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": [
+    "k_proj",
+    "gate_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "o_proj",
+    "down_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 sha256:391098d81c9d1927bcc75b09926a5bfcc28f2051f41941ad2e162c64877c0fc5
+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 sha256:8cb46dbf03c568a531b25835abecd23370ae768ccabb3d156330bc17227e3238
+size 1292087499

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c97a3d1c6d5c881de017e72ad79a2d76c7e3765a535a64f5dba9fa7071a7cc53
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b861cca576a9d71534b7055c7bc60f00c473798acd5024b74f3336542757889
+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 +1,831 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 2075,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.060350030175015085,
+      "grad_norm": 0.31306660175323486,
+      "learning_rate": 0.00010909090909090909,
+      "loss": 1.8834,
+      "mean_token_accuracy": 0.6204852849245072,
+      "num_tokens": 154723.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.12070006035003017,
+      "grad_norm": 0.24157091975212097,
+      "learning_rate": 0.00022272727272727272,
+      "loss": 0.9576,
+      "mean_token_accuracy": 0.7616125828027726,
+      "num_tokens": 280259.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.18105009052504525,
+      "grad_norm": 0.18688738346099854,
+      "learning_rate": 0.0003363636363636364,
+      "loss": 0.6349,
+      "mean_token_accuracy": 0.8277142947912216,
+      "num_tokens": 439149.0,
+      "step": 75
+    },
+    {
+      "epoch": 0.24140012070006034,
+      "grad_norm": 0.2762071490287781,
+      "learning_rate": 0.0003999849510577617,
+      "loss": 0.5192,
+      "mean_token_accuracy": 0.8541608083248139,
+      "num_tokens": 565243.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.30175015087507545,
+      "grad_norm": 0.1952812373638153,
+      "learning_rate": 0.0003998388342637495,
+      "loss": 0.4126,
+      "mean_token_accuracy": 0.8826167666912079,
+      "num_tokens": 723668.0,
+      "step": 125
+    },
+    {
+      "epoch": 0.3621001810500905,
+      "grad_norm": 0.2645445168018341,
+      "learning_rate": 0.00039953738658223166,
+      "loss": 0.327,
+      "mean_token_accuracy": 0.9054123073816299,
+      "num_tokens": 850612.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.4224502112251056,
+      "grad_norm": 0.1461791694164276,
+      "learning_rate": 0.00039908084232270096,
+      "loss": 0.2626,
+      "mean_token_accuracy": 0.9239887505769729,
+      "num_tokens": 1009483.0,
+      "step": 175
+    },
+    {
+      "epoch": 0.4828002414001207,
+      "grad_norm": 0.23679733276367188,
+      "learning_rate": 0.00039846955634824144,
+      "loss": 0.2515,
+      "mean_token_accuracy": 0.9286696869134903,
+      "num_tokens": 1135805.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.5431502715751357,
+      "grad_norm": 0.1763329952955246,
+      "learning_rate": 0.00039770400379969973,
+      "loss": 0.1806,
+      "mean_token_accuracy": 0.9484398293495179,
+      "num_tokens": 1293580.0,
+      "step": 225
+    },
+    {
+      "epoch": 0.6035003017501509,
+      "grad_norm": 0.2555539011955261,
+      "learning_rate": 0.00039678477972636774,
+      "loss": 0.1573,
+      "mean_token_accuracy": 0.9544410169124603,
+      "num_tokens": 1420337.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.663850331925166,
