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 +1,72 @@
+---
+library_name: peft
+license: other
+base_model: Qwen/Qwen2.5-7B
+tags:
+- base_model:adapter:Qwen/Qwen2.5-7B
+- llama-factory
+- lora
+- transformers
+pipeline_tag: text-generation
+model-index:
+- name: qwen7b_lora_sft_8gpu_s13
+  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. -->
+
+# qwen7b_lora_sft_8gpu_s13
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) on the assimilation_strict_json_v2 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1527
+
+## 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: 0.0001
+- train_batch_size: 8
+- eval_batch_size: 4
+- seed: 13
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 64
+- 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_steps: 0.05
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.1567        | 0.6667 | 50   | 0.1561          |
+| 0.1533        | 1.3333 | 100  | 0.1532          |
+| 0.1528        | 2.0    | 150  | 0.1527          |
+| 0.1527        | 2.6667 | 200  | 0.1527          |
+| 0.1527        | 3.0    | 225  | 0.1527          |
+
+
+### Framework versions
+
+- PEFT 0.18.1
+- Transformers 5.6.0
+- Pytorch 2.7.0+cu128
+- Datasets 4.0.0
+- Tokenizers 0.22.2

adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B",
+  "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": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "down_proj",
+    "gate_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bd5612db05d87fc488ecab6daff65b402647d54e5463e5e31a299dbc56dce98
+size 645975704

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.1526603251695633,
+    "eval_runtime": 0.7925,
+    "eval_samples_per_second": 315.469,
+    "eval_steps_per_second": 10.095,
+    "total_flos": 9.49777223122944e+16,
+    "train_loss": 0.29038675096299915,
+    "train_runtime": 174.0086,
+    "train_samples_per_second": 81.892,
+    "train_steps_per_second": 1.293
+}

chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.1526603251695633,
+    "eval_runtime": 0.7925,
+    "eval_samples_per_second": 315.469,
+    "eval_steps_per_second": 10.095
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "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": 3.0,
+    "total_flos": 9.49777223122944e+16,
+    "train_loss": 0.29038675096299915,
+    "train_runtime": 174.0086,
+    "train_samples_per_second": 81.892,
+    "train_steps_per_second": 1.293
+}

trainer_log.jsonl

@@ -0,0 +1,51 @@
+{"current_steps": 5, "total_steps": 225, "loss": 3.553193283081055, "lr": 3.3333333333333335e-05, "epoch": 0.06666666666666667, "percentage": 2.22, "elapsed_time": "0:00:04", "remaining_time": "0:03:14"}
+{"current_steps": 10, "total_steps": 225, "loss": 2.196733856201172, "lr": 7.500000000000001e-05, "epoch": 0.13333333333333333, "percentage": 4.44, "elapsed_time": "0:00:07", "remaining_time": "0:02:35"}
+{"current_steps": 15, "total_steps": 225, "loss": 0.5981613159179687, "lr": 9.997824750657585e-05, "epoch": 0.2, "percentage": 6.67, "elapsed_time": "0:00:10", "remaining_time": "0:02:21"}
+{"current_steps": 20, "total_steps": 225, "loss": 0.25100862979888916, "lr": 9.973374926646116e-05, "epoch": 0.26666666666666666, "percentage": 8.89, "elapsed_time": "0:00:12", "remaining_time": "0:02:12"}
+{"current_steps": 25, "total_steps": 225, "loss": 0.21380953788757323, "lr": 9.921889571113628e-05, "epoch": 0.3333333333333333, "percentage": 11.11, "elapsed_time": "0:00:15", "remaining_time": "0:02:06"}
+{"current_steps": 30, "total_steps": 225, "loss": 0.19729268550872803, "lr": 9.843648561200475e-05, "epoch": 0.4, "percentage": 13.33, "elapsed_time": "0:00:18", "remaining_time": "0:02:00"}
