042105263157894736, "percentage": 1.41, "elapsed_time": "0:00:07", "remaining_time": "0:09:08"}
+{"current_steps": 20, "total_steps": 711, "loss": 10.3595, "learning_rate": 5.555555555555557e-06, "epoch": 0.08421052631578947, "percentage": 2.81, "elapsed_time": "0:00:15", "remaining_time": "0:08:38"}
+{"current_steps": 30, "total_steps": 711, "loss": 9.7902, "learning_rate": 8.333333333333334e-06, "epoch": 0.12631578947368421, "percentage": 4.22, "elapsed_time": "0:00:22", "remaining_time": "0:08:26"}
+{"current_steps": 40, "total_steps": 711, "loss": 8.8659, "learning_rate": 9.99913355769784e-06, "epoch": 0.16842105263157894, "percentage": 5.63, "elapsed_time": "0:00:29", "remaining_time": "0:08:13"}
+{"current_steps": 50, "total_steps": 711, "loss": 6.9104, "learning_rate": 9.989389530100242e-06, "epoch": 0.21052631578947367, "percentage": 7.03, "elapsed_time": "0:00:36", "remaining_time": "0:08:03"}
+{"current_steps": 60, "total_steps": 711, "loss": 7.166, "learning_rate": 9.968839595802982e-06, "epoch": 0.25263157894736843, "percentage": 8.44, "elapsed_time": "0:00:43", "remaining_time": "0:07:55"}
+{"current_steps": 70, "total_steps": 711, "loss": 9.6891, "learning_rate": 9.937528261387753e-06, "epoch": 0.29473684210526313, "percentage": 9.85, "elapsed_time": "0:00:51", "remaining_time": "0:07:48"}
+{"current_steps": 80, "total_steps": 711, "loss": 9.0896, "learning_rate": 9.89552334023258e-06, "epoch": 0.3368421052631579, "percentage": 11.25, "elapsed_time": "0:00:58", "remaining_time": "0:07:41"}
+{"current_steps": 90, "total_steps": 711, "loss": 6.6979, "learning_rate": 9.842915805643156e-06, "epoch": 0.37894736842105264, "percentage": 12.66, "elapsed_time": "0:01:05", "remaining_time": "0:07:33"}
+{"current_steps": 100, "total_steps": 711, "loss": 6.3685, "learning_rate": 9.779819593824909e-06, "epoch": 0.42105263157894735, "percentage": 14.06, "elapsed_time": "0:01:12", "remaining_time": "0:07:25"}
+{"current_steps": 110, "total_steps": 711, "loss": 5.2505, "learning_rate": 9.70637135712256e-06, "epoch": 0.4631578947368421, "percentage": 15.47, "elapsed_time": "0:01:20", "remaining_time": "0:07:20"}
+{"current_steps": 120, "total_steps": 711, "loss": 6.0048, "learning_rate": 9.622730168061568e-06, "epoch": 0.5052631578947369, "percentage": 16.88, "elapsed_time": "0:01:27", "remaining_time": "0:07:12"}
+{"current_steps": 130, "total_steps": 711, "loss": 6.9066, "learning_rate": 9.529077174832466e-06, "epoch": 0.5473684210526316, "percentage": 18.28, "elapsed_time": "0:01:35", "remaining_time": "0:07:06"}
+{"current_steps": 140, "total_steps": 711, "loss": 4.7802, "learning_rate": 9.425615208964217e-06, "epoch": 0.5894736842105263, "percentage": 19.69, "elapsed_time": "0:01:43", "remaining_time": "0:07:00"}
+{"current_steps": 150, "total_steps": 711, "loss": 6.1819, "learning_rate": 9.312568346036288e-06, "epoch": 0.631578947368421, "percentage": 21.1, "elapsed_time": "0:01:50", "remaining_time": "0:06:54"}
+{"current_steps": 160, "total_steps": 711, "loss": 8.0877, "learning_rate": 9.190181420380838e-06, "epoch": 0.6736842105263158, "percentage": 22.5, "elapsed_time": "0:01:58", "remaining_time": "0:06:47"}
+{"current_steps": 170, "total_steps": 711, "loss": 5.9154, "learning_rate": 9.058719494826076e-06, "epoch": 0.7157894736842105, "percentage": 23.91, "elapsed_time": "0:02:05", "remaining_time": "0:06:39"}
