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

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: google/gemma-3-12b-it
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: sft
+  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. -->
+
+# sft
+
+This model is a fine-tuned version of [google/gemma-3-12b-it](https://huggingface.co/google/gemma-3-12b-it) on the cmv-gemma-3-27b-it 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: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 32
+- total_train_batch_size: 64
+- total_eval_batch_size: 16
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.05
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.51.3
+- Pytorch 2.6.0+cu124
+- Datasets 3.3.2
+- Tokenizers 0.21.0

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9984162179284131,
+    "total_flos": 318229560426496.0,
+    "train_loss": 0.8606352945269667,
+    "train_runtime": 15262.586,
+    "train_samples_per_second": 1.655,
+    "train_steps_per_second": 0.026
+}

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{{ bos_token }}\n{%- if messages[0]['role'] == 'system' -%}\n    {%- if messages[0]['content'] is string -%}\n        {%- set first_user_prefix = messages[0]['content'] + '\n\n' -%}\n    {%- else -%}\n        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '\n\n' -%}\n    {%- endif -%}\n    {%- set loop_messages = messages[1:] -%}\n{%- else -%}\n    {%- set first_user_prefix = \"\" -%}\n    {%- set loop_messages = messages -%}\n{%- endif -%}\n{%- for message in loop_messages -%}\n    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}\n        {{ raise_exception(\"Conversation roles must alternate user/assistant/user/assistant/...\") }}\n    {%- endif -%}\n    {%- if (message['role'] == 'assistant') -%}\n        {%- set role = \"model\" -%}\n    {%- else -%}\n        {%- set role = message['role'] -%}\n    {%- endif -%}\n    {{ '<start_of_turn>' + role + '\n' + (first_user_prefix if loop.first else \"\") }}\n    {%- if message['content'] is string -%}\n        {{ message['content'] | trim }}\n    {%- elif message['content'] is iterable -%}\n        {%- for item in message['content'] -%}\n            {%- if item['type'] == 'image' -%}\n                {{ '<start_of_image>' }}\n            {%- elif item['type'] == 'text' -%}\n                {{ item['text'] | trim }}\n            {%- endif -%}\n        {%- endfor -%}\n    {%- else -%}\n        {{ raise_exception(\"Invalid content type\") }}\n    {%- endif -%}\n    {{ '<end_of_turn>\n' }}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n    {{'<start_of_turn>model\n'}}\n{%- endif -%}\n"
+}

config.json

@@ -0,0 +1,64 @@
+{
+  "architectures": [
+    "Gemma3ForConditionalGeneration"
+  ],
+  "boi_token_index": 255999,
+  "eoi_token_index": 256000,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "hidden_size": 3840,
+  "image_token_index": 262144,
+  "initializer_range": 0.02,
+  "mm_tokens_per_image": 256,
+  "model_type": "gemma3",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_logit_softcapping": null,
+    "cache_implementation": "hybrid",
+    "final_logit_softcapping": null,
+    "head_dim": 256,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 3840,
+    "initializer_range": 0.02,
+    "intermediate_size": 15360,
+    "max_position_embeddings": 131072,
+    "model_type": "gemma3_text",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 48,
+    "num_key_value_heads": 8,
+    "query_pre_attn_scalar": 256,
+    "rms_norm_eps": 1e-06,
+    "rope_local_base_freq": 10000.0,
+    "rope_scaling": {
+      "factor": 8.0,
+      "rope_type": "linear"
+    },
+    "rope_theta": 1000000.0,
+    "sliding_window": 1024,
+    "sliding_window_pattern": 6,
+    "torch_dtype": "float32",
+    "use_cache": false,
+    "vocab_size": 262208
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "image_size": 896,
+    "intermediate_size": 4304,
+    "layer_norm_eps": 1e-06,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 27,
+    "patch_size": 14,
+    "torch_dtype": "float32",
+    "vision_use_head": false
+  }
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "pad_token_id": 0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "4.51.3"
+}

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a62761566b053ef2831e4489457c6248eba1a1232ad004b3c6385cd6a5e0e380
+size 4979902192

