Upload folder using huggingface_hub

adapter_config.json

@@ -16,7 +16,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 64,
   "lora_bias": false,
   "lora_dropout": 0.05,
   "lora_ga_config": null,
@@ -26,17 +26,17 @@
   "peft_type": "LORA",
   "peft_version": "0.19.1",
   "qalora_group_size": 16,
-  "r": 16,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "v_proj",
     "down_proj",
-    "gate_proj",
-    "k_proj",
+    "v_proj",
+    "o_proj",
     "q_proj",
-    "o_proj"
+    "up_proj",
+    "k_proj",
+    "gate_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa34af23bf5f627420056c6ca93614eccb89a13a6b26ee39654b1c76f98c7b57
-size 36981856
+oid sha256:daa327a08e34b24d1fb838778e344666e08dc9be064f4729fa28e8d9aa75a75f
+size 73911504

checkpoint-100/adapter_config.json

@@ -16,7 +16,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 64,
   "lora_bias": false,
   "lora_dropout": 0.05,
   "lora_ga_config": null,
@@ -26,17 +26,17 @@
   "peft_type": "LORA",
   "peft_version": "0.19.1",
   "qalora_group_size": 16,
-  "r": 16,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "v_proj",
     "down_proj",
-    "gate_proj",
-    "k_proj",
+    "v_proj",
+    "o_proj",
     "q_proj",
-    "o_proj"
+    "up_proj",
+    "k_proj",
+    "gate_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

checkpoint-100/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa9275bf8376983416fa96843cefbf7e481b80c2337a48afe8223b447bc7aff2
-size 36981856
+oid sha256:41a352eac3525221c7e6492006ccf1a168de968d1936bfc484ec82d8516c1e7d
+size 73911504

checkpoint-100/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dad7021362a705070b53d5b1fa56cd1fa4a9d6c14ae6591b7f0e4844da0dbf4
-size 37974277
+oid sha256:1da9240a6a4f53d033d1c7ccb9219a8db25cf2054b464320188be62afbbc7005
+size 75480837

checkpoint-100/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b00cceb7f37cfbd31e90b394ecb76bb027606e7d08fb604a18f1196079d2df1
+oid sha256:0a1fc27eff0c588988dbf01aac3e8e85433fcd6f5a7b71ef1b74c5e8820fc929
 size 14581

checkpoint-100/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a551ce0dc3a0b68845751a0c5e671b9aae2271abcf89a90290c712dcbcc1aa1f
+oid sha256:eb811f4a295c24e566f01228b6c8c274ddb3baab0e0c84cddf589d01ddc42a55
 size 1465

checkpoint-100/trainer_state.json

@@ -2,7 +2,7 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.111731843575419,
+  "epoch": 0.1968503937007874,
   "eval_steps": 50,
   "global_step": 100,
   "is_hyper_param_search": false,
@@ -10,130 +10,130 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "entropy": 1.4779861330986024,
-      "epoch": 0.11173184357541899,
-      "grad_norm": 0.76953125,
-      "learning_rate": 0.0002,
-      "loss": 1.4731324195861817,
-      "mean_token_accuracy": 0.7202368557453156,
-      "num_tokens": 139114.0,
+      "entropy": 1.4378354728221894,
+      "epoch": 0.01968503937007874,
+      "grad_norm": 0.62109375,
+      "learning_rate": 3.91304347826087e-05,
+      "loss": 1.657682228088379,
+      "mean_token_accuracy": 0.6598833322525024,
+      "num_tokens": 115439.0,
       "step": 10
     },
     {
-      "entropy": 1.0133022338151931,
-      "epoch": 0.22346368715083798,
-      "grad_norm": 0.283203125,
-      "learning_rate": 0.0001992764570419069,
-      "loss": 0.8902671813964844,
-      "mean_token_accuracy": 0.8063317209482193,
-      "num_tokens": 287784.0,
+      "entropy": 1.5141301095485686,
+      "epoch": 0.03937007874015748,
+      "grad_norm": 0.44140625,
+      "learning_rate": 8.260869565217392e-05,
+      "loss": 1.4646138191223144,
+      "mean_token_accuracy": 0.6834615051746369,
+      "num_tokens": 225264.0,
       "step": 20
     },
     {
-      "entropy": 0.7525231212377548,
-      "epoch": 0.33519553072625696,
-      "grad_norm": 0.328125,
-      "learning_rate": 0.00019711629845587164,
-      "loss": 0.7365246772766113,
-      "mean_token_accuracy": 0.8312019616365433,
-      "num_tokens": 425110.0,
+      "entropy": 1.2295305937528611,
+      "epoch": 0.05905511811023622,
+      "grad_norm": 0.6796875,
+      "learning_rate": 0.00012608695652173915,
+      "loss": 1.1134957313537597,
+      "mean_token_accuracy": 0.7453642427921295,
+      "num_tokens": 330923.0,
       "step": 30
     },
     {
-      "entropy": 0.7569459870457649,
-      "epoch": 0.44692737430167595,
-      "grad_norm": 0.30859375,
-      "learning_rate": 0.0001935507835925601,
-      "loss": 0.7281070709228515,
-      "mean_token_accuracy": 0.8265180081129074,
-      "num_tokens": 557368.0,
+      "entropy": 1.0573274463415145,
+      "epoch": 0.07874015748031496,
+      "grad_norm": 0.474609375,
+      "learning_rate": 0.00016956521739130436,
+      "loss": 1.077296829223633,
+      "mean_token_accuracy": 0.7446383863687516,
+      "num_tokens": 437622.0,
       "step": 40
     },
     {
-      "entropy": 0.7587758377194405,
-      "epoch": 0.5586592178770949,
-      "grad_norm": 0.298828125,
-      "learning_rate": 0.00018863150851539877,
-      "loss": 0.7540057182312012,
-      "mean_token_accuracy": 0.8272259771823883,
-      "num_tokens": 697056.0,
+      "entropy": 0.952904561161995,
+      "epoch": 0.0984251968503937,
+      "grad_norm": 0.50390625,
+      "learning_rate": 0.00019999796688511753,
+      "loss": 0.9590332984924317,
+      "mean_token_accuracy": 0.768164387345314,
+      "num_tokens": 551175.0,
       "step": 50
     },
     {
-      "epoch": 0.5586592178770949,
-      "eval_entropy": 0.7372037768363953,
-      "eval_loss": 0.6630074381828308,
-      "eval_mean_token_accuracy": 0.8417112976312637,
-      "eval_num_tokens": 697056.0,
-      "eval_runtime": 2.5833,
-      "eval_samples_per_second": 24.774,
-      "eval_steps_per_second": 3.097,
+      "epoch": 0.0984251968503937,
+      "eval_entropy": 1.0900797645250957,
+      "eval_loss": 1.0484484434127808,
+      "eval_mean_token_accuracy": 0.7461776600943671,
+      "eval_num_tokens": 551175.0,
+      "eval_runtime": 15.9866,
+      "eval_samples_per_second": 26.71,
+      "eval_steps_per_second": 3.378,
       "step": 50
     },
     {
-      "entropy": 0.6524852216243744,
-      "epoch": 0.6703910614525139,
-      "grad_norm": 0.298828125,
-      "learning_rate": 0.00018242965936120768,
-      "loss": 0.6453401565551757,
-      "mean_token_accuracy": 0.8488216072320938,
-      "num_tokens": 839286.0,
+      "entropy": 0.9487997680902481,
+      "epoch": 0.11811023622047244,
+      "grad_norm": 0.59375,
+      "learning_rate": 0.0001999618249203163,
+      "loss": 0.9577752113342285,
+      "mean_token_accuracy": 0.7689193069934845,
+      "num_tokens": 658006.0,
       "step": 60
     },
     {
-      "entropy": 0.6424317806959152,
-      "epoch": 0.7821229050279329,
-      "grad_norm": 0.271484375,
-      "learning_rate": 0.00017503498221564025,
-      "loss": 0.6219259262084961,
-      "mean_token_accuracy": 0.8490033924579621,
-      "num_tokens": 975302.0,
+      "entropy": 1.0506175458431244,
+      "epoch": 0.1377952755905512,
+      "grad_norm": 0.5390625,
+      "learning_rate": 0.00019988052141977201,
+      "loss": 0.9976933479309082,
+      "mean_token_accuracy": 0.756487911939621,
+      "num_tokens": 771278.0,
       "step": 70
     },
     {
-      "entropy": 0.6861401617527008,
-      "epoch": 0.8938547486033519,
-      "grad_norm": 0.310546875,
-      "learning_rate": 0.00016655448441021747,
-      "loss": 0.6655363082885742,
-      "mean_token_accuracy": 0.8398628294467926,
-      "num_tokens": 1124078.0,
+      "entropy": 0.8528705358505249,
+      "epoch": 0.15748031496062992,
+      "grad_norm": 0.5078125,
+      "learning_rate": 0.0001997540931154166,
+      "loss": 0.8407608032226562,
+      "mean_token_accuracy": 0.7868376106023789,
+      "num_tokens": 886071.0,
       "step": 80
     },
     {
-      "entropy": 0.6849280376183359,
-      "epoch": 1.0,
-      "grad_norm": 0.52734375,
-      "learning_rate": 0.00015711088603430405,
-      "loss": 0.6517285823822021,
-      "mean_token_accuracy": 0.8404176392053303,
-      "num_tokens": 1253938.0,
+      "entropy": 0.9220433413982392,
+      "epoch": 0.17716535433070865,
+      "grad_norm": 0.484375,
+      "learning_rate": 0.00019958259712601903,
+      "loss": 0.8958203315734863,
+      "mean_token_accuracy": 0.7736223608255386,
+      "num_tokens": 996361.0,
       "step": 90
     },
     {
-      "entropy": 0.5663869976997375,
-      "epoch": 1.111731843575419,
-      "grad_norm": 0.3515625,
-      "learning_rate": 0.00014684084406997903,
-      "loss": 0.5269561767578125,
-      "mean_token_accuracy": 0.867387443780899,
-      "num_tokens": 1393724.0,
+      "entropy": 0.8399994730949402,
+      "epoch": 0.1968503937007874,
+      "grad_norm": 0.51953125,
+      "learning_rate": 0.00019936611093137983,
+      "loss": 0.8394058227539063,
+      "mean_token_accuracy": 0.7876519203186035,
+      "num_tokens": 1103999.0,
       "step": 100
     },
     {
-      "epoch": 1.111731843575419,
-      "eval_entropy": 0.5684726685285568,
-      "eval_loss": 0.6147818565368652,
-      "eval_mean_token_accuracy": 0.8511798083782196,
-      "eval_num_tokens": 1393724.0,
-      "eval_runtime": 2.5766,
-      "eval_samples_per_second": 24.839,
-      "eval_steps_per_second": 3.105,
+      "epoch": 0.1968503937007874,
+      "eval_entropy": 0.9908565746413337,
+      "eval_loss": 0.949418842792511,
+      "eval_mean_token_accuracy": 0.7609190278583102,
+      "eval_num_tokens": 1103999.0,
+      "eval_runtime": 15.9475,
+      "eval_samples_per_second": 26.775,
+      "eval_steps_per_second": 3.386,
       "step": 100
     }
   ],
   "logging_steps": 10,
-  "max_steps": 270,
+  "max_steps": 1524,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 50,
@@ -149,7 +149,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.9212723876870144e+16,
+  "total_flos": 1.5680413745086464e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null

checkpoint-1000/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-Math-1.5B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Math-1.5B-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-1000/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Math-1.5B-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": 0.05,
+  "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": [
+    "down_proj",
+    "v_proj",
+    "o_proj",
+    "q_proj",
+    "up_proj",
+    "k_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-1000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee24119072f11c0af081f59c58bed9bbb7997ac37fcd76fd929cf8d51da4f518
+size 73911504

checkpoint-1000/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'Please reason step by step, and put your final answer within \\boxed{}.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nPlease reason step by step, and put your final answer within \\boxed{}.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c64565b335948906b563dadefa773d27a12ffc17b35dc282189f2c04802e7ff
+size 75481221

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7a36d4490dcc66ffb5c91559101a1ded1d487a9d57e77bb66d6f525a1f7b3f9
+size 14581

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bf4431da4f9b62f328c3c855c395422d88886e20e8353946752b9c5d711e964
+size 1465

checkpoint-1000/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

checkpoint-1000/tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "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,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|fim_pad|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1000/trainer_state.json