+{"current_steps": 180, "total_steps": 711, "loss": 2.5935, "learning_rate": 8.9184672866292e-06, "epoch": 0.7578947368421053, "percentage": 25.32, "elapsed_time": "0:02:13", "remaining_time": "0:06:33"}
+{"current_steps": 190, "total_steps": 711, "loss": 8.8207, "learning_rate": 8.769728550842217e-06, "epoch": 0.8, "percentage": 26.72, "elapsed_time": "0:02:20", "remaining_time": "0:06:25"}
+{"current_steps": 200, "total_steps": 711, "loss": 3.5752, "learning_rate": 8.61282542244614e-06, "epoch": 0.8421052631578947, "percentage": 28.13, "elapsed_time": "0:02:28", "remaining_time": "0:06:18"}
+{"current_steps": 210, "total_steps": 711, "loss": 5.0309, "learning_rate": 8.44809771867835e-06, "epoch": 0.8842105263157894, "percentage": 29.54, "elapsed_time": "0:02:35", "remaining_time": "0:06:10"}
+{"current_steps": 220, "total_steps": 711, "loss": 4.364, "learning_rate": 8.275902203064125e-06, "epoch": 0.9263157894736842, "percentage": 30.94, "elapsed_time": "0:02:42", "remaining_time": "0:06:02"}
+{"current_steps": 230, "total_steps": 711, "loss": 4.4541, "learning_rate": 8.096611812746302e-06, "epoch": 0.968421052631579, "percentage": 32.35, "elapsed_time": "0:02:49", "remaining_time": "0:05:55"}
+{"current_steps": 240, "total_steps": 711, "loss": 7.2641, "learning_rate": 7.910614850786448e-06, "epoch": 1.0105263157894737, "percentage": 33.76, "elapsed_time": "0:02:57", "remaining_time": "0:05:47"}
+{"current_steps": 250, "total_steps": 711, "loss": 4.6563, "learning_rate": 7.718314145186918e-06, "epoch": 1.0526315789473684, "percentage": 35.16, "elapsed_time": "0:03:04", "remaining_time": "0:05:39"}
+{"current_steps": 260, "total_steps": 711, "loss": 4.6167, "learning_rate": 7.520126176455084e-06, "epoch": 1.0947368421052632, "percentage": 36.57, "elapsed_time": "0:03:11", "remaining_time": "0:05:32"}
+{"current_steps": 270, "total_steps": 711, "loss": 3.8117, "learning_rate": 7.31648017559931e-06, "epoch": 1.1368421052631579, "percentage": 37.97, "elapsed_time": "0:03:18", "remaining_time": "0:05:24"}
+{"current_steps": 280, "total_steps": 711, "loss": 5.6265, "learning_rate": 7.107817194510157e-06, "epoch": 1.1789473684210527, "percentage": 39.38, "elapsed_time": "0:03:25", "remaining_time": "0:05:16"}
+{"current_steps": 290, "total_steps": 711, "loss": 7.0092, "learning_rate": 6.8945891507402075e-06, "epoch": 1.2210526315789474, "percentage": 40.79, "elapsed_time": "0:03:32", "remaining_time": "0:05:08"}
+{"current_steps": 300, "total_steps": 711, "loss": 4.3322, "learning_rate": 6.677257848751276e-06, "epoch": 1.263157894736842, "percentage": 42.19, "elapsed_time": "0:03:39", "remaining_time": "0:05:01"}
+{"current_steps": 310, "total_steps": 711, "loss": 2.7404, "learning_rate": 6.456293979748778e-06, "epoch": 1.305263157894737, "percentage": 43.6, "elapsed_time": "0:03:47", "remaining_time": "0:04:53"}
+{"current_steps": 320, "total_steps": 711, "loss": 3.6143, "learning_rate": 6.23217610226939e-06, "epoch": 1.3473684210526315, "percentage": 45.01, "elapsed_time": "0:03:54", "remaining_time": "0:04:46"}
+{"current_steps": 330, "total_steps": 711, "loss": 4.3537, "learning_rate": 6.005389605729824e-06, "epoch": 1.3894736842105262, "percentage": 46.41, "elapsed_time": "0:04:01", "remaining_time": "0:04:38"}
+{"current_steps": 340, "total_steps": 711, "loss": 6.3674, "learning_rate": 5.776425659181438e-06, "epoch": 1.431578947368421, "percentage": 47.82, "elapsed_time": "0:04:08", "remaining_time": "0:04:31"}
