Upload 8 files

.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

@@ -1,3 +1,209 @@
----
-license: apache-2.0
----
+---
+base_model: Qwen/Qwen3-4B-Instruct-2507
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-4B-Instruct-2507
+- 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": "Qwen/Qwen3-4B-Instruct-2507",
+  "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": [
+    "v_proj",
+    "gate_proj",
+    "down_proj",
+    "up_proj",
+    "q_proj",
+    "k_proj",
+    "o_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 sha256:83b5c6c241d842a35bc4cf49d9979fa89226052cffefefe498c380035cc0f3dc
+size 264308896

chat_template.jinja

@@ -0,0 +1,61 @@
+{%- 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 %}
+{%- 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" %}
+        {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- 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' }}
+{%- endif %}

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "model_max_length": 1010000,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,478 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.4027183488547697,
+  "eval_steps": 50,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 0.9404663916677236,
+      "epoch": 0.010067958721369242,
+      "grad_norm": 2.6392252445220947,
+      "learning_rate": 2.666666666666667e-06,
+      "loss": 2.0117156982421873,
+      "mean_token_accuracy": 0.6191852029412985,
+      "num_tokens": 47701.0,
+      "step": 5
+    },
+    {
+      "entropy": 1.0189884781837464,
+      "epoch": 0.020135917442738484,
+      "grad_norm": 1.8436778783798218,
+      "learning_rate": 6e-06,
+      "loss": 2.1075166702270507,
+      "mean_token_accuracy": 0.5976856101304293,
+      "num_tokens": 92619.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.029310768097639,
+      "epoch": 0.03020387616410773,
+      "grad_norm": 1.815084457397461,
+      "learning_rate": 9.333333333333334e-06,
+      "loss": 2.01068058013916,
+      "mean_token_accuracy": 0.6073978751897812,
+      "num_tokens": 134847.0,
+      "step": 15
+    },
+    {
+      "entropy": 1.0625499848276376,
+      "epoch": 0.04027183488547697,
+      "grad_norm": 1.4827969074249268,
+      "learning_rate": 1.2666666666666667e-05,
+      "loss": 1.7313125610351563,
+      "mean_token_accuracy": 0.6392445303499699,
+      "num_tokens": 181821.0,
+      "step": 20
+    },
+    {
+      "entropy": 1.1866111695766448,
+      "epoch": 0.05033979360684621,
+      "grad_norm": 0.9268224835395813,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 1.6676939010620118,
+      "mean_token_accuracy": 0.6374935403466224,
+      "num_tokens": 225041.0,
+      "step": 25
+    },
+    {
+      "entropy": 1.284090331569314,
+      "epoch": 0.06040775232821546,
+      "grad_norm": 0.5153523683547974,
+      "learning_rate": 1.9333333333333333e-05,
+      "loss": 1.5365737915039062,
+      "mean_token_accuracy": 0.650652977451682,
+      "num_tokens": 271704.0,
+      "step": 30
+    },
+    {
+      "entropy": 1.4139859646558761,
+      "epoch": 0.0704757110495847,
+      "grad_norm": 0.4240514934062958,
+      "learning_rate": 1.998917111338525e-05,
+      "loss": 1.4139368057250976,
+      "mean_token_accuracy": 0.6503775727003813,
+      "num_tokens": 319422.0,
+      "step": 35
+    },
+    {
+      "entropy": 1.5055108167231084,
+      "epoch": 0.08054366977095394,
+      "grad_norm": 0.557256281375885,
+      "learning_rate": 1.9945218953682736e-05,
+      "loss": 1.3467309951782227,
+      "mean_token_accuracy": 0.6553127769380808,
+      "num_tokens": 368170.0,
+      "step": 40
+    },
+    {
+      "entropy": 1.5834380112588406,
+      "epoch": 0.09061162849232318,
+      "grad_norm": 0.5694743990898132,
+      "learning_rate": 1.9867615321125796e-05,