+      "grad_norm": 0.16816124320030212,
+      "learning_rate": 0.00039571259862346183,
+      "loss": 0.1405,
+      "mean_token_accuracy": 0.9602045881748199,
+      "num_tokens": 1579135.0,
+      "step": 275
+    },
+    {
+      "epoch": 0.724200362100181,
+      "grad_norm": 0.22802668809890747,
+      "learning_rate": 0.00039448829387675954,
+      "loss": 0.1239,
+      "mean_token_accuracy": 0.965777741074562,
+      "num_tokens": 1705618.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.7845503922751962,
+      "grad_norm": 0.14246080815792084,
+      "learning_rate": 0.0003931128171148249,
+      "loss": 0.1063,
+      "mean_token_accuracy": 0.9705592042207718,
+      "num_tokens": 1861381.0,
+      "step": 325
+    },
+    {
+      "epoch": 0.8449004224502112,
+      "grad_norm": 0.27060168981552124,
+      "learning_rate": 0.00039158723746932566,
+      "loss": 0.0986,
+      "mean_token_accuracy": 0.9729230922460556,
+      "num_tokens": 1988585.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.9052504526252263,
+      "grad_norm": 0.12157166004180908,
+      "learning_rate": 0.00038991274074401806,
+      "loss": 0.1032,
+      "mean_token_accuracy": 0.9719041043519974,
+      "num_tokens": 2146105.0,
+      "step": 375
+    },
+    {
+      "epoch": 0.9656004828002414,
+      "grad_norm": 0.242201030254364,
+      "learning_rate": 0.00038809062849304407,
+      "loss": 0.0759,
+      "mean_token_accuracy": 0.9785843056440353,
+      "num_tokens": 2274090.0,
+      "step": 400
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.08416249603033066,
+      "eval_mean_token_accuracy": 0.9767801961383304,
+      "eval_num_tokens": 2354180.0,
+      "eval_runtime": 62.4367,
+      "eval_samples_per_second": 5.91,
+      "eval_steps_per_second": 2.963,
+      "step": 415
+    },
+    {
+      "epoch": 1.024140012070006,
+      "grad_norm": 0.13536886870861053,
+      "learning_rate": 0.0003861223170092585,
+      "loss": 0.0827,
+      "mean_token_accuracy": 0.9768812951353407,
+      "num_tokens": 2423056.0,
+      "step": 425
+    },
+    {
+      "epoch": 1.0844900422450212,
+      "grad_norm": 0.1239558756351471,
+      "learning_rate": 0.00038400933622337167,
+      "loss": 0.0618,
+      "mean_token_accuracy": 0.9825653964281083,
+      "num_tokens": 2565200.0,
+      "step": 450
+    },
+    {
+      "epoch": 1.1448400724200363,
+      "grad_norm": 0.09863752126693726,
+      "learning_rate": 0.00038175332851476387,
+      "loss": 0.0737,
+      "mean_token_accuracy": 0.9798379677534104,
+      "num_tokens": 2705213.0,
+      "step": 475
+    },
+    {
+      "epoch": 1.2051901025950513,
+      "grad_norm": 0.12466593086719513,
+      "learning_rate": 0.00037935604743489506,
+      "loss": 0.0515,
+      "mean_token_accuracy": 0.9849727272987365,
+      "num_tokens": 2846701.0,
+      "step": 500
+    },
+    {
+      "epoch": 1.2655401327700664,
+      "grad_norm": 0.0887153372168541,
+      "learning_rate": 0.00037681935634430327,
+      "loss": 0.0739,
+      "mean_token_accuracy": 0.9796881800889969,
+      "num_tokens": 2989092.0,
+      "step": 525
+    },
+    {
+      "epoch": 1.3258901629450814,
+      "grad_norm": 0.10596460103988647,
+      "learning_rate": 0.0003741452269642502,
+      "loss": 0.053,
+      "mean_token_accuracy": 0.9847104620933532,
+      "num_tokens": 3132909.0,
+      "step": 550
+    },
+    {
+      "epoch": 1.3862401931200965,
+      "grad_norm": 0.0653795376420021,