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba5f916a5feb17697cdc3b7510b33fb46afc4a649681f803ed33ff4b358392e1
+size 4931296592

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ad2fb33ab5a677b09c2e5da2ddf080d4a2c61e2f0c381e2c57bcbd5f9c78c47
+size 4931296656

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0469bff466c0ecb1f11f489a61494a0fadfb907f104e8d3a8f730b7d76c8383
+size 4931296656

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:172fffe7f9dbbd0c241b4b40e537859b15c05c910ada335790dadbacd192871f
+size 4601000928

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_pan_and_scan": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Gemma3ImageProcessor",
+  "image_seq_length": 256,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "pan_and_scan_max_num_crops": null,
+  "pan_and_scan_min_crop_size": null,
+  "pan_and_scan_min_ratio_to_activate": null,
+  "processor_class": "Gemma3Processor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 896,
+    "width": 896
+  }
+}

processor_config.json

@@ -0,0 +1,4 @@
+{
+  "image_seq_length": 256,
+  "processor_class": "Gemma3Processor"
+}

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<end_of_turn>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9984162179284131,
+    "total_flos": 318229560426496.0,
+    "train_loss": 0.8606352945269667,
+    "train_runtime": 15262.586,
+    "train_samples_per_second": 1.655,
+    "train_steps_per_second": 0.026
+}