+{"current_steps": 35, "total_steps": 225, "loss": 0.19206844568252562, "lr": 9.73907721921212e-05, "epoch": 0.4666666666666667, "percentage": 15.56, "elapsed_time": "0:00:21", "remaining_time": "0:01:56"}
+{"current_steps": 40, "total_steps": 225, "loss": 0.1841310977935791, "lr": 9.608744000544392e-05, "epoch": 0.5333333333333333, "percentage": 17.78, "elapsed_time": "0:00:24", "remaining_time": "0:01:52"}
+{"current_steps": 45, "total_steps": 225, "loss": 0.16237072944641112, "lr": 9.453357403529609e-05, "epoch": 0.6, "percentage": 20.0, "elapsed_time": "0:00:27", "remaining_time": "0:01:48"}
+{"current_steps": 50, "total_steps": 225, "loss": 0.1566811203956604, "lr": 9.273762118001837e-05, "epoch": 0.6666666666666666, "percentage": 22.22, "elapsed_time": "0:00:29", "remaining_time": "0:01:44"}
+{"current_steps": 50, "total_steps": 225, "eval_loss": 0.15606221556663513, "epoch": 0.6666666666666666, "percentage": 22.22, "elapsed_time": "0:00:30", "remaining_time": "0:01:47"}
+{"current_steps": 55, "total_steps": 225, "loss": 0.15580005645751954, "lr": 9.070934433517873e-05, "epoch": 0.7333333333333333, "percentage": 24.44, "elapsed_time": "0:00:39", "remaining_time": "0:02:02"}
+{"current_steps": 60, "total_steps": 225, "loss": 0.1553624153137207, "lr": 8.845976932195103e-05, "epoch": 0.8, "percentage": 26.67, "elapsed_time": "0:00:42", "remaining_time": "0:01:56"}
+{"current_steps": 65, "total_steps": 225, "loss": 0.15475208759307862, "lr": 8.600112495016288e-05, "epoch": 0.8666666666666667, "percentage": 28.89, "elapsed_time": "0:00:45", "remaining_time": "0:01:51"}
+{"current_steps": 70, "total_steps": 225, "loss": 0.15437995195388793, "lr": 8.334677654183254e-05, "epoch": 0.9333333333333333, "percentage": 31.11, "elapsed_time": "0:00:48", "remaining_time": "0:01:46"}
+{"current_steps": 75, "total_steps": 225, "loss": 0.1542748212814331, "lr": 8.051115327656538e-05, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:00:50", "remaining_time": "0:01:41"}
+{"current_steps": 80, "total_steps": 225, "loss": 0.15384273529052733, "lr": 7.750966975376328e-05, "epoch": 1.0666666666666667, "percentage": 35.56, "elapsed_time": "0:00:53", "remaining_time": "0:01:37"}
+{"current_steps": 85, "total_steps": 225, "loss": 0.153655743598938, "lr": 7.435864219803983e-05, "epoch": 1.1333333333333333, "percentage": 37.78, "elapsed_time": "0:00:56", "remaining_time": "0:01:33"}
+{"current_steps": 90, "total_steps": 225, "loss": 0.15383241176605225, "lr": 7.10751997633524e-05, "epoch": 1.2, "percentage": 40.0, "elapsed_time": "0:00:59", "remaining_time": "0:01:29"}
+{"current_steps": 95, "total_steps": 225, "loss": 0.1533586263656616, "lr": 6.767719141800717e-05, "epoch": 1.2666666666666666, "percentage": 42.22, "elapsed_time": "0:01:02", "remaining_time": "0:01:25"}
+{"current_steps": 100, "total_steps": 225, "loss": 0.1532520055770874, "lr": 6.418308891671484e-05, "epoch": 1.3333333333333333, "percentage": 44.44, "elapsed_time": "0:01:05", "remaining_time": "0:01:21"}
+{"current_steps": 100, "total_steps": 225, "eval_loss": 0.15319058299064636, "epoch": 1.3333333333333333, "percentage": 44.44, "elapsed_time": "0:01:05", "remaining_time": "0:01:22"}
+{"current_steps": 105, "total_steps": 225, "loss": 0.15315526723861694, "lr": 6.0611886387146156e-05, "epoch": 1.4, "percentage": 46.67, "elapsed_time": "0:01:15", "remaining_time": "0:01:26"}
+{"current_steps": 110, "total_steps": 225, "loss": 0.15307013988494872, "lr": 5.6982997076840306e-05, "epoch": 1.4666666666666668, "percentage": 48.89, "elapsed_time": "0:01:18", "remaining_time": "0:01:22"}
+{"current_steps": 115, "total_steps": 225, "loss": 0.15306075811386108, "lr": 5.3316147821755205e-05, "epoch": 1.5333333333333332, "percentage": 51.11, "elapsed_time": "0:01:21", "remaining_time": "0:01:18"}
