Training in progress, step 450, checkpoint

checkpoint-450/README.md

@@ -0,0 +1,208 @@
+---
+base_model: meta-llama/Llama-3.2-3B-Instruct
+library_name: peft
+tags:
+- base_model:adapter:meta-llama/Llama-3.2-3B-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 0.19.1

checkpoint-450/adapter_config.json

@@ -0,0 +1,51 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "LlamaForCausalLM",
+    "parent_library": "transformers.models.llama.modeling_llama"
+  },
+  "base_model_name_or_path": "meta-llama/Llama-3.2-3B-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": 0.1,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "o_proj",
+    "k_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": null,
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-450/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b1fd4034c6c8d5d5fc57ad560bd28f85f0e066685a0547d0491fa6ff0b89e29
+size 97307936

checkpoint-450/chat_template.jinja

@@ -0,0 +1,93 @@
+{{- bos_token }}
+{%- if custom_tools is defined %}
+    {%- set tools = custom_tools %}
+{%- endif %}
+{%- if not tools_in_user_message is defined %}
+    {%- set tools_in_user_message = true %}
+{%- endif %}
+{%- if not date_string is defined %}
+    {%- if strftime_now is defined %}
+        {%- set date_string = strftime_now("%d %b %Y") %}
+    {%- else %}
+        {%- set date_string = "26 Jul 2024" %}
+    {%- endif %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+
+{#- This block extracts the system message, so we can slot it into the right place. #}
+{%- if messages[0]['role'] == 'system' %}
+    {%- set system_message = messages[0]['content']|trim %}
+    {%- set messages = messages[1:] %}
+{%- else %}
+    {%- set system_message = "" %}
+{%- endif %}
+
+{#- System message #}
+{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
+{%- if tools is not none %}
+    {{- "Environment: ipython\n" }}
+{%- endif %}
+{{- "Cutting Knowledge Date: December 2023\n" }}
+{{- "Today Date: " + date_string + "\n\n" }}
+{%- if tools is not none and not tools_in_user_message %}
+    {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+{%- endif %}
+{{- system_message }}
+{{- "<|eot_id|>" }}
+
+{#- Custom tools are passed in a user message with some extra guidance #}
+{%- if tools_in_user_message and not tools is none %}
+    {#- Extract the first user message so we can plug it in here #}
+    {%- if messages | length != 0 %}
+        {%- set first_user_message = messages[0]['content']|trim %}
+        {%- set messages = messages[1:] %}
+    {%- else %}
+        {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
+{%- endif %}
+    {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
+    {{- "Given the following functions, please respond with a JSON for a function call " }}
+    {{- "with its proper arguments that best answers the given prompt.\n\n" }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+    {{- first_user_message + "<|eot_id|>"}}
+{%- endif %}
+
+{%- for message in messages %}
+    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
+        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
+    {%- elif 'tool_calls' in message %}
+        {%- if not message.tool_calls|length == 1 %}
+            {{- raise_exception("This model only supports single tool-calls at once!") }}
+        {%- endif %}
+        {%- set tool_call = message.tool_calls[0].function %}
+        {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
+        {{- '{"name": "' + tool_call.name + '", ' }}
+        {{- '"parameters": ' }}
+        {{- tool_call.arguments | tojson }}
+        {{- "}" }}
+        {{- "<|eot_id|>" }}
+    {%- elif message.role == "tool" or message.role == "ipython" %}
+        {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
+        {%- if message.content is mapping or message.content is iterable %}
+            {{- message.content | tojson }}
+        {%- else %}
+            {{- message.content }}
+        {%- endif %}
+        {{- "<|eot_id|>" }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
+{%- endif %}

checkpoint-450/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3bd74662c46246122aad32309d503550cc04e1262d8c1250e3ed17aac2b1485
+size 99245189

checkpoint-450/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a44d14a601586275bc49f3c3b1fa52e14ef09615b1113424426f564878a43f0
+size 14773