trainer_log.jsonl

@@ -0,0 +1,40 @@
+{"current_steps": 10, "total_steps": 394, "loss": 1.1276, "lr": 4.5e-06, "epoch": 0.025340513145391194, "percentage": 2.54, "elapsed_time": "0:06:41", "remaining_time": "4:16:49"}
+{"current_steps": 20, "total_steps": 394, "loss": 0.9532, "lr": 9.5e-06, "epoch": 0.05068102629078239, "percentage": 5.08, "elapsed_time": "0:12:57", "remaining_time": "4:02:13"}
+{"current_steps": 30, "total_steps": 394, "loss": 0.9247, "lr": 9.985718470743916e-06, "epoch": 0.07602153943617358, "percentage": 7.61, "elapsed_time": "0:19:23", "remaining_time": "3:55:17"}
+{"current_steps": 40, "total_steps": 394, "loss": 0.9131, "lr": 9.936454954953108e-06, "epoch": 0.10136205258156478, "percentage": 10.15, "elapsed_time": "0:25:41", "remaining_time": "3:47:19"}
+{"current_steps": 50, "total_steps": 394, "loss": 0.9038, "lr": 9.852380451890723e-06, "epoch": 0.12670256572695598, "percentage": 12.69, "elapsed_time": "0:32:08", "remaining_time": "3:41:10"}
+{"current_steps": 60, "total_steps": 394, "loss": 0.9032, "lr": 9.734087839742152e-06, "epoch": 0.15204307887234716, "percentage": 15.23, "elapsed_time": "0:38:31", "remaining_time": "3:34:26"}
+{"current_steps": 70, "total_steps": 394, "loss": 0.8988, "lr": 9.58241129660755e-06, "epoch": 0.17738359201773837, "percentage": 17.77, "elapsed_time": "0:44:53", "remaining_time": "3:27:46"}
+{"current_steps": 80, "total_steps": 394, "loss": 0.9, "lr": 9.398420418028789e-06, "epoch": 0.20272410516312955, "percentage": 20.3, "elapsed_time": "0:51:17", "remaining_time": "3:21:19"}
+{"current_steps": 90, "total_steps": 394, "loss": 0.889, "lr": 9.183412674395193e-06, "epoch": 0.22806461830852076, "percentage": 22.84, "elapsed_time": "0:57:34", "remaining_time": "3:14:27"}
+{"current_steps": 100, "total_steps": 394, "loss": 0.8862, "lr": 8.938904261417088e-06, "epoch": 0.25340513145391197, "percentage": 25.38, "elapsed_time": "1:04:03", "remaining_time": "3:08:20"}
+{"current_steps": 110, "total_steps": 394, "loss": 0.8874, "lr": 8.666619408187953e-06, "epoch": 0.2787456445993031, "percentage": 27.92, "elapsed_time": "1:10:28", "remaining_time": "3:01:57"}
+{"current_steps": 120, "total_steps": 394, "loss": 0.8809, "lr": 8.368478218232787e-06, "epoch": 0.30408615774469433, "percentage": 30.46, "elapsed_time": "1:16:45", "remaining_time": "2:55:16"}
+{"current_steps": 130, "total_steps": 394, "loss": 0.8759, "lr": 8.046583129285422e-06, "epoch": 0.32942667089008554, "percentage": 32.99, "elapsed_time": "1:23:10", "remaining_time": "2:48:55"}
+{"current_steps": 140, "total_steps": 394, "loss": 0.8684, "lr": 7.703204087277989e-06, "epoch": 0.35476718403547675, "percentage": 35.53, "elapsed_time": "1:29:30", "remaining_time": "2:42:24"}
+{"current_steps": 150, "total_steps": 394, "loss": 0.8676, "lr": 7.340762539092858e-06, "epoch": 0.3801076971808679, "percentage": 38.07, "elapsed_time": "1:35:51", "remaining_time": "2:35:55"}
+{"current_steps": 160, "total_steps": 394, "loss": 0.8718, "lr": 6.961814356957308e-06, "epoch": 0.4054482103262591, "percentage": 40.61, "elapsed_time": "1:42:19", "remaining_time": "2:29:38"}
+{"current_steps": 170, "total_steps": 394, "loss": 0.8613, "lr": 6.569031814894962e-06, "epoch": 0.4307887234716503, "percentage": 43.15, "elapsed_time": "1:48:42", "remaining_time": "2:23:14"}
+{"current_steps": 180, "total_steps": 394, "loss": 0.8587, "lr": 6.165184744332824e-06, "epoch": 0.4561292366170415, "percentage": 45.69, "elapsed_time": "1:55:09", "remaining_time": "2:16:54"}
+{"current_steps": 190, "total_steps": 394, "loss": 0.8496, "lr": 5.753121001751161e-06, "epoch": 0.4814697497624327, "percentage": 48.22, "elapsed_time": "2:01:32", "remaining_time": "2:10:30"}
+{"current_steps": 200, "total_steps": 394, "loss": 0.8507, "lr": 5.335746386114814e-06, "epoch": 0.5068102629078239, "percentage": 50.76, "elapsed_time": "2:07:56", "remaining_time": "2:04:06"}
