ad9f0e7a370f: checkpoint-400

.gitattributes

@@ -51,3 +51,4 @@ c926ab54640f/checkpoint-1299/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 ad9f0e7a370f/checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 ad9f0e7a370f/checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 ad9f0e7a370f/checkpoint-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+ad9f0e7a370f/checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text

ad9f0e7a370f/checkpoint-400/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-Coder-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Coder-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 0.20.0

ad9f0e7a370f/checkpoint-400/adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-7B-Instruct",
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.20.0",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "down_proj",
+    "o_proj",
+    "up_proj",
+    "gate_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

ad9f0e7a370f/checkpoint-400/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cef968b4f680a6215f3720d103061412e1bf0929cf24de87016d9074186ba09b
+size 323014168

ad9f0e7a370f/checkpoint-400/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 %}

ad9f0e7a370f/checkpoint-400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70b87d4c33c3f33c00b5f9c434a48e2efe735dc5c75f0dfc1958391690f75ea4
+size 164477509

ad9f0e7a370f/checkpoint-400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02b3a4bee1efb20f4d1ad27ab636c8744618a25bfa569e685d18dc8d3f87c5f7
+size 14645

ad9f0e7a370f/checkpoint-400/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30858f23bcb22d0baef45bd4add9d6fa474141308c12653c706077b87d932e49
+size 1383

ad9f0e7a370f/checkpoint-400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7e69621e0e238aac514e00f3de76d7edf5c99776fc858ccc949f54d927619a7
+size 1465

ad9f0e7a370f/checkpoint-400/tokenizer.json

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

ad9f0e7a370f/checkpoint-400/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "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,
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

