Model save

.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 +1,60 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: Qwen/Qwen2.5-Coder-1.5B-Instruct
+tags:
+- llama-factory
+- generated_from_trainer
+model-index:
+- name: ex45_qwen2.5_1.5b_61k_source_16kcw_2ep_cuda_amd_os
+  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. -->
+
+# ex45_qwen2.5_1.5b_61k_source_16kcw_2ep_cuda_amd_os
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct) on an unknown 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: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 256
+- total_eval_batch_size: 32
+- 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: 0.1
+- num_epochs: 2.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.51.3
+- Pytorch 2.6.0+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

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
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.51.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59b21f25c33e9dd00bb9c1a4be9e0683c1a5d86bac206135f46e179221a857d4
+size 3087467144

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 +1,209 @@
+{
+  "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 Qwen, created by Alibaba Cloud. 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 Qwen, created by Alibaba Cloud. You 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",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_log.jsonl

@@ -0,0 +1,48 @@
+{"current_steps": 10, "total_steps": 478, "loss": 0.0243, "lr": 3.7500000000000005e-06, "epoch": 0.04184100418410042, "percentage": 2.09, "elapsed_time": "0:07:21", "remaining_time": "5:44:15"}
+{"current_steps": 20, "total_steps": 478, "loss": 0.0066, "lr": 7.916666666666667e-06, "epoch": 0.08368200836820083, "percentage": 4.18, "elapsed_time": "0:14:37", "remaining_time": "5:34:55"}
+{"current_steps": 30, "total_steps": 478, "loss": 0.0044, "lr": 1.2083333333333333e-05, "epoch": 0.12552301255230125, "percentage": 6.28, "elapsed_time": "0:21:43", "remaining_time": "5:24:28"}
+{"current_steps": 40, "total_steps": 478, "loss": 0.0028, "lr": 1.6250000000000002e-05, "epoch": 0.16736401673640167, "percentage": 8.37, "elapsed_time": "0:28:35", "remaining_time": "5:13:08"}
+{"current_steps": 50, "total_steps": 478, "loss": 0.0025, "lr": 1.9999733110857237e-05, "epoch": 0.20920502092050208, "percentage": 10.46, "elapsed_time": "0:34:55", "remaining_time": "4:59:01"}
+{"current_steps": 60, "total_steps": 478, "loss": 0.0018, "lr": 1.9967723647752463e-05, "epoch": 0.2510460251046025, "percentage": 12.55, "elapsed_time": "0:41:26", "remaining_time": "4:48:39"}
+{"current_steps": 70, "total_steps": 478, "loss": 0.0019, "lr": 1.988253206622306e-05, "epoch": 0.2928870292887029, "percentage": 14.64, "elapsed_time": "0:47:43", "remaining_time": "4:38:09"}
+{"current_steps": 80, "total_steps": 478, "loss": 0.0026, "lr": 1.9744612900216588e-05, "epoch": 0.33472803347280333, "percentage": 16.74, "elapsed_time": "0:54:25", "remaining_time": "4:30:47"}
+{"current_steps": 90, "total_steps": 478, "loss": 0.0017, "lr": 1.9554702008157567e-05, "epoch": 0.37656903765690375, "percentage": 18.83, "elapsed_time": "1:00:54", "remaining_time": "4:22:32"}
+{"current_steps": 100, "total_steps": 478, "loss": 0.0013, "lr": 1.9313812646824432e-05, "epoch": 0.41841004184100417, "percentage": 20.92, "elapsed_time": "1:07:51", "remaining_time": "4:16:30"}
+{"current_steps": 110, "total_steps": 478, "loss": 0.0031, "lr": 1.9023230065186192e-05, "epoch": 0.4602510460251046, "percentage": 23.01, "elapsed_time": "1:14:52", "remaining_time": "4:10:28"}