+      "learning_rate": 0.0003713357378441402,
+      "loss": 0.0757,
+      "mean_token_accuracy": 0.979733721613884,
+      "num_tokens": 3274856.0,
+      "step": 575
+    },
+    {
+      "epoch": 1.4465902232951118,
+      "grad_norm": 0.06851547211408615,
+      "learning_rate": 0.00036839307274590355,
+      "loss": 0.0474,
+      "mean_token_accuracy": 0.9862795966863632,
+      "num_tokens": 3416794.0,
+      "step": 600
+    },
+    {
+      "epoch": 1.5069402534701268,
+      "grad_norm": 0.07070258259773254,
+      "learning_rate": 0.00036531951894660034,
+      "loss": 0.0656,
+      "mean_token_accuracy": 0.9818123149871826,
+      "num_tokens": 3559722.0,
+      "step": 625
+    },
+    {
+      "epoch": 1.567290283645142,
+      "grad_norm": 0.07746811956167221,
+      "learning_rate": 0.00036211746546056415,
+      "loss": 0.0482,
+      "mean_token_accuracy": 0.9861001259088517,
+      "num_tokens": 3701966.0,
+      "step": 650
+    },
+    {
+      "epoch": 1.627640313820157,
+      "grad_norm": 0.08969739079475403,
+      "learning_rate": 0.00035878940118246673,
+      "loss": 0.0637,
+      "mean_token_accuracy": 0.9821346414089203,
+      "num_tokens": 3843082.0,
+      "step": 675
+    },
+    {
+      "epoch": 1.687990343995172,
+      "grad_norm": 0.11893229186534882,
+      "learning_rate": 0.00035533791295274834,
+      "loss": 0.0427,
+      "mean_token_accuracy": 0.9874290281534195,
+      "num_tokens": 3984912.0,
+      "step": 700
+    },
+    {
+      "epoch": 1.748340374170187,
+      "grad_norm": 0.05774044245481491,
+      "learning_rate": 0.0003517656835469161,
+      "loss": 0.0611,
+      "mean_token_accuracy": 0.9828303700685501,
+      "num_tokens": 4126511.0,
+      "step": 725
+    },
+    {
+      "epoch": 1.8086904043452021,
+      "grad_norm": 0.11688227951526642,
+      "learning_rate": 0.0003480754895902742,
+      "loss": 0.0461,
+      "mean_token_accuracy": 0.9871079170703888,
+      "num_tokens": 4270148.0,
+      "step": 750
+    },
+    {
+      "epoch": 1.8690404345202172,
+      "grad_norm": 0.0830027386546135,
+      "learning_rate": 0.0003442701993997064,
+      "loss": 0.0539,
+      "mean_token_accuracy": 0.9846111249923706,
+      "num_tokens": 4412028.0,
+      "step": 775
+    },
+    {
+      "epoch": 1.9293904646952322,
+      "grad_norm": 0.05426568165421486,
+      "learning_rate": 0.00034035277075418854,
+      "loss": 0.0431,
+      "mean_token_accuracy": 0.9877988594770432,
+      "num_tokens": 4555569.0,
+      "step": 800
+    },
+    {
+      "epoch": 1.9897404948702473,
+      "grad_norm": 0.10155733674764633,
+      "learning_rate": 0.0003363262485957633,
+      "loss": 0.0446,
+      "mean_token_accuracy": 0.9870548647642136,
+      "num_tokens": 4689023.0,
+      "step": 825
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.05280078575015068,
+      "eval_mean_token_accuracy": 0.9855066299438476,
+      "eval_num_tokens": 4708360.0,
+      "eval_runtime": 62.5623,
+      "eval_samples_per_second": 5.898,
+      "eval_steps_per_second": 2.957,
+      "step": 830
+    },
+    {
+      "epoch": 2.048280024140012,
+      "grad_norm": 0.044142208993434906,
+      "learning_rate": 0.00033219376266276594,
+      "loss": 0.044,
+      "mean_token_accuracy": 0.9868254723008146,
+      "num_tokens": 4837517.0,
+      "step": 850
+    },
+    {
+      "epoch": 2.1086300543150274,
+      "grad_norm": 0.05767173692584038,
+      "learning_rate": 0.00032795852505713806,