ad9f0e7a370f/checkpoint-400/trainer_state.json

@@ -0,0 +1,434 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9244547161635129,
+  "eval_steps": 500,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 0.11948550771921873,
+      "epoch": 0.023111367904087823,
+      "grad_norm": 0.26614415645599365,
+      "learning_rate": 6.923076923076924e-05,
+      "loss": 0.27834961414337156,
+      "mean_token_accuracy": 0.9158459510654211,
+      "num_tokens": 91409.0,
+      "step": 10
+    },
+    {
+      "entropy": 0.14536615274846554,
+      "epoch": 0.046222735808175645,
+      "grad_norm": 0.28414708375930786,
+      "learning_rate": 9.994965332706573e-05,
+      "loss": 0.13056882619857788,
+      "mean_token_accuracy": 0.9612345997244119,
+      "num_tokens": 186627.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.11003581081749872,
+      "epoch": 0.06933410371226346,
+      "grad_norm": 0.2106354683637619,
+      "learning_rate": 9.964234631709187e-05,
+      "loss": 0.09309924244880677,
+      "mean_token_accuracy": 0.9709797658026218,
+      "num_tokens": 276604.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.0915378995705396,
+      "epoch": 0.09244547161635129,
+      "grad_norm": 0.2663438022136688,
+      "learning_rate": 9.905741916970864e-05,
+      "loss": 0.10451314449310303,
+      "mean_token_accuracy": 0.9715173915028572,
+      "num_tokens": 368108.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.10749789654510096,
+      "epoch": 0.11555683952043912,
+      "grad_norm": 0.17998279631137848,
+      "learning_rate": 9.819814303479267e-05,
+      "loss": 0.10180811882019043,
+      "mean_token_accuracy": 0.9665989849716425,
+      "num_tokens": 457334.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.08793499013991095,
+      "epoch": 0.13866820742452693,
+      "grad_norm": 0.18421846628189087,
+      "learning_rate": 9.706932333304517e-05,
+      "loss": 0.10302398204803467,
+      "mean_token_accuracy": 0.9739916753023863,
+      "num_tokens": 547458.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.10031854717526585,
+      "epoch": 0.16177957532861476,
+      "grad_norm": 0.1583297848701477,
+      "learning_rate": 9.567727288213005e-05,
+      "loss": 0.09594225287437438,
+      "mean_token_accuracy": 0.9684251010417938,
+      "num_tokens": 633576.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.10018112544203177,
+      "epoch": 0.18489094323270258,
+      "grad_norm": 0.17029769718647003,
+      "learning_rate": 9.40297765928369e-05,
+      "loss": 0.08666939735412597,
+      "mean_token_accuracy": 0.9722081393003463,
+      "num_tokens": 725021.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.08978840237832628,
+      "epoch": 0.2080023111367904,
+      "grad_norm": 0.21113114058971405,
+      "learning_rate": 9.213604793270196e-05,
+      "loss": 0.10337703227996826,
+      "mean_token_accuracy": 0.9718282397836446,
+      "num_tokens": 809468.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.08143368383025518,
+      "epoch": 0.23111367904087823,
+      "grad_norm": 0.2660817801952362,
+      "learning_rate": 9.000667740056032e-05,
+      "loss": 0.07579125165939331,
+      "mean_token_accuracy": 0.9780994143337012,
+      "num_tokens": 898185.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.07822052207193338,
+      "epoch": 0.25422504694496606,
+      "grad_norm": 0.25105559825897217,
+      "learning_rate": 8.765357330018056e-05,
+      "loss": 0.0827728271484375,
+      "mean_token_accuracy": 0.9731388352811337,
+      "num_tokens": 988490.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.0850134992855601,
+      "epoch": 0.27733641484905386,
+      "grad_norm": 0.15802568197250366,
+      "learning_rate": 8.508989514419958e-05,
+      "loss": 0.07012671828269959,
+      "mean_token_accuracy": 0.9775275759398937,
+      "num_tokens": 1078890.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.07775390069000424,
+      "epoch": 0.3004477827531417,
+      "grad_norm": 0.3077862858772278,
+      "learning_rate": 8.232998006078997e-05,
+      "loss": 0.07896218299865723,
+      "mean_token_accuracy": 0.9768860664218664,
+      "num_tokens": 1171456.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.06990418929490261,
+      "epoch": 0.3235591506572295,