+{"current_steps": 120, "total_steps": 478, "loss": 0.0022, "lr": 1.8684504647043093e-05, "epoch": 0.502092050209205, "percentage": 25.1, "elapsed_time": "1:21:09", "remaining_time": "4:02:06"}
+{"current_steps": 130, "total_steps": 478, "loss": 0.0024, "lr": 1.8299443639058238e-05, "epoch": 0.5439330543933054, "percentage": 27.2, "elapsed_time": "1:27:42", "remaining_time": "3:54:47"}
+{"current_steps": 140, "total_steps": 478, "loss": 0.0008, "lr": 1.7870101508314686e-05, "epoch": 0.5857740585774058, "percentage": 29.29, "elapsed_time": "1:33:57", "remaining_time": "3:46:50"}
+{"current_steps": 150, "total_steps": 478, "loss": 0.002, "lr": 1.7398768980844664e-05, "epoch": 0.6276150627615062, "percentage": 31.38, "elapsed_time": "1:40:34", "remaining_time": "3:39:55"}
+{"current_steps": 160, "total_steps": 478, "loss": 0.0011, "lr": 1.6887960819615025e-05, "epoch": 0.6694560669456067, "percentage": 33.47, "elapsed_time": "1:46:20", "remaining_time": "3:31:21"}
+{"current_steps": 170, "total_steps": 478, "loss": 0.0008, "lr": 1.634040240717878e-05, "epoch": 0.7112970711297071, "percentage": 35.56, "elapsed_time": "1:53:05", "remaining_time": "3:24:53"}
+{"current_steps": 180, "total_steps": 478, "loss": 0.0012, "lr": 1.5759015204579958e-05, "epoch": 0.7531380753138075, "percentage": 37.66, "elapsed_time": "1:59:19", "remaining_time": "3:17:32"}
+{"current_steps": 190, "total_steps": 478, "loss": 0.0013, "lr": 1.5146901164094914e-05, "epoch": 0.7949790794979079, "percentage": 39.75, "elapsed_time": "2:06:06", "remaining_time": "3:11:09"}
+{"current_steps": 200, "total_steps": 478, "loss": 0.0021, "lr": 1.4507326178974789e-05, "epoch": 0.8368200836820083, "percentage": 41.84, "elapsed_time": "2:13:11", "remaining_time": "3:05:08"}
+{"current_steps": 210, "total_steps": 478, "loss": 0.0014, "lr": 1.3843702658491961e-05, "epoch": 0.8786610878661087, "percentage": 43.93, "elapsed_time": "2:20:09", "remaining_time": "2:58:51"}
+{"current_steps": 220, "total_steps": 478, "loss": 0.0007, "lr": 1.3159571321260114e-05, "epoch": 0.9205020920502092, "percentage": 46.03, "elapsed_time": "2:27:05", "remaining_time": "2:52:30"}
+{"current_steps": 230, "total_steps": 478, "loss": 0.0011, "lr": 1.2458582303968466e-05, "epoch": 0.9623430962343096, "percentage": 48.12, "elapsed_time": "2:33:44", "remaining_time": "2:45:46"}
+{"current_steps": 240, "total_steps": 478, "loss": 0.0018, "lr": 1.1744475686323225e-05, "epoch": 1.00418410041841, "percentage": 50.21, "elapsed_time": "2:40:34", "remaining_time": "2:39:14"}
+{"current_steps": 250, "total_steps": 478, "loss": 0.0007, "lr": 1.1021061536104093e-05, "epoch": 1.0460251046025104, "percentage": 52.3, "elapsed_time": "2:46:55", "remaining_time": "2:32:13"}
+{"current_steps": 260, "total_steps": 478, "loss": 0.0008, "lr": 1.02921995808042e-05, "epoch": 1.0878661087866108, "percentage": 54.39, "elapsed_time": "2:53:40", "remaining_time": "2:25:36"}
+{"current_steps": 270, "total_steps": 478, "loss": 0.0005, "lr": 9.561778614313876e-06, "epoch": 1.1297071129707112, "percentage": 56.49, "elapsed_time": "3:00:05", "remaining_time": "2:18:44"}
+{"current_steps": 280, "total_steps": 478, "loss": 0.0011, "lr": 8.833695748522702e-06, "epoch": 1.1715481171548117, "percentage": 58.58, "elapsed_time": "3:06:54", "remaining_time": "2:12:09"}
+{"current_steps": 290, "total_steps": 478, "loss": 0.0008, "lr": 8.111835620541397e-06, "epoch": 1.213389121338912, "percentage": 60.67, "elapsed_time": "3:14:02", "remaining_time": "2:05:47"}
+{"current_steps": 300, "total_steps": 478, "loss": 0.0005, "lr": 7.400049666482061e-06, "epoch": 1.2552301255230125, "percentage": 62.76, "elapsed_time": "3:20:28", "remaining_time": "1:58:56"}