+      "loss": 0.0328,
+      "mean_token_accuracy": 0.9904780650138855,
+      "num_tokens": 4970437.0,
+      "step": 875
+    },
+    {
+      "epoch": 2.1689800844900424,
+      "grad_norm": 0.10615792870521545,
+      "learning_rate": 0.0003236238277477231,
+      "loss": 0.0456,
+      "mean_token_accuracy": 0.9867289292812348,
+      "num_tokens": 5120504.0,
+      "step": 900
+    },
+    {
+      "epoch": 2.2293301146650575,
+      "grad_norm": 0.14517731964588165,
+      "learning_rate": 0.0003191930400114816,
+      "loss": 0.0341,
+      "mean_token_accuracy": 0.9898393619060516,
+      "num_tokens": 5252038.0,
+      "step": 925
+    },
+    {
+      "epoch": 2.2896801448400725,
+      "grad_norm": 0.0684775710105896,
+      "learning_rate": 0.0003146696058146176,
+      "loss": 0.0437,
+      "mean_token_accuracy": 0.987158373594284,
+      "num_tokens": 5402952.0,
+      "step": 950
+    },
+    {
+      "epoch": 2.3500301750150876,
+      "grad_norm": 0.05600373446941376,
+      "learning_rate": 0.00031005704113564917,
+      "loss": 0.0296,
+      "mean_token_accuracy": 0.9908739268779755,
+      "num_tokens": 5535327.0,
+      "step": 975
+    },
+    {
+      "epoch": 2.4103802051901027,
+      "grad_norm": 0.09332671761512756,
+      "learning_rate": 0.00030535893123250635,
+      "loss": 0.0474,
+      "mean_token_accuracy": 0.9863762366771698,
+      "num_tokens": 5685055.0,
+      "step": 1000
+    },
+    {
+      "epoch": 2.4707302353651177,
+      "grad_norm": 0.04388723522424698,
+      "learning_rate": 0.00030057892785577867,
+      "loss": 0.032,
+      "mean_token_accuracy": 0.9903759962320328,
+      "num_tokens": 5818131.0,
+      "step": 1025
+    },
+    {
+      "epoch": 2.5310802655401328,
+      "grad_norm": 0.08268223702907562,
+      "learning_rate": 0.00029572074641027996,
+      "loss": 0.0477,
+      "mean_token_accuracy": 0.9856782054901123,
+      "num_tokens": 5971347.0,
+      "step": 1050
+    },
+    {
+      "epoch": 2.591430295715148,
+      "grad_norm": 0.114966481924057,
+      "learning_rate": 0.0002907881630671351,
+      "loss": 0.0336,
+      "mean_token_accuracy": 0.98986423432827,
+      "num_tokens": 6104529.0,
+      "step": 1075
+    },
+    {
+      "epoch": 2.651780325890163,
+      "grad_norm": 0.07310790568590164,
+      "learning_rate": 0.00028578501182863507,
+      "loss": 0.0448,
+      "mean_token_accuracy": 0.9867177069187164,
+      "num_tokens": 6255598.0,
+      "step": 1100
+    },
+    {
+      "epoch": 2.712130356065178,
+      "grad_norm": 0.06806758791208267,
+      "learning_rate": 0.00028071518154814036,
+      "loss": 0.0305,
+      "mean_token_accuracy": 0.9908246058225632,
+      "num_tokens": 6388936.0,
+      "step": 1125
+    },
+    {
+      "epoch": 2.772480386240193,
+      "grad_norm": 0.06396596878767014,
+      "learning_rate": 0.0002755826129073503,
+      "loss": 0.0437,
+      "mean_token_accuracy": 0.9870491588115692,
+      "num_tokens": 6541365.0,
+      "step": 1150
+    },
+    {
+      "epoch": 2.832830416415208,
+      "grad_norm": 0.07528147846460342,
+      "learning_rate": 0.00027039129535328646,
+      "loss": 0.0315,
+      "mean_token_accuracy": 0.9906339544057846,
+      "num_tokens": 6675054.0,
+      "step": 1175
+    },
+    {
+      "epoch": 2.8931804465902236,
+      "grad_norm": 0.03258615359663963,
+      "learning_rate": 0.00026514526399737235,
+      "loss": 0.0401,
+      "mean_token_accuracy": 0.9878826344013214,