@@ -0,0 +1,1254 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.968503937007874,
+  "eval_steps": 50,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.4378354728221894,
+      "epoch": 0.01968503937007874,
+      "grad_norm": 0.62109375,
+      "learning_rate": 3.91304347826087e-05,
+      "loss": 1.657682228088379,
+      "mean_token_accuracy": 0.6598833322525024,
+      "num_tokens": 115439.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.5141301095485686,
+      "epoch": 0.03937007874015748,
+      "grad_norm": 0.44140625,
+      "learning_rate": 8.260869565217392e-05,
+      "loss": 1.4646138191223144,
+      "mean_token_accuracy": 0.6834615051746369,
+      "num_tokens": 225264.0,
+      "step": 20
+    },
+    {
+      "entropy": 1.2295305937528611,
+      "epoch": 0.05905511811023622,
+      "grad_norm": 0.6796875,
+      "learning_rate": 0.00012608695652173915,
+      "loss": 1.1134957313537597,
+      "mean_token_accuracy": 0.7453642427921295,
+      "num_tokens": 330923.0,
+      "step": 30
+    },
+    {
+      "entropy": 1.0573274463415145,
+      "epoch": 0.07874015748031496,
+      "grad_norm": 0.474609375,
+      "learning_rate": 0.00016956521739130436,
+      "loss": 1.077296829223633,
+      "mean_token_accuracy": 0.7446383863687516,
+      "num_tokens": 437622.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.952904561161995,
+      "epoch": 0.0984251968503937,
+      "grad_norm": 0.50390625,
+      "learning_rate": 0.00019999796688511753,
+      "loss": 0.9590332984924317,
+      "mean_token_accuracy": 0.768164387345314,
+      "num_tokens": 551175.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.0984251968503937,
+      "eval_entropy": 1.0900797645250957,
+      "eval_loss": 1.0484484434127808,
+      "eval_mean_token_accuracy": 0.7461776600943671,
+      "eval_num_tokens": 551175.0,
+      "eval_runtime": 15.9866,
+      "eval_samples_per_second": 26.71,
+      "eval_steps_per_second": 3.378,
+      "step": 50
+    },
+    {
+      "entropy": 0.9487997680902481,
+      "epoch": 0.11811023622047244,
+      "grad_norm": 0.59375,
+      "learning_rate": 0.0001999618249203163,
+      "loss": 0.9577752113342285,
+      "mean_token_accuracy": 0.7689193069934845,
+      "num_tokens": 658006.0,
+      "step": 60
+    },
+    {
+      "entropy": 1.0506175458431244,
+      "epoch": 0.1377952755905512,
+      "grad_norm": 0.5390625,
+      "learning_rate": 0.00019988052141977201,
+      "loss": 0.9976933479309082,
+      "mean_token_accuracy": 0.756487911939621,
+      "num_tokens": 771278.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.8528705358505249,
+      "epoch": 0.15748031496062992,
+      "grad_norm": 0.5078125,
+      "learning_rate": 0.0001997540931154166,
+      "loss": 0.8407608032226562,
+      "mean_token_accuracy": 0.7868376106023789,
+      "num_tokens": 886071.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.9220433413982392,
+      "epoch": 0.17716535433070865,
+      "grad_norm": 0.484375,
+      "learning_rate": 0.00019958259712601903,
+      "loss": 0.8958203315734863,
+      "mean_token_accuracy": 0.7736223608255386,
+      "num_tokens": 996361.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.8399994730949402,
+      "epoch": 0.1968503937007874,
+      "grad_norm": 0.51953125,
+      "learning_rate": 0.00019936611093137983,
+      "loss": 0.8394058227539063,
+      "mean_token_accuracy": 0.7876519203186035,
+      "num_tokens": 1103999.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.1968503937007874,
+      "eval_entropy": 0.9908565746413337,
+      "eval_loss": 0.949418842792511,
+      "eval_mean_token_accuracy": 0.7609190278583102,
+      "eval_num_tokens": 1103999.0,
+      "eval_runtime": 15.9475,
+      "eval_samples_per_second": 26.775,
+      "eval_steps_per_second": 3.386,
+      "step": 100
+    },
+    {
+      "entropy": 0.8772778362035751,
+      "epoch": 0.21653543307086615,
+      "grad_norm": 0.40625,
+      "learning_rate": 0.00019910473233732668,
+      "loss": 0.8347702026367188,
+      "mean_token_accuracy": 0.7877911299467086,
+      "num_tokens": 1216586.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.8745568007230758,
+      "epoch": 0.23622047244094488,
+      "grad_norm": 0.609375,
+      "learning_rate": 0.00019879857943152674,
+      "loss": 0.8359953880310058,
+      "mean_token_accuracy": 0.7790884494781494,
+      "num_tokens": 1324767.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.878146781027317,
+      "epoch": 0.2559055118110236,
+      "grad_norm": 0.5390625,
+      "learning_rate": 0.00019844779053013637,
+      "loss": 0.8335110664367675,
+      "mean_token_accuracy": 0.7791220843791962,
+      "num_tokens": 1432356.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.788033875823021,
+      "epoch": 0.2755905511811024,
+      "grad_norm": 0.546875,
+      "learning_rate": 0.00019805252411531126,
+      "loss": 0.7967269420623779,
+      "mean_token_accuracy": 0.7931749552488327,
+      "num_tokens": 1542545.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.8667207360267639,
+      "epoch": 0.2952755905511811,
+      "grad_norm": 0.5546875,
+      "learning_rate": 0.0001976129587636064,
+      "loss": 0.8101954460144043,
+      "mean_token_accuracy": 0.7908060193061829,
+      "num_tokens": 1654462.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.2952755905511811,
+      "eval_entropy": 0.9391163366812246,
+      "eval_loss": 0.9146928191184998,
+      "eval_mean_token_accuracy": 0.7670937886944523,
+      "eval_num_tokens": 1654462.0,
+      "eval_runtime": 15.956,
+      "eval_samples_per_second": 26.761,
+      "eval_steps_per_second": 3.384,
+      "step": 150
+    },
+    {
+      "entropy": 0.769407157599926,
+      "epoch": 0.31496062992125984,
+      "grad_norm": 0.470703125,
+      "learning_rate": 0.00019712929306529723,
+      "loss": 0.7655523777008056,
+      "mean_token_accuracy": 0.8053037762641907,
+      "num_tokens": 1760181.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.8818381905555726,
+      "epoch": 0.3346456692913386,
+      "grad_norm": 0.625,
+      "learning_rate": 0.000196601745534659,
+      "loss": 0.8408863067626953,
+      "mean_token_accuracy": 0.7815578579902649,
+      "num_tokens": 1864683.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.8344995141029358,
+      "epoch": 0.3543307086614173,
+      "grad_norm": 0.4765625,
+      "learning_rate": 0.0001960305545112445,
+      "loss": 0.8205550193786622,
+      "mean_token_accuracy": 0.7871369570493698,
+      "num_tokens": 1978641.0,
+      "step": 180
+    },
+    {
+      "entropy": 0.8058241099119187,
+      "epoch": 0.37401574803149606,
+      "grad_norm": 0.494140625,
+      "learning_rate": 0.0001954159780522056,
+      "loss": 0.8002825736999511,
+      "mean_token_accuracy": 0.7913093209266663,
+      "num_tokens": 2087989.0,
+      "step": 190
+    },
+    {
+      "entropy": 0.8938606142997741,
+      "epoch": 0.3937007874015748,
+      "grad_norm": 0.61328125,
+      "learning_rate": 0.00019475829381570566,
+      "loss": 0.8305434226989746,
+      "mean_token_accuracy": 0.7836446255445481,
+      "num_tokens": 2195494.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.3937007874015748,
+      "eval_entropy": 0.9502577009024443,
+      "eval_loss": 0.8978050351142883,
+      "eval_mean_token_accuracy": 0.7696934717672842,
+      "eval_num_tokens": 2195494.0,
+      "eval_runtime": 15.9419,
+      "eval_samples_per_second": 26.785,
+      "eval_steps_per_second": 3.387,
+      "step": 200
+    },
+    {
+      "entropy": 0.7890492826700211,
+      "epoch": 0.41338582677165353,
+      "grad_norm": 0.40625,
+      "learning_rate": 0.0001940577989354773,
+      "loss": 0.7953387260437011,
+      "mean_token_accuracy": 0.7982505321502685,
+      "num_tokens": 2314228.0,
+      "step": 210
+    },
+    {
+      "entropy": 0.8576261162757873,
+      "epoch": 0.4330708661417323,
+      "grad_norm": 0.66015625,
+      "learning_rate": 0.00019331480988658083,
+      "loss": 0.8120486259460449,
+      "mean_token_accuracy": 0.7829198718070984,
+      "num_tokens": 2419122.0,
+      "step": 220
+    },
+    {
+      "entropy": 0.8514308303594589,
+      "epoch": 0.452755905511811,
+      "grad_norm": 0.470703125,
+      "learning_rate": 0.00019252966234242468,
+      "loss": 0.8203784942626953,
+      "mean_token_accuracy": 0.7819343030452728,
+      "num_tokens": 2524623.0,
+      "step": 230
+    },
+    {
+      "entropy": 0.8994888842105866,
+      "epoch": 0.47244094488188976,
+      "grad_norm": 0.59765625,
+      "learning_rate": 0.00019170271102311238,
+      "loss": 0.9019557952880859,
+      "mean_token_accuracy": 0.7712395042181015,
+      "num_tokens": 2631031.0,
+      "step": 240
+    },
+    {
+      "entropy": 0.7910601049661636,
+      "epoch": 0.4921259842519685,
+      "grad_norm": 0.494140625,
+      "learning_rate": 0.00019083432953518418,
+      "loss": 0.8107678413391113,
+      "mean_token_accuracy": 0.7996705889701843,
+      "num_tokens": 2741031.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.4921259842519685,
+      "eval_entropy": 0.9037868281205496,
+      "eval_loss": 0.8843846917152405,
+      "eval_mean_token_accuracy": 0.7717091352851303,
+      "eval_num_tokens": 2741031.0,
+      "eval_runtime": 15.93,
+      "eval_samples_per_second": 26.805,
+      "eval_steps_per_second": 3.39,
+      "step": 250
+    },
+    {
+      "entropy": 0.7740790158510208,
+      "epoch": 0.5118110236220472,
+      "grad_norm": 0.57421875,
+      "learning_rate": 0.00018992491020282618,
+      "loss": 0.7579652309417725,
+      "mean_token_accuracy": 0.7955388814210892,
+      "num_tokens": 2853547.0,
+      "step": 260
+    },
+    {
+      "entropy": 0.8572690159082412,
+      "epoch": 0.531496062992126,
+      "grad_norm": 1.171875,
+      "learning_rate": 0.0001889748638906231,
+      "loss": 0.8072081565856933,
+      "mean_token_accuracy": 0.7910655379295349,
+      "num_tokens": 2968367.0,
+      "step": 270
+    },
+    {
+      "entropy": 0.8885004252195359,
+      "epoch": 0.5511811023622047,
+      "grad_norm": 0.451171875,
+      "learning_rate": 0.00018798461981793462,
+      "loss": 0.8460770606994629,
+      "mean_token_accuracy": 0.7776093751192092,
+      "num_tokens": 3075963.0,
+      "step": 280
+    },
+    {
+      "entropy": 0.829613895714283,
+      "epoch": 0.5708661417322834,
+      "grad_norm": 0.4453125,
+      "learning_rate": 0.00018695462536497934,
+      "loss": 0.823792839050293,
+      "mean_token_accuracy": 0.7848509013652801,
+      "num_tokens": 3185899.0,
+      "step": 290
+    },
+    {
+      "entropy": 0.8341330245137215,
+      "epoch": 0.5905511811023622,
+      "grad_norm": 0.490234375,
+      "learning_rate": 0.00018588534587071385,
+      "loss": 0.810818099975586,
+      "mean_token_accuracy": 0.7906568497419357,
+      "num_tokens": 3297319.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.5905511811023622,
+      "eval_entropy": 0.8445847459413387,
+      "eval_loss": 0.8718247413635254,
+      "eval_mean_token_accuracy": 0.774838043583764,
+      "eval_num_tokens": 3297319.0,
+      "eval_runtime": 15.9561,
+      "eval_samples_per_second": 26.761,
+      "eval_steps_per_second": 3.384,
+      "step": 300
+    },
+    {
+      "entropy": 0.8317201763391495,
+      "epoch": 0.610236220472441,
+      "grad_norm": 0.396484375,
+      "learning_rate": 0.00018477726442259806,
+      "loss": 0.80075101852417,
+      "mean_token_accuracy": 0.7886052161455155,
+      "num_tokens": 3415477.0,
+      "step": 310
+    },
+    {
+      "entropy": 0.8597566410899162,
+      "epoch": 0.6299212598425197,
+      "grad_norm": 0.404296875,
+      "learning_rate": 0.00018363088163834252,
+      "loss": 0.8123328208923339,
+      "mean_token_accuracy": 0.7854531407356262,
+      "num_tokens": 3524759.0,
+      "step": 320
+    },
+    {
+      "entropy": 0.8519140958786011,
+      "epoch": 0.6496062992125984,
+      "grad_norm": 0.458984375,
+      "learning_rate": 0.00018244671543973513,
+      "loss": 0.8214571952819825,
+      "mean_token_accuracy": 0.7828344345092774,
+      "num_tokens": 3640838.0,
+      "step": 330
+    },
+    {
+      "entropy": 0.7781533747911453,
+      "epoch": 0.6692913385826772,
+      "grad_norm": 0.51953125,
+      "learning_rate": 0.0001812253008186505,
+      "loss": 0.753899097442627,
+      "mean_token_accuracy": 0.8011120349168778,
+      "num_tokens": 3756735.0,
+      "step": 340
+    },
+    {
+      "entropy": 0.8384901583194733,