+      "grad_norm": 0.20379361510276794,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.0791102945804596,
+      "mean_token_accuracy": 0.9748555511236191,
+      "num_tokens": 1267191.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.07729233189020306,
+      "epoch": 0.34667051856131736,
+      "grad_norm": 0.2790727913379669,
+      "learning_rate": 7.628418849052523e-05,
+      "loss": 0.07758013606071472,
+      "mean_token_accuracy": 0.9756737377494573,
+      "num_tokens": 1354080.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.08708043664228171,
+      "epoch": 0.36978188646540516,
+      "grad_norm": 0.269930899143219,
+      "learning_rate": 7.303212252253162e-05,
+      "loss": 0.08181141018867492,
+      "mean_token_accuracy": 0.9762891136109829,
+      "num_tokens": 1442199.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.081081559494487,
+      "epoch": 0.392893254369493,
+      "grad_norm": 0.1513710916042328,
+      "learning_rate": 6.965125158269619e-05,
+      "loss": 0.0810213029384613,
+      "mean_token_accuracy": 0.9729760400950909,
+      "num_tokens": 1537565.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.07967969757737592,
+      "epoch": 0.4160046222735808,
+      "grad_norm": 0.26842933893203735,
+      "learning_rate": 6.616048287272301e-05,
+      "loss": 0.0828117549419403,
+      "mean_token_accuracy": 0.9750622134655714,
+      "num_tokens": 1631534.0,
+      "step": 180
+    },
+    {
+      "entropy": 0.08117348714149557,
+      "epoch": 0.4391159901776686,
+      "grad_norm": 1.2517547607421875,
+      "learning_rate": 6.257933818722543e-05,
+      "loss": 0.07101889252662659,
+      "mean_token_accuracy": 0.9764051765203476,
+      "num_tokens": 1718429.0,
+      "step": 190
+    },
+    {
+      "entropy": 0.0724065299378708,
+      "epoch": 0.46222735808175647,
+      "grad_norm": 0.3557807505130768,
+      "learning_rate": 5.8927844739931834e-05,
+      "loss": 0.07825151681900025,
+      "mean_token_accuracy": 0.9812528945505619,
+      "num_tokens": 1804347.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.07162103470182046,
+      "epoch": 0.48533872598584427,
+      "grad_norm": 0.13491679728031158,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.06295353174209595,
+      "mean_token_accuracy": 0.982288584113121,
+      "num_tokens": 1893854.0,
+      "step": 210
+    },
+    {
+      "entropy": 0.06431798301055096,
+      "epoch": 0.5084500938899321,
+      "grad_norm": 0.18494592607021332,
+      "learning_rate": 5.149577330846993e-05,
+      "loss": 0.058886730670928956,
+      "mean_token_accuracy": 0.9838358085602522,
+      "num_tokens": 1983498.0,
+      "step": 220
+    },
+    {
+      "entropy": 0.06635294057487044,
+      "epoch": 0.53156146179402,
+      "grad_norm": 0.24623480439186096,
+      "learning_rate": 4.775675848247427e-05,
+      "loss": 0.0680863082408905,
+      "mean_token_accuracy": 0.9789745938032866,
+      "num_tokens": 2069577.0,
+      "step": 230
+    },
+    {
+      "entropy": 0.05904825783218257,
+      "epoch": 0.5546728296981077,
+      "grad_norm": 0.1385364532470703,
+      "learning_rate": 4.403028877298779e-05,
+      "loss": 0.0629492461681366,
+      "mean_token_accuracy": 0.9808661632239819,
+      "num_tokens": 2165912.0,
+      "step": 240
+    },
+    {
+      "entropy": 0.06153596926887985,
+      "epoch": 0.5777841976021956,
+      "grad_norm": 0.23048147559165955,
+      "learning_rate": 4.0337204110222346e-05,
+      "loss": 0.06230597496032715,
+      "mean_token_accuracy": 0.9814305957406759,
+      "num_tokens": 2258129.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.07209547915845178,
+      "epoch": 0.6008955655062834,
+      "grad_norm": 0.31134361028671265,
+      "learning_rate": 3.6698157721666246e-05,
+      "loss": 0.07214216589927673,
+      "mean_token_accuracy": 0.9757671516388655,
+      "num_tokens": 2352490.0,
+      "step": 260
+    },
+    {
+      "entropy": 0.06986395110143348,
+      "epoch": 0.6240069334103713,
+      "grad_norm": 0.22902478277683258,
+      "learning_rate": 3.313350063085851e-05,
+      "loss": 0.061023789644241336,
+      "mean_token_accuracy": 0.9813447464257479,
+      "num_tokens": 2449939.0,
+      "step": 270
+    },
+    {
+      "entropy": 0.06509343424113467,
+      "epoch": 0.647118301314459,