+      "num_tokens": 6826525.0,
+      "step": 1200
+    },
+    {
+      "epoch": 2.9535304767652386,
+      "grad_norm": 0.04856796935200691,
+      "learning_rate": 0.00025984859647901865,
+      "loss": 0.028,
+      "mean_token_accuracy": 0.991591272354126,
+      "num_tokens": 6959118.0,
+      "step": 1225
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.045701634138822556,
+      "eval_mean_token_accuracy": 0.9873638832891309,
+      "eval_num_tokens": 7062540.0,
+      "eval_runtime": 62.4047,
+      "eval_samples_per_second": 5.913,
+      "eval_steps_per_second": 2.965,
+      "step": 1245
+    },
+    {
+      "epoch": 3.012070006035003,
+      "grad_norm": 0.05719737336039543,
+      "learning_rate": 0.0002545054097961527,
+      "loss": 0.0389,
+      "mean_token_accuracy": 0.988337146252701,
+      "num_tokens": 7098967.0,
+      "step": 1250
+    },
+    {
+      "epoch": 3.0724200362100182,
+      "grad_norm": 0.05094616115093231,
+      "learning_rate": 0.0002491198571051549,
+      "loss": 0.0264,
+      "mean_token_accuracy": 0.9917955195903778,
+      "num_tokens": 7246740.0,
+      "step": 1275
+    },
+    {
+      "epoch": 3.1327700663850333,
+      "grad_norm": 0.07518504559993744,
+      "learning_rate": 0.00024369612449268976,
+      "loss": 0.0312,
+      "mean_token_accuracy": 0.9902162319421768,
+      "num_tokens": 7382812.0,
+      "step": 1300
+    },
+    {
+      "epoch": 3.1931200965600484,
+      "grad_norm": 0.04833046346902847,
+      "learning_rate": 0.00023823842772194173,
+      "loss": 0.0275,
+      "mean_token_accuracy": 0.9915666264295578,
+      "num_tokens": 7530270.0,
+      "step": 1325
+    },
+    {
+      "epoch": 3.2534701267350634,
+      "grad_norm": 0.046463292092084885,
+      "learning_rate": 0.00023275100895578304,
+      "loss": 0.0287,
+      "mean_token_accuracy": 0.9908609116077423,
+      "num_tokens": 7665067.0,
+      "step": 1350
+    },
+    {
+      "epoch": 3.3138201569100785,
+      "grad_norm": 0.0375671461224556,
+      "learning_rate": 0.0002272381334594219,
+      "loss": 0.0283,
+      "mean_token_accuracy": 0.991553401350975,
+      "num_tokens": 7812484.0,
+      "step": 1375
+    },
+    {
+      "epoch": 3.3741701870850935,
+      "grad_norm": 0.06631741672754288,
+      "learning_rate": 0.00022170408628509423,
+      "loss": 0.029,
+      "mean_token_accuracy": 0.990810295343399,
+      "num_tokens": 7946869.0,
+      "step": 1400
+    },
+    {
+      "epoch": 3.4345202172601086,
+      "grad_norm": 0.06279897689819336,
+      "learning_rate": 0.00021615316894137441,
+      "loss": 0.0266,
+      "mean_token_accuracy": 0.991255716085434,
+      "num_tokens": 8094879.0,
+      "step": 1425
+    },
+    {
+      "epoch": 3.4948702474351236,
+      "grad_norm": 0.07480517029762268,
+      "learning_rate": 0.00021058969604969535,
+      "loss": 0.0286,
+      "mean_token_accuracy": 0.9908527129888535,
+      "num_tokens": 8230906.0,
+      "step": 1450
+    },
+    {
+      "epoch": 3.5552202776101387,
+      "grad_norm": 0.031132148578763008,
+      "learning_rate": 0.00020501799199067663,
+      "loss": 0.0261,
+      "mean_token_accuracy": 0.9916221016645431,
+      "num_tokens": 8380583.0,
+      "step": 1475
+    },
+    {
+      "epoch": 3.6155703077851538,
+      "grad_norm": 0.05212632939219475,
+      "learning_rate": 0.00019944238754286564,
+      "loss": 0.0288,
+      "mean_token_accuracy": 0.9909119439125061,