+      "loss": 1.3501482963562013,
+      "mean_token_accuracy": 0.6700987242162227,
+      "num_tokens": 408692.0,
+      "step": 45
+    },
+    {
+      "entropy": 1.5377649553120136,
+      "epoch": 0.10067958721369243,
+      "grad_norm": 0.48829907178878784,
+      "learning_rate": 1.9756622801842144e-05,
+      "loss": 1.2567365646362305,
+      "mean_token_accuracy": 0.6825098309665918,
+      "num_tokens": 454374.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.10067958721369243,
+      "eval_entropy": 1.3134305934906005,
+      "eval_loss": 1.1746762990951538,
+      "eval_mean_token_accuracy": 0.7086019682884216,
+      "eval_num_tokens": 454374.0,
+      "eval_runtime": 24163.8119,
+      "eval_samples_per_second": 0.041,
+      "eval_steps_per_second": 0.005,
+      "step": 50
+    },
+    {
+      "entropy": 1.4440373208373785,
+      "epoch": 0.11074754593506167,
+      "grad_norm": 0.4486835300922394,
+      "learning_rate": 1.961261695938319e-05,
+      "loss": 1.1860782623291015,
+      "mean_token_accuracy": 0.6934177171438932,
+      "num_tokens": 497453.0,
+      "step": 55
+    },
+    {
+      "entropy": 1.1991986483335495,
+      "epoch": 0.12081550465643091,
+      "grad_norm": 0.4323367476463318,
+      "learning_rate": 1.9436085063935837e-05,
+      "loss": 1.0048168182373047,
+      "mean_token_accuracy": 0.723202359676361,
+      "num_tokens": 547078.0,
+      "step": 60
+    },
+    {
+      "entropy": 1.1962539467960596,
+      "epoch": 0.13088346337780016,
+      "grad_norm": 0.4360666871070862,
+      "learning_rate": 1.9227624443554425e-05,
+      "loss": 1.049765682220459,
+      "mean_token_accuracy": 0.7247624807059765,
+      "num_tokens": 593207.0,
+      "step": 65
+    },
+    {
+      "entropy": 1.0165199358016253,
+      "epoch": 0.1409514220991694,
+      "grad_norm": 0.49459174275398254,
+      "learning_rate": 1.8987940462991673e-05,
+      "loss": 0.9207266807556153,
+      "mean_token_accuracy": 0.7483494646847249,
+      "num_tokens": 637938.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.895136122033,
+      "epoch": 0.15101938082053865,
+      "grad_norm": 0.4608009457588196,
+      "learning_rate": 1.8717844136967626e-05,
+      "loss": 0.8429131507873535,
+      "mean_token_accuracy": 0.7764634154736996,
+      "num_tokens": 679126.0,
+      "step": 75
+    },
+    {
+      "entropy": 0.8629299964755773,
+      "epoch": 0.16108733954190788,
+      "grad_norm": 0.38531047105789185,
+      "learning_rate": 1.8418249385952575e-05,
+      "loss": 0.8693387985229493,
+      "mean_token_accuracy": 0.7764782950282096,
+      "num_tokens": 719805.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.7840321972966194,
+      "epoch": 0.17115529826327713,
+      "grad_norm": 0.4015936255455017,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 0.789955997467041,
+      "mean_token_accuracy": 0.7866252034902572,
+      "num_tokens": 765446.0,
+      "step": 85
+    },
+    {
+      "entropy": 0.7604264505207539,
+      "epoch": 0.18122325698464636,
+      "grad_norm": 0.4798949658870697,
+      "learning_rate": 1.7734715927339642e-05,
+      "loss": 0.7473703861236572,
+      "mean_token_accuracy": 0.7978227443993091,
+      "num_tokens": 811505.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.7620996758341789,
+      "epoch": 0.1912912157060156,
+      "grad_norm": 0.4318743348121643,
+      "learning_rate": 1.735309008059829e-05,
+      "loss": 0.7961347579956055,
+      "mean_token_accuracy": 0.7934757456183433,
+      "num_tokens": 857681.0,
+      "step": 95
+    },
+    {
+      "entropy": 0.7531558889895678,
+      "epoch": 0.20135917442738485,
+      "grad_norm": 0.5560536980628967,
+      "learning_rate": 1.6946583704589973e-05,
+      "loss": 0.766410493850708,
