Upload checkpoint-374 adapter weights

.gitattributes

@@ -54,3 +54,4 @@ checkpoint-306/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-323/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-340/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-357/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-374/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-374/README.md

@@ -0,0 +1,208 @@
+---
+base_model: Qwen/Qwen2.5-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-7B-Instruct
+- llama-factory
+- lora
+- transformers
+---
+
+# 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 0.18.1

checkpoint-374/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "v_proj",
+    "o_proj",
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-374/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04cb8ef38d6b36008b073fb750fe9fae71ece203a3f590c1e2b5479552245e16
+size 80792096

checkpoint-374/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
+}

checkpoint-374/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 %}

checkpoint-374/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "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": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-374/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

checkpoint-374/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "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": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-374/trainer_state.json

@@ -0,0 +1,469 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.964285714285714,
+  "eval_steps": 17,
+  "global_step": 374,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.21428571428571427,
+      "grad_norm": 0.4302244484424591,
+      "learning_rate": 2.368421052631579e-06,
+      "loss": 1.5939,
+      "step": 10
+    },
+    {
+      "epoch": 0.36428571428571427,
+      "eval_loss": 0.9226195812225342,
+      "eval_runtime": 10.7221,
+      "eval_samples_per_second": 1.586,
+      "eval_steps_per_second": 0.187,
+      "step": 17
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 0.44374313950538635,
+      "learning_rate": 5e-06,
+      "loss": 1.5772,
+      "step": 20
+    },
+    {
+      "epoch": 0.6428571428571429,
+      "grad_norm": 0.5126215219497681,
+      "learning_rate": 7.631578947368423e-06,
+      "loss": 1.5939,
+      "step": 30
+    },
+    {
+      "epoch": 0.7285714285714285,
+      "eval_loss": 0.9095432758331299,
+      "eval_runtime": 5.9631,
+      "eval_samples_per_second": 2.851,
+      "eval_steps_per_second": 0.335,
+      "step": 34
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.5730246901512146,
+      "learning_rate": 9.999784025127187e-06,
+      "loss": 1.5892,
+      "step": 40
+    },
+    {
+      "epoch": 1.0642857142857143,
+      "grad_norm": 0.5065149664878845,
+      "learning_rate": 9.973889609034945e-06,
+      "loss": 1.4804,
+      "step": 50
+    },
+    {
+      "epoch": 1.0857142857142856,
+      "eval_loss": 0.8597972393035889,
+      "eval_runtime": 5.94,
+      "eval_samples_per_second": 2.862,
+      "eval_steps_per_second": 0.337,
+      "step": 51
+    },
+    {
+      "epoch": 1.2785714285714285,
+      "grad_norm": 0.36051928997039795,
+      "learning_rate": 9.905056402479933e-06,
+      "loss": 1.3989,
+      "step": 60
+    },
+    {
+      "epoch": 1.45,
+      "eval_loss": 0.8285245895385742,
+      "eval_runtime": 5.9301,
+      "eval_samples_per_second": 2.867,
+      "eval_steps_per_second": 0.337,
+      "step": 68
+    },
+    {
+      "epoch": 1.4928571428571429,
+      "grad_norm": 0.34493935108184814,
+      "learning_rate": 9.79387863148353e-06,
+      "loss": 1.3489,
+      "step": 70
+    },
+    {
+      "epoch": 1.7071428571428573,
+      "grad_norm": 0.3500029146671295,
+      "learning_rate": 9.641316075893731e-06,
+      "loss": 1.3442,
+      "step": 80
+    },
+    {
+      "epoch": 1.8142857142857143,
+      "eval_loss": 0.817111611366272,
+      "eval_runtime": 5.93,
+      "eval_samples_per_second": 2.867,
+      "eval_steps_per_second": 0.337,
+      "step": 85
+    },
+    {
+      "epoch": 1.9214285714285713,
+      "grad_norm": 0.33438020944595337,
+      "learning_rate": 9.448685783759825e-06,
+      "loss": 1.3746,
+      "step": 90
+    },
+    {
+      "epoch": 2.1285714285714286,
+      "grad_norm": 0.4562329947948456,
+      "learning_rate": 9.217650701468016e-06,
+      "loss": 1.3922,