checkpoint-450/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db657b5435ef5e50b8283afa9c1096272e47b58c830c703910449857b6625d48
+size 1465

checkpoint-450/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ad537f502cb4887e79ec677aadf59fc5601551711efcda3826ad17d4541e422
+size 17209467

checkpoint-450/tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "is_local": false,
+  "map_device": "auto",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|eot_id|>",
+  "tokenizer_class": "TokenizersBackend"
+}

checkpoint-450/trainer_state.json

@@ -0,0 +1,979 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.4096080910240203,
+  "eval_steps": 10,
+  "global_step": 450,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.116106641292572,
+      "epoch": 0.07585335018963338,
+      "grad_norm": 1.4921875,
+      "learning_rate": 5.6250000000000005e-05,
+      "loss": 2.914295959472656,
+      "mean_token_accuracy": 0.5410080701112747,
+      "num_tokens": 36823.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.07585335018963338,
+      "eval_entropy": 2.552819073200226,
+      "eval_loss": 2.6676909923553467,
+      "eval_mean_token_accuracy": 0.5321294479072094,
+      "eval_num_tokens": 36823.0,
+      "eval_runtime": 14.7674,
+      "eval_samples_per_second": 0.542,
+      "eval_steps_per_second": 0.542,
+      "step": 10
+    },
+    {
+      "entropy": 1.9473248382409414,
+      "epoch": 0.15170670037926676,
+      "grad_norm": 0.87890625,
+      "learning_rate": 9.999152908979117e-05,
+      "loss": 1.9090084075927733,
+      "mean_token_accuracy": 0.6584314892689387,
+      "num_tokens": 65881.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.15170670037926676,
+      "eval_entropy": 1.8724936991930008,
+      "eval_loss": 1.9479429721832275,
+      "eval_mean_token_accuracy": 0.6351580396294594,
+      "eval_num_tokens": 65881.0,
+      "eval_runtime": 14.8467,
+      "eval_samples_per_second": 0.539,
+      "eval_steps_per_second": 0.539,
+      "step": 20
+    },
+    {
+      "entropy": 1.5991886417071024,
+      "epoch": 0.22756005056890014,
+      "grad_norm": 1.4765625,
+      "learning_rate": 9.984101496455829e-05,
+      "loss": 1.5578083038330077,
+      "mean_token_accuracy": 0.7192381203174592,
+      "num_tokens": 89977.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.22756005056890014,
+      "eval_entropy": 1.6338046044111252,
+      "eval_loss": 1.694503903388977,
+      "eval_mean_token_accuracy": 0.6637412160634995,
+      "eval_num_tokens": 89977.0,
+      "eval_runtime": 14.8298,
+      "eval_samples_per_second": 0.539,
+      "eval_steps_per_second": 0.539,
+      "step": 30
+    },
+    {
+      "entropy": 1.6071883370478948,
+      "epoch": 0.3034134007585335,
+      "grad_norm": 0.71484375,
+      "learning_rate": 9.950291051311487e-05,
+      "loss": 1.6236091613769532,
+      "mean_token_accuracy": 0.6928597639004389,
+      "num_tokens": 122672.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.3034134007585335,
+      "eval_entropy": 1.5961390733718872,
+      "eval_loss": 1.5684512853622437,
+      "eval_mean_token_accuracy": 0.6787843257188797,
+      "eval_num_tokens": 122672.0,
+      "eval_runtime": 14.7973,
+      "eval_samples_per_second": 0.541,
+      "eval_steps_per_second": 0.541,
+      "step": 40
+    },
+    {
+      "entropy": 1.3055346330006918,
+      "epoch": 0.37926675094816686,
+      "grad_norm": 0.9453125,
+      "learning_rate": 9.897848828427202e-05,
+      "loss": 1.2936326026916505,
+      "mean_token_accuracy": 0.7341216415166855,
+      "num_tokens": 152626.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.37926675094816686,
+      "eval_entropy": 1.4331321269273758,
+      "eval_loss": 1.410101294517517,
+      "eval_mean_token_accuracy": 0.7011745795607567,
+      "eval_num_tokens": 152626.0,
+      "eval_runtime": 14.7788,
+      "eval_samples_per_second": 0.541,
+      "eval_steps_per_second": 0.541,
+      "step": 50
+    },
+    {
+      "entropy": 1.11328877111276,
+      "epoch": 0.45512010113780027,
+      "grad_norm": 0.82421875,
+      "learning_rate": 9.826972208488447e-05,
+      "loss": 1.0861340522766114,
+      "mean_token_accuracy": 0.766385022799174,
+      "num_tokens": 178156.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.45512010113780027,
+      "eval_entropy": 1.3111007660627365,