+      "epoch": 0.6889763779527559,
+      "grad_norm": 0.51171875,
+      "learning_rate": 0.0001799671895953471,
+      "loss": 0.8112489700317382,
+      "mean_token_accuracy": 0.7898134678602219,
+      "num_tokens": 3870377.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.6889763779527559,
+      "eval_entropy": 0.8795759567507991,
+      "eval_loss": 0.8568941354751587,
+      "eval_mean_token_accuracy": 0.7754804182935644,
+      "eval_num_tokens": 3870377.0,
+      "eval_runtime": 15.9337,
+      "eval_samples_per_second": 26.798,
+      "eval_steps_per_second": 3.389,
+      "step": 350
+    },
+    {
+      "entropy": 0.8008699864149094,
+      "epoch": 0.7086614173228346,
+      "grad_norm": 0.498046875,
+      "learning_rate": 0.00017867295016916167,
+      "loss": 0.7585730075836181,
+      "mean_token_accuracy": 0.7942175149917603,
+      "num_tokens": 3975692.0,
+      "step": 360
+    },
+    {
+      "entropy": 0.9035080641508102,
+      "epoch": 0.7283464566929134,
+      "grad_norm": 0.48046875,
+      "learning_rate": 0.0001773431672617132,
+      "loss": 0.8653995513916015,
+      "mean_token_accuracy": 0.7730168104171753,
+      "num_tokens": 4087256.0,
+      "step": 370
+    },
+    {
+      "entropy": 0.760843014717102,
+      "epoch": 0.7480314960629921,
+      "grad_norm": 0.49609375,
+      "learning_rate": 0.00017597844165273286,
+      "loss": 0.7377382278442383,
+      "mean_token_accuracy": 0.7972156703472137,
+      "num_tokens": 4192629.0,
+      "step": 380
+    },
+    {
+      "entropy": 0.8075762838125229,
+      "epoch": 0.7677165354330708,
+      "grad_norm": 0.447265625,
+      "learning_rate": 0.00017457938990863908,
+      "loss": 0.7615089893341065,
+      "mean_token_accuracy": 0.8005614727735519,
+      "num_tokens": 4303838.0,
+      "step": 390
+    },
+    {
+      "entropy": 0.8942124575376511,
+      "epoch": 0.7874015748031497,
+      "grad_norm": 0.48828125,
+      "learning_rate": 0.00017314664410398033,
+      "loss": 0.8365015983581543,
+      "mean_token_accuracy": 0.7790710270404816,
+      "num_tokens": 4414002.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.7874015748031497,
+      "eval_entropy": 0.8613758815659417,
+      "eval_loss": 0.8455358743667603,
+      "eval_mean_token_accuracy": 0.7789811304321995,
+      "eval_num_tokens": 4414002.0,
+      "eval_runtime": 16.2401,
+      "eval_samples_per_second": 26.293,
+      "eval_steps_per_second": 3.325,
+      "step": 400
+    },
+    {
+      "entropy": 0.7841676041483879,
+      "epoch": 0.8070866141732284,
+      "grad_norm": 0.57421875,
+      "learning_rate": 0.0001716808515358714,
+      "loss": 0.8027224540710449,
+      "mean_token_accuracy": 0.79732064306736,
+      "num_tokens": 4525758.0,
+      "step": 410
+    },
+    {
+      "entropy": 0.7710117936134339,
+      "epoch": 0.8267716535433071,
+      "grad_norm": 0.4453125,
+      "learning_rate": 0.00017018267443155268,
+      "loss": 0.7185665130615234,
+      "mean_token_accuracy": 0.807221668958664,
+      "num_tokens": 4640742.0,
+      "step": 420
+    },
+    {
+      "entropy": 0.8494665056467057,
+      "epoch": 0.8464566929133859,
+      "grad_norm": 0.453125,
+      "learning_rate": 0.00016865278964920378,
+      "loss": 0.8273701667785645,
+      "mean_token_accuracy": 0.7870708376169204,
+      "num_tokens": 4754244.0,
+      "step": 430
+    },
+    {
+      "entropy": 0.7938957527279854,
+      "epoch": 0.8661417322834646,
+      "grad_norm": 0.345703125,
+      "learning_rate": 0.00016709188837214732,
+      "loss": 0.7776453971862793,
+      "mean_token_accuracy": 0.7911081612110138,
+      "num_tokens": 4862576.0,
+      "step": 440
+    },
+    {
+      "entropy": 0.7948901996016502,
+      "epoch": 0.8858267716535433,
+      "grad_norm": 0.376953125,
+      "learning_rate": 0.0001655006757965806,
+      "loss": 0.7554664611816406,
+      "mean_token_accuracy": 0.7939331024885178,
+      "num_tokens": 4984410.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.8858267716535433,
+      "eval_entropy": 0.8405309479545664,
+      "eval_loss": 0.8371886610984802,
+      "eval_mean_token_accuracy": 0.7799682672376986,
+      "eval_num_tokens": 4984410.0,
+      "eval_runtime": 15.9419,
+      "eval_samples_per_second": 26.785,
+      "eval_steps_per_second": 3.387,
+      "step": 450
+    },
+    {
+      "entropy": 0.8764406844973565,
+      "epoch": 0.905511811023622,
+      "grad_norm": 0.5625,
+      "learning_rate": 0.0001638798708129768,
+      "loss": 0.8325652122497559,
+      "mean_token_accuracy": 0.7821455717086792,
+      "num_tokens": 5094029.0,
+      "step": 460
+    },
+    {
+      "entropy": 0.8582975655794144,
+      "epoch": 0.9251968503937008,
+      "grad_norm": 0.3828125,
+      "learning_rate": 0.00016223020568129854,
+      "loss": 0.8309861183166504,
+      "mean_token_accuracy": 0.7791573971509933,
+      "num_tokens": 5210613.0,
+      "step": 470
+    },
+    {
+      "entropy": 0.8273941457271576,
+      "epoch": 0.9448818897637795,
+      "grad_norm": 0.59375,
+      "learning_rate": 0.00016055242570017244,
+      "loss": 0.7878972053527832,
+      "mean_token_accuracy": 0.7900911033153534,
+      "num_tokens": 5322546.0,
+      "step": 480
+    },
+    {
+      "entropy": 0.8146103203296662,
+      "epoch": 0.9645669291338582,
+      "grad_norm": 0.42578125,
+      "learning_rate": 0.00015884728887017162,
+      "loss": 0.7865399837493896,
+      "mean_token_accuracy": 0.7947310745716095,
+      "num_tokens": 5434008.0,
+      "step": 490
+    },
+    {
+      "entropy": 0.6613125756382943,
+      "epoch": 0.984251968503937,
+      "grad_norm": 0.41796875,
+      "learning_rate": 0.0001571155655513606,
+      "loss": 0.6725417137145996,
+      "mean_token_accuracy": 0.816859421133995,
+      "num_tokens": 5544086.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.984251968503937,
+      "eval_entropy": 0.8118620448642306,
+      "eval_loss": 0.8308539986610413,
+      "eval_mean_token_accuracy": 0.781522473803273,
+      "eval_num_tokens": 5544086.0,
+      "eval_runtime": 15.9383,
+      "eval_samples_per_second": 26.791,
+      "eval_steps_per_second": 3.388,
+      "step": 500
+    },
+    {
+      "entropy": 0.7347942754626274,
+      "epoch": 1.0039370078740157,
+      "grad_norm": 0.39453125,
+      "learning_rate": 0.0001553580381152559,
+      "loss": 0.6915054798126221,
+      "mean_token_accuracy": 0.8176700383424759,
+      "num_tokens": 5657246.0,
+      "step": 510
+    },
+    {
+      "entropy": 0.7550317242741584,
+      "epoch": 1.0236220472440944,
+      "grad_norm": 0.4921875,
+      "learning_rate": 0.0001535755005913602,
+      "loss": 0.6865068912506104,
+      "mean_token_accuracy": 0.8140248268842697,
+      "num_tokens": 5768184.0,
+      "step": 520
+    },
+    {
+      "entropy": 0.7479684263467788,
+      "epoch": 1.0433070866141732,
+      "grad_norm": 0.60546875,
+      "learning_rate": 0.00015176875830842938,
+      "loss": 0.7037695407867431,
+      "mean_token_accuracy": 0.8133333414793015,
+      "num_tokens": 5885598.0,
+      "step": 530
+    },
+    {
+      "entropy": 0.6792907789349556,
+      "epoch": 1.0629921259842519,
+      "grad_norm": 0.439453125,
+      "learning_rate": 0.0001499386275306348,
+      "loss": 0.640275239944458,
+      "mean_token_accuracy": 0.8249545454978943,
+      "num_tokens": 6002120.0,
+      "step": 540
+    },
+    {
+      "entropy": 0.6819084867835045,
+      "epoch": 1.0826771653543308,
+      "grad_norm": 0.41015625,
+      "learning_rate": 0.0001480859350887852,
+      "loss": 0.6469451904296875,
+      "mean_token_accuracy": 0.8235166579484939,
+      "num_tokens": 6112085.0,
+      "step": 550
+    },
+    {
+      "epoch": 1.0826771653543308,
+      "eval_entropy": 0.8042021377219094,
+      "eval_loss": 0.8352769017219543,
+      "eval_mean_token_accuracy": 0.7806271998970596,
+      "eval_num_tokens": 6112085.0,
+      "eval_runtime": 15.9298,
+      "eval_samples_per_second": 26.805,
+      "eval_steps_per_second": 3.39,
+      "step": 550
+    },
+    {
+      "entropy": 0.7026952266693115,
+      "epoch": 1.1023622047244095,
+      "grad_norm": 0.47265625,
+      "learning_rate": 0.00014621151800677434,
+      "loss": 0.667764139175415,
+      "mean_token_accuracy": 0.8164290696382522,
+      "num_tokens": 6224645.0,
+      "step": 560
+    },
+    {
+      "entropy": 0.6083555489778518,
+      "epoch": 1.1220472440944882,
+      "grad_norm": 0.37890625,
+      "learning_rate": 0.0001443162231234242,
+      "loss": 0.5703843116760254,
+      "mean_token_accuracy": 0.8396952480077744,
+      "num_tokens": 6336790.0,
+      "step": 570
+    },
+    {
+      "entropy": 0.6823922500014306,
+      "epoch": 1.141732283464567,
+      "grad_norm": 0.55078125,
+      "learning_rate": 0.0001424009067098931,
+      "loss": 0.6488718032836914,
+      "mean_token_accuracy": 0.8208951652050018,
+      "num_tokens": 6450761.0,
+      "step": 580
+    },
+    {
+      "entropy": 0.6331134095788002,
+      "epoch": 1.1614173228346456,
+      "grad_norm": 0.482421875,
+      "learning_rate": 0.00014046643408282305,
+      "loss": 0.5916334629058838,
+      "mean_token_accuracy": 0.8340157747268677,
+      "num_tokens": 6562060.0,
+      "step": 590
+    },
+    {
+      "entropy": 0.6203767985105515,
+      "epoch": 1.1811023622047245,
+      "grad_norm": 0.45703125,
+      "learning_rate": 0.00013851367921340017,
+      "loss": 0.5833216667175293,
+      "mean_token_accuracy": 0.8345949351787567,
+      "num_tokens": 6676922.0,
+      "step": 600
+    },
+    {
+      "epoch": 1.1811023622047245,
+      "eval_entropy": 0.7756788493306549,
+      "eval_loss": 0.8351659178733826,
+      "eval_mean_token_accuracy": 0.7810865651678156,
+      "eval_num_tokens": 6676922.0,
+      "eval_runtime": 15.9481,
+      "eval_samples_per_second": 26.774,
+      "eval_steps_per_second": 3.386,
+      "step": 600
+    },
+    {
+      "entropy": 0.645186324417591,
+      "epoch": 1.2007874015748032,
+      "grad_norm": 0.498046875,
+      "learning_rate": 0.0001365435243325051,
+      "loss": 0.6237170219421386,
+      "mean_token_accuracy": 0.8277532249689102,
+      "num_tokens": 6783497.0,
+      "step": 610
+    },
+    {
+      "entropy": 0.6759833052754403,
+      "epoch": 1.220472440944882,
+      "grad_norm": 0.546875,
+      "learning_rate": 0.00013455685953213194,
+      "loss": 0.6462036609649658,
+      "mean_token_accuracy": 0.8247299671173096,
+      "num_tokens": 6894014.0,
+      "step": 620
+    },
+    {
+      "entropy": 0.6737162366509437,
+      "epoch": 1.2401574803149606,
+      "grad_norm": 0.48828125,
+      "learning_rate": 0.0001325545823632554,
+      "loss": 0.6107028484344482,
+      "mean_token_accuracy": 0.8260864973068237,
+      "num_tokens": 6997350.0,
+      "step": 630
+    },
+    {
+      "entropy": 0.6702337503433228,
+      "epoch": 1.2598425196850394,
+      "grad_norm": 0.451171875,
+      "learning_rate": 0.00013053759743032823,
+      "loss": 0.6504123210906982,
+      "mean_token_accuracy": 0.818900191783905,
+      "num_tokens": 7109067.0,
+      "step": 640
+    },
+    {
+      "entropy": 0.7739008516073227,
+      "epoch": 1.279527559055118,
+      "grad_norm": 0.56640625,
+      "learning_rate": 0.00012850681598259195,
+      "loss": 0.7173595905303956,
+      "mean_token_accuracy": 0.7997365325689316,
+      "num_tokens": 7218739.0,
+      "step": 650
+    },
+    {
+      "epoch": 1.279527559055118,
+      "eval_entropy": 0.7500080190323017,
+      "eval_loss": 0.8297256231307983,
+      "eval_mean_token_accuracy": 0.7822851461392862,
+      "eval_num_tokens": 7218739.0,
+      "eval_runtime": 15.9417,
+      "eval_samples_per_second": 26.785,
+      "eval_steps_per_second": 3.387,
+      "step": 650
+    },
+    {
+      "entropy": 0.7080179423093795,
+      "epoch": 1.2992125984251968,
+      "grad_norm": 0.53125,
+      "learning_rate": 0.0001264631555023856,
+      "loss": 0.661363172531128,
+      "mean_token_accuracy": 0.8172380715608597,
+      "num_tokens": 7334561.0,
+      "step": 660
+    },
+    {
+      "entropy": 0.6184108316898346,
+      "epoch": 1.3188976377952755,
+      "grad_norm": 0.78515625,
+      "learning_rate": 0.00012440753929063826,
+      "loss": 0.6013145923614502,
+      "mean_token_accuracy": 0.8273262619972229,
+      "num_tokens": 7443871.0,
+      "step": 670
+    },
+    {
+      "entropy": 0.71297377794981,
+      "epoch": 1.3385826771653544,
+      "grad_norm": 0.5078125,