+      "step": 100
+    },
+    {
+      "epoch": 2.1714285714285713,
+      "eval_loss": 0.8083997964859009,
+      "eval_runtime": 5.9297,
+      "eval_samples_per_second": 2.867,
+      "eval_steps_per_second": 0.337,
+      "step": 102
+    },
+    {
+      "epoch": 2.342857142857143,
+      "grad_norm": 0.49083271622657776,
+      "learning_rate": 8.95020531779225e-06,
+      "loss": 1.2936,
+      "step": 110
+    },
+    {
+      "epoch": 2.5357142857142856,
+      "eval_loss": 0.8002251982688904,
+      "eval_runtime": 5.9306,
+      "eval_samples_per_second": 2.866,
+      "eval_steps_per_second": 0.337,
+      "step": 119
+    },
+    {
+      "epoch": 2.557142857142857,
+      "grad_norm": 0.4263967275619507,
+      "learning_rate": 8.64865844579284e-06,
+      "loss": 1.2567,
+      "step": 120
+    },
+    {
+      "epoch": 2.7714285714285714,
+      "grad_norm": 0.19324518740177155,
+      "learning_rate": 8.315613291203977e-06,
+      "loss": 1.1387,
+      "step": 130
+    },
+    {
+      "epoch": 2.9,
+      "eval_loss": 0.7924517393112183,
+      "eval_runtime": 5.9418,
+      "eval_samples_per_second": 2.861,
+      "eval_steps_per_second": 0.337,
+      "step": 136
+    },
+    {
+      "epoch": 2.9857142857142858,
+      "grad_norm": 0.31606367230415344,
+      "learning_rate": 7.953944979376567e-06,
+      "loss": 1.1648,
+      "step": 140
+    },
+    {
+      "epoch": 3.192857142857143,
+      "grad_norm": 0.3288721740245819,
+      "learning_rate": 7.566775734782656e-06,
+      "loss": 1.1698,
+      "step": 150
+    },
+    {
+      "epoch": 3.257142857142857,
+      "eval_loss": 0.7860405445098877,
+      "eval_runtime": 5.9335,
+      "eval_samples_per_second": 2.865,
+      "eval_steps_per_second": 0.337,
+      "step": 153
+    },
+    {
+      "epoch": 3.407142857142857,
+      "grad_norm": 0.4146527945995331,
+      "learning_rate": 7.157447927352821e-06,
+      "loss": 1.1983,
+      "step": 160
+    },
+    {
+      "epoch": 3.6214285714285714,
+      "grad_norm": 0.3805901110172272,
+      "learning_rate": 6.729495218333157e-06,
+      "loss": 1.1235,
+      "step": 170
+    },
+    {
+      "epoch": 3.6214285714285714,
+      "eval_loss": 0.7802702188491821,
+      "eval_runtime": 5.9232,
+      "eval_samples_per_second": 2.87,
+      "eval_steps_per_second": 0.338,
+      "step": 170
+    },
+    {
+      "epoch": 3.835714285714286,
+      "grad_norm": 0.29032182693481445,
+      "learning_rate": 6.286612054755056e-06,
+      "loss": 1.0361,
+      "step": 180
+    },
+    {
+      "epoch": 3.9857142857142858,
+      "eval_loss": 0.7751054763793945,
+      "eval_runtime": 5.9366,
+      "eval_samples_per_second": 2.864,
+      "eval_steps_per_second": 0.337,
+      "step": 187
+    },
+    {
+      "epoch": 4.042857142857143,
+      "grad_norm": 0.3270094692707062,
+      "learning_rate": 5.83262177586711e-06,
+      "loss": 1.1055,
+      "step": 190
+    },
+    {
+      "epoch": 4.257142857142857,
+      "grad_norm": 0.42061907052993774,
+      "learning_rate": 5.371443606861186e-06,
+      "loss": 1.0718,
+      "step": 200
+    },
+    {
+      "epoch": 4.3428571428571425,
+      "eval_loss": 0.7703974843025208,
+      "eval_runtime": 5.957,
+      "eval_samples_per_second": 2.854,
+      "eval_steps_per_second": 0.336,
+      "step": 204
+    },
+    {
+      "epoch": 4.4714285714285715,
+      "grad_norm": 0.27980759739875793,
+      "learning_rate": 4.90705882483056e-06,
+      "loss": 1.0514,
+      "step": 210
+    },
+    {
+      "epoch": 4.685714285714286,
+      "grad_norm": 0.41214802861213684,
+      "learning_rate": 4.443476389043955e-06,
+      "loss": 1.0717,
+      "step": 220
+    },
+    {
+      "epoch": 4.707142857142857,
+      "eval_loss": 0.766619086265564,
+      "eval_runtime": 5.9563,
+      "eval_samples_per_second": 2.854,
+      "eval_steps_per_second": 0.336,
+      "step": 221
+    },
+    {
+      "epoch": 4.9,
+      "grad_norm": 0.6345829367637634,
+      "learning_rate": 3.984698332243767e-06,
+      "loss": 1.0294,
+      "step": 230
+    },
+    {
+      "epoch": 5.064285714285714,
+      "eval_loss": 0.7633779048919678,
+      "eval_runtime": 5.9633,
+      "eval_samples_per_second": 2.851,
+      "eval_steps_per_second": 0.335,
+      "step": 238
+    },
+    {
+      "epoch": 5.107142857142857,
+      "grad_norm": 0.4971616268157959,
+      "learning_rate": 3.534685211739935e-06,