+      "mean_token_accuracy": 0.7901870187371969,
+      "num_tokens": 901933.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.20135917442738485,
+      "eval_entropy": 0.7256068153381348,
+      "eval_loss": 0.7321593165397644,
+      "eval_mean_token_accuracy": 0.7850314078330993,
+      "eval_num_tokens": 901933.0,
+      "eval_runtime": 18225.1125,
+      "eval_samples_per_second": 0.054,
+      "eval_steps_per_second": 0.007,
+      "step": 100
+    },
+    {
+      "entropy": 0.7856348525732756,
+      "epoch": 0.21142713314875408,
+      "grad_norm": 0.3850078582763672,
+      "learning_rate": 1.6516572288214555e-05,
+      "loss": 0.8023449897766113,
+      "mean_token_accuracy": 0.7852729022502899,
+      "num_tokens": 946888.0,
+      "step": 105
+    },
+    {
+      "entropy": 0.7041983786970377,
+      "epoch": 0.22149509187012334,
+      "grad_norm": 0.3476756811141968,
+      "learning_rate": 1.6064510853988137e-05,
+      "loss": 0.7184148311614991,
+      "mean_token_accuracy": 0.8035397931933403,
+      "num_tokens": 994267.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.6575290430337191,
+      "epoch": 0.23156305059149257,
+      "grad_norm": 0.42202460765838623,
+      "learning_rate": 1.5591929034707468e-05,
+      "loss": 0.7003682613372803,
+      "mean_token_accuracy": 0.8060932837426662,
+      "num_tokens": 1038543.0,
+      "step": 115
+    },
+    {
+      "entropy": 0.7608727779239416,
+      "epoch": 0.24163100931286183,
+      "grad_norm": 0.3540622889995575,
+      "learning_rate": 1.5100425897656754e-05,
+      "loss": 0.7738057613372803,
+      "mean_token_accuracy": 0.7889790445566177,
+      "num_tokens": 1085867.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.6082758061587811,
+      "epoch": 0.2516989680342311,
+      "grad_norm": 0.32112520933151245,
+      "learning_rate": 1.4591664533870118e-05,
+      "loss": 0.6715522766113281,
+      "mean_token_accuracy": 0.8123787805438042,
+      "num_tokens": 1133833.0,
+      "step": 125
+    },
+    {
+      "entropy": 0.6413897173479199,
+      "epoch": 0.2617669267556003,
+      "grad_norm": 0.43722981214523315,
+      "learning_rate": 1.4067366430758004e-05,
+      "loss": 0.7195887565612793,
+      "mean_token_accuracy": 0.8123183585703373,
+      "num_tokens": 1178512.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.5526509841904044,
+      "epoch": 0.27183488547696955,
+      "grad_norm": 0.3406974673271179,
+      "learning_rate": 1.3529305647138689e-05,
+      "loss": 0.5937692165374756,
+      "mean_token_accuracy": 0.8311853632330894,
+      "num_tokens": 1224601.0,
+      "step": 135
+    },
+    {
+      "entropy": 0.6579740298911929,
+      "epoch": 0.2819028441983388,
+      "grad_norm": 0.43954288959503174,
+      "learning_rate": 1.297930281038482e-05,
+      "loss": 0.6883365631103515,
+      "mean_token_accuracy": 0.8083381243050098,
+      "num_tokens": 1270506.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.5645570032298565,
+      "epoch": 0.291970802919708,
+      "grad_norm": 0.36275994777679443,
+      "learning_rate": 1.2419218955996677e-05,
+      "loss": 0.6089091777801514,
+      "mean_token_accuracy": 0.8329982027411461,
+      "num_tokens": 1311666.0,
+      "step": 145
+    },
+    {
+      "entropy": 0.6062236651778221,
+      "epoch": 0.3020387616410773,
+      "grad_norm": 0.3385237157344818,
+      "learning_rate": 1.1850949230447146e-05,
+      "loss": 0.6368993282318115,
+      "mean_token_accuracy": 0.8212810829281807,
+      "num_tokens": 1357022.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.3020387616410773,
+      "eval_entropy": 0.6711692655086517,
+      "eval_loss": 0.674369752407074,
+      "eval_mean_token_accuracy": 0.7935635781288147,
+      "eval_num_tokens": 1357022.0,
+      "eval_runtime": 23687.9198,