+      "learning_rate": 0.00012234089604973303,
+      "loss": 0.6702734470367432,
+      "mean_token_accuracy": 0.8151450455188751,
+      "num_tokens": 7555559.0,
+      "step": 680
+    },
+    {
+      "entropy": 0.6389088705182076,
+      "epoch": 1.358267716535433,
+      "grad_norm": 0.50390625,
+      "learning_rate": 0.0001202641594639305,
+      "loss": 0.6133567810058593,
+      "mean_token_accuracy": 0.8298202604055405,
+      "num_tokens": 7669861.0,
+      "step": 690
+    },
+    {
+      "entropy": 0.7520714432001114,
+      "epoch": 1.3779527559055118,
+      "grad_norm": 0.5390625,
+      "learning_rate": 0.00011817826777754171,
+      "loss": 0.6847642421722412,
+      "mean_token_accuracy": 0.8055585384368896,
+      "num_tokens": 7782831.0,
+      "step": 700
+    },
+    {
+      "epoch": 1.3779527559055118,
+      "eval_entropy": 0.7791200037355777,
+      "eval_loss": 0.8222253322601318,
+      "eval_mean_token_accuracy": 0.7843283326537521,
+      "eval_num_tokens": 7782831.0,
+      "eval_runtime": 15.9494,
+      "eval_samples_per_second": 26.772,
+      "eval_steps_per_second": 3.386,
+      "step": 700
+    },
+    {
+      "entropy": 0.7161616936326027,
+      "epoch": 1.3976377952755905,
+      "grad_norm": 0.421875,
+      "learning_rate": 0.00011608416337104065,
+      "loss": 0.6723262786865234,
+      "mean_token_accuracy": 0.8196182817220687,
+      "num_tokens": 7895511.0,
+      "step": 710
+    },
+    {
+      "entropy": 0.6407245740294456,
+      "epoch": 1.4173228346456692,
+      "grad_norm": 0.443359375,
+      "learning_rate": 0.00011398279233530829,
+      "loss": 0.6370048522949219,
+      "mean_token_accuracy": 0.8265632688999176,
+      "num_tokens": 8006186.0,
+      "step": 720
+    },
+    {
+      "entropy": 0.704089181125164,
+      "epoch": 1.4370078740157481,
+      "grad_norm": 0.51953125,
+      "learning_rate": 0.00011187510404420028,
+      "loss": 0.645330286026001,
+      "mean_token_accuracy": 0.8142861813306809,
+      "num_tokens": 8110444.0,
+      "step": 730
+    },
+    {
+      "entropy": 0.7673430755734444,
+      "epoch": 1.4566929133858268,
+      "grad_norm": 0.7109375,
+      "learning_rate": 0.00010976205072563132,
+      "loss": 0.7298968315124512,
+      "mean_token_accuracy": 0.8080587953329086,
+      "num_tokens": 8220128.0,
+      "step": 740
+    },
+    {
+      "entropy": 0.6395664170384407,
+      "epoch": 1.4763779527559056,
+      "grad_norm": 0.5078125,
+      "learning_rate": 0.00010764458703137024,
+      "loss": 0.6174263477325439,
+      "mean_token_accuracy": 0.8285290688276291,
+      "num_tokens": 8327961.0,
+      "step": 750
+    },
+    {
+      "epoch": 1.4763779527559056,
+      "eval_entropy": 0.7358508281133793,
+      "eval_loss": 0.8263605833053589,
+      "eval_mean_token_accuracy": 0.7838875507866895,
+      "eval_num_tokens": 8327961.0,
+      "eval_runtime": 15.9403,
+      "eval_samples_per_second": 26.787,
+      "eval_steps_per_second": 3.388,
+      "step": 750
+    },
+    {
+      "entropy": 0.701068015396595,
+      "epoch": 1.4960629921259843,
+      "grad_norm": 0.65625,
+      "learning_rate": 0.00010552366960573985,
+      "loss": 0.6718067646026611,
+      "mean_token_accuracy": 0.8166692137718201,
+      "num_tokens": 8432725.0,
+      "step": 760
+    },
+    {
+      "entropy": 0.6750249415636063,
+      "epoch": 1.515748031496063,
+      "grad_norm": 0.41796875,
+      "learning_rate": 0.00010340025665341684,
+      "loss": 0.6471256256103516,
+      "mean_token_accuracy": 0.8236999034881591,
+      "num_tokens": 8550042.0,
+      "step": 770
+    },
+    {
+      "entropy": 0.6500637173652649,
+      "epoch": 1.5354330708661417,
+      "grad_norm": 0.470703125,
+      "learning_rate": 0.00010127530750652642,
+      "loss": 0.5989052295684815,
+      "mean_token_accuracy": 0.8357917547225953,
+      "num_tokens": 8664499.0,
+      "step": 780
+    },
+    {
+      "entropy": 0.6429416075348854,
+      "epoch": 1.5551181102362204,
+      "grad_norm": 0.69140625,
+      "learning_rate": 9.914978219122791e-05,
+      "loss": 0.6052910327911377,
+      "mean_token_accuracy": 0.8295481771230697,
+      "num_tokens": 8778459.0,
+      "step": 790
+    },
+    {
+      "entropy": 0.6374648019671441,
+      "epoch": 1.574803149606299,
+      "grad_norm": 0.6484375,
+      "learning_rate": 9.702464099398632e-05,
+      "loss": 0.6044469833374023,
+      "mean_token_accuracy": 0.8315474331378937,
+      "num_tokens": 8886361.0,
+      "step": 800
+    },
+    {
+      "epoch": 1.574803149606299,
+      "eval_entropy": 0.7627564834223853,
+      "eval_loss": 0.8170398473739624,
+      "eval_mean_token_accuracy": 0.7843498874593664,
+      "eval_num_tokens": 8886361.0,
+      "eval_runtime": 15.9518,
+      "eval_samples_per_second": 26.768,
+      "eval_steps_per_second": 3.385,
+      "step": 800
+    },
+    {
+      "entropy": 0.6787230268120765,
+      "epoch": 1.594488188976378,
+      "grad_norm": 0.515625,
+      "learning_rate": 9.4900844027727e-05,
+      "loss": 0.6268706321716309,
+      "mean_token_accuracy": 0.8275486946105957,
+      "num_tokens": 8995558.0,
+      "step": 810
+    },
+    {
+      "entropy": 0.7012800723314285,
+      "epoch": 1.6141732283464567,
+      "grad_norm": 0.5390625,
+      "learning_rate": 9.277935079806795e-05,
+      "loss": 0.652205228805542,
+      "mean_token_accuracy": 0.8216399610042572,
+      "num_tokens": 9096245.0,
+      "step": 820
+    },
+    {
+      "entropy": 0.6063105046749115,
+      "epoch": 1.6338582677165354,
+      "grad_norm": 0.8125,
+      "learning_rate": 9.066111976982712e-05,
+      "loss": 0.597124719619751,
+      "mean_token_accuracy": 0.836309888958931,
+      "num_tokens": 9204264.0,
+      "step": 830
+    },
+    {
+      "entropy": 0.6953654140233994,
+      "epoch": 1.6535433070866141,
+      "grad_norm": 0.5,
+      "learning_rate": 8.854710793399947e-05,
+      "loss": 0.6501974105834961,
+      "mean_token_accuracy": 0.8178625762462616,
+      "num_tokens": 9314940.0,
+      "step": 840
+    },
+    {
+      "entropy": 0.6784902378916741,
+      "epoch": 1.673228346456693,
+      "grad_norm": 0.546875,
+      "learning_rate": 8.64382703754003e-05,
+      "loss": 0.636347484588623,
+      "mean_token_accuracy": 0.8207234263420105,
+      "num_tokens": 9429496.0,
+      "step": 850
+    },
+    {
+      "epoch": 1.673228346456693,
+      "eval_entropy": 0.7619620506410245,
+      "eval_loss": 0.8146092295646667,
+      "eval_mean_token_accuracy": 0.7850696554890385,
+      "eval_num_tokens": 9429496.0,
+      "eval_runtime": 15.937,
+      "eval_samples_per_second": 26.793,
+      "eval_steps_per_second": 3.388,
+      "step": 850
+    },
+    {
+      "entropy": 0.6777935117483139,
+      "epoch": 1.6929133858267718,
+      "grad_norm": 0.478515625,
+      "learning_rate": 8.433555984116937e-05,
+      "loss": 0.6113362312316895,
+      "mean_token_accuracy": 0.8263391226530075,
+      "num_tokens": 9544270.0,
+      "step": 860
+    },
+    {
+      "entropy": 0.6014138415455819,
+      "epoch": 1.7125984251968505,
+      "grad_norm": 0.53125,
+      "learning_rate": 8.22399263103314e-05,
+      "loss": 0.6068051338195801,
+      "mean_token_accuracy": 0.8325248181819915,
+      "num_tokens": 9654198.0,
+      "step": 870
+    },
+    {
+      "entropy": 0.6414325833320618,
+      "epoch": 1.7322834645669292,
+      "grad_norm": 0.69140625,
+      "learning_rate": 8.015231656460712e-05,
+      "loss": 0.6324831008911133,
+      "mean_token_accuracy": 0.834089708328247,
+      "num_tokens": 9769457.0,
+      "step": 880
+    },
+    {
+      "entropy": 0.6839869737625122,
+      "epoch": 1.7519685039370079,
+      "grad_norm": 0.5390625,
+      "learning_rate": 7.807367376066889e-05,
+      "loss": 0.6296841144561768,
+      "mean_token_accuracy": 0.8278504878282547,
+      "num_tokens": 9875831.0,
+      "step": 890
+    },
+    {
+      "entropy": 0.6922678858041763,
+      "epoch": 1.7716535433070866,
+      "grad_norm": 0.48046875,
+      "learning_rate": 7.60049370040338e-05,
+      "loss": 0.6325759887695312,
+      "mean_token_accuracy": 0.8210694164037704,
+      "num_tokens": 9991758.0,
+      "step": 900
+    },
+    {
+      "epoch": 1.7716535433070866,
+      "eval_entropy": 0.7464290934580343,
+      "eval_loss": 0.8118129372596741,
+      "eval_mean_token_accuracy": 0.7863925894101461,
+      "eval_num_tokens": 9991758.0,
+      "eval_runtime": 15.9375,
+      "eval_samples_per_second": 26.792,
+      "eval_steps_per_second": 3.388,
+      "step": 900
+    },
+    {
+      "entropy": 0.7232977166771889,
+      "epoch": 1.7913385826771653,
+      "grad_norm": 0.50390625,
+      "learning_rate": 7.394704092478742e-05,
+      "loss": 0.6871041774749755,
+      "mean_token_accuracy": 0.8109384387731552,
+      "num_tokens": 10106255.0,
+      "step": 910
+    },
+    {
+      "entropy": 0.639159494638443,
+      "epoch": 1.811023622047244,
+      "grad_norm": 0.51953125,
+      "learning_rate": 7.190091525532921e-05,
+      "loss": 0.5977220058441162,
+      "mean_token_accuracy": 0.8346921026706695,
+      "num_tokens": 10218066.0,
+      "step": 920
+    },
+    {
+      "entropy": 0.6970785558223724,
+      "epoch": 1.8307086614173227,
+      "grad_norm": 0.625,
+      "learning_rate": 6.98674844103308e-05,
+      "loss": 0.6659546852111816,
+      "mean_token_accuracy": 0.8177712321281433,
+      "num_tokens": 10326991.0,
+      "step": 930
+    },
+    {
+      "entropy": 0.705052088201046,
+      "epoch": 1.8503937007874016,
+      "grad_norm": 0.52734375,
+      "learning_rate": 6.784766706909662e-05,
+      "loss": 0.6586481094360351,
+      "mean_token_accuracy": 0.8198566019535065,
+      "num_tokens": 10432558.0,
+      "step": 940
+    },
+    {
+      "entropy": 0.6612584158778191,
+      "epoch": 1.8700787401574803,
+      "grad_norm": 0.65625,
+      "learning_rate": 6.58423757605158e-05,
+      "loss": 0.6631102561950684,
+      "mean_token_accuracy": 0.8250136137008667,
+      "num_tokens": 10541702.0,
+      "step": 950
+    },
+    {
+      "epoch": 1.8700787401574803,
+      "eval_entropy": 0.7582799510823356,
+      "eval_loss": 0.8087909817695618,
+      "eval_mean_token_accuracy": 0.7858658830324808,
+      "eval_num_tokens": 10541702.0,
+      "eval_runtime": 15.9386,
+      "eval_samples_per_second": 26.79,
+      "eval_steps_per_second": 3.388,
+      "step": 950
+    },
+    {
+      "entropy": 0.7153135001659393,
+      "epoch": 1.889763779527559,
+      "grad_norm": 0.52734375,
+      "learning_rate": 6.38525164507927e-05,
+      "loss": 0.6485848426818848,
+      "mean_token_accuracy": 0.8191622495651245,
+      "num_tokens": 10652431.0,
+      "step": 960
+    },
+    {
+      "entropy": 0.6808911249041557,
+      "epoch": 1.909448818897638,
+      "grad_norm": 0.578125,
+      "learning_rate": 6.187898813414251e-05,
+      "loss": 0.6528217315673828,
+      "mean_token_accuracy": 0.8256954222917556,
+      "num_tokens": 10766036.0,
+      "step": 970
+    },
+    {
+      "entropy": 0.6457046732306481,
+      "epoch": 1.9291338582677167,
+      "grad_norm": 0.65625,
+      "learning_rate": 5.99226824266365e-05,
+      "loss": 0.6104453086853028,
+      "mean_token_accuracy": 0.8297607868909835,
+      "num_tokens": 10869598.0,
+      "step": 980
+    },
+    {
+      "entropy": 0.6919459193944931,
+      "epoch": 1.9488188976377954,
+      "grad_norm": 0.640625,
+      "learning_rate": 5.7984483163380764e-05,
+      "loss": 0.6459432601928711,
+      "mean_token_accuracy": 0.8180149614810943,
+      "num_tokens": 10983085.0,
+      "step": 990
+    },
+    {
+      "entropy": 0.6444254025816918,
+      "epoch": 1.968503937007874,
+      "grad_norm": 0.578125,
+      "learning_rate": 5.606526599921026e-05,
+      "loss": 0.6290760517120362,
+      "mean_token_accuracy": 0.8319308578968048,
+      "num_tokens": 11090966.0,
+      "step": 1000
+    },
+    {
+      "epoch": 1.968503937007874,
+      "eval_entropy": 0.7388938731617398,
+      "eval_loss": 0.8063948154449463,
+      "eval_mean_token_accuracy": 0.786332004600101,
+      "eval_num_tokens": 11090966.0,
+      "eval_runtime": 15.9242,
+      "eval_samples_per_second": 26.814,
+      "eval_steps_per_second": 3.391,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1524,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.5660697793799168e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3f0e55ef6f28af070d9ef917c7e02ff815b9b702bccb82471082d69e77b490b
+size 5713