+      "loss": 1.005,
+      "step": 240
+    },
+    {
+      "epoch": 5.321428571428571,
+      "grad_norm": 0.49103766679763794,
+      "learning_rate": 3.0973219185545077e-06,
+      "loss": 1.0395,
+      "step": 250
+    },
+    {
+      "epoch": 5.428571428571429,
+      "eval_loss": 0.7608006596565247,
+      "eval_runtime": 5.9216,
+      "eval_samples_per_second": 2.871,
+      "eval_steps_per_second": 0.338,
+      "step": 255
+    },
+    {
+      "epoch": 5.535714285714286,
+      "grad_norm": 0.43664228916168213,
+      "learning_rate": 2.6763841397811576e-06,
+      "loss": 1.0123,
+      "step": 260
+    },
+    {
+      "epoch": 5.75,
+      "grad_norm": 0.3548373281955719,
+      "learning_rate": 2.275505763684674e-06,
+      "loss": 0.9842,
+      "step": 270
+    },
+    {
+      "epoch": 5.792857142857143,
+      "eval_loss": 0.758660078048706,
+      "eval_runtime": 5.931,
+      "eval_samples_per_second": 2.866,
+      "eval_steps_per_second": 0.337,
+      "step": 272
+    },
+    {
+      "epoch": 5.964285714285714,
+      "grad_norm": 0.5326474905014038,
+      "learning_rate": 1.8981475089269641e-06,
+      "loss": 1.0187,
+      "step": 280
+    },
+    {
+      "epoch": 6.15,
+      "eval_loss": 0.7571306824684143,
+      "eval_runtime": 5.9279,
+      "eval_samples_per_second": 2.868,
+      "eval_steps_per_second": 0.337,
+      "step": 289
+    },
+    {
+      "epoch": 6.171428571428572,
+      "grad_norm": 0.4667930006980896,
+      "learning_rate": 1.547567048738452e-06,
+      "loss": 1.0115,
+      "step": 290
+    },
+    {
+      "epoch": 6.385714285714286,
+      "grad_norm": 0.3626402020454407,
+      "learning_rate": 1.2267908879480822e-06,
+      "loss": 0.9602,
+      "step": 300
+    },
+    {
+      "epoch": 6.514285714285714,
+      "eval_loss": 0.7561742663383484,
+      "eval_runtime": 5.9392,
+      "eval_samples_per_second": 2.862,
+      "eval_steps_per_second": 0.337,
+      "step": 306
+    },
+    {
+      "epoch": 6.6,
+      "grad_norm": 0.5340692400932312,
+      "learning_rate": 9.385882356530179e-07,
+      "loss": 0.9985,
+      "step": 310
+    },
+    {
+      "epoch": 6.814285714285714,
+      "grad_norm": 0.38837724924087524,
+      "learning_rate": 6.854470990810907e-07,
+      "loss": 0.9836,
+      "step": 320
+    },
+    {
+      "epoch": 6.878571428571428,
+      "eval_loss": 0.7553987503051758,
+      "eval_runtime": 5.9341,
+      "eval_samples_per_second": 2.865,
+      "eval_steps_per_second": 0.337,
+      "step": 323
+    },
+    {
+      "epoch": 7.021428571428571,
+      "grad_norm": 0.36160409450531006,
+      "learning_rate": 4.695528050238368e-07,
+      "loss": 0.968,
+      "step": 330
+    },
+    {
+      "epoch": 7.235714285714286,
+      "grad_norm": 0.40136322379112244,
+      "learning_rate": 2.927691342611505e-07,
+      "loss": 1.0053,
+      "step": 340
+    },
+    {
+      "epoch": 7.235714285714286,
+      "eval_loss": 0.7550451755523682,
+      "eval_runtime": 5.9322,
+      "eval_samples_per_second": 2.866,
+      "eval_steps_per_second": 0.337,
+      "step": 340
+    },
+    {
+      "epoch": 7.45,
+      "grad_norm": 0.4293939471244812,
+      "learning_rate": 1.5662223184102876e-07,
+      "loss": 0.9853,
+      "step": 350
+    },
+    {
+      "epoch": 7.6,
+      "eval_loss": 0.7549826502799988,
+      "eval_runtime": 5.9317,
+      "eval_samples_per_second": 2.866,
+      "eval_steps_per_second": 0.337,
+      "step": 357
+    },
+    {
+      "epoch": 7.664285714285715,
+      "grad_norm": 0.579329788684845,
+      "learning_rate": 6.22874321143907e-08,
+      "loss": 0.9806,
+      "step": 360
+    },
+    {
+      "epoch": 7.878571428571428,
+      "grad_norm": 0.45310232043266296,
+      "learning_rate": 1.0579112262316116e-08,
+      "loss": 0.9663,
+      "step": 370
+    },
+    {
+      "epoch": 7.964285714285714,
+      "eval_loss": 0.7548511624336243,
+      "eval_runtime": 5.9392,
+      "eval_samples_per_second": 2.862,
+      "eval_steps_per_second": 0.337,
+      "step": 374
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 376,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 17,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.1088627194454344e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-374/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca2eb6e328fb52c1d91f02ce5b6e83e547d214918f2f7ebc274b00c49ea7c9e4
+size 6161