+      "eval_loss": 1.2872167825698853,
+      "eval_mean_token_accuracy": 0.7273842021822929,
+      "eval_num_tokens": 178156.0,
+      "eval_runtime": 14.7936,
+      "eval_samples_per_second": 0.541,
+      "eval_steps_per_second": 0.541,
+      "step": 60
+    },
+    {
+      "entropy": 1.3175925850868224,
+      "epoch": 0.5309734513274337,
+      "grad_norm": 0.625,
+      "learning_rate": 9.737927955088705e-05,
+      "loss": 1.2941490173339845,
+      "mean_token_accuracy": 0.7372792253891627,
+      "num_tokens": 209487.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.5309734513274337,
+      "eval_entropy": 1.2998864650726318,
+      "eval_loss": 1.2285542488098145,
+      "eval_mean_token_accuracy": 0.7347995787858963,
+      "eval_num_tokens": 209487.0,
+      "eval_runtime": 14.8531,
+      "eval_samples_per_second": 0.539,
+      "eval_steps_per_second": 0.539,
+      "step": 70
+    },
+    {
+      "entropy": 1.1506140291690827,
+      "epoch": 0.606826801517067,
+      "grad_norm": 0.828125,
+      "learning_rate": 9.631051210691558e-05,
+      "loss": 1.134031391143799,
+      "mean_token_accuracy": 0.760423094034195,
+      "num_tokens": 239555.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.606826801517067,
+      "eval_entropy": 1.2010595947504044,
+      "eval_loss": 1.1256182193756104,
+      "eval_mean_token_accuracy": 0.7571268677711487,
+      "eval_num_tokens": 239555.0,
+      "eval_runtime": 15.6324,
+      "eval_samples_per_second": 0.512,
+      "eval_steps_per_second": 0.512,
+      "step": 80
+    },
+    {
+      "entropy": 0.9923018544912339,
+      "epoch": 0.6826801517067004,
+      "grad_norm": 1.0078125,
+      "learning_rate": 9.50674423523011e-05,
+      "loss": 0.9289534568786622,
+      "mean_token_accuracy": 0.7951417863368988,
+      "num_tokens": 265306.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.6826801517067004,
+      "eval_entropy": 1.0992150977253914,
+      "eval_loss": 1.0379621982574463,
+      "eval_mean_token_accuracy": 0.7777058333158493,
+      "eval_num_tokens": 265306.0,
+      "eval_runtime": 15.7361,
+      "eval_samples_per_second": 0.508,
+      "eval_steps_per_second": 0.508,
+      "step": 90
+    },
+    {
+      "entropy": 1.0375868437190852,
+      "epoch": 0.7585335018963337,
+      "grad_norm": 0.609375,
+      "learning_rate": 9.365474892091451e-05,
+      "loss": 1.0106287956237794,
+      "mean_token_accuracy": 0.7893585612376531,
+      "num_tokens": 292993.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.7585335018963337,
+      "eval_entropy": 1.072925515472889,
+      "eval_loss": 1.0008392333984375,
+      "eval_mean_token_accuracy": 0.7823155149817467,
+      "eval_num_tokens": 292993.0,
+      "eval_runtime": 15.602,
+      "eval_samples_per_second": 0.513,
+      "eval_steps_per_second": 0.513,
+      "step": 100
+    },
+    {
+      "entropy": 1.0960371459523837,
+      "epoch": 0.8343868520859671,
+      "grad_norm": 0.7890625,
+      "learning_rate": 9.207774887184493e-05,
+      "loss": 1.0759888648986817,
+      "mean_token_accuracy": 0.7768891970316569,
+      "num_tokens": 324472.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.8343868520859671,
+      "eval_entropy": 0.9983096048235893,
+      "eval_loss": 0.965083658695221,
+      "eval_mean_token_accuracy": 0.7886351868510246,
+      "eval_num_tokens": 324472.0,
+      "eval_runtime": 15.6552,
+      "eval_samples_per_second": 0.511,
+      "eval_steps_per_second": 0.511,
+      "step": 110
+    },
+    {
+      "entropy": 0.8683194468418757,
+      "epoch": 0.9102402022756005,
+      "grad_norm": 0.859375,
+      "learning_rate": 9.034237767718997e-05,
+      "loss": 0.839997386932373,
+      "mean_token_accuracy": 0.8105442355076472,
+      "num_tokens": 350423.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.9102402022756005,
+      "eval_entropy": 0.9654994606971741,
+      "eval_loss": 0.9282829761505127,
+      "eval_mean_token_accuracy": 0.8008697852492332,
+      "eval_num_tokens": 350423.0,
+      "eval_runtime": 15.7206,
+      "eval_samples_per_second": 0.509,
+      "eval_steps_per_second": 0.509,
+      "step": 120
+    },
+    {
+      "entropy": 0.8921634897589683,
+      "epoch": 0.9860935524652339,
+      "grad_norm": 0.66015625,
+      "learning_rate": 8.8455166882279e-05,
+      "loss": 0.8713577270507813,