checkpoint-1050/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-Math-1.5B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Math-1.5B-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-1050/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Math-1.5B-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": 0.05,
+  "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": [
+    "down_proj",
+    "v_proj",
+    "o_proj",
+    "q_proj",
+    "up_proj",
+    "k_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-1050/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0adfe83ac12e39dc651a070343bc45b759ef58974ef14941c46f12971fa902bc
+size 73911504

checkpoint-1050/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'Please reason step by step, and put your final answer within \\boxed{}.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nPlease reason step by step, and put your final answer within \\boxed{}.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoint-1050/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07b45d83bdad1b2e9f30ea5c8a59789f0e9b89dfad37650c70f0f666e2de072b
+size 75481221

checkpoint-1050/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:390fc870f4ade423a549d8a2e2709fb1d7044ee4045de597cdb25006a87bc748
+size 14581

checkpoint-1050/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ba5e4970732fab54b57f4efe63c132ac3f4d4d587d25cf239934cb85e74c6f9
+size 1465

checkpoint-1050/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

checkpoint-1050/tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "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,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|fim_pad|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1050/trainer_state.json

@@ -0,0 +1,1315 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0669291338582676,
+  "eval_steps": 50,
+  "global_step": 1050,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.4378354728221894,
+      "epoch": 0.01968503937007874,
+      "grad_norm": 0.62109375,
+      "learning_rate": 3.91304347826087e-05,
+      "loss": 1.657682228088379,
+      "mean_token_accuracy": 0.6598833322525024,
+      "num_tokens": 115439.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.5141301095485686,
+      "epoch": 0.03937007874015748,
+      "grad_norm": 0.44140625,
+      "learning_rate": 8.260869565217392e-05,
+      "loss": 1.4646138191223144,
+      "mean_token_accuracy": 0.6834615051746369,
+      "num_tokens": 225264.0,
+      "step": 20
+    },
+    {
+      "entropy": 1.2295305937528611,
+      "epoch": 0.05905511811023622,
+      "grad_norm": 0.6796875,
+      "learning_rate": 0.00012608695652173915,
+      "loss": 1.1134957313537597,
+      "mean_token_accuracy": 0.7453642427921295,
+      "num_tokens": 330923.0,
+      "step": 30
+    },
+    {
+      "entropy": 1.0573274463415145,
+      "epoch": 0.07874015748031496,
+      "grad_norm": 0.474609375,
+      "learning_rate": 0.00016956521739130436,
+      "loss": 1.077296829223633,
+      "mean_token_accuracy": 0.7446383863687516,
+      "num_tokens": 437622.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.952904561161995,
+      "epoch": 0.0984251968503937,
+      "grad_norm": 0.50390625,
+      "learning_rate": 0.00019999796688511753,
+      "loss": 0.9590332984924317,
+      "mean_token_accuracy": 0.768164387345314,
+      "num_tokens": 551175.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.0984251968503937,
+      "eval_entropy": 1.0900797645250957,
+      "eval_loss": 1.0484484434127808,
+      "eval_mean_token_accuracy": 0.7461776600943671,
+      "eval_num_tokens": 551175.0,
+      "eval_runtime": 15.9866,
+      "eval_samples_per_second": 26.71,
+      "eval_steps_per_second": 3.378,
+      "step": 50
+    },
+    {
+      "entropy": 0.9487997680902481,
+      "epoch": 0.11811023622047244,
+      "grad_norm": 0.59375,
+      "learning_rate": 0.0001999618249203163,
+      "loss": 0.9577752113342285,
+      "mean_token_accuracy": 0.7689193069934845,
+      "num_tokens": 658006.0,
+      "step": 60
+    },
+    {
+      "entropy": 1.0506175458431244,
+      "epoch": 0.1377952755905512,
+      "grad_norm": 0.5390625,
+      "learning_rate": 0.00019988052141977201,
+      "loss": 0.9976933479309082,
+      "mean_token_accuracy": 0.756487911939621,
+      "num_tokens": 771278.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.8528705358505249,
+      "epoch": 0.15748031496062992,
+      "grad_norm": 0.5078125,
+      "learning_rate": 0.0001997540931154166,
+      "loss": 0.8407608032226562,
+      "mean_token_accuracy": 0.7868376106023789,
+      "num_tokens": 886071.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.9220433413982392,
+      "epoch": 0.17716535433070865,
+      "grad_norm": 0.484375,
+      "learning_rate": 0.00019958259712601903,
+      "loss": 0.8958203315734863,
+      "mean_token_accuracy": 0.7736223608255386,
+      "num_tokens": 996361.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.8399994730949402,
+      "epoch": 0.1968503937007874,
+      "grad_norm": 0.51953125,
+      "learning_rate": 0.00019936611093137983,
+      "loss": 0.8394058227539063,
+      "mean_token_accuracy": 0.7876519203186035,
+      "num_tokens": 1103999.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.1968503937007874,
+      "eval_entropy": 0.9908565746413337,
+      "eval_loss": 0.949418842792511,
+      "eval_mean_token_accuracy": 0.7609190278583102,
+      "eval_num_tokens": 1103999.0,
+      "eval_runtime": 15.9475,
+      "eval_samples_per_second": 26.775,
+      "eval_steps_per_second": 3.386,
+      "step": 100
+    },
+    {
+      "entropy": 0.8772778362035751,
+      "epoch": 0.21653543307086615,
+      "grad_norm": 0.40625,
+      "learning_rate": 0.00019910473233732668,
+      "loss": 0.8347702026367188,
+      "mean_token_accuracy": 0.7877911299467086,
+      "num_tokens": 1216586.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.8745568007230758,
+      "epoch": 0.23622047244094488,
+      "grad_norm": 0.609375,
+      "learning_rate": 0.00019879857943152674,
+      "loss": 0.8359953880310058,
+      "mean_token_accuracy": 0.7790884494781494,
+      "num_tokens": 1324767.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.878146781027317,
+      "epoch": 0.2559055118110236,
+      "grad_norm": 0.5390625,
+      "learning_rate": 0.00019844779053013637,
+      "loss": 0.8335110664367675,
+      "mean_token_accuracy": 0.7791220843791962,
+      "num_tokens": 1432356.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.788033875823021,
+      "epoch": 0.2755905511811024,
+      "grad_norm": 0.546875,
+      "learning_rate": 0.00019805252411531126,
+      "loss": 0.7967269420623779,
+      "mean_token_accuracy": 0.7931749552488327,
+      "num_tokens": 1542545.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.8667207360267639,
+      "epoch": 0.2952755905511811,
+      "grad_norm": 0.5546875,
+      "learning_rate": 0.0001976129587636064,
+      "loss": 0.8101954460144043,
+      "mean_token_accuracy": 0.7908060193061829,
+      "num_tokens": 1654462.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.2952755905511811,
+      "eval_entropy": 0.9391163366812246,
+      "eval_loss": 0.9146928191184998,
+      "eval_mean_token_accuracy": 0.7670937886944523,
+      "eval_num_tokens": 1654462.0,
+      "eval_runtime": 15.956,
+      "eval_samples_per_second": 26.761,
+      "eval_steps_per_second": 3.384,
+      "step": 150
+    },
+    {
+      "entropy": 0.769407157599926,
+      "epoch": 0.31496062992125984,
+      "grad_norm": 0.470703125,
+      "learning_rate": 0.00019712929306529723,
+      "loss": 0.7655523777008056,
+      "mean_token_accuracy": 0.8053037762641907,
+      "num_tokens": 1760181.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.8818381905555726,
+      "epoch": 0.3346456692913386,
+      "grad_norm": 0.625,
+      "learning_rate": 0.000196601745534659,
+      "loss": 0.8408863067626953,
+      "mean_token_accuracy": 0.7815578579902649,
+      "num_tokens": 1864683.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.8344995141029358,
+      "epoch": 0.3543307086614173,
+      "grad_norm": 0.4765625,
+      "learning_rate": 0.0001960305545112445,
+      "loss": 0.8205550193786622,
+      "mean_token_accuracy": 0.7871369570493698,
+      "num_tokens": 1978641.0,
+      "step": 180
+    },
+    {
+      "entropy": 0.8058241099119187,
+      "epoch": 0.37401574803149606,
+      "grad_norm": 0.494140625,
+      "learning_rate": 0.0001954159780522056,
+      "loss": 0.8002825736999511,
+      "mean_token_accuracy": 0.7913093209266663,
+      "num_tokens": 2087989.0,
+      "step": 190
+    },
+    {
+      "entropy": 0.8938606142997741,
+      "epoch": 0.3937007874015748,
+      "grad_norm": 0.61328125,
+      "learning_rate": 0.00019475829381570566,
+      "loss": 0.8305434226989746,
+      "mean_token_accuracy": 0.7836446255445481,
+      "num_tokens": 2195494.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.3937007874015748,
+      "eval_entropy": 0.9502577009024443,
+      "eval_loss": 0.8978050351142883,
+      "eval_mean_token_accuracy": 0.7696934717672842,
+      "eval_num_tokens": 2195494.0,
+      "eval_runtime": 15.9419,
+      "eval_samples_per_second": 26.785,
+      "eval_steps_per_second": 3.387,
+      "step": 200
+    },
+    {
+      "entropy": 0.7890492826700211,
+      "epoch": 0.41338582677165353,
+      "grad_norm": 0.40625,
+      "learning_rate": 0.0001940577989354773,
+      "loss": 0.7953387260437011,
+      "mean_token_accuracy": 0.7982505321502685,
+      "num_tokens": 2314228.0,
+      "step": 210
+    },
+    {
+      "entropy": 0.8576261162757873,
+      "epoch": 0.4330708661417323,
+      "grad_norm": 0.66015625,
+      "learning_rate": 0.00019331480988658083,
+      "loss": 0.8120486259460449,
+      "mean_token_accuracy": 0.7829198718070984,
+      "num_tokens": 2419122.0,
+      "step": 220
+    },
+    {
+      "entropy": 0.8514308303594589,
+      "epoch": 0.452755905511811,
+      "grad_norm": 0.470703125,
+      "learning_rate": 0.00019252966234242468,
+      "loss": 0.8203784942626953,
+      "mean_token_accuracy": 0.7819343030452728,
+      "num_tokens": 2524623.0,
+      "step": 230
+    },
+    {
+      "entropy": 0.8994888842105866,
+      "epoch": 0.47244094488188976,
+      "grad_norm": 0.59765625,
+      "learning_rate": 0.00019170271102311238,
+      "loss": 0.9019557952880859,
+      "mean_token_accuracy": 0.7712395042181015,
+      "num_tokens": 2631031.0,
+      "step": 240
+    },
+    {
+      "entropy": 0.7910601049661636,
+      "epoch": 0.4921259842519685,
+      "grad_norm": 0.494140625,
+      "learning_rate": 0.00019083432953518418,
+      "loss": 0.8107678413391113,
+      "mean_token_accuracy": 0.7996705889701843,
+      "num_tokens": 2741031.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.4921259842519685,
+      "eval_entropy": 0.9037868281205496,
+      "eval_loss": 0.8843846917152405,
+      "eval_mean_token_accuracy": 0.7717091352851303,
+      "eval_num_tokens": 2741031.0,
+      "eval_runtime": 15.93,
+      "eval_samples_per_second": 26.805,
+      "eval_steps_per_second": 3.39,
+      "step": 250
+    },
+    {
+      "entropy": 0.7740790158510208,
+      "epoch": 0.5118110236220472,
+      "grad_norm": 0.57421875,
+      "learning_rate": 0.00018992491020282618,
+      "loss": 0.7579652309417725,
+      "mean_token_accuracy": 0.7955388814210892,
+      "num_tokens": 2853547.0,
+      "step": 260
+    },
+    {
+      "entropy": 0.8572690159082412,
+      "epoch": 0.531496062992126,
+      "grad_norm": 1.171875,
+      "learning_rate": 0.0001889748638906231,
+      "loss": 0.8072081565856933,
+      "mean_token_accuracy": 0.7910655379295349,
+      "num_tokens": 2968367.0,
+      "step": 270
+    },
+    {
+      "entropy": 0.8885004252195359,
+      "epoch": 0.5511811023622047,
+      "grad_norm": 0.451171875,
+      "learning_rate": 0.00018798461981793462,
+      "loss": 0.8460770606994629,
+      "mean_token_accuracy": 0.7776093751192092,
+      "num_tokens": 3075963.0,
+      "step": 280
+    },
+    {
+      "entropy": 0.829613895714283,
+      "epoch": 0.5708661417322834,
+      "grad_norm": 0.4453125,
+      "learning_rate": 0.00018695462536497934,
+      "loss": 0.823792839050293,
+      "mean_token_accuracy": 0.7848509013652801,
+      "num_tokens": 3185899.0,
+      "step": 290
+    },
+    {
+      "entropy": 0.8341330245137215,
+      "epoch": 0.5905511811023622,
+      "grad_norm": 0.490234375,
+      "learning_rate": 0.00018588534587071385,
+      "loss": 0.810818099975586,
+      "mean_token_accuracy": 0.7906568497419357,
+      "num_tokens": 3297319.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.5905511811023622,
+      "eval_entropy": 0.8445847459413387,
+      "eval_loss": 0.8718247413635254,
+      "eval_mean_token_accuracy": 0.774838043583764,
+      "eval_num_tokens": 3297319.0,
+      "eval_runtime": 15.9561,
+      "eval_samples_per_second": 26.761,
+      "eval_steps_per_second": 3.384,
+      "step": 300
+    },
+    {
+      "entropy": 0.8317201763391495,
+      "epoch": 0.610236220472441,
+      "grad_norm": 0.396484375,
+      "learning_rate": 0.00018477726442259806,
+      "loss": 0.80075101852417,
+      "mean_token_accuracy": 0.7886052161455155,
+      "num_tokens": 3415477.0,
+      "step": 310
+    },
+    {
+      "entropy": 0.8597566410899162,
+      "epoch": 0.6299212598425197,
+      "grad_norm": 0.404296875,
+      "learning_rate": 0.00018363088163834252,
+      "loss": 0.8123328208923339,
+      "mean_token_accuracy": 0.7854531407356262,
+      "num_tokens": 3524759.0,
+      "step": 320
+    },
+    {
+      "entropy": 0.8519140958786011,
+      "epoch": 0.6496062992125984,
+      "grad_norm": 0.458984375,