+{"current_steps": 210, "total_steps": 394, "loss": 0.8465, "lr": 4.9160041477046e-06, "epoch": 0.532150776053215, "percentage": 53.3, "elapsed_time": "2:14:18", "remaining_time": "1:57:40"}
+{"current_steps": 220, "total_steps": 394, "loss": 0.8543, "lr": 4.4968542328488e-06, "epoch": 0.5574912891986062, "percentage": 55.84, "elapsed_time": "2:20:36", "remaining_time": "1:51:12"}
+{"current_steps": 230, "total_steps": 394, "loss": 0.841, "lr": 4.081252410917148e-06, "epoch": 0.5828318023439975, "percentage": 58.38, "elapsed_time": "2:26:59", "remaining_time": "1:44:48"}
+{"current_steps": 240, "total_steps": 394, "loss": 0.8358, "lr": 3.6721294307699786e-06, "epoch": 0.6081723154893887, "percentage": 60.91, "elapsed_time": "2:33:27", "remaining_time": "1:38:28"}
+{"current_steps": 250, "total_steps": 394, "loss": 0.8242, "lr": 3.272370353647465e-06, "epoch": 0.6335128286347799, "percentage": 63.45, "elapsed_time": "2:39:46", "remaining_time": "1:32:01"}
+{"current_steps": 260, "total_steps": 394, "loss": 0.83, "lr": 2.8847942082397112e-06, "epoch": 0.6588533417801711, "percentage": 65.99, "elapsed_time": "2:46:09", "remaining_time": "1:25:38"}
+{"current_steps": 270, "total_steps": 394, "loss": 0.8256, "lr": 2.512134111406422e-06, "epoch": 0.6841938549255623, "percentage": 68.53, "elapsed_time": "2:52:37", "remaining_time": "1:19:16"}
+{"current_steps": 280, "total_steps": 394, "loss": 0.8219, "lr": 2.1570179947312674e-06, "epoch": 0.7095343680709535, "percentage": 71.07, "elapsed_time": "2:59:01", "remaining_time": "1:12:53"}
+{"current_steps": 290, "total_steps": 394, "loss": 0.8211, "lr": 1.8219500728237849e-06, "epoch": 0.7348748812163446, "percentage": 73.6, "elapsed_time": "3:05:29", "remaining_time": "1:06:31"}
+{"current_steps": 300, "total_steps": 394, "loss": 0.8124, "lr": 1.509293184050995e-06, "epoch": 0.7602153943617358, "percentage": 76.14, "elapsed_time": "3:11:45", "remaining_time": "1:00:04"}
+{"current_steps": 310, "total_steps": 394, "loss": 0.8189, "lr": 1.2212521282287093e-06, "epoch": 0.785555907507127, "percentage": 78.68, "elapsed_time": "3:18:13", "remaining_time": "0:53:42"}
+{"current_steps": 320, "total_steps": 394, "loss": 0.8151, "lr": 9.59858118772105e-07, "epoch": 0.8108964206525182, "percentage": 81.22, "elapsed_time": "3:24:35", "remaining_time": "0:47:18"}
+{"current_steps": 330, "total_steps": 394, "loss": 0.8189, "lr": 7.269544589461968e-07, "epoch": 0.8362369337979094, "percentage": 83.76, "elapsed_time": "3:30:52", "remaining_time": "0:40:53"}
+{"current_steps": 340, "total_steps": 394, "loss": 0.8107, "lr": 5.241835432246888e-07, "epoch": 0.8615774469433006, "percentage": 86.29, "elapsed_time": "3:37:16", "remaining_time": "0:34:30"}
+{"current_steps": 350, "total_steps": 394, "loss": 0.8062, "lr": 3.5297527542127675e-07, "epoch": 0.8869179600886918, "percentage": 88.83, "elapsed_time": "3:43:41", "remaining_time": "0:28:07"}
+{"current_steps": 360, "total_steps": 394, "loss": 0.8155, "lr": 2.1453698526664513e-07, "epoch": 0.912258473234083, "percentage": 91.37, "elapsed_time": "3:50:06", "remaining_time": "0:21:43"}
+{"current_steps": 370, "total_steps": 394, "loss": 0.8078, "lr": 1.0984491453762402e-07, "epoch": 0.9375989863794741, "percentage": 93.91, "elapsed_time": "3:56:28", "remaining_time": "0:15:20"}
+{"current_steps": 380, "total_steps": 394, "loss": 0.802, "lr": 3.963733277679904e-08, "epoch": 0.9629394995248653, "percentage": 96.45, "elapsed_time": "4:02:52", "remaining_time": "0:08:56"}
+{"current_steps": 390, "total_steps": 394, "loss": 0.8076, "lr": 4.409331149256013e-09, "epoch": 0.9882800126702566, "percentage": 98.98, "elapsed_time": "4:09:11", "remaining_time": "0:02:33"}