+{"current_steps": 350, "total_steps": 711, "loss": 5.5102, "learning_rate": 5.54578014754744e-06, "epoch": 1.4736842105263157, "percentage": 49.23, "elapsed_time": "0:04:16", "remaining_time": "0:04:24"}
+{"current_steps": 360, "total_steps": 711, "loss": 3.8598, "learning_rate": 5.3139525976465675e-06, "epoch": 1.5157894736842106, "percentage": 50.63, "elapsed_time": "0:04:23", "remaining_time": "0:04:16"}
+{"current_steps": 370, "total_steps": 711, "loss": 4.5186, "learning_rate": 5.081445096329229e-06, "epoch": 1.5578947368421052, "percentage": 52.04, "elapsed_time": "0:04:30", "remaining_time": "0:04:09"}
+{"current_steps": 380, "total_steps": 711, "loss": 5.3117, "learning_rate": 4.8487612030691975e-06, "epoch": 1.6, "percentage": 53.45, "elapsed_time": "0:04:37", "remaining_time": "0:04:01"}
+{"current_steps": 390, "total_steps": 711, "loss": 3.8823, "learning_rate": 4.6164048593659076e-06, "epoch": 1.6421052631578947, "percentage": 54.85, "elapsed_time": "0:04:44", "remaining_time": "0:03:54"}
+{"current_steps": 400, "total_steps": 711, "loss": 3.2185, "learning_rate": 4.384879297319398e-06, "epoch": 1.6842105263157894, "percentage": 56.26, "elapsed_time": "0:04:51", "remaining_time": "0:03:46"}
+{"current_steps": 410, "total_steps": 711, "loss": 4.8082, "learning_rate": 4.154685949741631e-06, "epoch": 1.7263157894736842, "percentage": 57.67, "elapsed_time": "0:04:58", "remaining_time": "0:03:39"}
+{"current_steps": 420, "total_steps": 711, "loss": 6.0446, "learning_rate": 3.926323364164684e-06, "epoch": 1.768421052631579, "percentage": 59.07, "elapsed_time": "0:05:05", "remaining_time": "0:03:31"}
+{"current_steps": 430, "total_steps": 711, "loss": 4.6896, "learning_rate": 3.700286123097814e-06, "epoch": 1.8105263157894735, "percentage": 60.48, "elapsed_time": "0:05:13", "remaining_time": "0:03:24"}
+{"current_steps": 440, "total_steps": 711, "loss": 3.4427, "learning_rate": 3.4770637728718608e-06, "epoch": 1.8526315789473684, "percentage": 61.88, "elapsed_time": "0:05:20", "remaining_time": "0:03:17"}
+{"current_steps": 450, "total_steps": 711, "loss": 4.7614, "learning_rate": 3.2571397633909252e-06, "epoch": 1.8947368421052633, "percentage": 63.29, "elapsed_time": "0:05:28", "remaining_time": "0:03:10"}
+{"current_steps": 460, "total_steps": 711, "loss": 1.9746, "learning_rate": 3.040990401087508e-06, "epoch": 1.936842105263158, "percentage": 64.7, "elapsed_time": "0:05:36", "remaining_time": "0:03:03"}
+{"current_steps": 470, "total_steps": 711, "loss": 2.8462, "learning_rate": 2.82908381734886e-06, "epoch": 1.9789473684210526, "percentage": 66.1, "elapsed_time": "0:05:45", "remaining_time": "0:02:56"}
+{"current_steps": 480, "total_steps": 711, "loss": 3.9965, "learning_rate": 2.6218789546486235e-06, "epoch": 2.0210526315789474, "percentage": 67.51, "elapsed_time": "0:05:54", "remaining_time": "0:02:50"}
+{"current_steps": 490, "total_steps": 711, "loss": 4.5259, "learning_rate": 2.4198245725796427e-06, "epoch": 2.0631578947368423, "percentage": 68.92, "elapsed_time": "0:06:01", "remaining_time": "0:02:43"}
+{"current_steps": 500, "total_steps": 711, "loss": 5.2339, "learning_rate": 2.2233582759406065e-06, "epoch": 2.1052631578947367, "percentage": 70.32, "elapsed_time": "0:06:09", "remaining_time": "0:02:35"}
+{"current_steps": 510, "total_steps": 711, "loss": 4.3149, "learning_rate": 2.0329055669814936e-06, "epoch": 2.1473684210526316, "percentage": 71.73, "elapsed_time": "0:06:16", "remaining_time": "0:02:28"}
