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: roy-0309/Affine-1-5FNbAdWA9umLzLTpFwfsfybcEfS66jdcWoJTVhsJL6SXxofZ
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:roy-0309/Affine-1-5FNbAdWA9umLzLTpFwfsfybcEfS66jdcWoJTVhsJL6SXxofZ
+- 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 0.18.1

adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "/root/train_web/train/models/roy-0309--Affine-1-5FNbAdWA9umLzLTpFwfsfybcEfS66jdcWoJTVhsJL6SXxofZ",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "gate_proj",
+    "k_proj",
+    "down_proj",
+    "v_proj",
+    "q_proj",
+    "up_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 sha256:65560346ee59dc73851f2932ab18262df62e7ff232f1089c0ceeeed63c420c40
+size 536992880

chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- 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' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51e9db4efb74b1f1f5f7060be3e74ccdd73a24e8c705592c4f466583960cb557
+size 1074512995

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c33ad9e1e1864d293fa4976239062ac531facbdac3e5c530a519ea90e2bf4cf
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:321d3dffae38e466cc8e8f00911f2ae180c60fe4907305d66a33938ae9409664
+size 1465

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": true,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,400 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 5,
+  "global_step": 30,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 0.7555069377024969,
+      "epoch": 0.10810810810810811,
+      "grad_norm": 0.06494140625,
+      "learning_rate": 0.0,
+      "loss": 1.4478646516799927,
+      "mean_token_accuracy": 0.7140519370635351,
+      "num_tokens": 23243.0,
+      "step": 1
+    },
+    {
+      "entropy": 0.7560049295425415,
+      "epoch": 0.21621621621621623,
+      "grad_norm": 0.059814453125,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.4522969722747803,
+      "mean_token_accuracy": 0.7139862030744553,
+      "num_tokens": 46481.0,
+      "step": 2
+    },
+    {
+      "entropy": 0.7542048245668411,
+      "epoch": 0.32432432432432434,
+      "grad_norm": 0.05810546875,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.4361679553985596,
+      "mean_token_accuracy": 0.7170769820610682,
+      "num_tokens": 69771.0,
+      "step": 3
+    },
+    {
+      "entropy": 0.758419468998909,
+      "epoch": 0.43243243243243246,
+      "grad_norm": 0.05517578125,
+      "learning_rate": 6e-06,
+      "loss": 1.4303441047668457,
+      "mean_token_accuracy": 0.7165101716915766,
+      "num_tokens": 92954.0,
+      "step": 4
+    },
+    {
+      "entropy": 0.7581100612878799,
+      "epoch": 0.5405405405405406,
+      "grad_norm": 0.053466796875,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.4206496477127075,
+      "mean_token_accuracy": 0.7176701774199804,
+      "num_tokens": 116247.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.5405405405405406,
+      "eval_entropy": 0.7647502720355988,
+      "eval_loss": 1.4109477996826172,
+      "eval_mean_token_accuracy": 0.7173480987548828,
+      "eval_num_tokens": 116247.0,
+      "eval_runtime": 2.5082,
+      "eval_samples_per_second": 4.784,
+      "eval_steps_per_second": 0.797,
+      "step": 5
+    },
+    {
+      "entropy": 0.760763923327128,
+      "epoch": 0.6486486486486487,
+      "grad_norm": 0.0478515625,
+      "learning_rate": 1e-05,
+      "loss": 1.3971761465072632,
+      "mean_token_accuracy": 0.7190355559190115,
+      "num_tokens": 139452.0,
+      "step": 6
+    },
+    {
+      "entropy": 0.7620154668887457,
+      "epoch": 0.7567567567567568,
+      "grad_norm": 0.04443359375,
+      "learning_rate": 9.600000000000001e-06,
+      "loss": 1.3679012060165405,
+      "mean_token_accuracy": 0.7238030383984247,
+      "num_tokens": 162759.0,
+      "step": 7
+    },
+    {
+      "entropy": 0.7665750781695048,
+      "epoch": 0.8648648648648649,
+      "grad_norm": 0.04248046875,
+      "learning_rate": 9.200000000000002e-06,
+      "loss": 1.356690526008606,
+      "mean_token_accuracy": 0.7252735594908396,
+      "num_tokens": 186007.0,
+      "step": 8
+    },
+    {
+      "entropy": 0.7697029163440069,
+      "epoch": 0.972972972972973,