+      "mean_token_accuracy": 0.805043849349022,
+      "num_tokens": 374888.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.9860935524652339,
+      "eval_entropy": 0.925379566848278,
+      "eval_loss": 0.9301751852035522,
+      "eval_mean_token_accuracy": 0.8013799041509628,
+      "eval_num_tokens": 374888.0,
+      "eval_runtime": 15.7302,
+      "eval_samples_per_second": 0.509,
+      "eval_steps_per_second": 0.509,
+      "step": 130
+    },
+    {
+      "entropy": 1.1222206217757726,
+      "epoch": 1.0606826801517066,
+      "grad_norm": 0.65625,
+      "learning_rate": 8.642321952241126e-05,
+      "loss": 1.0791142463684082,
+      "mean_token_accuracy": 0.779176946413719,
+      "num_tokens": 408924.0,
+      "step": 140
+    },
+    {
+      "epoch": 1.0606826801517066,
+      "eval_entropy": 0.9091628380119801,
+      "eval_loss": 0.9220267534255981,
+      "eval_mean_token_accuracy": 0.8066961765289307,
+      "eval_num_tokens": 408924.0,
+      "eval_runtime": 15.6764,
+      "eval_samples_per_second": 0.51,
+      "eval_steps_per_second": 0.51,
+      "step": 140
+    },
+    {
+      "entropy": 0.7742048308253289,
+      "epoch": 1.13653603034134,
+      "grad_norm": 0.74609375,
+      "learning_rate": 8.425418338863502e-05,
+      "loss": 0.7456035137176513,
+      "mean_token_accuracy": 0.8373923808336258,
+      "num_tokens": 437721.0,
+      "step": 150
+    },
+    {
+      "epoch": 1.13653603034134,
+      "eval_entropy": 0.8886274918913841,
+      "eval_loss": 0.8979178071022034,
+      "eval_mean_token_accuracy": 0.8057176694273949,
+      "eval_num_tokens": 437721.0,
+      "eval_runtime": 15.6592,
+      "eval_samples_per_second": 0.511,
+      "eval_steps_per_second": 0.511,
+      "step": 150
+    },
+    {
+      "entropy": 0.7018384074171384,
+      "epoch": 1.2123893805309733,
+      "grad_norm": 0.6484375,
+      "learning_rate": 8.195622224318879e-05,
+      "loss": 0.6607318878173828,
+      "mean_token_accuracy": 0.8447161267201105,
+      "num_tokens": 462626.0,
+      "step": 160
+    },
+    {
+      "epoch": 1.2123893805309733,
+      "eval_entropy": 0.8706388957798481,
+      "eval_loss": 0.9000320434570312,
+      "eval_mean_token_accuracy": 0.8101153001189232,
+      "eval_num_tokens": 462626.0,
+      "eval_runtime": 15.6367,
+      "eval_samples_per_second": 0.512,
+      "eval_steps_per_second": 0.512,
+      "step": 160
+    },
+    {
+      "entropy": 0.9497246752182643,
+      "epoch": 1.2882427307206068,
+      "grad_norm": 0.64453125,
+      "learning_rate": 7.953798509294372e-05,
+      "loss": 0.9422295570373536,
+      "mean_token_accuracy": 0.8010553220907847,
+      "num_tokens": 492653.0,
+      "step": 170
+    },
+    {
+      "epoch": 1.2882427307206068,
+      "eval_entropy": 0.9001824222505093,
+      "eval_loss": 0.9093658924102783,
+      "eval_mean_token_accuracy": 0.8088075593113899,
+      "eval_num_tokens": 492653.0,
+      "eval_runtime": 15.6666,
+      "eval_samples_per_second": 0.511,
+      "eval_steps_per_second": 0.511,
+      "step": 170
+    },
+    {
+      "entropy": 0.8425602326790492,
+      "epoch": 1.3640960809102403,
+      "grad_norm": 0.609375,
+      "learning_rate": 7.700857363649465e-05,
+      "loss": 0.8109879493713379,
+      "mean_token_accuracy": 0.8285688976446788,
+      "num_tokens": 523035.0,
+      "step": 180
+    },
+    {
+      "epoch": 1.3640960809102403,
+      "eval_entropy": 0.8594749756157398,
+      "eval_loss": 0.8847923278808594,
+      "eval_mean_token_accuracy": 0.8098366558551788,
+      "eval_num_tokens": 523035.0,
+      "eval_runtime": 15.7401,
+      "eval_samples_per_second": 0.508,
+      "eval_steps_per_second": 0.508,
+      "step": 180
+    },
+    {
+      "entropy": 0.7103817813098431,
+      "epoch": 1.4399494310998735,
+      "grad_norm": 0.625,
+      "learning_rate": 7.43775080074218e-05,
+      "loss": 0.6827019214630127,
+      "mean_token_accuracy": 0.8422260383764902,
+      "num_tokens": 548885.0,
+      "step": 190
+    },
+    {
+      "epoch": 1.4399494310998735,
+      "eval_entropy": 0.8456171080470085,
+      "eval_loss": 0.8787115812301636,
+      "eval_mean_token_accuracy": 0.8125583752989769,
+      "eval_num_tokens": 548885.0,
+      "eval_runtime": 15.8473,
+      "eval_samples_per_second": 0.505,
+      "eval_steps_per_second": 0.505,