+{"current_steps": 394, "total_steps": 394, "epoch": 0.9984162179284131, "percentage": 100.0, "elapsed_time": "4:14:21", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,316 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9984162179284131,
+  "eval_steps": 500,
+  "global_step": 394,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.025340513145391194,
+      "grad_norm": 7.014422278343604,
+      "learning_rate": 4.5e-06,
+      "loss": 1.1276,
+      "step": 10
+    },
+    {
+      "epoch": 0.05068102629078239,
+      "grad_norm": 3.950172585471577,
+      "learning_rate": 9.5e-06,
+      "loss": 0.9532,
+      "step": 20
+    },
+    {
+      "epoch": 0.07602153943617358,
+      "grad_norm": 2.8852145535313203,
+      "learning_rate": 9.985718470743916e-06,
+      "loss": 0.9247,
+      "step": 30
+    },
+    {
+      "epoch": 0.10136205258156478,
+      "grad_norm": 4.372398694120704,
+      "learning_rate": 9.936454954953108e-06,
+      "loss": 0.9131,
+      "step": 40
+    },
+    {
+      "epoch": 0.12670256572695598,
+      "grad_norm": 2.678600773280688,
+      "learning_rate": 9.852380451890723e-06,
+      "loss": 0.9038,
+      "step": 50
+    },
+    {
+      "epoch": 0.15204307887234716,
+      "grad_norm": 3.1616554933826584,
+      "learning_rate": 9.734087839742152e-06,
+      "loss": 0.9032,
+      "step": 60
+    },
+    {
+      "epoch": 0.17738359201773837,
+      "grad_norm": 2.711129850639537,
+      "learning_rate": 9.58241129660755e-06,
+      "loss": 0.8988,
+      "step": 70
+    },
+    {
+      "epoch": 0.20272410516312955,
+      "grad_norm": 2.816882812285983,
+      "learning_rate": 9.398420418028789e-06,
+      "loss": 0.9,
+      "step": 80
+    },
+    {
+      "epoch": 0.22806461830852076,
+      "grad_norm": 2.4491670100971437,
+      "learning_rate": 9.183412674395193e-06,
+      "loss": 0.889,
+      "step": 90
+    },
+    {
+      "epoch": 0.25340513145391197,
+      "grad_norm": 2.3671858961630132,
+      "learning_rate": 8.938904261417088e-06,
+      "loss": 0.8862,
+      "step": 100
+    },
+    {
+      "epoch": 0.2787456445993031,
+      "grad_norm": 25.362434554086317,
+      "learning_rate": 8.666619408187953e-06,
+      "loss": 0.8874,
+      "step": 110
+    },
+    {
+      "epoch": 0.30408615774469433,
+      "grad_norm": 2.435185075586954,
+      "learning_rate": 8.368478218232787e-06,
+      "loss": 0.8809,
+      "step": 120
+    },
+    {
+      "epoch": 0.32942667089008554,
+      "grad_norm": 2.3423241237120522,
+      "learning_rate": 8.046583129285422e-06,
+      "loss": 0.8759,
+      "step": 130
+    },
+    {
+      "epoch": 0.35476718403547675,
+      "grad_norm": 2.295983766372591,
+      "learning_rate": 7.703204087277989e-06,
+      "loss": 0.8684,
+      "step": 140
+    },
+    {
+      "epoch": 0.3801076971808679,
+      "grad_norm": 2.8544179633447255,
+      "learning_rate": 7.340762539092858e-06,
+      "loss": 0.8676,
+      "step": 150
+    },
+    {
+      "epoch": 0.4054482103262591,
+      "grad_norm": 2.2374422127818963,
+      "learning_rate": 6.961814356957308e-06,
+      "loss": 0.8718,
+      "step": 160
+    },
+    {
+      "epoch": 0.4307887234716503,
+      "grad_norm": 2.1472864212507976,
+      "learning_rate": 6.569031814894962e-06,
+      "loss": 0.8613,
+      "step": 170
+    },
+    {
+      "epoch": 0.4561292366170415,
+      "grad_norm": 2.2467067956901183,
+      "learning_rate": 6.165184744332824e-06,
+      "loss": 0.8587,
+      "step": 180
+    },
+    {
+      "epoch": 0.4814697497624327,
+      "grad_norm": 2.2528338735220905,
+      "learning_rate": 5.753121001751161e-06,
+      "loss": 0.8496,
+      "step": 190
+    },
+    {
+      "epoch": 0.5068102629078239,
+      "grad_norm": 2.4179129846566636,
+      "learning_rate": 5.335746386114814e-06,
+      "loss": 0.8507,
+      "step": 200
+    },
+    {
+      "epoch": 0.532150776053215,
+      "grad_norm": 16.529801921641155,