+      "num_tokens": 8518383.0,
+      "step": 1500
+    },
+    {
+      "epoch": 3.675920337960169,
+      "grad_norm": 0.04208264872431755,
+      "learning_rate": 0.00019386721651650743,
+      "loss": 0.0243,
+      "mean_token_accuracy": 0.9922912389039993,
+      "num_tokens": 8665306.0,
+      "step": 1525
+    },
+    {
+      "epoch": 3.736270368135184,
+      "grad_norm": 0.050886742770671844,
+      "learning_rate": 0.0001882968123849565,
+      "loss": 0.0273,
+      "mean_token_accuracy": 0.9911774802207947,
+      "num_tokens": 8801678.0,
+      "step": 1550
+    },
+    {
+      "epoch": 3.796620398310199,
+      "grad_norm": 0.04032604768872261,
+      "learning_rate": 0.00018273550491635195,
+      "loss": 0.0271,
+      "mean_token_accuracy": 0.9913617885112762,
+      "num_tokens": 8954473.0,
+      "step": 1575
+    },
+    {
+      "epoch": 3.856970428485214,
+      "grad_norm": 0.03876972198486328,
+      "learning_rate": 0.00017718761680817142,
+      "loss": 0.0299,
+      "mean_token_accuracy": 0.9905554604530334,
+      "num_tokens": 9090583.0,
+      "step": 1600
+    },
+    {
+      "epoch": 3.9173204586602295,
+      "grad_norm": 0.03687777742743492,
+      "learning_rate": 0.00017165746032728115,
+      "loss": 0.0233,
+      "mean_token_accuracy": 0.9923606491088868,
+      "num_tokens": 9237175.0,
+      "step": 1625
+    },
+    {
+      "epoch": 3.9776704888352445,
+      "grad_norm": 0.02980276383459568,
+      "learning_rate": 0.00016614933395809448,
+      "loss": 0.0243,
+      "mean_token_accuracy": 0.9923855990171433,
+      "num_tokens": 9369366.0,
+      "step": 1650
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.04291478171944618,
+      "eval_mean_token_accuracy": 0.9888523813840505,
+      "eval_num_tokens": 9416720.0,
+      "eval_runtime": 62.3817,
+      "eval_samples_per_second": 5.915,
+      "eval_steps_per_second": 2.966,
+      "step": 1660
+    },
+    {
+      "epoch": 4.036210018105009,
+      "grad_norm": 0.06441241502761841,
+      "learning_rate": 0.00016066751906144167,
+      "loss": 0.0246,
+      "mean_token_accuracy": 0.991977270730992,
+      "num_tokens": 9516901.0,
+      "step": 1675
+    },
+    {
+      "epoch": 4.096560048280024,
+      "grad_norm": 0.0492124930024147,
+      "learning_rate": 0.0001552162765467511,
+      "loss": 0.0191,
+      "mean_token_accuracy": 0.9936403614282608,
+      "num_tokens": 9656969.0,
+      "step": 1700
+    },
+    {
+      "epoch": 4.15691007845504,
+      "grad_norm": 0.04349420592188835,
+      "learning_rate": 0.00014979984356012555,
+      "loss": 0.0236,
+      "mean_token_accuracy": 0.9925002872943878,
+      "num_tokens": 9802771.0,
+      "step": 1725
+    },
+    {
+      "epoch": 4.217260108630055,
+      "grad_norm": 0.03172674775123596,
+      "learning_rate": 0.0001444224301908905,
+      "loss": 0.0197,
+      "mean_token_accuracy": 0.9935035490989685,
+      "num_tokens": 9939595.0,
+      "step": 1750
+    },
+    {
+      "epoch": 4.27761013880507,
+      "grad_norm": 0.033489931374788284,
+      "learning_rate": 0.00013908821619917217,
+      "loss": 0.023,
+      "mean_token_accuracy": 0.9925221472978591,
+      "num_tokens": 10087030.0,
+      "step": 1775
+    },
+    {
+      "epoch": 4.337960168980085,
+      "grad_norm": 0.02928924933075905,
+      "learning_rate": 0.0001338013477670504,
+      "loss": 0.0187,
+      "mean_token_accuracy": 0.9935985404253006,
+      "num_tokens": 10223369.0,