+      "step": 190
+    },
+    {
+      "entropy": 0.9479823822776476,
+      "epoch": 1.515802781289507,
+      "grad_norm": 0.734375,
+      "learning_rate": 7.16546909426576e-05,
+      "loss": 0.949166202545166,
+      "mean_token_accuracy": 0.7941406567891439,
+      "num_tokens": 577576.0,
+      "step": 200
+    },
+    {
+      "epoch": 1.515802781289507,
+      "eval_entropy": 0.8673977516591549,
+      "eval_loss": 0.8828094005584717,
+      "eval_mean_token_accuracy": 0.8098664358258247,
+      "eval_num_tokens": 577576.0,
+      "eval_runtime": 15.5839,
+      "eval_samples_per_second": 0.513,
+      "eval_steps_per_second": 0.513,
+      "step": 200
+    },
+    {
+      "entropy": 1.0111428305506707,
+      "epoch": 1.5916561314791404,
+      "grad_norm": 0.7265625,
+      "learning_rate": 6.885037051082091e-05,
+      "loss": 0.9710953712463379,
+      "mean_token_accuracy": 0.7993101666371027,
+      "num_tokens": 609960.0,
+      "step": 210
+    },
+    {
+      "epoch": 1.5916561314791404,
+      "eval_entropy": 0.856759961694479,
+      "eval_loss": 0.8776929378509521,
+      "eval_mean_token_accuracy": 0.8108815997838974,
+      "eval_num_tokens": 609960.0,
+      "eval_runtime": 15.6851,
+      "eval_samples_per_second": 0.51,
+      "eval_steps_per_second": 0.51,
+      "step": 210
+    },
+    {
+      "entropy": 0.6799834683537483,
+      "epoch": 1.6675094816687737,
+      "grad_norm": 0.7109375,
+      "learning_rate": 6.597510154080078e-05,
+      "loss": 0.6525429248809814,
+      "mean_token_accuracy": 0.8495604753494262,
+      "num_tokens": 636497.0,
+      "step": 220
+    },
+    {
+      "epoch": 1.6675094816687737,
+      "eval_entropy": 0.8356063477694988,
+      "eval_loss": 0.8647487759590149,
+      "eval_mean_token_accuracy": 0.8143020421266556,
+      "eval_num_tokens": 636497.0,
+      "eval_runtime": 15.8097,
+      "eval_samples_per_second": 0.506,
+      "eval_steps_per_second": 0.506,
+      "step": 220
+    },
+    {
+      "entropy": 0.8049038504560788,
+      "epoch": 1.7433628318584071,
+      "grad_norm": 0.76171875,
+      "learning_rate": 6.303970589576378e-05,
+      "loss": 0.7930676937103271,
+      "mean_token_accuracy": 0.8221095313628515,
+      "num_tokens": 662413.0,
+      "step": 230
+    },
+    {
+      "epoch": 1.7433628318584071,
+      "eval_entropy": 0.8299686685204506,
+      "eval_loss": 0.8727775812149048,
+      "eval_mean_token_accuracy": 0.811675526201725,
+      "eval_num_tokens": 662413.0,
+      "eval_runtime": 15.6522,
+      "eval_samples_per_second": 0.511,
+      "eval_steps_per_second": 0.511,
+      "step": 230
+    },
+    {
+      "entropy": 1.0564268256227176,
+      "epoch": 1.8192161820480406,
+      "grad_norm": 0.578125,
+      "learning_rate": 6.00552317421046e-05,
+      "loss": 1.028653335571289,
+      "mean_token_accuracy": 0.790699835618337,
+      "num_tokens": 696264.0,
+      "step": 240
+    },
+    {
+      "epoch": 1.8192161820480406,
+      "eval_entropy": 0.8743892759084702,
+      "eval_loss": 0.8777971267700195,
+      "eval_mean_token_accuracy": 0.8138757944107056,
+      "eval_num_tokens": 696264.0,
+      "eval_runtime": 15.7076,
+      "eval_samples_per_second": 0.509,
+      "eval_steps_per_second": 0.509,
+      "step": 240
+    },
+    {
+      "entropy": 0.7534422516822815,
+      "epoch": 1.8950695322376738,
+      "grad_norm": 0.578125,
+      "learning_rate": 5.703291196664247e-05,
+      "loss": 0.7200803279876709,
+      "mean_token_accuracy": 0.841905082265536,
+      "num_tokens": 724679.0,
+      "step": 250
+    },
+    {
+      "epoch": 1.8950695322376738,
+      "eval_entropy": 0.8260066509246826,
+      "eval_loss": 0.8556550741195679,
+      "eval_mean_token_accuracy": 0.8176052942872047,
+      "eval_num_tokens": 724679.0,
+      "eval_runtime": 15.5383,
+      "eval_samples_per_second": 0.515,
+      "eval_steps_per_second": 0.515,
+      "step": 250
+    },
+    {
+      "entropy": 0.6556119327743848,
+      "epoch": 1.970922882427307,
+      "grad_norm": 0.90625,
+      "learning_rate": 5.39841218985715e-05,
+      "loss": 0.6228540897369385,
+      "mean_token_accuracy": 0.8531604041655858,
+      "num_tokens": 747645.0,
+      "step": 260
+    },
+    {
+      "epoch": 1.970922882427307,
+      "eval_entropy": 0.7757505960762501,
