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 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-7B-Instruct
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.0

adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "down_proj",
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "up_proj",
+    "gate_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 sha256:648a338c27901a2e18f1e783d5e7688d0717a38b03aee942bfa15f906a3531bd
+size 645975704

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
+}

chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. 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 Qwen, created by Alibaba Cloud. You 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 %}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c99e8926d4c596b7e29f88b3e7af9802b8452379b4a272adec05c9e868858bd
+size 1292087499

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba38bdecc343a6514c6f5ba7ea1cc651e5dadf81e9b371b1ca715c7bad2e3dc6
+size 14917

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e1050514bdfa0ed27320f41e9c255c0e138bd459c14db299a56274532d69dd2
+size 14917

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25c7f0c11a632f64b9e7e8aaa231e0f7ca0acbc577fe4fef5c0b323f9b2e5a60
+size 1383

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54093d653e19af28f1975f14611ada654488878917f02e00680cafe281c9818a
+size 1465

special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "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": "<|im_end|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3f9d93e80cff961819dcba7d892cf9656e086a0cf83cdbef23f10c1a493faa2
+size 11422061

tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "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,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,280 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 624,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12062726176115803,
+      "grad_norm": 0.21568018198013306,
+      "learning_rate": 0.00027872727272727267,
+      "loss": 1.5868,
+      "mean_token_accuracy": 0.6624862551689148,
+      "num_tokens": 281912.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.24125452352231605,
+      "grad_norm": 0.18077188730239868,
+      "learning_rate": 0.0005109841901849095,
+      "loss": 0.6885,
+      "mean_token_accuracy": 0.814376802444458,
+      "num_tokens": 567502.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.3618817852834741,
+      "grad_norm": 0.21275386214256287,
+      "learning_rate": 0.0005104310520681908,
+      "loss": 0.4572,
+      "mean_token_accuracy": 0.8698280012607574,
+      "num_tokens": 851707.0,
+      "step": 75
+    },
+    {
+      "epoch": 0.4825090470446321,
+      "grad_norm": 0.21209321916103363,
+      "learning_rate": 0.0005090893786665853,
+      "loss": 0.2886,
+      "mean_token_accuracy": 0.9166975712776184,
+      "num_tokens": 1136836.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.6031363088057901,
+      "grad_norm": 0.21541441977024078,
+      "learning_rate": 0.0005069633199524458,
+      "loss": 0.2088,
+      "mean_token_accuracy": 0.9403706526756287,
+      "num_tokens": 1421665.0,
+      "step": 125
+    },
+    {
+      "epoch": 0.7237635705669482,
+      "grad_norm": 0.2024364322423935,
+      "learning_rate": 0.000504059452105097,
+      "loss": 0.1676,
+      "mean_token_accuracy": 0.9520682036876679,
+      "num_tokens": 1707215.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.8443908323281062,
+      "grad_norm": 0.15191498398780823,
+      "learning_rate": 0.0005003867571698477,
+      "loss": 0.1272,
+      "mean_token_accuracy": 0.9645591104030609,
+      "num_tokens": 1990889.0,
+      "step": 175
+    },
+    {
+      "epoch": 0.9650180940892642,
+      "grad_norm": 0.16032542288303375,
+      "learning_rate": 0.0004959565952753427,
+      "loss": 0.1091,
+      "mean_token_accuracy": 0.9695405942201615,
+      "num_tokens": 2274523.0,
+      "step": 200
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.09917861223220825,
+      "eval_mean_token_accuracy": 0.9725541690344451,
+      "eval_num_tokens": 2355152.0,
+      "eval_runtime": 14.4426,
+      "eval_samples_per_second": 25.549,
+      "eval_steps_per_second": 6.439,
+      "step": 208
+    },
+    {
+      "epoch": 1.0820265379975875,
+      "grad_norm": 0.08378228545188904,
+      "learning_rate": 0.0004907826694951906,
+      "loss": 0.0898,
+      "mean_token_accuracy": 0.9755665328084808,
+      "num_tokens": 2562109.0,
+      "step": 225
+    },
+    {
+      "epoch": 1.2026537997587454,
+      "grad_norm": 0.10287031531333923,
+      "learning_rate": 0.0004848809834625538,