+      "learning_rate": 0.00018244671543973513,
+      "loss": 0.8214571952819825,
+      "mean_token_accuracy": 0.7828344345092774,
+      "num_tokens": 3640838.0,
+      "step": 330
+    },
+    {
+      "entropy": 0.7781533747911453,
+      "epoch": 0.6692913385826772,
+      "grad_norm": 0.51953125,
+      "learning_rate": 0.0001812253008186505,
+      "loss": 0.753899097442627,
+      "mean_token_accuracy": 0.8011120349168778,
+      "num_tokens": 3756735.0,
+      "step": 340
+    },
+    {
+      "entropy": 0.8384901583194733,
+      "epoch": 0.6889763779527559,
+      "grad_norm": 0.51171875,
+      "learning_rate": 0.0001799671895953471,
+      "loss": 0.8112489700317382,
+      "mean_token_accuracy": 0.7898134678602219,
+      "num_tokens": 3870377.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.6889763779527559,
+      "eval_entropy": 0.8795759567507991,
+      "eval_loss": 0.8568941354751587,
+      "eval_mean_token_accuracy": 0.7754804182935644,
+      "eval_num_tokens": 3870377.0,
+      "eval_runtime": 15.9337,
+      "eval_samples_per_second": 26.798,
+      "eval_steps_per_second": 3.389,
+      "step": 350
+    },
+    {
+      "entropy": 0.8008699864149094,
+      "epoch": 0.7086614173228346,
+      "grad_norm": 0.498046875,
+      "learning_rate": 0.00017867295016916167,
+      "loss": 0.7585730075836181,
+      "mean_token_accuracy": 0.7942175149917603,
+      "num_tokens": 3975692.0,
+      "step": 360
+    },
+    {
+      "entropy": 0.9035080641508102,
+      "epoch": 0.7283464566929134,
+      "grad_norm": 0.48046875,
+      "learning_rate": 0.0001773431672617132,
+      "loss": 0.8653995513916015,
+      "mean_token_accuracy": 0.7730168104171753,
+      "num_tokens": 4087256.0,
+      "step": 370
+    },
+    {
+      "entropy": 0.760843014717102,
+      "epoch": 0.7480314960629921,
+      "grad_norm": 0.49609375,
+      "learning_rate": 0.00017597844165273286,
+      "loss": 0.7377382278442383,
+      "mean_token_accuracy": 0.7972156703472137,
+      "num_tokens": 4192629.0,
+      "step": 380
+    },
+    {
+      "entropy": 0.8075762838125229,
+      "epoch": 0.7677165354330708,
+      "grad_norm": 0.447265625,
+      "learning_rate": 0.00017457938990863908,
+      "loss": 0.7615089893341065,
+      "mean_token_accuracy": 0.8005614727735519,
+      "num_tokens": 4303838.0,
+      "step": 390
+    },
+    {
+      "entropy": 0.8942124575376511,
+      "epoch": 0.7874015748031497,
+      "grad_norm": 0.48828125,
+      "learning_rate": 0.00017314664410398033,
+      "loss": 0.8365015983581543,
+      "mean_token_accuracy": 0.7790710270404816,
+      "num_tokens": 4414002.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.7874015748031497,
+      "eval_entropy": 0.8613758815659417,
+      "eval_loss": 0.8455358743667603,
+      "eval_mean_token_accuracy": 0.7789811304321995,
+      "eval_num_tokens": 4414002.0,
+      "eval_runtime": 16.2401,
+      "eval_samples_per_second": 26.293,
+      "eval_steps_per_second": 3.325,
+      "step": 400
+    },
+    {
+      "entropy": 0.7841676041483879,
+      "epoch": 0.8070866141732284,
+      "grad_norm": 0.57421875,
+      "learning_rate": 0.0001716808515358714,
+      "loss": 0.8027224540710449,
+      "mean_token_accuracy": 0.79732064306736,
+      "num_tokens": 4525758.0,
+      "step": 410
+    },
+    {
+      "entropy": 0.7710117936134339,
+      "epoch": 0.8267716535433071,
+      "grad_norm": 0.4453125,
+      "learning_rate": 0.00017018267443155268,
+      "loss": 0.7185665130615234,
+      "mean_token_accuracy": 0.807221668958664,
+      "num_tokens": 4640742.0,
+      "step": 420
+    },
+    {
+      "entropy": 0.8494665056467057,
+      "epoch": 0.8464566929133859,
+      "grad_norm": 0.453125,
+      "learning_rate": 0.00016865278964920378,
+      "loss": 0.8273701667785645,
+      "mean_token_accuracy": 0.7870708376169204,
+      "num_tokens": 4754244.0,
+      "step": 430
+    },
+    {
+      "entropy": 0.7938957527279854,
+      "epoch": 0.8661417322834646,
+      "grad_norm": 0.345703125,
+      "learning_rate": 0.00016709188837214732,
+      "loss": 0.7776453971862793,
+      "mean_token_accuracy": 0.7911081612110138,
+      "num_tokens": 4862576.0,
+      "step": 440
+    },
+    {
+      "entropy": 0.7948901996016502,
+      "epoch": 0.8858267716535433,
+      "grad_norm": 0.376953125,
+      "learning_rate": 0.0001655006757965806,
+      "loss": 0.7554664611816406,
+      "mean_token_accuracy": 0.7939331024885178,
+      "num_tokens": 4984410.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.8858267716535433,
+      "eval_entropy": 0.8405309479545664,
+      "eval_loss": 0.8371886610984802,
+      "eval_mean_token_accuracy": 0.7799682672376986,
+      "eval_num_tokens": 4984410.0,
+      "eval_runtime": 15.9419,
+      "eval_samples_per_second": 26.785,
+      "eval_steps_per_second": 3.387,
+      "step": 450
+    },
+    {
+      "entropy": 0.8764406844973565,
+      "epoch": 0.905511811023622,
+      "grad_norm": 0.5625,
+      "learning_rate": 0.0001638798708129768,
+      "loss": 0.8325652122497559,
+      "mean_token_accuracy": 0.7821455717086792,
+      "num_tokens": 5094029.0,
+      "step": 460
+    },
+    {
+      "entropy": 0.8582975655794144,
+      "epoch": 0.9251968503937008,
+      "grad_norm": 0.3828125,
+      "learning_rate": 0.00016223020568129854,
+      "loss": 0.8309861183166504,
+      "mean_token_accuracy": 0.7791573971509933,
+      "num_tokens": 5210613.0,
+      "step": 470
+    },
+    {
+      "entropy": 0.8273941457271576,
+      "epoch": 0.9448818897637795,
+      "grad_norm": 0.59375,
+      "learning_rate": 0.00016055242570017244,
+      "loss": 0.7878972053527832,
+      "mean_token_accuracy": 0.7900911033153534,
+      "num_tokens": 5322546.0,
+      "step": 480
+    },
+    {
+      "entropy": 0.8146103203296662,
+      "epoch": 0.9645669291338582,
+      "grad_norm": 0.42578125,
+      "learning_rate": 0.00015884728887017162,
+      "loss": 0.7865399837493896,
+      "mean_token_accuracy": 0.7947310745716095,
+      "num_tokens": 5434008.0,
+      "step": 490
+    },
+    {
+      "entropy": 0.6613125756382943,
+      "epoch": 0.984251968503937,
+      "grad_norm": 0.41796875,
+      "learning_rate": 0.0001571155655513606,
+      "loss": 0.6725417137145996,
+      "mean_token_accuracy": 0.816859421133995,
+      "num_tokens": 5544086.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.984251968503937,
+      "eval_entropy": 0.8118620448642306,
+      "eval_loss": 0.8308539986610413,
+      "eval_mean_token_accuracy": 0.781522473803273,
+      "eval_num_tokens": 5544086.0,
+      "eval_runtime": 15.9383,
+      "eval_samples_per_second": 26.791,
+      "eval_steps_per_second": 3.388,
+      "step": 500
+    },
+    {
+      "entropy": 0.7347942754626274,
+      "epoch": 1.0039370078740157,
+      "grad_norm": 0.39453125,
+      "learning_rate": 0.0001553580381152559,
+      "loss": 0.6915054798126221,
+      "mean_token_accuracy": 0.8176700383424759,
+      "num_tokens": 5657246.0,
+      "step": 510
+    },
+    {
+      "entropy": 0.7550317242741584,
+      "epoch": 1.0236220472440944,
+      "grad_norm": 0.4921875,
+      "learning_rate": 0.0001535755005913602,
+      "loss": 0.6865068912506104,
+      "mean_token_accuracy": 0.8140248268842697,
+      "num_tokens": 5768184.0,
+      "step": 520
+    },
+    {
+      "entropy": 0.7479684263467788,
+      "epoch": 1.0433070866141732,
+      "grad_norm": 0.60546875,
+      "learning_rate": 0.00015176875830842938,
+      "loss": 0.7037695407867431,
+      "mean_token_accuracy": 0.8133333414793015,
+      "num_tokens": 5885598.0,
+      "step": 530
+    },
+    {
+      "entropy": 0.6792907789349556,
+      "epoch": 1.0629921259842519,
+      "grad_norm": 0.439453125,
+      "learning_rate": 0.0001499386275306348,
+      "loss": 0.640275239944458,
+      "mean_token_accuracy": 0.8249545454978943,
+      "num_tokens": 6002120.0,
+      "step": 540
+    },
+    {
+      "entropy": 0.6819084867835045,
+      "epoch": 1.0826771653543308,
+      "grad_norm": 0.41015625,
+      "learning_rate": 0.0001480859350887852,
+      "loss": 0.6469451904296875,
+      "mean_token_accuracy": 0.8235166579484939,
+      "num_tokens": 6112085.0,
+      "step": 550
+    },
+    {
+      "epoch": 1.0826771653543308,
+      "eval_entropy": 0.8042021377219094,
+      "eval_loss": 0.8352769017219543,
+      "eval_mean_token_accuracy": 0.7806271998970596,
+      "eval_num_tokens": 6112085.0,
+      "eval_runtime": 15.9298,
+      "eval_samples_per_second": 26.805,
+      "eval_steps_per_second": 3.39,
+      "step": 550
+    },
+    {
+      "entropy": 0.7026952266693115,
+      "epoch": 1.1023622047244095,
+      "grad_norm": 0.47265625,
+      "learning_rate": 0.00014621151800677434,
+      "loss": 0.667764139175415,
+      "mean_token_accuracy": 0.8164290696382522,
+      "num_tokens": 6224645.0,
+      "step": 560
+    },
+    {
+      "entropy": 0.6083555489778518,
+      "epoch": 1.1220472440944882,
+      "grad_norm": 0.37890625,
+      "learning_rate": 0.0001443162231234242,
+      "loss": 0.5703843116760254,
+      "mean_token_accuracy": 0.8396952480077744,
+      "num_tokens": 6336790.0,
+      "step": 570
+    },
+    {
+      "entropy": 0.6823922500014306,
+      "epoch": 1.141732283464567,
+      "grad_norm": 0.55078125,
+      "learning_rate": 0.0001424009067098931,
+      "loss": 0.6488718032836914,
+      "mean_token_accuracy": 0.8208951652050018,
+      "num_tokens": 6450761.0,
+      "step": 580
+    },
+    {
+      "entropy": 0.6331134095788002,
+      "epoch": 1.1614173228346456,
+      "grad_norm": 0.482421875,
+      "learning_rate": 0.00014046643408282305,
+      "loss": 0.5916334629058838,
+      "mean_token_accuracy": 0.8340157747268677,
+      "num_tokens": 6562060.0,
+      "step": 590
+    },
+    {
+      "entropy": 0.6203767985105515,
+      "epoch": 1.1811023622047245,
+      "grad_norm": 0.45703125,
+      "learning_rate": 0.00013851367921340017,
+      "loss": 0.5833216667175293,
+      "mean_token_accuracy": 0.8345949351787567,
+      "num_tokens": 6676922.0,
+      "step": 600
+    },
+    {
+      "epoch": 1.1811023622047245,
+      "eval_entropy": 0.7756788493306549,
+      "eval_loss": 0.8351659178733826,
+      "eval_mean_token_accuracy": 0.7810865651678156,
+      "eval_num_tokens": 6676922.0,
+      "eval_runtime": 15.9481,
+      "eval_samples_per_second": 26.774,
+      "eval_steps_per_second": 3.386,
+      "step": 600
+    },
+    {
+      "entropy": 0.645186324417591,
+      "epoch": 1.2007874015748032,
+      "grad_norm": 0.498046875,
+      "learning_rate": 0.0001365435243325051,
+      "loss": 0.6237170219421386,
+      "mean_token_accuracy": 0.8277532249689102,
+      "num_tokens": 6783497.0,
+      "step": 610
+    },
+    {
+      "entropy": 0.6759833052754403,
+      "epoch": 1.220472440944882,
+      "grad_norm": 0.546875,
+      "learning_rate": 0.00013455685953213194,
+      "loss": 0.6462036609649658,
+      "mean_token_accuracy": 0.8247299671173096,
+      "num_tokens": 6894014.0,
+      "step": 620
+    },
+    {
+      "entropy": 0.6737162366509437,
+      "epoch": 1.2401574803149606,
+      "grad_norm": 0.48828125,
+      "learning_rate": 0.0001325545823632554,
+      "loss": 0.6107028484344482,
+      "mean_token_accuracy": 0.8260864973068237,
+      "num_tokens": 6997350.0,
+      "step": 630
+    },
+    {
+      "entropy": 0.6702337503433228,
+      "epoch": 1.2598425196850394,
+      "grad_norm": 0.451171875,
+      "learning_rate": 0.00013053759743032823,
+      "loss": 0.6504123210906982,
+      "mean_token_accuracy": 0.818900191783905,
+      "num_tokens": 7109067.0,
+      "step": 640
+    },
+    {
+      "entropy": 0.7739008516073227,
+      "epoch": 1.279527559055118,
+      "grad_norm": 0.56640625,
+      "learning_rate": 0.00012850681598259195,
+      "loss": 0.7173595905303956,
+      "mean_token_accuracy": 0.7997365325689316,
+      "num_tokens": 7218739.0,
+      "step": 650
+    },
+    {
+      "epoch": 1.279527559055118,
+      "eval_entropy": 0.7500080190323017,
+      "eval_loss": 0.8297256231307983,
+      "eval_mean_token_accuracy": 0.7822851461392862,
+      "eval_num_tokens": 7218739.0,
+      "eval_runtime": 15.9417,
+      "eval_samples_per_second": 26.785,
+      "eval_steps_per_second": 3.387,
+      "step": 650
+    },
+    {
+      "entropy": 0.7080179423093795,
+      "epoch": 1.2992125984251968,
+      "grad_norm": 0.53125,
+      "learning_rate": 0.0001264631555023856,
+      "loss": 0.661363172531128,
+      "mean_token_accuracy": 0.8172380715608597,
+      "num_tokens": 7334561.0,
+      "step": 660
+    },
+    {
+      "entropy": 0.6184108316898346,
+      "epoch": 1.3188976377952755,
+      "grad_norm": 0.78515625,
+      "learning_rate": 0.00012440753929063826,
+      "loss": 0.6013145923614502,
+      "mean_token_accuracy": 0.8273262619972229,
+      "num_tokens": 7443871.0,
+      "step": 670
+    },
+    {
+      "entropy": 0.71297377794981,
+      "epoch": 1.3385826771653544,
+      "grad_norm": 0.5078125,
+      "learning_rate": 0.00012234089604973303,
+      "loss": 0.6702734470367432,
+      "mean_token_accuracy": 0.8151450455188751,
+      "num_tokens": 7555559.0,
+      "step": 680
+    },
+    {
+      "entropy": 0.6389088705182076,
+      "epoch": 1.358267716535433,
+      "grad_norm": 0.50390625,
+      "learning_rate": 0.0001202641594639305,
+      "loss": 0.6133567810058593,
+      "mean_token_accuracy": 0.8298202604055405,
+      "num_tokens": 7669861.0,
+      "step": 690
+    },
+    {
+      "entropy": 0.7520714432001114,
+      "epoch": 1.3779527559055118,
+      "grad_norm": 0.5390625,
+      "learning_rate": 0.00011817826777754171,
+      "loss": 0.6847642421722412,
+      "mean_token_accuracy": 0.8055585384368896,