+      "eval_samples_per_second": 0.042,
+      "eval_steps_per_second": 0.005,
+      "step": 150
+    },
+    {
+      "entropy": 0.6150166101753711,
+      "epoch": 0.3121067203624465,
+      "grad_norm": 0.33184218406677246,
+      "learning_rate": 1.127641647860595e-05,
+      "loss": 0.6427908897399902,
+      "mean_token_accuracy": 0.8106721416115761,
+      "num_tokens": 1409201.0,
+      "step": 155
+    },
+    {
+      "entropy": 0.6546612774953247,
+      "epoch": 0.32217467908381575,
+      "grad_norm": 0.443172812461853,
+      "learning_rate": 1.0697564737441254e-05,
+      "loss": 0.6632843971252441,
+      "mean_token_accuracy": 0.8050490751862526,
+      "num_tokens": 1461178.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.6669658403843641,
+      "epoch": 0.332242637805185,
+      "grad_norm": 0.3493345379829407,
+      "learning_rate": 1.0116352658013973e-05,
+      "loss": 0.6666298389434815,
+      "mean_token_accuracy": 0.8056038625538349,
+      "num_tokens": 1508214.0,
+      "step": 165
+    },
+    {
+      "entropy": 0.5695202240720392,
+      "epoch": 0.34231059652655427,
+      "grad_norm": 0.413866251707077,
+      "learning_rate": 9.534746878022533e-06,
+      "loss": 0.6183717727661133,
+      "mean_token_accuracy": 0.8245324343442917,
+      "num_tokens": 1552040.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.5897262109443545,
+      "epoch": 0.3523785552479235,
+      "grad_norm": 0.3123251795768738,
+      "learning_rate": 8.954715367323468e-06,
+      "loss": 0.6161505699157714,
+      "mean_token_accuracy": 0.8233651638031005,
+      "num_tokens": 1594387.0,
+      "step": 175
+    },
+    {
+      "entropy": 0.6046821037307382,
+      "epoch": 0.3624465139692927,
+      "grad_norm": 0.4404999911785126,
+      "learning_rate": 8.378220768944328e-06,
+      "loss": 0.6254678249359131,
+      "mean_token_accuracy": 0.823454175889492,
+      "num_tokens": 1640543.0,
+      "step": 180
+    },
+    {
+      "entropy": 0.6329730719327926,
+      "epoch": 0.37251447269066196,
+      "grad_norm": 0.32642191648483276,
+      "learning_rate": 7.807213758120965e-06,
+      "loss": 0.6730523109436035,
+      "mean_token_accuracy": 0.810814143717289,
+      "num_tokens": 1684800.0,
+      "step": 185
+    },
+    {
+      "entropy": 0.7039387376978994,
+      "epoch": 0.3825824314120312,
+      "grad_norm": 0.4055386185646057,
+      "learning_rate": 7.243626441830009e-06,
+      "loss": 0.6949094772338867,
+      "mean_token_accuracy": 0.7998988643288613,
+      "num_tokens": 1728741.0,
+      "step": 190
+    },
+    {
+      "entropy": 0.5845075074583292,
+      "epoch": 0.3926503901334005,
+      "grad_norm": 0.7357484698295593,
+      "learning_rate": 6.689365821150421e-06,
+      "loss": 0.6154315948486329,
+      "mean_token_accuracy": 0.8205408222973347,
+      "num_tokens": 1778359.0,
+      "step": 195
+    },
+    {
+      "entropy": 0.683666481077671,
+      "epoch": 0.4027183488547697,
+      "grad_norm": 0.4041738510131836,
+      "learning_rate": 6.146307338575519e-06,
+      "loss": 0.6790355205535888,
+      "mean_token_accuracy": 0.7988370589911937,
+      "num_tokens": 1828434.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.4027183488547697,
+      "eval_entropy": 0.6506109157800675,
+      "eval_loss": 0.6566110253334045,
+      "eval_mean_token_accuracy": 0.7965194163322449,
+      "eval_num_tokens": 1828434.0,
+      "eval_runtime": 22699.7349,
+      "eval_samples_per_second": 0.044,
+      "eval_steps_per_second": 0.006,
+      "step": 200
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 300,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.05865418389033e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3c92e6d4b3cb2f3ddf41a98f19c1e99328ad7746f0a35bf8f024db49c4bba21
+size 5649