+      "loss": 0.0713,
+      "mean_token_accuracy": 0.9797296553850174,
+      "num_tokens": 2845938.0,
+      "step": 250
+    },
+    {
+      "epoch": 1.3232810615199035,
+      "grad_norm": 0.06548517942428589,
+      "learning_rate": 0.00047826979186880607,
+      "loss": 0.0673,
+      "mean_token_accuracy": 0.9813395547866821,
+      "num_tokens": 3129801.0,
+      "step": 275
+    },
+    {
+      "epoch": 1.4439083232810614,
+      "grad_norm": 0.10134833306074142,
+      "learning_rate": 0.00047096954399936976,
+      "loss": 0.0597,
+      "mean_token_accuracy": 0.9829099756479264,
+      "num_tokens": 3412051.0,
+      "step": 300
+    },
+    {
+      "epoch": 1.5645355850422196,
+      "grad_norm": 0.09496472030878067,
+      "learning_rate": 0.00046300282048138635,
+      "loss": 0.0608,
+      "mean_token_accuracy": 0.9829603230953217,
+      "num_tokens": 3697161.0,
+      "step": 325
+    },
+    {
+      "epoch": 1.6851628468033777,
+      "grad_norm": 0.07210717350244522,
+      "learning_rate": 0.0004543942634388648,
+      "loss": 0.0574,
+      "mean_token_accuracy": 0.9837546187639237,
+      "num_tokens": 3980794.0,
+      "step": 350
+    },
+    {
+      "epoch": 1.8057901085645356,
+      "grad_norm": 0.07639794051647186,
+      "learning_rate": 0.00044517050027135087,
+      "loss": 0.055,
+      "mean_token_accuracy": 0.9842740440368652,
+      "num_tokens": 4265160.0,
+      "step": 375
+    },
+    {
+      "epoch": 1.9264173703256935,
+      "grad_norm": 0.06361191719770432,
+      "learning_rate": 0.00043536006129187623,
+      "loss": 0.0483,
+      "mean_token_accuracy": 0.9864062821865082,
+      "num_tokens": 4549538.0,
+      "step": 400
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.054612528532743454,
+      "eval_mean_token_accuracy": 0.9850417369155473,
+      "eval_num_tokens": 4710428.0,
+      "eval_runtime": 14.4072,
+      "eval_samples_per_second": 25.612,
+      "eval_steps_per_second": 6.455,
+      "step": 416
+    },
+    {
+      "epoch": 2.0434258142340167,
+      "grad_norm": 0.05373181030154228,
+      "learning_rate": 0.00042499329147894713,
+      "loss": 0.0502,
+      "mean_token_accuracy": 0.986190964266197,
+      "num_tokens": 4827513.0,
+      "step": 425
+    },
+    {
+      "epoch": 2.164053075995175,
+      "grad_norm": 0.06150342524051666,
+      "learning_rate": 0.0004141022566155328,
+      "loss": 0.0439,
+      "mean_token_accuracy": 0.9872288095951081,
+      "num_tokens": 5110985.0,
+      "step": 450
+    },
+    {
+      "epoch": 2.284680337756333,
+      "grad_norm": 0.06713089346885681,
+      "learning_rate": 0.00040272064410538054,
+      "loss": 0.0449,
+      "mean_token_accuracy": 0.9868355304002762,
+      "num_tokens": 5396931.0,
+      "step": 475
+    },
+    {
+      "epoch": 2.405307599517491,
+      "grad_norm": 0.04453020170331001,
+      "learning_rate": 0.0003908836587734436,
+      "loss": 0.0406,
+      "mean_token_accuracy": 0.9880980604887009,
+      "num_tokens": 5682413.0,
+      "step": 500
+    },
+    {
+      "epoch": 2.5259348612786487,
+      "grad_norm": 0.07445702701807022,
+      "learning_rate": 0.00037862791397272533,
+      "loss": 0.0365,
+      "mean_token_accuracy": 0.988963897228241,
+      "num_tokens": 5965283.0,
+      "step": 525
+    },
+    {
+      "epoch": 2.646562123039807,
+      "grad_norm": 0.046956002712249756,
+      "learning_rate": 0.00036599131833436156,
+      "loss": 0.0373,
+      "mean_token_accuracy": 0.9889561772346497,
+      "num_tokens": 6249629.0,
+      "step": 550
+    },
+    {
+      "epoch": 2.767189384800965,
+      "grad_norm": 0.05231843888759613,
+      "learning_rate": 0.000353012958511237,
+      "loss": 0.0357,
+      "mean_token_accuracy": 0.9893056184053421,
+      "num_tokens": 6535592.0,
+      "step": 575
+    },
+    {
+      "epoch": 2.887816646562123,
+      "grad_norm": 0.046165380626916885,
+      "learning_rate": 0.000339732978277825,
+      "loss": 0.0331,
+      "mean_token_accuracy": 0.9900722551345825,
+      "num_tokens": 6818437.0,
+      "step": 600
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.04674848914146423,
+      "eval_mean_token_accuracy": 0.9872116202949196,
+      "eval_num_tokens": 7065581.0,
+      "eval_runtime": 14.4011,
+      "eval_samples_per_second": 25.623,
+      "eval_steps_per_second": 6.458,
+      "step": 624
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 1456,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.073091636570358e+17,
+  "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 sha256:67747685e2f9693ca77991d2cca316f2415071ec2082ee481efa069dffdac6f3
+size 6097