+{"current_steps": 520, "total_steps": 711, "loss": 3.2703, "learning_rate": 1.8488789238604676e-06, "epoch": 2.1894736842105265, "percentage": 73.14, "elapsed_time": "0:06:24", "remaining_time": "0:02:21"}
+{"current_steps": 530, "total_steps": 711, "loss": 5.5007, "learning_rate": 1.671676907308018e-06, "epoch": 2.231578947368421, "percentage": 74.54, "elapsed_time": "0:06:32", "remaining_time": "0:02:13"}
+{"current_steps": 540, "total_steps": 711, "loss": 5.9824, "learning_rate": 1.5016832974331725e-06, "epoch": 2.2736842105263158, "percentage": 75.95, "elapsed_time": "0:06:41", "remaining_time": "0:02:07"}
+{"current_steps": 550, "total_steps": 711, "loss": 3.6694, "learning_rate": 1.339266262541249e-06, "epoch": 2.3157894736842106, "percentage": 77.36, "elapsed_time": "0:06:49", "remaining_time": "0:01:59"}
+{"current_steps": 560, "total_steps": 711, "loss": 4.1387, "learning_rate": 1.1847775617632746e-06, "epoch": 2.3578947368421055, "percentage": 78.76, "elapsed_time": "0:06:56", "remaining_time": "0:01:52"}
+{"current_steps": 570, "total_steps": 711, "loss": 3.1171, "learning_rate": 1.0385517832240472e-06, "epoch": 2.4, "percentage": 80.17, "elapsed_time": "0:07:04", "remaining_time": "0:01:45"}
+{"current_steps": 580, "total_steps": 711, "loss": 4.4169, "learning_rate": 9.009056193987569e-07, "epoch": 2.442105263157895, "percentage": 81.58, "elapsed_time": "0:07:12", "remaining_time": "0:01:37"}
+{"current_steps": 590, "total_steps": 711, "loss": 3.1303, "learning_rate": 7.72137181227608e-07, "epoch": 2.4842105263157896, "percentage": 82.98, "elapsed_time": "0:07:19", "remaining_time": "0:01:30"}
+{"current_steps": 600, "total_steps": 711, "loss": 5.1205, "learning_rate": 6.52525352473905e-07, "epoch": 2.526315789473684, "percentage": 84.39, "elapsed_time": "0:07:28", "remaining_time": "0:01:22"}
+{"current_steps": 610, "total_steps": 711, "loss": 4.4733, "learning_rate": 5.423291857239177e-07, "epoch": 2.568421052631579, "percentage": 85.79, "elapsed_time": "0:07:35", "remaining_time": "0:01:15"}
+{"current_steps": 620, "total_steps": 711, "loss": 4.1638, "learning_rate": 4.417873413366702e-07, "epoch": 2.610526315789474, "percentage": 87.2, "elapsed_time": "0:07:43", "remaining_time": "0:01:07"}
+{"current_steps": 630, "total_steps": 711, "loss": 5.343, "learning_rate": 3.511175705587433e-07, "epoch": 2.6526315789473687, "percentage": 88.61, "elapsed_time": "0:07:51", "remaining_time": "0:01:00"}
+{"current_steps": 640, "total_steps": 711, "loss": 4.0892, "learning_rate": 2.705162439235648e-07, "epoch": 2.694736842105263, "percentage": 90.01, "elapsed_time": "0:07:58", "remaining_time": "0:00:53"}
+{"current_steps": 650, "total_steps": 711, "loss": 3.1226, "learning_rate": 2.0015792595656225e-07, "epoch": 2.736842105263158, "percentage": 91.42, "elapsed_time": "0:08:06", "remaining_time": "0:00:45"}
+{"current_steps": 660, "total_steps": 711, "loss": 4.6847, "learning_rate": 1.4019499710726913e-07, "epoch": 2.7789473684210524, "percentage": 92.83, "elapsed_time": "0:08:14", "remaining_time": "0:00:38"}
+{"current_steps": 670, "total_steps": 711, "loss": 3.4289, "learning_rate": 9.075732372720414e-08, "epoch": 2.8210526315789473, "percentage": 94.23, "elapsed_time": "0:08:21", "remaining_time": "0:00:30"}
+{"current_steps": 680, "total_steps": 711, "loss": 6.4088, "learning_rate": 5.19519768082738e-08, "epoch": 2.863157894736842, "percentage": 95.64, "elapsed_time": "0:08:29", "remaining_time": "0:00:23"}