+      "learning_rate": 4.9160041477046e-06,
+      "loss": 0.8465,
+      "step": 210
+    },
+    {
+      "epoch": 0.5574912891986062,
+      "grad_norm": 2.1966500837147556,
+      "learning_rate": 4.4968542328488e-06,
+      "loss": 0.8543,
+      "step": 220
+    },
+    {
+      "epoch": 0.5828318023439975,
+      "grad_norm": 2.2370934180241986,
+      "learning_rate": 4.081252410917148e-06,
+      "loss": 0.841,
+      "step": 230
+    },
+    {
+      "epoch": 0.6081723154893887,
+      "grad_norm": 2.086887732081978,
+      "learning_rate": 3.6721294307699786e-06,
+      "loss": 0.8358,
+      "step": 240
+    },
+    {
+      "epoch": 0.6335128286347799,
+      "grad_norm": 2.263852568221778,
+      "learning_rate": 3.272370353647465e-06,
+      "loss": 0.8242,
+      "step": 250
+    },
+    {
+      "epoch": 0.6588533417801711,
+      "grad_norm": 2.24355503619341,
+      "learning_rate": 2.8847942082397112e-06,
+      "loss": 0.83,
+      "step": 260
+    },
+    {
+      "epoch": 0.6841938549255623,
+      "grad_norm": 2.2286503006725806,
+      "learning_rate": 2.512134111406422e-06,
+      "loss": 0.8256,
+      "step": 270
+    },
+    {
+      "epoch": 0.7095343680709535,
+      "grad_norm": 2.1171293835945155,
+      "learning_rate": 2.1570179947312674e-06,
+      "loss": 0.8219,
+      "step": 280
+    },
+    {
+      "epoch": 0.7348748812163446,
+      "grad_norm": 2.087191484034938,
+      "learning_rate": 1.8219500728237849e-06,
+      "loss": 0.8211,
+      "step": 290
+    },
+    {
+      "epoch": 0.7602153943617358,
+      "grad_norm": 2.3605396760707866,
+      "learning_rate": 1.509293184050995e-06,
+      "loss": 0.8124,
+      "step": 300
+    },
+    {
+      "epoch": 0.785555907507127,
+      "grad_norm": 2.1652486052680384,
+      "learning_rate": 1.2212521282287093e-06,
+      "loss": 0.8189,
+      "step": 310
+    },
+    {
+      "epoch": 0.8108964206525182,
+      "grad_norm": 2.04980952594426,
+      "learning_rate": 9.59858118772105e-07,
+      "loss": 0.8151,
+      "step": 320
+    },
+    {
+      "epoch": 0.8362369337979094,
+      "grad_norm": 2.0755635014559606,
+      "learning_rate": 7.269544589461968e-07,
+      "loss": 0.8189,
+      "step": 330
+    },
+    {
+      "epoch": 0.8615774469433006,
+      "grad_norm": 2.0129993073524095,
+      "learning_rate": 5.241835432246888e-07,
+      "loss": 0.8107,
+      "step": 340
+    },
+    {
+      "epoch": 0.8869179600886918,
+      "grad_norm": 2.0409156226901315,
+      "learning_rate": 3.5297527542127675e-07,
+      "loss": 0.8062,
+      "step": 350
+    },
+    {
+      "epoch": 0.912258473234083,
+      "grad_norm": 2.3050144167741613,
+      "learning_rate": 2.1453698526664513e-07,
+      "loss": 0.8155,
+      "step": 360
+    },
+    {
+      "epoch": 0.9375989863794741,
+      "grad_norm": 2.0906040167387188,
+      "learning_rate": 1.0984491453762402e-07,
+      "loss": 0.8078,
+      "step": 370
+    },
+    {
+      "epoch": 0.9629394995248653,
+      "grad_norm": 1.94641588069489,
+      "learning_rate": 3.963733277679904e-08,
+      "loss": 0.802,
+      "step": 380
+    },
+    {
+      "epoch": 0.9882800126702566,
+      "grad_norm": 2.333717554003802,
+      "learning_rate": 4.409331149256013e-09,
+      "loss": 0.8076,
+      "step": 390
+    },
+    {
+      "epoch": 0.9984162179284131,
+      "step": 394,
+      "total_flos": 318229560426496.0,
+      "train_loss": 0.8606352945269667,
+      "train_runtime": 15262.586,
+      "train_samples_per_second": 1.655,
+      "train_steps_per_second": 0.026
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 394,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 318229560426496.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86a068ca4e3136c75b4af0873420c2dd592d64a9c0dcd60f6bb14bee59463a65
+size 7608