+{"current_steps": 120, "total_steps": 225, "loss": 0.15295226573944093, "lr": 4.963127181013438e-05, "epoch": 1.6, "percentage": 53.33, "elapsed_time": "0:01:24", "remaining_time": "0:01:13"}
+{"current_steps": 125, "total_steps": 225, "loss": 0.15291054248809816, "lr": 4.5948400224632e-05, "epoch": 1.6666666666666665, "percentage": 55.56, "elapsed_time": "0:01:27", "remaining_time": "0:01:09"}
+{"current_steps": 130, "total_steps": 225, "loss": 0.15286383628845215, "lr": 4.228755335173488e-05, "epoch": 1.7333333333333334, "percentage": 57.78, "elapsed_time": "0:01:30", "remaining_time": "0:01:05"}
+{"current_steps": 135, "total_steps": 225, "loss": 0.15282795429229737, "lr": 3.866863175041666e-05, "epoch": 1.8, "percentage": 60.0, "elapsed_time": "0:01:32", "remaining_time": "0:01:01"}
+{"current_steps": 140, "total_steps": 225, "loss": 0.1527980923652649, "lr": 3.511130807163724e-05, "epoch": 1.8666666666666667, "percentage": 62.22, "elapsed_time": "0:01:35", "remaining_time": "0:00:58"}
+{"current_steps": 145, "total_steps": 225, "loss": 0.15277599096298217, "lr": 3.1634920116762176e-05, "epoch": 1.9333333333333333, "percentage": 64.44, "elapsed_time": "0:01:38", "remaining_time": "0:00:54"}
+{"current_steps": 150, "total_steps": 225, "loss": 0.15276691913604737, "lr": 2.825836571624254e-05, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:01:41", "remaining_time": "0:00:50"}
+{"current_steps": 150, "total_steps": 225, "eval_loss": 0.15274152159690857, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:01:42", "remaining_time": "0:00:51"}
+{"current_steps": 155, "total_steps": 225, "loss": 0.1527329206466675, "lr": 2.500000000000001e-05, "epoch": 2.066666666666667, "percentage": 68.89, "elapsed_time": "0:01:51", "remaining_time": "0:00:50"}
+{"current_steps": 160, "total_steps": 225, "loss": 0.15271611213684083, "lr": 2.187753561796097e-05, "epoch": 2.1333333333333333, "percentage": 71.11, "elapsed_time": "0:01:53", "remaining_time": "0:00:46"}
+{"current_steps": 165, "total_steps": 225, "loss": 0.152712082862854, "lr": 1.890794645314633e-05, "epoch": 2.2, "percentage": 73.33, "elapsed_time": "0:01:56", "remaining_time": "0:00:42"}
+{"current_steps": 170, "total_steps": 225, "loss": 0.1527017116546631, "lr": 1.6107375350737437e-05, "epoch": 2.2666666666666666, "percentage": 75.56, "elapsed_time": "0:01:59", "remaining_time": "0:00:38"}
+{"current_steps": 175, "total_steps": 225, "loss": 0.15268385410308838, "lr": 1.3491046364708293e-05, "epoch": 2.3333333333333335, "percentage": 77.78, "elapsed_time": "0:02:02", "remaining_time": "0:00:34"}
+{"current_steps": 180, "total_steps": 225, "loss": 0.15267916917800903, "lr": 1.1073181999055538e-05, "epoch": 2.4, "percentage": 80.0, "elapsed_time": "0:02:05", "remaining_time": "0:00:31"}
+{"current_steps": 185, "total_steps": 225, "loss": 0.152678918838501, "lr": 8.866925893507805e-06, "epoch": 2.466666666666667, "percentage": 82.22, "elapsed_time": "0:02:08", "remaining_time": "0:00:27"}
+{"current_steps": 190, "total_steps": 225, "loss": 0.15267302989959716, "lr": 6.8842713739986075e-06, "epoch": 2.533333333333333, "percentage": 84.44, "elapsed_time": "0:02:10", "remaining_time": "0:00:24"}
+{"current_steps": 195, "total_steps": 225, "loss": 0.15266704559326172, "lr": 5.135996256306619e-06, "epoch": 2.6, "percentage": 86.67, "elapsed_time": "0:02:13", "remaining_time": "0:00:20"}
+{"current_steps": 200, "total_steps": 225, "loss": 0.15267045497894288, "lr": 3.631604257273774e-06, "epoch": 2.6666666666666665, "percentage": 88.89, "elapsed_time": "0:02:16", "remaining_time": "0:00:17"}
+{"current_steps": 200, "total_steps": 225, "eval_loss": 0.15265707671642303, "epoch": 2.6666666666666665, "percentage": 88.89, "elapsed_time": "0:02:17", "remaining_time": "0:00:17"}