+{"current_steps": 690, "total_steps": 711, "loss": 2.7733, "learning_rate": 2.386300009084408e-08, "epoch": 2.905263157894737, "percentage": 97.05, "elapsed_time": "0:08:37", "remaining_time": "0:00:15"}
+{"current_steps": 700, "total_steps": 711, "loss": 2.3366, "learning_rate": 6.551228043715218e-09, "epoch": 2.9473684210526314, "percentage": 98.45, "elapsed_time": "0:08:44", "remaining_time": "0:00:08"}
+{"current_steps": 710, "total_steps": 711, "loss": 6.0433, "learning_rate": 5.4154110206150465e-11, "epoch": 2.9894736842105263, "percentage": 99.86, "elapsed_time": "0:08:52", "remaining_time": "0:00:00"}
+{"current_steps": 711, "total_steps": 711, "epoch": 2.993684210526316, "percentage": 100.0, "elapsed_time": "0:08:55", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,539 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.993684210526316,
+  "eval_steps": 1000,
+  "global_step": 711,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.042105263157894736,
+      "grad_norm": 0.0,
+      "learning_rate": 2.7777777777777783e-06,
+      "loss": 11.5876,
+      "step": 10
+    },
+    {
+      "epoch": 0.08421052631578947,
+      "grad_norm": 0.0,
+      "learning_rate": 5.555555555555557e-06,
+      "loss": 10.3595,
+      "step": 20
+    },
+    {
+      "epoch": 0.12631578947368421,
+      "grad_norm": 65.21126556396484,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 9.7902,
+      "step": 30
+    },
+    {
+      "epoch": 0.16842105263157894,
+      "grad_norm": 28.380247116088867,
+      "learning_rate": 9.99913355769784e-06,
+      "loss": 8.8659,
+      "step": 40
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 41.90730667114258,
+      "learning_rate": 9.989389530100242e-06,
+      "loss": 6.9104,
+      "step": 50
+    },
+    {
+      "epoch": 0.25263157894736843,
+      "grad_norm": 0.0,
+      "learning_rate": 9.968839595802982e-06,
+      "loss": 7.166,
+      "step": 60
+    },
+    {
+      "epoch": 0.29473684210526313,
+      "grad_norm": 40.83852767944336,
+      "learning_rate": 9.937528261387753e-06,
+      "loss": 9.6891,
+      "step": 70
+    },
+    {
+      "epoch": 0.3368421052631579,
+      "grad_norm": 0.0,
+      "learning_rate": 9.89552334023258e-06,
+      "loss": 9.0896,
+      "step": 80
+    },
+    {
+      "epoch": 0.37894736842105264,
+      "grad_norm": 38.14816665649414,
+      "learning_rate": 9.842915805643156e-06,
+      "loss": 6.6979,
+      "step": 90
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 0.0,
+      "learning_rate": 9.779819593824909e-06,
+      "loss": 6.3685,
+      "step": 100
+    },
+    {
+      "epoch": 0.4631578947368421,
+      "grad_norm": 38.70355987548828,
+      "learning_rate": 9.70637135712256e-06,
+      "loss": 5.2505,
+      "step": 110
+    },
+    {
+      "epoch": 0.5052631578947369,
+      "grad_norm": 56.77521514892578,
+      "learning_rate": 9.622730168061568e-06,
+      "loss": 6.0048,
+      "step": 120
+    },
+    {
+      "epoch": 0.5473684210526316,
+      "grad_norm": 45.47364044189453,
+      "learning_rate": 9.529077174832466e-06,
+      "loss": 6.9066,
+      "step": 130
+    },
+    {
+      "epoch": 0.5894736842105263,
+      "grad_norm": 46.9012451171875,
+      "learning_rate": 9.425615208964217e-06,
+      "loss": 4.7802,
+      "step": 140
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 53.24531173706055,
