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",
+    "down_proj",
+    "o_proj",
+    "q_proj",
+    "v_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 sha256:6a0c1f01af04ec0d51c229f63e9191c2baab2c2e7a1ad6795ccffe749aae29ff
+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 sha256:85a21d03c2ea98d53c52fd96d7e7982e7d6b7827185339dabc6a151f19b15814
+size 1292087499

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:994c2cba2555eef301d8087ae1484ed0e7252f44df4637c6e9af3389b996ceee
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b1736ec6627ebf927133b64702a5b6824ab5d43b5017e4277694c355a4f042e
+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 +1,505 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1245,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.060350030175015085,
+      "grad_norm": 0.292353093624115,
+      "learning_rate": 0.00013971818181818181,
+      "loss": 1.8075,
+      "mean_token_accuracy": 0.6316984993219376,
+      "num_tokens": 155458.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.12070006035003017,
+      "grad_norm": 0.23519554734230042,
+      "learning_rate": 0.00028525795454545453,
+      "loss": 0.8594,
+      "mean_token_accuracy": 0.7813338875770569,
+      "num_tokens": 280957.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.18105009052504525,
+      "grad_norm": 0.17745567858219147,
+      "learning_rate": 0.0004307977272727273,
+      "loss": 0.6189,
+      "mean_token_accuracy": 0.8301489073038101,
+      "num_tokens": 439583.0,
+      "step": 75
+    },
+    {
+      "epoch": 0.24140012070006034,
+      "grad_norm": 0.28904563188552856,
+      "learning_rate": 0.0005122807260672283,
+      "loss": 0.514,
+      "mean_token_accuracy": 0.8567226785421371,
+      "num_tokens": 566372.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.30175015087507545,
+      "grad_norm": 0.18326736986637115,
+      "learning_rate": 0.0005120935869832972,
+      "loss": 0.3703,
+      "mean_token_accuracy": 0.8942542725801468,
+      "num_tokens": 721871.0,
+      "step": 125
+    },
+    {
+      "epoch": 0.3621001810500905,
+      "grad_norm": 0.22670747339725494,
+      "learning_rate": 0.0005117075078651932,
+      "loss": 0.3122,
+      "mean_token_accuracy": 0.9121941888332367,
+      "num_tokens": 848123.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.4224502112251056,
+      "grad_norm": 0.1902594268321991,
+      "learning_rate": 0.0005111227888047993,
+      "loss": 0.2411,
+      "mean_token_accuracy": 0.9314639317989349,
+      "num_tokens": 1005664.0,
+      "step": 175
+    },
+    {
+      "epoch": 0.4828002414001207,
+      "grad_norm": 0.29753610491752625,
+      "learning_rate": 0.0005103398842930102,
+      "loss": 0.2266,
+      "mean_token_accuracy": 0.9340476477146149,
+      "num_tokens": 1132284.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.5431502715751357,
+      "grad_norm": 0.1415078341960907,
+      "learning_rate": 0.0005093594028664655,
+      "loss": 0.1822,
+      "mean_token_accuracy": 0.9487657606601715,
+      "num_tokens": 1290915.0,
+      "step": 225
+    },
+    {
+      "epoch": 0.6035003017501509,
+      "grad_norm": 0.19810789823532104,
+      "learning_rate": 0.0005081821066345455,
+      "loss": 0.1458,
+      "mean_token_accuracy": 0.9581668329238892,
+      "num_tokens": 1418595.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.663850331925166,
+      "grad_norm": 0.1245037168264389,
+      "learning_rate": 0.0005068089106869988,
+      "loss": 0.1361,
+      "mean_token_accuracy": 0.9611250156164169,
+      "num_tokens": 1576137.0,
+      "step": 275
+    },
+    {
+      "epoch": 0.724200362100181,