+      "eval_loss": 0.8425352573394775,
+      "eval_mean_token_accuracy": 0.8199078440666199,
+      "eval_num_tokens": 747645.0,
+      "eval_runtime": 15.5078,
+      "eval_samples_per_second": 0.516,
+      "eval_steps_per_second": 0.516,
+      "step": 260
+    },
+    {
+      "entropy": 0.9678725031977993,
+      "epoch": 2.04551201011378,
+      "grad_norm": 0.66015625,
+      "learning_rate": 5.0920336495290244e-05,
+      "loss": 0.9681121826171875,
+      "mean_token_accuracy": 0.7974661972563145,
+      "num_tokens": 782139.0,
+      "step": 270
+    },
+    {
+      "epoch": 2.04551201011378,
+      "eval_entropy": 0.80567791685462,
+      "eval_loss": 0.8436932563781738,
+      "eval_mean_token_accuracy": 0.8152260556817055,
+      "eval_num_tokens": 782139.0,
+      "eval_runtime": 15.8016,
+      "eval_samples_per_second": 0.506,
+      "eval_steps_per_second": 0.506,
+      "step": 270
+    },
+    {
+      "entropy": 0.8536191220084827,
+      "epoch": 2.1213653603034133,
+      "grad_norm": 0.5546875,
+      "learning_rate": 4.785308715325296e-05,
+      "loss": 0.7874747276306152,
+      "mean_token_accuracy": 0.8298017164071401,
+      "num_tokens": 813720.0,
+      "step": 280
+    },
+    {
+      "epoch": 2.1213653603034133,
+      "eval_entropy": 0.7856072653084993,
+      "eval_loss": 0.846335232257843,
+      "eval_mean_token_accuracy": 0.819606214761734,
+      "eval_num_tokens": 813720.0,
+      "eval_runtime": 15.6923,
+      "eval_samples_per_second": 0.51,
+      "eval_steps_per_second": 0.51,
+      "step": 280
+    },
+    {
+      "entropy": 0.6638347759842873,
+      "epoch": 2.197218710493047,
+      "grad_norm": 0.51953125,
+      "learning_rate": 4.479391830639727e-05,
+      "loss": 0.6242609977722168,
+      "mean_token_accuracy": 0.8523363530635834,
+      "num_tokens": 839868.0,
+      "step": 290
+    },
+    {
+      "epoch": 2.197218710493047,
+      "eval_entropy": 0.7590906117111444,
+      "eval_loss": 0.8308372497558594,
+      "eval_mean_token_accuracy": 0.8229880109429359,
+      "eval_num_tokens": 839868.0,
+      "eval_runtime": 15.7361,
+      "eval_samples_per_second": 0.508,
+      "eval_steps_per_second": 0.508,
+      "step": 290
+    },
+    {
+      "entropy": 0.7667473425467809,
+      "epoch": 2.27307206068268,
+      "grad_norm": 0.85546875,
+      "learning_rate": 4.1754343975501505e-05,
+      "loss": 0.7497875690460205,
+      "mean_token_accuracy": 0.8307713508605957,
+      "num_tokens": 868083.0,
+      "step": 300
+    },
+    {
+      "epoch": 2.27307206068268,
+      "eval_entropy": 0.7566840350627899,
+      "eval_loss": 0.8286334276199341,
+      "eval_mean_token_accuracy": 0.8229979053139687,
+      "eval_num_tokens": 868083.0,
+      "eval_runtime": 15.5791,
+      "eval_samples_per_second": 0.514,
+      "eval_steps_per_second": 0.514,
+      "step": 300
+    },
+    {
+      "entropy": 0.7993048436939716,
+      "epoch": 2.3489254108723134,
+      "grad_norm": 0.65234375,
+      "learning_rate": 3.8745804432010366e-05,
+      "loss": 0.742991590499878,
+      "mean_token_accuracy": 0.8361959497133891,
+      "num_tokens": 899190.0,
+      "step": 310
+    },
+    {
+      "epoch": 2.3489254108723134,
+      "eval_entropy": 0.777919439598918,
+      "eval_loss": 0.8299288749694824,
+      "eval_mean_token_accuracy": 0.8192910104990005,
+      "eval_num_tokens": 899190.0,
+      "eval_runtime": 15.6799,
+      "eval_samples_per_second": 0.51,
+      "eval_steps_per_second": 0.51,
+      "step": 310
+    },
+    {
+      "entropy": 0.6293849530319373,
+      "epoch": 2.4247787610619467,
+      "grad_norm": 0.8359375,
+      "learning_rate": 3.577962313943641e-05,
+      "loss": 0.581805419921875,
+      "mean_token_accuracy": 0.8652591675519943,
+      "num_tokens": 925260.0,
+      "step": 320
+    },
+    {
+      "epoch": 2.4247787610619467,
+      "eval_entropy": 0.7613311521708965,
+      "eval_loss": 0.8267746567726135,
+      "eval_mean_token_accuracy": 0.8222377151250839,
+      "eval_num_tokens": 925260.0,
+      "eval_runtime": 15.633,
+      "eval_samples_per_second": 0.512,
+      "eval_steps_per_second": 0.512,
+      "step": 320
+    },
+    {
+      "entropy": 0.7733801044523716,
+      "epoch": 2.5006321112515804,
+      "grad_norm": 1.015625,
+      "learning_rate": 3.2866964134400294e-05,
+      "loss": 0.7303842067718506,