+      "grad_norm": 0.04150390625,
+      "learning_rate": 8.8e-06,
+      "loss": 1.3409219980239868,
+      "mean_token_accuracy": 0.7272671411434809,
+      "num_tokens": 209238.0,
+      "step": 9
+    },
+    {
+      "entropy": 0.7716555595397949,
+      "epoch": 1.0,
+      "grad_norm": 0.041748046875,
+      "learning_rate": 8.400000000000001e-06,
+      "loss": 1.3095864057540894,
+      "mean_token_accuracy": 0.7310146689414978,
+      "num_tokens": 214083.0,
+      "step": 10
+    },
+    {
+      "epoch": 1.0,
+      "eval_entropy": 0.7737017571926117,
+      "eval_loss": 1.3151968717575073,
+      "eval_mean_token_accuracy": 0.7290042340755463,
+      "eval_num_tokens": 214083.0,
+      "eval_runtime": 2.4636,
+      "eval_samples_per_second": 4.871,
+      "eval_steps_per_second": 0.812,
+      "step": 10
+    },
+    {
+      "entropy": 0.7714254210392634,
+      "epoch": 1.1081081081081081,
+      "grad_norm": 0.039794921875,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.3024636507034302,
+      "mean_token_accuracy": 0.7293276637792587,
+      "num_tokens": 237309.0,
+      "step": 11
+    },
+    {
+      "entropy": 0.7747663805882136,
+      "epoch": 1.2162162162162162,
+      "grad_norm": 0.039794921875,
+      "learning_rate": 7.600000000000001e-06,
+      "loss": 1.294501543045044,
+      "mean_token_accuracy": 0.7312390059232712,
+      "num_tokens": 260477.0,
+      "step": 12
+    },
+    {
+      "entropy": 0.7733762711286545,
+      "epoch": 1.3243243243243243,
+      "grad_norm": 0.0390625,
+      "learning_rate": 7.2000000000000005e-06,
+      "loss": 1.2725481986999512,
+      "mean_token_accuracy": 0.7331224282582601,
+      "num_tokens": 283716.0,
+      "step": 13
+    },
+    {
+      "entropy": 0.7727305938800176,
+      "epoch": 1.4324324324324325,
+      "grad_norm": 0.0390625,
+      "learning_rate": 6.800000000000001e-06,
+      "loss": 1.2624328136444092,
+      "mean_token_accuracy": 0.7335619429747263,
+      "num_tokens": 306913.0,
+      "step": 14
+    },
+    {
+      "entropy": 0.7709511965513229,
+      "epoch": 1.5405405405405406,
+      "grad_norm": 0.0390625,
+      "learning_rate": 6.4000000000000006e-06,
+      "loss": 1.2448844909667969,
+      "mean_token_accuracy": 0.7347658028205236,
+      "num_tokens": 330197.0,
+      "step": 15
+    },
+    {
+      "epoch": 1.5405405405405406,
+      "eval_entropy": 0.7766477465629578,
+      "eval_loss": 1.2467765808105469,
+      "eval_mean_token_accuracy": 0.7340552508831024,
+      "eval_num_tokens": 330197.0,
+      "eval_runtime": 2.4603,
+      "eval_samples_per_second": 4.877,
+      "eval_steps_per_second": 0.813,
+      "step": 15
+    },
+    {
+      "entropy": 0.7691091199715933,
+      "epoch": 1.6486486486486487,
+      "grad_norm": 0.038330078125,
+      "learning_rate": 6e-06,
+      "loss": 1.2266374826431274,
+      "mean_token_accuracy": 0.7370726317167282,
+      "num_tokens": 353521.0,
+      "step": 16
+    },
+    {
+      "entropy": 0.7754013985395432,
+      "epoch": 1.7567567567567568,
+      "grad_norm": 0.0390625,
+      "learning_rate": 5.600000000000001e-06,
+      "loss": 1.2258557081222534,
+      "mean_token_accuracy": 0.7370856006940206,
+      "num_tokens": 376793.0,
+      "step": 17
+    },
+    {
+      "entropy": 0.7713897029558817,
+      "epoch": 1.864864864864865,
+      "grad_norm": 0.0380859375,
+      "learning_rate": 5.2e-06,
+      "loss": 1.2122540473937988,
+      "mean_token_accuracy": 0.7382917404174805,
+      "num_tokens": 400077.0,
+      "step": 18
+    },
+    {
+      "entropy": 0.7698435584704081,
+      "epoch": 1.972972972972973,
+      "grad_norm": 0.038330078125,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 1.1965689659118652,
+      "mean_token_accuracy": 0.7406730304161707,
+      "num_tokens": 423316.0,
+      "step": 19
+    },
+    {
+      "entropy": 0.7725256482760111,
+      "epoch": 2.0,
+      "grad_norm": 0.039306640625,
+      "learning_rate": 4.4e-06,
+      "loss": 1.1841669082641602,
+      "mean_token_accuracy": 0.7414616743723551,
+      "num_tokens": 428166.0,
+      "step": 20
+    },
+    {
+      "epoch": 2.0,
+      "eval_entropy": 0.7773982584476471,