+      "grad_norm": 0.18405039608478546,
+      "learning_rate": 0.0005052408823826598,
+      "loss": 0.1393,
+      "mean_token_accuracy": 0.9614962357282638,
+      "num_tokens": 1701485.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.7845503922751962,
+      "grad_norm": 0.18599726259708405,
+      "learning_rate": 0.000503479240519812,
+      "loss": 0.1137,
+      "mean_token_accuracy": 0.9682038247585296,
+      "num_tokens": 1859818.0,
+      "step": 325
+    },
+    {
+      "epoch": 0.8449004224502112,
+      "grad_norm": 0.1856354922056198,
+      "learning_rate": 0.0005015253543888389,
+      "loss": 0.0891,
+      "mean_token_accuracy": 0.9745866447687149,
+      "num_tokens": 1987015.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.9052504526252263,
+      "grad_norm": 0.10939127951860428,
+      "learning_rate": 0.0004993807427079012,
+      "loss": 0.1001,
+      "mean_token_accuracy": 0.9714098435640335,
+      "num_tokens": 2146234.0,
+      "step": 375
+    },
+    {
+      "epoch": 0.9656004828002414,
+      "grad_norm": 0.3307282030582428,
+      "learning_rate": 0.0004970470724424662,
+      "loss": 0.0884,
+      "mean_token_accuracy": 0.9754749721288681,
+      "num_tokens": 2273585.0,
+      "step": 400
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.08956408500671387,
+      "eval_mean_token_accuracy": 0.9750892632716411,
+      "eval_num_tokens": 2354180.0,
+      "eval_runtime": 16.024,
+      "eval_samples_per_second": 23.028,
+      "eval_steps_per_second": 11.545,
+      "step": 415
+    },
+    {
+      "epoch": 1.024140012070006,
+      "grad_norm": 0.16935159265995026,
+      "learning_rate": 0.0004945261575096078,
+      "loss": 0.101,
+      "mean_token_accuracy": 0.9729157378993083,
+      "num_tokens": 2425025.0,
+      "step": 425
+    },
+    {
+      "epoch": 1.0844900422450212,
+      "grad_norm": 0.12800893187522888,
+      "learning_rate": 0.0004918199573680834,
+      "loss": 0.0615,
+      "mean_token_accuracy": 0.9824073499441147,
+      "num_tokens": 2568833.0,
+      "step": 450
+    },
+    {
+      "epoch": 1.1448400724200363,
+      "grad_norm": 0.10300774872303009,
+      "learning_rate": 0.0004889305754952839,
+      "loss": 0.0805,
+      "mean_token_accuracy": 0.9773273587226867,
+      "num_tokens": 2710895.0,
+      "step": 475
+    },
+    {
+      "epoch": 1.2051901025950513,
+      "grad_norm": 0.11092197895050049,
+      "learning_rate": 0.0004858602577522418,
+      "loss": 0.0588,
+      "mean_token_accuracy": 0.9833286923170089,
+      "num_tokens": 2853318.0,
+      "step": 500
+    },
+    {
+      "epoch": 1.2655401327700664,
+      "grad_norm": 0.0948944017291069,
+      "learning_rate": 0.0004826113906379664,
+      "loss": 0.0838,
+      "mean_token_accuracy": 0.9770084321498871,
+      "num_tokens": 2994882.0,
+      "step": 525
+    },
+    {
+      "epoch": 1.3258901629450814,
+      "grad_norm": 0.12024246156215668,
+      "learning_rate": 0.00047918649943446345,
+      "loss": 0.0572,
+      "mean_token_accuracy": 0.9838370496034622,
+      "num_tokens": 3137930.0,
+      "step": 550
+    },
+    {
+      "epoch": 1.3862401931200965,
+      "grad_norm": 0.12121743708848953,
+      "learning_rate": 0.0004755882462438826,
+      "loss": 0.0611,
+      "mean_token_accuracy": 0.9828894352912902,
+      "num_tokens": 3279894.0,
+      "step": 575
+    },
+    {
+      "epoch": 1.4465902232951118,
+      "grad_norm": 0.19103674590587616,
+      "learning_rate": 0.000471819427919316,
+      "loss": 0.0455,
+      "mean_token_accuracy": 0.9865969383716583,
+      "num_tokens": 3420462.0,
+      "step": 600
+    },
+    {