+      "mean_token_accuracy": 0.832006515065829,
+      "num_tokens": 950926.0,
+      "step": 330
+    },
+    {
+      "epoch": 2.5006321112515804,
+      "eval_entropy": 0.7464305143803358,
+      "eval_loss": 0.832525372505188,
+      "eval_mean_token_accuracy": 0.8221687376499176,
+      "eval_num_tokens": 950926.0,
+      "eval_runtime": 15.5554,
+      "eval_samples_per_second": 0.514,
+      "eval_steps_per_second": 0.514,
+      "step": 330
+    },
+    {
+      "entropy": 0.8778012414773305,
+      "epoch": 2.5764854614412136,
+      "grad_norm": 0.6640625,
+      "learning_rate": 3.0018790007717667e-05,
+      "loss": 0.846740436553955,
+      "mean_token_accuracy": 0.8213575114806493,
+      "num_tokens": 984461.0,
+      "step": 340
+    },
+    {
+      "epoch": 2.5764854614412136,
+      "eval_entropy": 0.7818077709525824,
+      "eval_loss": 0.8265244960784912,
+      "eval_mean_token_accuracy": 0.8209226876497269,
+      "eval_num_tokens": 984461.0,
+      "eval_runtime": 15.6839,
+      "eval_samples_per_second": 0.51,
+      "eval_steps_per_second": 0.51,
+      "step": 340
+    },
+    {
+      "entropy": 0.6396931484341621,
+      "epoch": 2.6523388116308473,
+      "grad_norm": 0.59765625,
+      "learning_rate": 2.7245820643682818e-05,
+      "loss": 0.5814118385314941,
+      "mean_token_accuracy": 0.8639077583948771,
+      "num_tokens": 1012244.0,
+      "step": 350
+    },
+    {
+      "epoch": 2.6523388116308473,
+      "eval_entropy": 0.764773041009903,
+      "eval_loss": 0.8262049555778503,
+      "eval_mean_token_accuracy": 0.8203835636377335,
+      "eval_num_tokens": 1012244.0,
+      "eval_runtime": 15.7071,
+      "eval_samples_per_second": 0.509,
+      "eval_steps_per_second": 0.509,
+      "step": 350
+    },
+    {
+      "entropy": 0.5754020652423303,
+      "epoch": 2.7281921618204805,
+      "grad_norm": 0.89453125,
+      "learning_rate": 2.4558492872844647e-05,
+      "loss": 0.5285086154937744,
+      "mean_token_accuracy": 0.8705056806405386,
+      "num_tokens": 1035096.0,
+      "step": 360
+    },
+    {
+      "epoch": 2.7281921618204805,
+      "eval_entropy": 0.7516557332128286,
+      "eval_loss": 0.828058123588562,
+      "eval_mean_token_accuracy": 0.8215344399213791,
+      "eval_num_tokens": 1035096.0,
+      "eval_runtime": 15.6975,
+      "eval_samples_per_second": 0.51,
+      "eval_steps_per_second": 0.51,
+      "step": 360
+    },
+    {
+      "entropy": 0.8988088116049766,
+      "epoch": 2.8040455120101138,
+      "grad_norm": 0.7421875,
+      "learning_rate": 2.1966921190133207e-05,
+      "loss": 0.8750938415527344,
+      "mean_token_accuracy": 0.8111113180716832,
+      "num_tokens": 1070103.0,
+      "step": 370
+    },
+    {
+      "epoch": 2.8040455120101138,
+      "eval_entropy": 0.7701939102262259,
+      "eval_loss": 0.8284878730773926,
+      "eval_mean_token_accuracy": 0.8210262954235077,
+      "eval_num_tokens": 1070103.0,
+      "eval_runtime": 15.6584,
+      "eval_samples_per_second": 0.511,
+      "eval_steps_per_second": 0.511,
+      "step": 370
+    },
+    {
+      "entropy": 0.611414231856664,
+      "epoch": 2.879898862199747,
+      "grad_norm": 0.46875,
+      "learning_rate": 1.948085968618452e-05,
+      "loss": 0.5515973567962646,
+      "mean_token_accuracy": 0.8679946422576904,
+      "num_tokens": 1098379.0,
+      "step": 380
+    },
+    {
+      "epoch": 2.879898862199747,
+      "eval_entropy": 0.7635957412421703,
+      "eval_loss": 0.8278843760490417,
+      "eval_mean_token_accuracy": 0.8201632648706436,
+      "eval_num_tokens": 1098379.0,
+      "eval_runtime": 15.5657,
+      "eval_samples_per_second": 0.514,
+      "eval_steps_per_second": 0.514,
+      "step": 380
+    },
+    {
+      "entropy": 0.552935478836298,
+      "epoch": 2.9557522123893807,
+      "grad_norm": 0.60546875,
+      "learning_rate": 1.710966533514607e-05,
+      "loss": 0.5143342971801758,
+      "mean_token_accuracy": 0.8708932220935821,
+      "num_tokens": 1122556.0,
+      "step": 390
+    },
+    {
+      "epoch": 2.9557522123893807,
+      "eval_entropy": 0.7534672636538744,
+      "eval_loss": 0.8248686790466309,
+      "eval_mean_token_accuracy": 0.8210486173629761,
+      "eval_num_tokens": 1122556.0,
+      "eval_runtime": 15.7131,
+      "eval_samples_per_second": 0.509,