+{"current_steps": 310, "total_steps": 478, "loss": 0.001, "lr": 6.702135572380078e-06, "epoch": 1.297071129707113, "percentage": 64.85, "elapsed_time": "3:27:18", "remaining_time": "1:52:20"}
+{"current_steps": 320, "total_steps": 478, "loss": 0.0014, "lr": 6.021817011896004e-06, "epoch": 1.3389121338912133, "percentage": 66.95, "elapsed_time": "3:34:03", "remaining_time": "1:45:41"}
+{"current_steps": 330, "total_steps": 478, "loss": 0.001, "lr": 5.362723778905427e-06, "epoch": 1.3807531380753137, "percentage": 69.04, "elapsed_time": "3:40:34", "remaining_time": "1:38:55"}
+{"current_steps": 340, "total_steps": 478, "loss": 0.0012, "lr": 4.728372420978119e-06, "epoch": 1.4225941422594142, "percentage": 71.13, "elapsed_time": "3:46:53", "remaining_time": "1:32:05"}
+{"current_steps": 350, "total_steps": 478, "loss": 0.0014, "lr": 4.12214747707527e-06, "epoch": 1.4644351464435146, "percentage": 73.22, "elapsed_time": "3:53:12", "remaining_time": "1:25:17"}
+{"current_steps": 360, "total_steps": 478, "loss": 0.0005, "lr": 3.5472834195697017e-06, "epoch": 1.506276150627615, "percentage": 75.31, "elapsed_time": "3:59:48", "remaining_time": "1:18:36"}
+{"current_steps": 370, "total_steps": 478, "loss": 0.0016, "lr": 3.0068473969362998e-06, "epoch": 1.5481171548117154, "percentage": 77.41, "elapsed_time": "4:06:13", "remaining_time": "1:11:52"}
+{"current_steps": 380, "total_steps": 478, "loss": 0.0011, "lr": 2.5037228691878424e-06, "epoch": 1.5899581589958158, "percentage": 79.5, "elapsed_time": "4:13:06", "remaining_time": "1:05:16"}
+{"current_steps": 390, "total_steps": 478, "loss": 0.0011, "lr": 2.0405942233682017e-06, "epoch": 1.6317991631799162, "percentage": 81.59, "elapsed_time": "4:20:00", "remaining_time": "0:58:40"}
+{"current_steps": 400, "total_steps": 478, "loss": 0.0019, "lr": 1.619932451186048e-06, "epoch": 1.6736401673640167, "percentage": 83.68, "elapsed_time": "4:27:18", "remaining_time": "0:52:07"}
+{"current_steps": 410, "total_steps": 478, "loss": 0.0008, "lr": 1.2439819652049178e-06, "epoch": 1.715481171548117, "percentage": 85.77, "elapsed_time": "4:33:52", "remaining_time": "0:45:25"}
+{"current_steps": 420, "total_steps": 478, "loss": 0.001, "lr": 9.147486239311032e-07, "epoch": 1.7573221757322175, "percentage": 87.87, "elapsed_time": "4:40:21", "remaining_time": "0:38:43"}
+{"current_steps": 430, "total_steps": 478, "loss": 0.0013, "lr": 6.339890296906493e-07, "epoch": 1.799163179916318, "percentage": 89.96, "elapsed_time": "4:46:28", "remaining_time": "0:31:58"}
+{"current_steps": 440, "total_steps": 478, "loss": 0.0014, "lr": 4.032011563958893e-07, "epoch": 1.8410041841004183, "percentage": 92.05, "elapsed_time": "4:52:51", "remaining_time": "0:25:17"}
+{"current_steps": 450, "total_steps": 478, "loss": 0.0012, "lr": 2.2361635720651199e-07, "epoch": 1.8828451882845187, "percentage": 94.14, "elapsed_time": "4:59:55", "remaining_time": "0:18:39"}
+{"current_steps": 460, "total_steps": 478, "loss": 0.0008, "lr": 9.619279472766863e-08, "epoch": 1.9246861924686192, "percentage": 96.23, "elapsed_time": "5:06:12", "remaining_time": "0:11:58"}
+{"current_steps": 470, "total_steps": 478, "loss": 0.002, "lr": 2.1610328797904145e-08, "epoch": 1.9665271966527196, "percentage": 98.33, "elapsed_time": "5:12:31", "remaining_time": "0:05:19"}
+{"current_steps": 478, "total_steps": 478, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "5:17:51", "remaining_time": "0:00:00"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbffd93a57199e48d8d1ed0bfaae02b24812e001033d4640b6d8a1856b735c93
+size 7864