+      "learning_rate": 9.312568346036288e-06,
+      "loss": 6.1819,
+      "step": 150
+    },
+    {
+      "epoch": 0.6736842105263158,
+      "grad_norm": 0.0,
+      "learning_rate": 9.190181420380838e-06,
+      "loss": 8.0877,
+      "step": 160
+    },
+    {
+      "epoch": 0.7157894736842105,
+      "grad_norm": 0.0,
+      "learning_rate": 9.058719494826076e-06,
+      "loss": 5.9154,
+      "step": 170
+    },
+    {
+      "epoch": 0.7578947368421053,
+      "grad_norm": 120.6329574584961,
+      "learning_rate": 8.9184672866292e-06,
+      "loss": 2.5935,
+      "step": 180
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 42.83644485473633,
+      "learning_rate": 8.769728550842217e-06,
+      "loss": 8.8207,
+      "step": 190
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 56.459957122802734,
+      "learning_rate": 8.61282542244614e-06,
+      "loss": 3.5752,
+      "step": 200
+    },
+    {
+      "epoch": 0.8842105263157894,
+      "grad_norm": 0.0,
+      "learning_rate": 8.44809771867835e-06,
+      "loss": 5.0309,
+      "step": 210
+    },
+    {
+      "epoch": 0.9263157894736842,
+      "grad_norm": 0.0,
+      "learning_rate": 8.275902203064125e-06,
+      "loss": 4.364,
+      "step": 220
+    },
+    {
+      "epoch": 0.968421052631579,
+      "grad_norm": 65.06415557861328,
+      "learning_rate": 8.096611812746302e-06,
+      "loss": 4.4541,
+      "step": 230
+    },
+    {
+      "epoch": 1.0105263157894737,
+      "grad_norm": 43.25813293457031,
+      "learning_rate": 7.910614850786448e-06,
+      "loss": 7.2641,
+      "step": 240
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "grad_norm": 67.50498962402344,
+      "learning_rate": 7.718314145186918e-06,
+      "loss": 4.6563,
+      "step": 250
+    },
+    {
+      "epoch": 1.0947368421052632,
+      "grad_norm": 69.25511169433594,
+      "learning_rate": 7.520126176455084e-06,
+      "loss": 4.6167,
+      "step": 260
+    },
+    {
+      "epoch": 1.1368421052631579,
+      "grad_norm": 0.0,
+      "learning_rate": 7.31648017559931e-06,
+      "loss": 3.8117,
+      "step": 270
+    },
+    {
+      "epoch": 1.1789473684210527,
+      "grad_norm": 40.56947708129883,
+      "learning_rate": 7.107817194510157e-06,
+      "loss": 5.6265,
+      "step": 280
+    },
+    {
+      "epoch": 1.2210526315789474,
+      "grad_norm": 0.0,
+      "learning_rate": 6.8945891507402075e-06,
+      "loss": 7.0092,
+      "step": 290
+    },
+    {
+      "epoch": 1.263157894736842,
+      "grad_norm": 33.956756591796875,
+      "learning_rate": 6.677257848751276e-06,
+      "loss": 4.3322,
+      "step": 300
+    },
+    {
+      "epoch": 1.305263157894737,
+      "grad_norm": 29.54796600341797,
+      "learning_rate": 6.456293979748778e-06,
+      "loss": 2.7404,
+      "step": 310
+    },
+    {
+      "epoch": 1.3473684210526315,
+      "grad_norm": 51.423606872558594,
+      "learning_rate": 6.23217610226939e-06,
+      "loss": 3.6143,
+      "step": 320
+    },
+    {
+      "epoch": 1.3894736842105262,
+      "grad_norm": 31.011917114257812,
+      "learning_rate": 6.005389605729824e-06,
+      "loss": 4.3537,
+      "step": 330
+    },
+    {
+      "epoch": 1.431578947368421,
+      "grad_norm": 0.0,
+      "learning_rate": 5.776425659181438e-06,
+      "loss": 6.3674,
+      "step": 340
+    },
+    {
+      "epoch": 1.4736842105263157,
+      "grad_norm": 44.12076950073242,
+      "learning_rate": 5.54578014754744e-06,