+      "eval_steps_per_second": 0.509,
+      "step": 390
+    },
+    {
+      "entropy": 0.8567168667154798,
+      "epoch": 3.030341340075853,
+      "grad_norm": 0.7890625,
+      "learning_rate": 1.4862262777138747e-05,
+      "loss": 0.7992874622344971,
+      "mean_token_accuracy": 0.8247433890730648,
+      "num_tokens": 1154463.0,
+      "step": 400
+    },
+    {
+      "epoch": 3.030341340075853,
+      "eval_entropy": 0.7517867274582386,
+      "eval_loss": 0.8263809680938721,
+      "eval_mean_token_accuracy": 0.8206864297389984,
+      "eval_num_tokens": 1154463.0,
+      "eval_runtime": 15.7327,
+      "eval_samples_per_second": 0.508,
+      "eval_steps_per_second": 0.508,
+      "step": 400
+    },
+    {
+      "entropy": 0.7660068737963835,
+      "epoch": 3.106194690265487,
+      "grad_norm": 0.84765625,
+      "learning_rate": 1.2747110727926704e-05,
+      "loss": 0.6917660713195801,
+      "mean_token_accuracy": 0.8465665926535925,
+      "num_tokens": 1185696.0,
+      "step": 410
+    },
+    {
+      "epoch": 3.106194690265487,
+      "eval_entropy": 0.7465294413268566,
+      "eval_loss": 0.8320755362510681,
+      "eval_mean_token_accuracy": 0.821786604821682,
+      "eval_num_tokens": 1185696.0,
+      "eval_runtime": 15.6774,
+      "eval_samples_per_second": 0.51,
+      "eval_steps_per_second": 0.51,
+      "step": 410
+    },
+    {
+      "entropy": 0.5761802410085995,
+      "epoch": 3.18204804045512,
+      "grad_norm": 0.6875,
+      "learning_rate": 1.077217014222125e-05,
+      "loss": 0.511052131652832,
+      "mean_token_accuracy": 0.8756706555684407,
+      "num_tokens": 1211766.0,
+      "step": 420
+    },
+    {
+      "epoch": 3.18204804045512,
+      "eval_entropy": 0.7379602193832397,
+      "eval_loss": 0.8376328349113464,
+      "eval_mean_token_accuracy": 0.8224689140915871,
+      "eval_num_tokens": 1211766.0,
+      "eval_runtime": 15.7026,
+      "eval_samples_per_second": 0.509,
+      "eval_steps_per_second": 0.509,
+      "step": 420
+    },
+    {
+      "entropy": 0.6564679868519306,
+      "epoch": 3.2579013906447534,
+      "grad_norm": 0.94140625,
+      "learning_rate": 8.944874250444768e-06,
+      "loss": 0.5985485553741455,
+      "mean_token_accuracy": 0.8599840154250463,
+      "num_tokens": 1237420.0,
+      "step": 430
+    },
+    {
+      "epoch": 3.2579013906447534,
+      "eval_entropy": 0.7303919699043036,
+      "eval_loss": 0.8405498266220093,
+      "eval_mean_token_accuracy": 0.8218415826559067,
+      "eval_num_tokens": 1237420.0,
+      "eval_runtime": 15.6316,
+      "eval_samples_per_second": 0.512,
+      "eval_steps_per_second": 0.512,
+      "step": 430
+    },
+    {
+      "entropy": 0.8293299699823061,
+      "epoch": 3.3337547408343866,
+      "grad_norm": 0.75390625,
+      "learning_rate": 7.2721005817299795e-06,
+      "loss": 0.7763681411743164,
+      "mean_token_accuracy": 0.8325149426857631,
+      "num_tokens": 1271456.0,
+      "step": 440
+    },
+    {
+      "epoch": 3.3337547408343866,
+      "eval_entropy": 0.7389508597552776,
+      "eval_loss": 0.8369100093841553,
+      "eval_mean_token_accuracy": 0.8209600448608398,
+      "eval_num_tokens": 1271456.0,
+      "eval_runtime": 15.8315,
+      "eval_samples_per_second": 0.505,
+      "eval_steps_per_second": 0.505,
+      "step": 440
+    },
+    {
+      "entropy": 0.5659994448224703,
+      "epoch": 3.4096080910240203,
+      "grad_norm": 0.6015625,
+      "learning_rate": 5.7601450784531105e-06,
+      "loss": 0.5014583587646484,
+      "mean_token_accuracy": 0.8805189063151677,
+      "num_tokens": 1299758.0,
+      "step": 450
+    },
+    {
+      "epoch": 3.4096080910240203,
+      "eval_entropy": 0.7447542995214462,
+      "eval_loss": 0.8348008394241333,
+      "eval_mean_token_accuracy": 0.8216045647859573,
+      "eval_num_tokens": 1299758.0,
+      "eval_runtime": 15.6248,
+      "eval_samples_per_second": 0.512,
+      "eval_steps_per_second": 0.512,
+      "step": 450
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 528,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 10,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.236136238254899e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-450/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de885d042fc883bdb1746107d1f7f854d09c4109e6e2b887d27994f901abb697
+size 5713