+      "epoch": 1.5069402534701268,
+      "grad_norm": 0.06473100930452347,
+      "learning_rate": 0.0004678829738908584,
+      "loss": 0.0647,
+      "mean_token_accuracy": 0.9815235859155655,
+      "num_tokens": 3561941.0,
+      "step": 625
+    },
+    {
+      "epoch": 1.567290283645142,
+      "grad_norm": 0.09202416986227036,
+      "learning_rate": 0.0004637819438886175,
+      "loss": 0.0517,
+      "mean_token_accuracy": 0.9851528346538544,
+      "num_tokens": 3703510.0,
+      "step": 650
+    },
+    {
+      "epoch": 1.627640313820157,
+      "grad_norm": 0.08362529426813126,
+      "learning_rate": 0.00045951952556444426,
+      "loss": 0.0642,
+      "mean_token_accuracy": 0.9822886544466018,
+      "num_tokens": 3842063.0,
+      "step": 675
+    },
+    {
+      "epoch": 1.687990343995172,
+      "grad_norm": 0.0631742924451828,
+      "learning_rate": 0.0004550990320142324,
+      "loss": 0.0441,
+      "mean_token_accuracy": 0.9875086861848831,
+      "num_tokens": 3984506.0,
+      "step": 700
+    },
+    {
+      "epoch": 1.748340374170187,
+      "grad_norm": 0.07872219383716583,
+      "learning_rate": 0.00045052389920271276,
+      "loss": 0.0569,
+      "mean_token_accuracy": 0.9842114639282227,
+      "num_tokens": 4127213.0,
+      "step": 725
+    },
+    {
+      "epoch": 1.8086904043452021,
+      "grad_norm": 0.08871777355670929,
+      "learning_rate": 0.0004457976832927436,
+      "loss": 0.0437,
+      "mean_token_accuracy": 0.9873430663347245,
+      "num_tokens": 4270185.0,
+      "step": 750
+    },
+    {
+      "epoch": 1.8690404345202172,
+      "grad_norm": 0.08713535219430923,
+      "learning_rate": 0.00044092405788117396,
+      "loss": 0.0583,
+      "mean_token_accuracy": 0.9836823076009751,
+      "num_tokens": 4412354.0,
+      "step": 775
+    },
+    {
+      "epoch": 1.9293904646952322,
+      "grad_norm": 0.10155721753835678,
+      "learning_rate": 0.00043590681114342696,
+      "loss": 0.0404,
+      "mean_token_accuracy": 0.9879835307598114,
+      "num_tokens": 4556520.0,
+      "step": 800
+    },
+    {
+      "epoch": 1.9897404948702473,
+      "grad_norm": 0.0794239267706871,
+      "learning_rate": 0.0004307498428890239,
+      "loss": 0.045,
+      "mean_token_accuracy": 0.9872637808322906,
+      "num_tokens": 4688903.0,
+      "step": 825
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.05410139262676239,
+      "eval_mean_token_accuracy": 0.9851650663324305,
+      "eval_num_tokens": 4708360.0,
+      "eval_runtime": 16.0082,
+      "eval_samples_per_second": 23.051,
+      "eval_steps_per_second": 11.557,
+      "step": 830
+    },
+    {
+      "epoch": 2.048280024140012,
+      "grad_norm": 0.10252567380666733,
+      "learning_rate": 0.00042545716153033746,
+      "loss": 0.0495,
+      "mean_token_accuracy": 0.9853065284257082,
+      "num_tokens": 4838468.0,
+      "step": 850
+    },
+    {
+      "epoch": 2.1086300543150274,
+      "grad_norm": 0.04914547875523567,
+      "learning_rate": 0.0004200328809669296,
+      "loss": 0.0313,
+      "mean_token_accuracy": 0.9909292554855347,
+      "num_tokens": 4972061.0,
+      "step": 875
+    },
+    {
+      "epoch": 2.1689800844900424,
+      "grad_norm": 0.06335192173719406,
+      "learning_rate": 0.00041448121738789633,
+      "loss": 0.0449,
+      "mean_token_accuracy": 0.9870324164628983,
+      "num_tokens": 5123609.0,
+      "step": 900
+    },
+    {
+      "epoch": 2.2293301146650575,
+      "grad_norm": 0.09024782478809357,
+      "learning_rate": 0.0004088064859947051,
+      "loss": 0.0336,
+      "mean_token_accuracy": 0.9899903804063797,
+      "num_tokens": 5255900.0,
+      "step": 925