+      "grad_norm": 0.20774446427822113,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 0.06663904786109924,
+      "mean_token_accuracy": 0.9776077982038259,
+      "num_tokens": 2536315.0,
+      "step": 280
+    },
+    {
+      "entropy": 0.07028964825440198,
+      "epoch": 0.6702296692185469,
+      "grad_norm": 0.5163052678108215,
+      "learning_rate": 2.630656687635007e-05,
+      "loss": 0.06851853728294373,
+      "mean_token_accuracy": 0.9816378477960825,
+      "num_tokens": 2620461.0,
+      "step": 290
+    },
+    {
+      "entropy": 0.06622880457434803,
+      "epoch": 0.6933410371226347,
+      "grad_norm": 0.20420022308826447,
+      "learning_rate": 2.3082469195465893e-05,
+      "loss": 0.060293692350387576,
+      "mean_token_accuracy": 0.9812385808676481,
+      "num_tokens": 2707354.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.05972621100372635,
+      "epoch": 0.7164524050267225,
+      "grad_norm": 0.23962542414665222,
+      "learning_rate": 2.0008905265604316e-05,
+      "loss": 0.059133869409561154,
+      "mean_token_accuracy": 0.9837360788136721,
+      "num_tokens": 2799514.0,
+      "step": 310
+    },
+    {
+      "entropy": 0.064708915000665,
+      "epoch": 0.7395637729308103,
+      "grad_norm": 0.36816108226776123,
+      "learning_rate": 1.7103063703014372e-05,
+      "loss": 0.06433560252189637,
+      "mean_token_accuracy": 0.9801775582134724,
+      "num_tokens": 2886235.0,
+      "step": 320
+    },
+    {
+      "entropy": 0.06845741930883378,
+      "epoch": 0.7626751408348982,
+      "grad_norm": 0.3006114065647125,
+      "learning_rate": 1.438119515243277e-05,
+      "loss": 0.08132993578910827,
+      "mean_token_accuracy": 0.9770394150167704,
+      "num_tokens": 2982258.0,
+      "step": 330
+    },
+    {
+      "entropy": 0.06192119924526196,
+      "epoch": 0.785786508738986,
+      "grad_norm": 0.18720364570617676,
+      "learning_rate": 1.1858521406886675e-05,
+      "loss": 0.06992543935775757,
+      "mean_token_accuracy": 0.9823945354670286,
+      "num_tokens": 3073595.0,
+      "step": 340
+    },
+    {
+      "entropy": 0.06460340030607767,
+      "epoch": 0.8088978766430738,
+      "grad_norm": 0.184926837682724,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.054811447858810425,
+      "mean_token_accuracy": 0.9821836479008198,
+      "num_tokens": 3164209.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.058504054805962366,
+      "epoch": 0.8320092445471616,
+      "grad_norm": 0.14722444117069244,
+      "learning_rate": 7.465996715633028e-06,
+      "loss": 0.052557700872421266,
+      "mean_token_accuracy": 0.9828244287520647,
+      "num_tokens": 3251398.0,
+      "step": 360
+    },
+    {
+      "entropy": 0.0587506559852045,
+      "epoch": 0.8551206124512495,
+      "grad_norm": 0.2183341383934021,
+      "learning_rate": 5.620710549772295e-06,
+      "loss": 0.047099152207374574,
+      "mean_token_accuracy": 0.9847885105758906,
+      "num_tokens": 3339179.0,
+      "step": 370
+    },
+    {
+      "entropy": 0.06087374361522961,
+      "epoch": 0.8782319803553372,
+      "grad_norm": 0.25436943769454956,
+      "learning_rate": 4.023611372427471e-06,
+      "loss": 0.0633423924446106,
+      "mean_token_accuracy": 0.9787029094994069,
+      "num_tokens": 3432843.0,
+      "step": 380
+    },
+    {
+      "entropy": 0.06056068325706292,
+      "epoch": 0.9013433482594251,
+      "grad_norm": 0.30825623869895935,
+      "learning_rate": 2.6836308100417873e-06,
+      "loss": 0.06760269403457642,
+      "mean_token_accuracy": 0.9815809104591608,
+      "num_tokens": 3527052.0,
+      "step": 390
+    },
+    {
+      "entropy": 0.05664928670958034,
+      "epoch": 0.9244547161635129,
+      "grad_norm": 0.23580507934093475,
+      "learning_rate": 1.6082625774666794e-06,
+      "loss": 0.05145724415779114,
+      "mean_token_accuracy": 0.984954122826457,
+      "num_tokens": 3614848.0,
+      "step": 400
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 433,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.5510646525486694e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

ad9f0e7a370f/checkpoint-400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b236f601a7d3fec470cccd668efc5f0908cd82b56964b743de3deba4126d01ac
+size 5777