+{"current_steps": 205, "total_steps": 225, "loss": 0.15267107486724854, "lr": 2.3792733320934346e-06, "epoch": 2.7333333333333334, "percentage": 91.11, "elapsed_time": "0:02:26", "remaining_time": "0:00:14"}
+{"current_steps": 210, "total_steps": 225, "loss": 0.1526672959327698, "lr": 1.3858112185094418e-06, "epoch": 2.8, "percentage": 93.33, "elapsed_time": "0:02:29", "remaining_time": "0:00:10"}
+{"current_steps": 215, "total_steps": 225, "loss": 0.1526732087135315, "lr": 6.566184295904776e-07, "epoch": 2.8666666666666667, "percentage": 95.56, "elapsed_time": "0:02:31", "remaining_time": "0:00:07"}
+{"current_steps": 220, "total_steps": 225, "loss": 0.15266685485839843, "lr": 1.9565889625275946e-07, "epoch": 2.9333333333333336, "percentage": 97.78, "elapsed_time": "0:02:34", "remaining_time": "0:00:03"}
+{"current_steps": 225, "total_steps": 225, "loss": 0.15266673564910888, "lr": 5.438419120062932e-09, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:02:37", "remaining_time": "0:00:00"}
+{"current_steps": 225, "total_steps": 225, "eval_loss": 0.1526603251695633, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:02:38", "remaining_time": "0:00:00"}
+{"current_steps": 225, "total_steps": 225, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:02:44", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,398 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 50,
+  "global_step": 225,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 3.3095102310180664,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 3.553193283081055,
+      "step": 5
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 3.525651454925537,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 2.196733856201172,
+      "step": 10
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.8955384492874146,
+      "learning_rate": 9.997824750657585e-05,
+      "loss": 0.5981613159179687,
+      "step": 15
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.9316425919532776,
+      "learning_rate": 9.973374926646116e-05,
+      "loss": 0.25100862979888916,
+      "step": 20
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.470761775970459,
+      "learning_rate": 9.921889571113628e-05,
+      "loss": 0.21380953788757323,
+      "step": 25
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.24911896884441376,
+      "learning_rate": 9.843648561200475e-05,
+      "loss": 0.19729268550872803,
+      "step": 30
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "grad_norm": 0.1331823319196701,
+      "learning_rate": 9.73907721921212e-05,
+      "loss": 0.19206844568252562,
+      "step": 35
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.3001701235771179,
+      "learning_rate": 9.608744000544392e-05,
+      "loss": 0.1841310977935791,
+      "step": 40
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.025193708017468452,
+      "learning_rate": 9.453357403529609e-05,
+      "loss": 0.16237072944641112,
+      "step": 45
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.01090251188725233,
+      "learning_rate": 9.273762118001837e-05,
+      "loss": 0.1566811203956604,
+      "step": 50
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "eval_loss": 0.15606221556663513,
+      "eval_runtime": 0.812,
+      "eval_samples_per_second": 307.886,
+      "eval_steps_per_second": 9.852,
+      "step": 50
+    },
+    {
+      "epoch": 0.7333333333333333,
+      "grad_norm": 0.00922091118991375,
+      "learning_rate": 9.070934433517873e-05,
+      "loss": 0.15580005645751954,
+      "step": 55
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.0077132065780460835,
+      "learning_rate": 8.845976932195103e-05,
+      "loss": 0.1553624153137207,