+      "loss": 5.5102,
+      "step": 350
+    },
+    {
+      "epoch": 1.5157894736842106,
+      "grad_norm": 38.640594482421875,
+      "learning_rate": 5.3139525976465675e-06,
+      "loss": 3.8598,
+      "step": 360
+    },
+    {
+      "epoch": 1.5578947368421052,
+      "grad_norm": 36.51955032348633,
+      "learning_rate": 5.081445096329229e-06,
+      "loss": 4.5186,
+      "step": 370
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 17.60165786743164,
+      "learning_rate": 4.8487612030691975e-06,
+      "loss": 5.3117,
+      "step": 380
+    },
+    {
+      "epoch": 1.6421052631578947,
+      "grad_norm": 23.683897018432617,
+      "learning_rate": 4.6164048593659076e-06,
+      "loss": 3.8823,
+      "step": 390
+    },
+    {
+      "epoch": 1.6842105263157894,
+      "grad_norm": 22.112548828125,
+      "learning_rate": 4.384879297319398e-06,
+      "loss": 3.2185,
+      "step": 400
+    },
+    {
+      "epoch": 1.7263157894736842,
+      "grad_norm": 65.37483215332031,
+      "learning_rate": 4.154685949741631e-06,
+      "loss": 4.8082,
+      "step": 410
+    },
+    {
+      "epoch": 1.768421052631579,
+      "grad_norm": 93.4825439453125,
+      "learning_rate": 3.926323364164684e-06,
+      "loss": 6.0446,
+      "step": 420
+    },
+    {
+      "epoch": 1.8105263157894735,
+      "grad_norm": 32.05006790161133,
+      "learning_rate": 3.700286123097814e-06,
+      "loss": 4.6896,
+      "step": 430
+    },
+    {
+      "epoch": 1.8526315789473684,
+      "grad_norm": 112.52412414550781,
+      "learning_rate": 3.4770637728718608e-06,
+      "loss": 3.4427,
+      "step": 440
+    },
+    {
+      "epoch": 1.8947368421052633,
+      "grad_norm": 107.17741394042969,
+      "learning_rate": 3.2571397633909252e-06,
+      "loss": 4.7614,
+      "step": 450
+    },
+    {
+      "epoch": 1.936842105263158,
+      "grad_norm": 97.92442321777344,
+      "learning_rate": 3.040990401087508e-06,
+      "loss": 1.9746,
+      "step": 460
+    },
+    {
+      "epoch": 1.9789473684210526,
+      "grad_norm": 45.69737243652344,
+      "learning_rate": 2.82908381734886e-06,
+      "loss": 2.8462,
+      "step": 470
+    },
+    {
+      "epoch": 2.0210526315789474,
+      "grad_norm": 41.78928756713867,
+      "learning_rate": 2.6218789546486235e-06,
+      "loss": 3.9965,
+      "step": 480
+    },
+    {
+      "epoch": 2.0631578947368423,
+      "grad_norm": 55.92274475097656,
+      "learning_rate": 2.4198245725796427e-06,
+      "loss": 4.5259,
+      "step": 490
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "grad_norm": 0.0,
+      "learning_rate": 2.2233582759406065e-06,
+      "loss": 5.2339,
+      "step": 500
+    },
+    {
+      "epoch": 2.1473684210526316,
+      "grad_norm": 38.3224983215332,
+      "learning_rate": 2.0329055669814936e-06,
+      "loss": 4.3149,
+      "step": 510
+    },
+    {
+      "epoch": 2.1894736842105265,
+      "grad_norm": 78.6894302368164,
+      "learning_rate": 1.8488789238604676e-06,
+      "loss": 3.2703,
+      "step": 520
+    },
+    {
+      "epoch": 2.231578947368421,
+      "grad_norm": 36.631046295166016,
+      "learning_rate": 1.671676907308018e-06,
+      "loss": 5.5007,
+      "step": 530
+    },
+    {
+      "epoch": 2.2736842105263158,
+      "grad_norm": 31.433311462402344,
+      "learning_rate": 1.5016832974331725e-06,
+      "loss": 5.9824,
+      "step": 540
+    },
+    {