+      "num_tokens": 7782831.0,
+      "step": 700
+    },
+    {
+      "epoch": 1.3779527559055118,
+      "eval_entropy": 0.7791200037355777,
+      "eval_loss": 0.8222253322601318,
+      "eval_mean_token_accuracy": 0.7843283326537521,
+      "eval_num_tokens": 7782831.0,
+      "eval_runtime": 15.9494,
+      "eval_samples_per_second": 26.772,
+      "eval_steps_per_second": 3.386,
+      "step": 700
+    },
+    {
+      "entropy": 0.7161616936326027,
+      "epoch": 1.3976377952755905,
+      "grad_norm": 0.421875,
+      "learning_rate": 0.00011608416337104065,
+      "loss": 0.6723262786865234,
+      "mean_token_accuracy": 0.8196182817220687,
+      "num_tokens": 7895511.0,
+      "step": 710
+    },
+    {
+      "entropy": 0.6407245740294456,
+      "epoch": 1.4173228346456692,
+      "grad_norm": 0.443359375,
+      "learning_rate": 0.00011398279233530829,
+      "loss": 0.6370048522949219,
+      "mean_token_accuracy": 0.8265632688999176,
+      "num_tokens": 8006186.0,
+      "step": 720
+    },
+    {
+      "entropy": 0.704089181125164,
+      "epoch": 1.4370078740157481,
+      "grad_norm": 0.51953125,
+      "learning_rate": 0.00011187510404420028,
+      "loss": 0.645330286026001,
+      "mean_token_accuracy": 0.8142861813306809,
+      "num_tokens": 8110444.0,
+      "step": 730
+    },
+    {
+      "entropy": 0.7673430755734444,
+      "epoch": 1.4566929133858268,
+      "grad_norm": 0.7109375,
+      "learning_rate": 0.00010976205072563132,
+      "loss": 0.7298968315124512,
+      "mean_token_accuracy": 0.8080587953329086,
+      "num_tokens": 8220128.0,
+      "step": 740
+    },
+    {
+      "entropy": 0.6395664170384407,
+      "epoch": 1.4763779527559056,
+      "grad_norm": 0.5078125,
+      "learning_rate": 0.00010764458703137024,
+      "loss": 0.6174263477325439,
+      "mean_token_accuracy": 0.8285290688276291,
+      "num_tokens": 8327961.0,
+      "step": 750
+    },
+    {
+      "epoch": 1.4763779527559056,
+      "eval_entropy": 0.7358508281133793,
+      "eval_loss": 0.8263605833053589,
+      "eval_mean_token_accuracy": 0.7838875507866895,
+      "eval_num_tokens": 8327961.0,
+      "eval_runtime": 15.9403,
+      "eval_samples_per_second": 26.787,
+      "eval_steps_per_second": 3.388,
+      "step": 750
+    },
+    {
+      "entropy": 0.701068015396595,
+      "epoch": 1.4960629921259843,
+      "grad_norm": 0.65625,
+      "learning_rate": 0.00010552366960573985,
+      "loss": 0.6718067646026611,
+      "mean_token_accuracy": 0.8166692137718201,
+      "num_tokens": 8432725.0,
+      "step": 760
+    },
+    {
+      "entropy": 0.6750249415636063,
+      "epoch": 1.515748031496063,
+      "grad_norm": 0.41796875,
+      "learning_rate": 0.00010340025665341684,
+      "loss": 0.6471256256103516,
+      "mean_token_accuracy": 0.8236999034881591,
+      "num_tokens": 8550042.0,
+      "step": 770
+    },
+    {
+      "entropy": 0.6500637173652649,
+      "epoch": 1.5354330708661417,
+      "grad_norm": 0.470703125,
+      "learning_rate": 0.00010127530750652642,
+      "loss": 0.5989052295684815,
+      "mean_token_accuracy": 0.8357917547225953,
+      "num_tokens": 8664499.0,
+      "step": 780
+    },
+    {
+      "entropy": 0.6429416075348854,
+      "epoch": 1.5551181102362204,
+      "grad_norm": 0.69140625,
+      "learning_rate": 9.914978219122791e-05,
+      "loss": 0.6052910327911377,
+      "mean_token_accuracy": 0.8295481771230697,
+      "num_tokens": 8778459.0,
+      "step": 790
+    },
+    {
+      "entropy": 0.6374648019671441,
+      "epoch": 1.574803149606299,
+      "grad_norm": 0.6484375,
+      "learning_rate": 9.702464099398632e-05,
+      "loss": 0.6044469833374023,
+      "mean_token_accuracy": 0.8315474331378937,
+      "num_tokens": 8886361.0,
+      "step": 800
+    },
+    {
+      "epoch": 1.574803149606299,
+      "eval_entropy": 0.7627564834223853,
+      "eval_loss": 0.8170398473739624,
+      "eval_mean_token_accuracy": 0.7843498874593664,
+      "eval_num_tokens": 8886361.0,
+      "eval_runtime": 15.9518,
+      "eval_samples_per_second": 26.768,
+      "eval_steps_per_second": 3.385,
+      "step": 800
+    },
+    {
+      "entropy": 0.6787230268120765,
+      "epoch": 1.594488188976378,
+      "grad_norm": 0.515625,
+      "learning_rate": 9.4900844027727e-05,
+      "loss": 0.6268706321716309,
+      "mean_token_accuracy": 0.8275486946105957,
+      "num_tokens": 8995558.0,
+      "step": 810
+    },
+    {
+      "entropy": 0.7012800723314285,
+      "epoch": 1.6141732283464567,
+      "grad_norm": 0.5390625,
+      "learning_rate": 9.277935079806795e-05,
+      "loss": 0.652205228805542,
+      "mean_token_accuracy": 0.8216399610042572,
+      "num_tokens": 9096245.0,
+      "step": 820
+    },
+    {
+      "entropy": 0.6063105046749115,
+      "epoch": 1.6338582677165354,
+      "grad_norm": 0.8125,
+      "learning_rate": 9.066111976982712e-05,
+      "loss": 0.597124719619751,
+      "mean_token_accuracy": 0.836309888958931,
+      "num_tokens": 9204264.0,
+      "step": 830
+    },
+    {
+      "entropy": 0.6953654140233994,
+      "epoch": 1.6535433070866141,
+      "grad_norm": 0.5,
+      "learning_rate": 8.854710793399947e-05,
+      "loss": 0.6501974105834961,
+      "mean_token_accuracy": 0.8178625762462616,
+      "num_tokens": 9314940.0,
+      "step": 840
+    },
+    {
+      "entropy": 0.6784902378916741,
+      "epoch": 1.673228346456693,
+      "grad_norm": 0.546875,
+      "learning_rate": 8.64382703754003e-05,
+      "loss": 0.636347484588623,
+      "mean_token_accuracy": 0.8207234263420105,
+      "num_tokens": 9429496.0,
+      "step": 850
+    },
+    {
+      "epoch": 1.673228346456693,
+      "eval_entropy": 0.7619620506410245,
+      "eval_loss": 0.8146092295646667,
+      "eval_mean_token_accuracy": 0.7850696554890385,
+      "eval_num_tokens": 9429496.0,
+      "eval_runtime": 15.937,
+      "eval_samples_per_second": 26.793,
+      "eval_steps_per_second": 3.388,
+      "step": 850
+    },
+    {
+      "entropy": 0.6777935117483139,
+      "epoch": 1.6929133858267718,
+      "grad_norm": 0.478515625,
+      "learning_rate": 8.433555984116937e-05,
+      "loss": 0.6113362312316895,
+      "mean_token_accuracy": 0.8263391226530075,
+      "num_tokens": 9544270.0,
+      "step": 860
+    },
+    {
+      "entropy": 0.6014138415455819,
+      "epoch": 1.7125984251968505,
+      "grad_norm": 0.53125,
+      "learning_rate": 8.22399263103314e-05,
+      "loss": 0.6068051338195801,
+      "mean_token_accuracy": 0.8325248181819915,
+      "num_tokens": 9654198.0,
+      "step": 870
+    },
+    {
+      "entropy": 0.6414325833320618,
+      "epoch": 1.7322834645669292,
+      "grad_norm": 0.69140625,
+      "learning_rate": 8.015231656460712e-05,
+      "loss": 0.6324831008911133,
+      "mean_token_accuracy": 0.834089708328247,
+      "num_tokens": 9769457.0,
+      "step": 880
+    },
+    {
+      "entropy": 0.6839869737625122,
+      "epoch": 1.7519685039370079,
+      "grad_norm": 0.5390625,
+      "learning_rate": 7.807367376066889e-05,
+      "loss": 0.6296841144561768,
+      "mean_token_accuracy": 0.8278504878282547,
+      "num_tokens": 9875831.0,
+      "step": 890
+    },
+    {
+      "entropy": 0.6922678858041763,
+      "epoch": 1.7716535433070866,
+      "grad_norm": 0.48046875,
+      "learning_rate": 7.60049370040338e-05,
+      "loss": 0.6325759887695312,
+      "mean_token_accuracy": 0.8210694164037704,
+      "num_tokens": 9991758.0,
+      "step": 900
+    },
+    {
+      "epoch": 1.7716535433070866,
+      "eval_entropy": 0.7464290934580343,
+      "eval_loss": 0.8118129372596741,
+      "eval_mean_token_accuracy": 0.7863925894101461,
+      "eval_num_tokens": 9991758.0,
+      "eval_runtime": 15.9375,
+      "eval_samples_per_second": 26.792,
+      "eval_steps_per_second": 3.388,
+      "step": 900
+    },
+    {
+      "entropy": 0.7232977166771889,
+      "epoch": 1.7913385826771653,
+      "grad_norm": 0.50390625,
+      "learning_rate": 7.394704092478742e-05,
+      "loss": 0.6871041774749755,
+      "mean_token_accuracy": 0.8109384387731552,
+      "num_tokens": 10106255.0,
+      "step": 910
+    },
+    {
+      "entropy": 0.639159494638443,
+      "epoch": 1.811023622047244,
+      "grad_norm": 0.51953125,
+      "learning_rate": 7.190091525532921e-05,
+      "loss": 0.5977220058441162,
+      "mean_token_accuracy": 0.8346921026706695,
+      "num_tokens": 10218066.0,
+      "step": 920
+    },
+    {
+      "entropy": 0.6970785558223724,
+      "epoch": 1.8307086614173227,
+      "grad_norm": 0.625,
+      "learning_rate": 6.98674844103308e-05,
+      "loss": 0.6659546852111816,
+      "mean_token_accuracy": 0.8177712321281433,
+      "num_tokens": 10326991.0,
+      "step": 930
+    },
+    {
+      "entropy": 0.705052088201046,
+      "epoch": 1.8503937007874016,
+      "grad_norm": 0.52734375,
+      "learning_rate": 6.784766706909662e-05,
+      "loss": 0.6586481094360351,
+      "mean_token_accuracy": 0.8198566019535065,
+      "num_tokens": 10432558.0,
+      "step": 940
+    },
+    {
+      "entropy": 0.6612584158778191,
+      "epoch": 1.8700787401574803,
+      "grad_norm": 0.65625,
+      "learning_rate": 6.58423757605158e-05,
+      "loss": 0.6631102561950684,
+      "mean_token_accuracy": 0.8250136137008667,
+      "num_tokens": 10541702.0,
+      "step": 950
+    },
+    {
+      "epoch": 1.8700787401574803,
+      "eval_entropy": 0.7582799510823356,
+      "eval_loss": 0.8087909817695618,
+      "eval_mean_token_accuracy": 0.7858658830324808,
+      "eval_num_tokens": 10541702.0,
+      "eval_runtime": 15.9386,
+      "eval_samples_per_second": 26.79,
+      "eval_steps_per_second": 3.388,
+      "step": 950
+    },
+    {
+      "entropy": 0.7153135001659393,
+      "epoch": 1.889763779527559,
+      "grad_norm": 0.52734375,
+      "learning_rate": 6.38525164507927e-05,
+      "loss": 0.6485848426818848,
+      "mean_token_accuracy": 0.8191622495651245,
+      "num_tokens": 10652431.0,
+      "step": 960
+    },
+    {
+      "entropy": 0.6808911249041557,
+      "epoch": 1.909448818897638,
+      "grad_norm": 0.578125,
+      "learning_rate": 6.187898813414251e-05,
+      "loss": 0.6528217315673828,
+      "mean_token_accuracy": 0.8256954222917556,
+      "num_tokens": 10766036.0,
+      "step": 970
+    },
+    {
+      "entropy": 0.6457046732306481,
+      "epoch": 1.9291338582677167,
+      "grad_norm": 0.65625,
+      "learning_rate": 5.99226824266365e-05,
+      "loss": 0.6104453086853028,
+      "mean_token_accuracy": 0.8297607868909835,
+      "num_tokens": 10869598.0,
+      "step": 980
+    },
+    {
+      "entropy": 0.6919459193944931,
+      "epoch": 1.9488188976377954,
+      "grad_norm": 0.640625,
+      "learning_rate": 5.7984483163380764e-05,
+      "loss": 0.6459432601928711,
+      "mean_token_accuracy": 0.8180149614810943,
+      "num_tokens": 10983085.0,
+      "step": 990
+    },
+    {
+      "entropy": 0.6444254025816918,
+      "epoch": 1.968503937007874,
+      "grad_norm": 0.578125,
+      "learning_rate": 5.606526599921026e-05,
+      "loss": 0.6290760517120362,
+      "mean_token_accuracy": 0.8319308578968048,
+      "num_tokens": 11090966.0,
+      "step": 1000
+    },
+    {
+      "epoch": 1.968503937007874,
+      "eval_entropy": 0.7388938731617398,
+      "eval_loss": 0.8063948154449463,
+      "eval_mean_token_accuracy": 0.786332004600101,
+      "eval_num_tokens": 11090966.0,
+      "eval_runtime": 15.9242,
+      "eval_samples_per_second": 26.814,
+      "eval_steps_per_second": 3.391,
+      "step": 1000
+    },
+    {
+      "entropy": 0.716805949807167,
+      "epoch": 1.9881889763779528,
+      "grad_norm": 0.51953125,
+      "learning_rate": 5.416589801307874e-05,
+      "loss": 0.6740987300872803,
+      "mean_token_accuracy": 0.8161014556884766,
+      "num_tokens": 11204584.0,
+      "step": 1010
+    },
+    {
+      "entropy": 0.6367674544453621,
+      "epoch": 2.0078740157480315,
+      "grad_norm": 0.38671875,
+      "learning_rate": 5.2287237316322676e-05,
+      "loss": 0.5608503341674804,
+      "mean_token_accuracy": 0.843386459350586,
+      "num_tokens": 11314232.0,
+      "step": 1020
+    },
+    {
+      "entropy": 0.5910033389925957,
+      "epoch": 2.02755905511811,
+      "grad_norm": 0.515625,
+      "learning_rate": 5.043013266497751e-05,
+      "loss": 0.5252383708953857,
+      "mean_token_accuracy": 0.8537230730056763,
+      "num_tokens": 11422130.0,
+      "step": 1030
+    },
+    {
+      "entropy": 0.5933422192931175,
+      "epoch": 2.047244094488189,
+      "grad_norm": 0.45703125,
+      "learning_rate": 4.85954230763197e-05,
+      "loss": 0.5412720680236817,
+      "mean_token_accuracy": 0.8524353206157684,
+      "num_tokens": 11538400.0,
+      "step": 1040
+    },
+    {
+      "entropy": 0.5587056159973145,
+      "epoch": 2.0669291338582676,
+      "grad_norm": 0.482421875,
+      "learning_rate": 4.6783937449808856e-05,
+      "loss": 0.4972053050994873,
+      "mean_token_accuracy": 0.8567238092422486,
+      "num_tokens": 11645829.0,
+      "step": 1050
+    },
+    {
+      "epoch": 2.0669291338582676,
+      "eval_entropy": 0.6584087091463583,
+      "eval_loss": 0.8380542993545532,
+      "eval_mean_token_accuracy": 0.7845212673699414,
+      "eval_num_tokens": 11645829.0,
+      "eval_runtime": 15.9414,
+      "eval_samples_per_second": 26.786,
+      "eval_steps_per_second": 3.387,
+      "step": 1050
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1524,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.642644303100416e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1050/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3f0e55ef6f28af070d9ef917c7e02ff815b9b702bccb82471082d69e77b490b
+size 5713