+      "step": 60
+    },
+    {
+      "epoch": 0.8666666666666667,
+      "grad_norm": 0.007066451478749514,
+      "learning_rate": 8.600112495016288e-05,
+      "loss": 0.15475208759307862,
+      "step": 65
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 0.005823033396154642,
+      "learning_rate": 8.334677654183254e-05,
+      "loss": 0.15437995195388793,
+      "step": 70
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.005354343447834253,
+      "learning_rate": 8.051115327656538e-05,
+      "loss": 0.1542748212814331,
+      "step": 75
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 0.005110330879688263,
+      "learning_rate": 7.750966975376328e-05,
+      "loss": 0.15384273529052733,
+      "step": 80
+    },
+    {
+      "epoch": 1.1333333333333333,
+      "grad_norm": 0.004773593507707119,
+      "learning_rate": 7.435864219803983e-05,
+      "loss": 0.153655743598938,
+      "step": 85
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.004483514931052923,
+      "learning_rate": 7.10751997633524e-05,
+      "loss": 0.15383241176605225,
+      "step": 90
+    },
+    {
+      "epoch": 1.2666666666666666,
+      "grad_norm": 0.004061458632349968,
+      "learning_rate": 6.767719141800717e-05,
+      "loss": 0.1533586263656616,
+      "step": 95
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.0037068487145006657,
+      "learning_rate": 6.418308891671484e-05,
+      "loss": 0.1532520055770874,
+      "step": 100
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "eval_loss": 0.15319058299064636,
+      "eval_runtime": 0.7898,
+      "eval_samples_per_second": 316.544,
+      "eval_steps_per_second": 10.129,
+      "step": 100
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.0036922406870871782,
+      "learning_rate": 6.0611886387146156e-05,
+      "loss": 0.15315526723861694,
+      "step": 105
+    },
+    {
+      "epoch": 1.4666666666666668,
+      "grad_norm": 0.003276499453932047,
+      "learning_rate": 5.6982997076840306e-05,
+      "loss": 0.15307013988494872,
+      "step": 110
+    },
+    {
+      "epoch": 1.5333333333333332,
+      "grad_norm": 0.0030743591487407684,
+      "learning_rate": 5.3316147821755205e-05,
+      "loss": 0.15306075811386108,
+      "step": 115
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.002890027826651931,
+      "learning_rate": 4.963127181013438e-05,
+      "loss": 0.15295226573944093,
+      "step": 120
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.002783812815323472,
+      "learning_rate": 4.5948400224632e-05,
+      "loss": 0.15291054248809816,
+      "step": 125
+    },
+    {
+      "epoch": 1.7333333333333334,
+      "grad_norm": 0.0026604756712913513,
+      "learning_rate": 4.228755335173488e-05,
+      "loss": 0.15286383628845215,
+      "step": 130
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.002499212510883808,
+      "learning_rate": 3.866863175041666e-05,
+      "loss": 0.15282795429229737,
+      "step": 135
+    },
+    {
+      "epoch": 1.8666666666666667,
+      "grad_norm": 0.0029253114480525255,
+      "learning_rate": 3.511130807163724e-05,
+      "loss": 0.1527980923652649,
+      "step": 140
+    },
+    {
+      "epoch": 1.9333333333333333,
+      "grad_norm": 0.0025290725752711296,
+      "learning_rate": 3.1634920116762176e-05,
+      "loss": 0.15277599096298217,
+      "step": 145
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.002358167665079236,
+      "learning_rate": 2.825836571624254e-05,
+      "loss": 0.15276691913604737,
+      "step": 150
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.15274152159690857,
+      "eval_runtime": 0.7897,
+      "eval_samples_per_second": 316.557,
+      "eval_steps_per_second": 10.13,