+      "eval_loss": 1.199079990386963,
+      "eval_mean_token_accuracy": 0.7407890260219574,
+      "eval_num_tokens": 428166.0,
+      "eval_runtime": 2.4584,
+      "eval_samples_per_second": 4.881,
+      "eval_steps_per_second": 0.814,
+      "step": 20
+    },
+    {
+      "entropy": 0.7739374836285909,
+      "epoch": 2.108108108108108,
+      "grad_norm": 0.037841796875,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.1883115768432617,
+      "mean_token_accuracy": 0.7420839418967565,
+      "num_tokens": 451399.0,
+      "step": 21
+    },
+    {
+      "entropy": 0.7725292791922888,
+      "epoch": 2.2162162162162162,
+      "grad_norm": 0.037109375,
+      "learning_rate": 3.6000000000000003e-06,
+      "loss": 1.1734648942947388,
+      "mean_token_accuracy": 0.7434294323126475,
+      "num_tokens": 474686.0,
+      "step": 22
+    },
+    {
+      "entropy": 0.7727770308653513,
+      "epoch": 2.3243243243243246,
+      "grad_norm": 0.03759765625,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 1.1688286066055298,
+      "mean_token_accuracy": 0.7453656494617462,
+      "num_tokens": 497937.0,
+      "step": 23
+    },
+    {
+      "entropy": 0.7705194850762686,
+      "epoch": 2.4324324324324325,
+      "grad_norm": 0.037353515625,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 1.1595253944396973,
+      "mean_token_accuracy": 0.7453472961982092,
+      "num_tokens": 521221.0,
+      "step": 24
+    },
+    {
+      "entropy": 0.7714516917864481,
+      "epoch": 2.5405405405405403,
+      "grad_norm": 0.037109375,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 1.164218783378601,
+      "mean_token_accuracy": 0.7445596506198248,
+      "num_tokens": 544500.0,
+      "step": 25
+    },
+    {
+      "epoch": 2.5405405405405403,
+      "eval_entropy": 0.7762394845485687,
+      "eval_loss": 1.1709049940109253,
+      "eval_mean_token_accuracy": 0.7427328824996948,
+      "eval_num_tokens": 544500.0,
+      "eval_runtime": 2.4586,
+      "eval_samples_per_second": 4.881,
+      "eval_steps_per_second": 0.813,
+      "step": 25
+    },
+    {
+      "entropy": 0.7758622417847315,
+      "epoch": 2.6486486486486487,
+      "grad_norm": 0.037841796875,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.1615042686462402,
+      "mean_token_accuracy": 0.7436568190654119,
+      "num_tokens": 567654.0,
+      "step": 26
+    },
+    {
+      "entropy": 0.7720395823319753,
+      "epoch": 2.756756756756757,
+      "grad_norm": 0.03759765625,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 1.151614785194397,
+      "mean_token_accuracy": 0.7442129651705424,
+      "num_tokens": 590913.0,
+      "step": 27
+    },
+    {
+      "entropy": 0.7733467568953832,
+      "epoch": 2.864864864864865,
+      "grad_norm": 0.037353515625,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 1.1556271314620972,
+      "mean_token_accuracy": 0.7446945160627365,
+      "num_tokens": 614138.0,
+      "step": 28
+    },
+    {
+      "entropy": 0.7718540579080582,
+      "epoch": 2.972972972972973,
+      "grad_norm": 0.03759765625,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 1.1523997783660889,
+      "mean_token_accuracy": 0.7444420705238978,
+      "num_tokens": 637411.0,
+      "step": 29
+    },
+    {
+      "entropy": 0.7697569529215494,
+      "epoch": 3.0,
+      "grad_norm": 0.038330078125,
+      "learning_rate": 4.0000000000000003e-07,
+      "loss": 1.1426969766616821,
+      "mean_token_accuracy": 0.7479291160901388,
+      "num_tokens": 642249.0,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "eval_entropy": 0.775920033454895,
+      "eval_loss": 1.1602760553359985,
+      "eval_mean_token_accuracy": 0.7437030673027039,
+      "eval_num_tokens": 642249.0,
+      "eval_runtime": 2.4597,
+      "eval_samples_per_second": 4.879,
+      "eval_steps_per_second": 0.813,
+      "step": 30
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 30,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 5,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.249982918825472e+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 sha256:99fa1e0fd0630edd3afde6058431319425b2d5386fc60a39099edcb7f282085b
+size 5649