+    },
+    {
+      "epoch": 2.2896801448400725,
+      "grad_norm": 0.06487799435853958,
+      "learning_rate": 0.0004030130976470715,
+      "loss": 0.0471,
+      "mean_token_accuracy": 0.9861943638324737,
+      "num_tokens": 5408377.0,
+      "step": 950
+    },
+    {
+      "epoch": 2.3500301750150876,
+      "grad_norm": 0.03881136327981949,
+      "learning_rate": 0.00039710555543448267,
+      "loss": 0.033,
+      "mean_token_accuracy": 0.9898175239562989,
+      "num_tokens": 5540979.0,
+      "step": 975
+    },
+    {
+      "epoch": 2.4103802051901027,
+      "grad_norm": 0.05819237604737282,
+      "learning_rate": 0.0003910884511760325,
+      "loss": 0.0428,
+      "mean_token_accuracy": 0.9870308661460876,
+      "num_tokens": 5693030.0,
+      "step": 1000
+    },
+    {
+      "epoch": 2.4707302353651177,
+      "grad_norm": 0.06926289945840836,
+      "learning_rate": 0.00038496646185128854,
+      "loss": 0.0288,
+      "mean_token_accuracy": 0.9914705574512481,
+      "num_tokens": 5827027.0,
+      "step": 1025
+    },
+    {
+      "epoch": 2.5310802655401328,
+      "grad_norm": 0.09394887089729309,
+      "learning_rate": 0.000378744345964966,
+      "loss": 0.0439,
+      "mean_token_accuracy": 0.9866676324605942,
+      "num_tokens": 5975797.0,
+      "step": 1050
+    },
+    {
+      "epoch": 2.591430295715148,
+      "grad_norm": 0.07537297159433365,
+      "learning_rate": 0.0003724269398482333,
+      "loss": 0.0316,
+      "mean_token_accuracy": 0.9907770365476608,
+      "num_tokens": 6107036.0,
+      "step": 1075
+    },
+    {
+      "epoch": 2.651780325890163,
+      "grad_norm": 0.044363752007484436,
+      "learning_rate": 0.00036601915389952434,
+      "loss": 0.046,
+      "mean_token_accuracy": 0.9861960715055466,
+      "num_tokens": 6258873.0,
+      "step": 1100
+    },
+    {
+      "epoch": 2.712130356065178,
+      "grad_norm": 0.084761843085289,
+      "learning_rate": 0.00035952596876778076,
+      "loss": 0.031,
+      "mean_token_accuracy": 0.9905279046297073,
+      "num_tokens": 6392411.0,
+      "step": 1125
+    },
+    {
+      "epoch": 2.772480386240193,
+      "grad_norm": 0.05843805894255638,
+      "learning_rate": 0.00035295243148108894,
+      "loss": 0.0441,
+      "mean_token_accuracy": 0.9872340881824493,
+      "num_tokens": 6542051.0,
+      "step": 1150
+    },
+    {
+      "epoch": 2.832830416415208,
+      "grad_norm": 0.05149897560477257,
+      "learning_rate": 0.00034630365152372165,
+      "loss": 0.0286,
+      "mean_token_accuracy": 0.9911447340250015,
+      "num_tokens": 6674951.0,
+      "step": 1175
+    },
+    {
+      "epoch": 2.8931804465902236,
+      "grad_norm": 0.04212498292326927,
+      "learning_rate": 0.00033958479686463464,
+      "loss": 0.042,
+      "mean_token_accuracy": 0.9873944985866546,
+      "num_tokens": 6827063.0,
+      "step": 1200
+    },
+    {
+      "epoch": 2.9535304767652386,
+      "grad_norm": 0.02952578291296959,
+      "learning_rate": 0.00033280108994050315,
+      "loss": 0.0288,
+      "mean_token_accuracy": 0.9914515954256058,
+      "num_tokens": 6960300.0,
+      "step": 1225
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.045313552021980286,
+      "eval_mean_token_accuracy": 0.9875944820610253,
+      "eval_num_tokens": 7062540.0,
+      "eval_runtime": 15.9787,
+      "eval_samples_per_second": 23.093,
+      "eval_steps_per_second": 11.578,
+      "step": 1245
+    }
+  ],
+  "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": 3.0685210928193024e+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 sha256:3aca81315bde14ece69eb9f4dddd5f4b7bb5393ac99e6a78ae025523ceef1a1d
+size 6097