+      "step": 150
+    },
+    {
+      "epoch": 2.066666666666667,
+      "grad_norm": 0.002371756825596094,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.1527329206466675,
+      "step": 155
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 0.002244981937110424,
+      "learning_rate": 2.187753561796097e-05,
+      "loss": 0.15271611213684083,
+      "step": 160
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.002219752175733447,
+      "learning_rate": 1.890794645314633e-05,
+      "loss": 0.152712082862854,
+      "step": 165
+    },
+    {
+      "epoch": 2.2666666666666666,
+      "grad_norm": 0.0022663031704723835,
+      "learning_rate": 1.6107375350737437e-05,
+      "loss": 0.1527017116546631,
+      "step": 170
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 0.0020821872167289257,
+      "learning_rate": 1.3491046364708293e-05,
+      "loss": 0.15268385410308838,
+      "step": 175
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.002131885616108775,
+      "learning_rate": 1.1073181999055538e-05,
+      "loss": 0.15267916917800903,
+      "step": 180
+    },
+    {
+      "epoch": 2.466666666666667,
+      "grad_norm": 0.0020295437425374985,
+      "learning_rate": 8.866925893507805e-06,
+      "loss": 0.152678918838501,
+      "step": 185
+    },
+    {
+      "epoch": 2.533333333333333,
+      "grad_norm": 0.002005334012210369,
+      "learning_rate": 6.8842713739986075e-06,
+      "loss": 0.15267302989959716,
+      "step": 190
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.0021423636935651302,
+      "learning_rate": 5.135996256306619e-06,
+      "loss": 0.15266704559326172,
+      "step": 195
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.001974227372556925,
+      "learning_rate": 3.631604257273774e-06,
+      "loss": 0.15267045497894288,
+      "step": 200
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "eval_loss": 0.15265707671642303,
+      "eval_runtime": 0.7886,
+      "eval_samples_per_second": 317.034,
+      "eval_steps_per_second": 10.145,
+      "step": 200
+    },
+    {
+      "epoch": 2.7333333333333334,
+      "grad_norm": 0.0023210777435451746,
+      "learning_rate": 2.3792733320934346e-06,
+      "loss": 0.15267107486724854,
+      "step": 205
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.0020230039954185486,
+      "learning_rate": 1.3858112185094418e-06,
+      "loss": 0.1526672959327698,
+      "step": 210
+    },
+    {
+      "epoch": 2.8666666666666667,
+      "grad_norm": 0.0019893497228622437,
+      "learning_rate": 6.566184295904776e-07,
+      "loss": 0.1526732087135315,
+      "step": 215
+    },
+    {
+      "epoch": 2.9333333333333336,
+      "grad_norm": 0.0020170097704976797,
+      "learning_rate": 1.9565889625275946e-07,
+      "loss": 0.15266685485839843,
+      "step": 220
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.001985270995646715,
+      "learning_rate": 5.438419120062932e-09,
+      "loss": 0.15266673564910888,
+      "step": 225
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.1526603251695633,
+      "eval_runtime": 0.7874,
+      "eval_samples_per_second": 317.482,
+      "eval_steps_per_second": 10.159,
+      "step": 225
+    },
+    {
+      "epoch": 3.0,
+      "step": 225,
+      "total_flos": 9.49777223122944e+16,
+      "train_loss": 0.29038675096299915,
+      "train_runtime": 174.0086,
+      "train_samples_per_second": 81.892,
+      "train_steps_per_second": 1.293
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 225,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 9.49777223122944e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:762644dbf0506a9ff67da9f72e6f4a48007b2bb02b35651909ffabedbee5573c
+size 5777