+      "epoch": 2.3157894736842106,
+      "grad_norm": 0.0,
+      "learning_rate": 1.339266262541249e-06,
+      "loss": 3.6694,
+      "step": 550
+    },
+    {
+      "epoch": 2.3578947368421055,
+      "grad_norm": 31.136545181274414,
+      "learning_rate": 1.1847775617632746e-06,
+      "loss": 4.1387,
+      "step": 560
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 27.67391586303711,
+      "learning_rate": 1.0385517832240472e-06,
+      "loss": 3.1171,
+      "step": 570
+    },
+    {
+      "epoch": 2.442105263157895,
+      "grad_norm": 23.40445899963379,
+      "learning_rate": 9.009056193987569e-07,
+      "loss": 4.4169,
+      "step": 580
+    },
+    {
+      "epoch": 2.4842105263157896,
+      "grad_norm": 31.044822692871094,
+      "learning_rate": 7.72137181227608e-07,
+      "loss": 3.1303,
+      "step": 590
+    },
+    {
+      "epoch": 2.526315789473684,
+      "grad_norm": 47.2055549621582,
+      "learning_rate": 6.52525352473905e-07,
+      "loss": 5.1205,
+      "step": 600
+    },
+    {
+      "epoch": 2.568421052631579,
+      "grad_norm": 0.0,
+      "learning_rate": 5.423291857239177e-07,
+      "loss": 4.4733,
+      "step": 610
+    },
+    {
+      "epoch": 2.610526315789474,
+      "grad_norm": 0.0,
+      "learning_rate": 4.417873413366702e-07,
+      "loss": 4.1638,
+      "step": 620
+    },
+    {
+      "epoch": 2.6526315789473687,
+      "grad_norm": 35.935455322265625,
+      "learning_rate": 3.511175705587433e-07,
+      "loss": 5.343,
+      "step": 630
+    },
+    {
+      "epoch": 2.694736842105263,
+      "grad_norm": 0.0,
+      "learning_rate": 2.705162439235648e-07,
+      "loss": 4.0892,
+      "step": 640
+    },
+    {
+      "epoch": 2.736842105263158,
+      "grad_norm": 24.754562377929688,
+      "learning_rate": 2.0015792595656225e-07,
+      "loss": 3.1226,
+      "step": 650
+    },
+    {
+      "epoch": 2.7789473684210524,
+      "grad_norm": 52.272216796875,
+      "learning_rate": 1.4019499710726913e-07,
+      "loss": 4.6847,
+      "step": 660
+    },
+    {
+      "epoch": 2.8210526315789473,
+      "grad_norm": 0.0,
+      "learning_rate": 9.075732372720414e-08,
+      "loss": 3.4289,
+      "step": 670
+    },
+    {
+      "epoch": 2.863157894736842,
+      "grad_norm": 23.337787628173828,
+      "learning_rate": 5.19519768082738e-08,
+      "loss": 6.4088,
+      "step": 680
+    },
+    {
+      "epoch": 2.905263157894737,
+      "grad_norm": 24.626935958862305,
+      "learning_rate": 2.386300009084408e-08,
+      "loss": 2.7733,
+      "step": 690
+    },
+    {
+      "epoch": 2.9473684210526314,
+      "grad_norm": 47.77521896362305,
+      "learning_rate": 6.551228043715218e-09,
+      "loss": 2.3366,
+      "step": 700
+    },
+    {
+      "epoch": 2.9894736842105263,
+      "grad_norm": 29.56805419921875,
+      "learning_rate": 5.4154110206150465e-11,
+      "loss": 6.0433,
+      "step": 710
+    },
+    {
+      "epoch": 2.993684210526316,
+      "step": 711,
+      "total_flos": 49457916387328.0,
+      "train_loss": 5.2246711257473155,
+      "train_runtime": 535.0123,
+      "train_samples_per_second": 5.327,
+      "train_steps_per_second": 1.329
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 711,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 49457916387328.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34cbc3ecd5cc699e47a0527a459a4dc3969b00f5ea15e9b8da42355ecd9c0819
+size 5432