+      "step": 1800
+    },
+    {
+      "epoch": 4.3983101991551,
+      "grad_norm": 0.03093547932803631,
+      "learning_rate": 0.0001285659342758108,
+      "loss": 0.0237,
+      "mean_token_accuracy": 0.9922171854972839,
+      "num_tokens": 10369224.0,
+      "step": 1825
+    },
+    {
+      "epoch": 4.458660229330115,
+      "grad_norm": 0.03724528104066849,
+      "learning_rate": 0.0001233860451118021,
+      "loss": 0.0192,
+      "mean_token_accuracy": 0.9937897402048111,
+      "num_tokens": 10506089.0,
+      "step": 1850
+    },
+    {
+      "epoch": 4.51901025950513,
+      "grad_norm": 0.04538549855351448,
+      "learning_rate": 0.00011826570650337947,
+      "loss": 0.0225,
+      "mean_token_accuracy": 0.9928374934196472,
+      "num_tokens": 10651807.0,
+      "step": 1875
+    },
+    {
+      "epoch": 4.579360289680145,
+      "grad_norm": 0.032116539776325226,
+      "learning_rate": 0.0001132088983913955,
+      "loss": 0.0188,
+      "mean_token_accuracy": 0.9937463319301605,
+      "num_tokens": 10789905.0,
+      "step": 1900
+    },
+    {
+      "epoch": 4.63971031985516,
+      "grad_norm": 0.05610141530632973,
+      "learning_rate": 0.00010821955133566773,
+      "loss": 0.0228,
+      "mean_token_accuracy": 0.9926589637994766,
+      "num_tokens": 10938232.0,
+      "step": 1925
+    },
+    {
+      "epoch": 4.700060350030175,
+      "grad_norm": 0.0295253936201334,
+      "learning_rate": 0.00010330154345983075,
+      "loss": 0.0192,
+      "mean_token_accuracy": 0.9936003339290619,
+      "num_tokens": 11076979.0,
+      "step": 1950
+    },
+    {
+      "epoch": 4.76041038020519,
+      "grad_norm": 0.029600035399198532,
+      "learning_rate": 9.845869743694469e-05,
+      "loss": 0.0215,
+      "mean_token_accuracy": 0.9927308022975921,
+      "num_tokens": 11224634.0,
+      "step": 1975
+    },
+    {
+      "epoch": 4.820760410380205,
+      "grad_norm": 0.03853334113955498,
+      "learning_rate": 9.369477751820505e-05,
+      "loss": 0.0182,
+      "mean_token_accuracy": 0.9941325181722641,
+      "num_tokens": 11362853.0,
+      "step": 2000
+    },
+    {
+      "epoch": 4.88111044055522,
+      "grad_norm": 0.03447585180401802,
+      "learning_rate": 8.90134866070625e-05,
+      "loss": 0.0233,
+      "mean_token_accuracy": 0.992638527750969,
+      "num_tokens": 11507857.0,
+      "step": 2025
+    },
+    {
+      "epoch": 4.941460470730235,
+      "grad_norm": 0.03993140533566475,
+      "learning_rate": 8.441846338102744e-05,
+      "loss": 0.0178,
+      "mean_token_accuracy": 0.9941539931297302,
+      "num_tokens": 11644551.0,
+      "step": 2050
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.08531560748815536,
+      "learning_rate": 7.991327946339508e-05,
+      "loss": 0.0199,
+      "mean_token_accuracy": 0.9933595823258469,
+      "num_tokens": 11770900.0,
+      "step": 2075
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.04117002710700035,
+      "eval_mean_token_accuracy": 0.9896370224050574,
+      "eval_num_tokens": 11770900.0,
+      "eval_runtime": 62.5366,
+      "eval_samples_per_second": 5.901,
+      "eval_steps_per_second": 2.958,
+      "step": 2075
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 2905,
+  "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": 5.113905883840051e+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 sha256:3980b9330086c9c10ddcf1c18c7403ba2fe6af757dd03226f55cc32b7b14fdeb
+size 6097