checkpoint-1100/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-Math-1.5B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Math-1.5B-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-1100/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Math-1.5B-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": 0.05,
+  "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": [
+    "down_proj",
+    "v_proj",
+    "o_proj",
+    "q_proj",
+    "up_proj",
+    "k_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-1100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:638afaae366c6bb200e202b47dbf15d3d4ec51cee6afd45a9c47b13e49648b37
+size 73911504

checkpoint-1100/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'Please reason step by step, and put your final answer within \\boxed{}.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nPlease reason step by step, and put your final answer within \\boxed{}.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoint-1100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b57ac7c918ec515e39245ff3eff83139cc8c503c0a78904ba2de8f7f8f37916
+size 75481221

checkpoint-1100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5edb98e8c589e3319cfb7c2e86073a778d47397ebccbd5d51adff5536404040b
+size 14581

checkpoint-1100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58306f796b4f41184f1068ccc068423547e5b3a13bbc20d807dd37db02917919
+size 1465

checkpoint-1100/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

checkpoint-1100/tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "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,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|fim_pad|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1100/trainer_state.json

@@ -0,0 +1,1376 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.1653543307086616,
+  "eval_steps": 50,
+  "global_step": 1100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.4378354728221894,
+      "epoch": 0.01968503937007874,
+      "grad_norm": 0.62109375,
+      "learning_rate": 3.91304347826087e-05,
+      "loss": 1.657682228088379,
+      "mean_token_accuracy": 0.6598833322525024,
+      "num_tokens": 115439.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.5141301095485686,
+      "epoch": 0.03937007874015748,
+      "grad_norm": 0.44140625,
+      "learning_rate": 8.260869565217392e-05,
+      "loss": 1.4646138191223144,
+      "mean_token_accuracy": 0.6834615051746369,
+      "num_tokens": 225264.0,
+      "step": 20
+    },
+    {
+      "entropy": 1.2295305937528611,
+      "epoch": 0.05905511811023622,
+      "grad_norm": 0.6796875,
+      "learning_rate": 0.00012608695652173915,
+      "loss": 1.1134957313537597,
+      "mean_token_accuracy": 0.7453642427921295,
+      "num_tokens": 330923.0,
+      "step": 30
+    },
+    {
+      "entropy": 1.0573274463415145,
+      "epoch": 0.07874015748031496,
+      "grad_norm": 0.474609375,
+      "learning_rate": 0.00016956521739130436,
+      "loss": 1.077296829223633,
+      "mean_token_accuracy": 0.7446383863687516,
+      "num_tokens": 437622.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.952904561161995,
+      "epoch": 0.0984251968503937,
+      "grad_norm": 0.50390625,
+      "learning_rate": 0.00019999796688511753,
+      "loss": 0.9590332984924317,
+      "mean_token_accuracy": 0.768164387345314,
+      "num_tokens": 551175.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.0984251968503937,
+      "eval_entropy": 1.0900797645250957,
+      "eval_loss": 1.0484484434127808,
+      "eval_mean_token_accuracy": 0.7461776600943671,
+      "eval_num_tokens": 551175.0,
+      "eval_runtime": 15.9866,
+      "eval_samples_per_second": 26.71,
+      "eval_steps_per_second": 3.378,
+      "step": 50
+    },
+    {
+      "entropy": 0.9487997680902481,
+      "epoch": 0.11811023622047244,
+      "grad_norm": 0.59375,
+      "learning_rate": 0.0001999618249203163,
+      "loss": 0.9577752113342285,
+      "mean_token_accuracy": 0.7689193069934845,
+      "num_tokens": 658006.0,
+      "step": 60
+    },
+    {
+      "entropy": 1.0506175458431244,
+      "epoch": 0.1377952755905512,
+      "grad_norm": 0.5390625,
+      "learning_rate": 0.00019988052141977201,
+      "loss": 0.9976933479309082,
+      "mean_token_accuracy": 0.756487911939621,
+      "num_tokens": 771278.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.8528705358505249,
+      "epoch": 0.15748031496062992,
+      "grad_norm": 0.5078125,
+      "learning_rate": 0.0001997540931154166,
+      "loss": 0.8407608032226562,
+      "mean_token_accuracy": 0.7868376106023789,
+      "num_tokens": 886071.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.9220433413982392,
+      "epoch": 0.17716535433070865,
+      "grad_norm": 0.484375,
+      "learning_rate": 0.00019958259712601903,
+      "loss": 0.8958203315734863,
+      "mean_token_accuracy": 0.7736223608255386,
+      "num_tokens": 996361.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.8399994730949402,
+      "epoch": 0.1968503937007874,
+      "grad_norm": 0.51953125,
+      "learning_rate": 0.00019936611093137983,
+      "loss": 0.8394058227539063,
+      "mean_token_accuracy": 0.7876519203186035,
+      "num_tokens": 1103999.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.1968503937007874,
+      "eval_entropy": 0.9908565746413337,
+      "eval_loss": 0.949418842792511,
+      "eval_mean_token_accuracy": 0.7609190278583102,
+      "eval_num_tokens": 1103999.0,
+      "eval_runtime": 15.9475,
+      "eval_samples_per_second": 26.775,
+      "eval_steps_per_second": 3.386,
+      "step": 100
+    },
+    {
+      "entropy": 0.8772778362035751,
+      "epoch": 0.21653543307086615,
+      "grad_norm": 0.40625,
+      "learning_rate": 0.00019910473233732668,
+      "loss": 0.8347702026367188,
+      "mean_token_accuracy": 0.7877911299467086,
+      "num_tokens": 1216586.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.8745568007230758,
+      "epoch": 0.23622047244094488,
+      "grad_norm": 0.609375,
+      "learning_rate": 0.00019879857943152674,
+      "loss": 0.8359953880310058,
+      "mean_token_accuracy": 0.7790884494781494,
+      "num_tokens": 1324767.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.878146781027317,
+      "epoch": 0.2559055118110236,
+      "grad_norm": 0.5390625,
+      "learning_rate": 0.00019844779053013637,
+      "loss": 0.8335110664367675,
+      "mean_token_accuracy": 0.7791220843791962,
+      "num_tokens": 1432356.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.788033875823021,
+      "epoch": 0.2755905511811024,
+      "grad_norm": 0.546875,
+      "learning_rate": 0.00019805252411531126,
+      "loss": 0.7967269420623779,
+      "mean_token_accuracy": 0.7931749552488327,
+      "num_tokens": 1542545.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.8667207360267639,
+      "epoch": 0.2952755905511811,
+      "grad_norm": 0.5546875,
+      "learning_rate": 0.0001976129587636064,
+      "loss": 0.8101954460144043,
+      "mean_token_accuracy": 0.7908060193061829,
+      "num_tokens": 1654462.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.2952755905511811,
+      "eval_entropy": 0.9391163366812246,
+      "eval_loss": 0.9146928191184998,
+      "eval_mean_token_accuracy": 0.7670937886944523,
+      "eval_num_tokens": 1654462.0,
+      "eval_runtime": 15.956,
+      "eval_samples_per_second": 26.761,
+      "eval_steps_per_second": 3.384,
+      "step": 150
+    },
+    {
+      "entropy": 0.769407157599926,
+      "epoch": 0.31496062992125984,
+      "grad_norm": 0.470703125,
+      "learning_rate": 0.00019712929306529723,
+      "loss": 0.7655523777008056,
+      "mean_token_accuracy": 0.8053037762641907,
+      "num_tokens": 1760181.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.8818381905555726,
+      "epoch": 0.3346456692913386,
+      "grad_norm": 0.625,
+      "learning_rate": 0.000196601745534659,
+      "loss": 0.8408863067626953,
+      "mean_token_accuracy": 0.7815578579902649,
+      "num_tokens": 1864683.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.8344995141029358,
+      "epoch": 0.3543307086614173,
+      "grad_norm": 0.4765625,
+      "learning_rate": 0.0001960305545112445,
+      "loss": 0.8205550193786622,
+      "mean_token_accuracy": 0.7871369570493698,
+      "num_tokens": 1978641.0,
+      "step": 180
+    },
+    {
+      "entropy": 0.8058241099119187,
+      "epoch": 0.37401574803149606,
+      "grad_norm": 0.494140625,
+      "learning_rate": 0.0001954159780522056,
+      "loss": 0.8002825736999511,
+      "mean_token_accuracy": 0.7913093209266663,
+      "num_tokens": 2087989.0,
+      "step": 190
+    },
+    {
+      "entropy": 0.8938606142997741,
+      "epoch": 0.3937007874015748,
+      "grad_norm": 0.61328125,
+      "learning_rate": 0.00019475829381570566,
+      "loss": 0.8305434226989746,
+      "mean_token_accuracy": 0.7836446255445481,
+      "num_tokens": 2195494.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.3937007874015748,
+      "eval_entropy": 0.9502577009024443,
+      "eval_loss": 0.8978050351142883,
+      "eval_mean_token_accuracy": 0.7696934717672842,
+      "eval_num_tokens": 2195494.0,
+      "eval_runtime": 15.9419,
+      "eval_samples_per_second": 26.785,
+      "eval_steps_per_second": 3.387,
+      "step": 200
+    },
+    {
+      "entropy": 0.7890492826700211,
+      "epoch": 0.41338582677165353,
+      "grad_norm": 0.40625,
+      "learning_rate": 0.0001940577989354773,
+      "loss": 0.7953387260437011,
+      "mean_token_accuracy": 0.7982505321502685,
+      "num_tokens": 2314228.0,
+      "step": 210
+    },
+    {
+      "entropy": 0.8576261162757873,
+      "epoch": 0.4330708661417323,
+      "grad_norm": 0.66015625,
+      "learning_rate": 0.00019331480988658083,
+      "loss": 0.8120486259460449,
+      "mean_token_accuracy": 0.7829198718070984,
+      "num_tokens": 2419122.0,
+      "step": 220
+    },
+    {
+      "entropy": 0.8514308303594589,
+      "epoch": 0.452755905511811,
+      "grad_norm": 0.470703125,
+      "learning_rate": 0.00019252966234242468,
+      "loss": 0.8203784942626953,
+      "mean_token_accuracy": 0.7819343030452728,
+      "num_tokens": 2524623.0,
+      "step": 230
+    },
+    {
+      "entropy": 0.8994888842105866,
+      "epoch": 0.47244094488188976,
+      "grad_norm": 0.59765625,
+      "learning_rate": 0.00019170271102311238,
+      "loss": 0.9019557952880859,
+      "mean_token_accuracy": 0.7712395042181015,
+      "num_tokens": 2631031.0,
+      "step": 240
+    },
+    {
+      "entropy": 0.7910601049661636,
+      "epoch": 0.4921259842519685,
+      "grad_norm": 0.494140625,
+      "learning_rate": 0.00019083432953518418,
+      "loss": 0.8107678413391113,
+      "mean_token_accuracy": 0.7996705889701843,
+      "num_tokens": 2741031.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.4921259842519685,
+      "eval_entropy": 0.9037868281205496,
+      "eval_loss": 0.8843846917152405,
+      "eval_mean_token_accuracy": 0.7717091352851303,
+      "eval_num_tokens": 2741031.0,
+      "eval_runtime": 15.93,
+      "eval_samples_per_second": 26.805,
+      "eval_steps_per_second": 3.39,
+      "step": 250
+    },
+    {
+      "entropy": 0.7740790158510208,
+      "epoch": 0.5118110236220472,
+      "grad_norm": 0.57421875,
+      "learning_rate": 0.00018992491020282618,
+      "loss": 0.7579652309417725,
+      "mean_token_accuracy": 0.7955388814210892,
+      "num_tokens": 2853547.0,
+      "step": 260
+    },
+    {
+      "entropy": 0.8572690159082412,
+      "epoch": 0.531496062992126,
+      "grad_norm": 1.171875,
+      "learning_rate": 0.0001889748638906231,
+      "loss": 0.8072081565856933,
+      "mean_token_accuracy": 0.7910655379295349,
+      "num_tokens": 2968367.0,
+      "step": 270
+    },
+    {
+      "entropy": 0.8885004252195359,
+      "epoch": 0.5511811023622047,
+      "grad_norm": 0.451171875,
+      "learning_rate": 0.00018798461981793462,
+      "loss": 0.8460770606994629,
+      "mean_token_accuracy": 0.7776093751192092,
+      "num_tokens": 3075963.0,
+      "step": 280
+    },
+    {
+      "entropy": 0.829613895714283,
+      "epoch": 0.5708661417322834,
+      "grad_norm": 0.4453125,
+      "learning_rate": 0.00018695462536497934,
+      "loss": 0.823792839050293,
+      "mean_token_accuracy": 0.7848509013652801,
+      "num_tokens": 3185899.0,
+      "step": 290
+    },
+    {
+      "entropy": 0.8341330245137215,
+      "epoch": 0.5905511811023622,
+      "grad_norm": 0.490234375,
+      "learning_rate": 0.00018588534587071385,
+      "loss": 0.810818099975586,
+      "mean_token_accuracy": 0.7906568497419357,
+      "num_tokens": 3297319.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.5905511811023622,
+      "eval_entropy": 0.8445847459413387,
+      "eval_loss": 0.8718247413635254,
+      "eval_mean_token_accuracy": 0.774838043583764,
+      "eval_num_tokens": 3297319.0,
+      "eval_runtime": 15.9561,
+      "eval_samples_per_second": 26.761,
+      "eval_steps_per_second": 3.384,
+      "step": 300
+    },
+    {
+      "entropy": 0.8317201763391495,
+      "epoch": 0.610236220472441,
+      "grad_norm": 0.396484375,
+      "learning_rate": 0.00018477726442259806,
+      "loss": 0.80075101852417,
+      "mean_token_accuracy": 0.7886052161455155,
+      "num_tokens": 3415477.0,
+      "step": 310
+    },
+    {
+      "entropy": 0.8597566410899162,
+      "epoch": 0.6299212598425197,
+      "grad_norm": 0.404296875,
+      "learning_rate": 0.00018363088163834252,
+      "loss": 0.8123328208923339,
+      "mean_token_accuracy": 0.7854531407356262,
+      "num_tokens": 3524759.0,
+      "step": 320
+    },
+    {
+      "entropy": 0.8519140958786011,
+      "epoch": 0.6496062992125984,
+      "grad_norm": 0.458984375,
+      "learning_rate": 0.00018244671543973513,
+      "loss": 0.8214571952819825,
+      "mean_token_accuracy": 0.7828344345092774,
+      "num_tokens": 3640838.0,
+      "step": 330
+    },
+    {
+      "entropy": 0.7781533747911453,
+      "epoch": 0.6692913385826772,
+      "grad_norm": 0.51953125,
+      "learning_rate": 0.0001812253008186505,
+      "loss": 0.753899097442627,
+      "mean_token_accuracy": 0.8011120349168778,
+      "num_tokens": 3756735.0,
+      "step": 340
+    },
+    {
+      "entropy": 0.8384901583194733,
+      "epoch": 0.6889763779527559,
+      "grad_norm": 0.51171875,
+      "learning_rate": 0.0001799671895953471,
+      "loss": 0.8112489700317382,
+      "mean_token_accuracy": 0.7898134678602219,
+      "num_tokens": 3870377.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.6889763779527559,
+      "eval_entropy": 0.8795759567507991,
+      "eval_loss": 0.8568941354751587,
+      "eval_mean_token_accuracy": 0.7754804182935644,
+      "eval_num_tokens": 3870377.0,
+      "eval_runtime": 15.9337,
+      "eval_samples_per_second": 26.798,
+      "eval_steps_per_second": 3.389,
+      "step": 350
+    },
+    {
+      "entropy": 0.8008699864149094,
+      "epoch": 0.7086614173228346,
+      "grad_norm": 0.498046875,
+      "learning_rate": 0.00017867295016916167,
+      "loss": 0.7585730075836181,
+      "mean_token_accuracy": 0.7942175149917603,
+      "num_tokens": 3975692.0,
+      "step": 360
+    },
+    {
+      "entropy": 0.9035080641508102,
+      "epoch": 0.7283464566929134,
+      "grad_norm": 0.48046875,
+      "learning_rate": 0.0001773431672617132,
+      "loss": 0.8653995513916015,
+      "mean_token_accuracy": 0.7730168104171753,
+      "num_tokens": 4087256.0,
+      "step": 370
+    },
+    {
+      "entropy": 0.760843014717102,
+      "epoch": 0.7480314960629921,
+      "grad_norm": 0.49609375,
+      "learning_rate": 0.00017597844165273286,
+      "loss": 0.7377382278442383,
+      "mean_token_accuracy": 0.7972156703472137,
+      "num_tokens": 4192629.0,
+      "step": 380
+    },
+    {
+      "entropy": 0.8075762838125229,
+      "epoch": 0.7677165354330708,
+      "grad_norm": 0.447265625,
+      "learning_rate": 0.00017457938990863908,
+      "loss": 0.7615089893341065,
+      "mean_token_accuracy": 0.8005614727735519,
+      "num_tokens": 4303838.0,
+      "step": 390
+    },
+    {
+      "entropy": 0.8942124575376511,
+      "epoch": 0.7874015748031497,
+      "grad_norm": 0.48828125,
+      "learning_rate": 0.00017314664410398033,
+      "loss": 0.8365015983581543,
+      "mean_token_accuracy": 0.7790710270404816,
+      "num_tokens": 4414002.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.7874015748031497,
+      "eval_entropy": 0.8613758815659417,
+      "eval_loss": 0.8455358743667603,
+      "eval_mean_token_accuracy": 0.7789811304321995,
+      "eval_num_tokens": 4414002.0,
+      "eval_runtime": 16.2401,
+      "eval_samples_per_second": 26.293,
+      "eval_steps_per_second": 3.325,
+      "step": 400
+    },
+    {
+      "entropy": 0.7841676041483879,
+      "epoch": 0.8070866141732284,
+      "grad_norm": 0.57421875,
+      "learning_rate": 0.0001716808515358714,
+      "loss": 0.8027224540710449,
+      "mean_token_accuracy": 0.79732064306736,
+      "num_tokens": 4525758.0,
+      "step": 410
+    },
+    {
+      "entropy": 0.7710117936134339,
+      "epoch": 0.8267716535433071,
+      "grad_norm": 0.4453125,
+      "learning_rate": 0.00017018267443155268,
+      "loss": 0.7185665130615234,
+      "mean_token_accuracy": 0.807221668958664,
+      "num_tokens": 4640742.0,
+      "step": 420
+    },
+    {
+      "entropy": 0.8494665056467057,
+      "epoch": 0.8464566929133859,
+      "grad_norm": 0.453125,
+      "learning_rate": 0.00016865278964920378,
+      "loss": 0.8273701667785645,
+      "mean_token_accuracy": 0.7870708376169204,
+      "num_tokens": 4754244.0,
+      "step": 430
+    },
+    {
+      "entropy": 0.7938957527279854,
+      "epoch": 0.8661417322834646,
+      "grad_norm": 0.345703125,
+      "learning_rate": 0.00016709188837214732,
+      "loss": 0.7776453971862793,
+      "mean_token_accuracy": 0.7911081612110138,
+      "num_tokens": 4862576.0,
+      "step": 440
+    },
+    {
+      "entropy": 0.7948901996016502,
+      "epoch": 0.8858267716535433,
+      "grad_norm": 0.376953125,
+      "learning_rate": 0.0001655006757965806,
+      "loss": 0.7554664611816406,
+      "mean_token_accuracy": 0.7939331024885178,
+      "num_tokens": 4984410.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.8858267716535433,
+      "eval_entropy": 0.8405309479545664,
+      "eval_loss": 0.8371886610984802,
+      "eval_mean_token_accuracy": 0.7799682672376986,
+      "eval_num_tokens": 4984410.0,
+      "eval_runtime": 15.9419,
+      "eval_samples_per_second": 26.785,
+      "eval_steps_per_second": 3.387,
+      "step": 450
+    },
+    {
+      "entropy": 0.8764406844973565,
+      "epoch": 0.905511811023622,
+      "grad_norm": 0.5625,
+      "learning_rate": 0.0001638798708129768,
+      "loss": 0.8325652122497559,
+      "mean_token_accuracy": 0.7821455717086792,
+      "num_tokens": 5094029.0,
+      "step": 460
+    },
+    {
+      "entropy": 0.8582975655794144,
+      "epoch": 0.9251968503937008,
+      "grad_norm": 0.3828125,
+      "learning_rate": 0.00016223020568129854,
+      "loss": 0.8309861183166504,
+      "mean_token_accuracy": 0.7791573971509933,
+      "num_tokens": 5210613.0,
+      "step": 470
+    },
+    {
+      "entropy": 0.8273941457271576,
+      "epoch": 0.9448818897637795,
+      "grad_norm": 0.59375,
+      "learning_rate": 0.00016055242570017244,
+      "loss": 0.7878972053527832,
+      "mean_token_accuracy": 0.7900911033153534,
+      "num_tokens": 5322546.0,
+      "step": 480
+    },
+    {
+      "entropy": 0.8146103203296662,
+      "epoch": 0.9645669291338582,
+      "grad_norm": 0.42578125,
+      "learning_rate": 0.00015884728887017162,
+      "loss": 0.7865399837493896,
+      "mean_token_accuracy": 0.7947310745716095,
+      "num_tokens": 5434008.0,
+      "step": 490
+    },
+    {
+      "entropy": 0.6613125756382943,
+      "epoch": 0.984251968503937,
+      "grad_norm": 0.41796875,
+      "learning_rate": 0.0001571155655513606,
+      "loss": 0.6725417137145996,
+      "mean_token_accuracy": 0.816859421133995,
+      "num_tokens": 5544086.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.984251968503937,
+      "eval_entropy": 0.8118620448642306,
+      "eval_loss": 0.8308539986610413,
+      "eval_mean_token_accuracy": 0.781522473803273,
+      "eval_num_tokens": 5544086.0,
+      "eval_runtime": 15.9383,
+      "eval_samples_per_second": 26.791,
+      "eval_steps_per_second": 3.388,
+      "step": 500
+    },
+    {
+      "entropy": 0.7347942754626274,
+      "epoch": 1.0039370078740157,
+      "grad_norm": 0.39453125,
+      "learning_rate": 0.0001553580381152559,
+      "loss": 0.6915054798126221,
+      "mean_token_accuracy": 0.8176700383424759,
+      "num_tokens": 5657246.0,
+      "step": 510
+    },
+    {
+      "entropy": 0.7550317242741584,
+      "epoch": 1.0236220472440944,
+      "grad_norm": 0.4921875,
+      "learning_rate": 0.0001535755005913602,
+      "loss": 0.6865068912506104,
+      "mean_token_accuracy": 0.8140248268842697,
+      "num_tokens": 5768184.0,
+      "step": 520
+    },
+    {
+      "entropy": 0.7479684263467788,
+      "epoch": 1.0433070866141732,
+      "grad_norm": 0.60546875,
+      "learning_rate": 0.00015176875830842938,
+      "loss": 0.7037695407867431,
+      "mean_token_accuracy": 0.8133333414793015,
+      "num_tokens": 5885598.0,
+      "step": 530
+    },
+    {
+      "entropy": 0.6792907789349556,
+      "epoch": 1.0629921259842519,
+      "grad_norm": 0.439453125,
+      "learning_rate": 0.0001499386275306348,
+      "loss": 0.640275239944458,
+      "mean_token_accuracy": 0.8249545454978943,
+      "num_tokens": 6002120.0,
+      "step": 540
+    },
+    {
+      "entropy": 0.6819084867835045,
+      "epoch": 1.0826771653543308,
+      "grad_norm": 0.41015625,
+      "learning_rate": 0.0001480859350887852,
+      "loss": 0.6469451904296875,
+      "mean_token_accuracy": 0.8235166579484939,
+      "num_tokens": 6112085.0,
+      "step": 550
+    },
+    {
+      "epoch": 1.0826771653543308,
+      "eval_entropy": 0.8042021377219094,
+      "eval_loss": 0.8352769017219543,
+      "eval_mean_token_accuracy": 0.7806271998970596,
+      "eval_num_tokens": 6112085.0,
+      "eval_runtime": 15.9298,
+      "eval_samples_per_second": 26.805,
+      "eval_steps_per_second": 3.39,
+      "step": 550
+    },
+    {
+      "entropy": 0.7026952266693115,
+      "epoch": 1.1023622047244095,
+      "grad_norm": 0.47265625,
+      "learning_rate": 0.00014621151800677434,
+      "loss": 0.667764139175415,
+      "mean_token_accuracy": 0.8164290696382522,
+      "num_tokens": 6224645.0,
+      "step": 560
+    },
+    {
+      "entropy": 0.6083555489778518,
+      "epoch": 1.1220472440944882,
+      "grad_norm": 0.37890625,
+      "learning_rate": 0.0001443162231234242,
+      "loss": 0.5703843116760254,
+      "mean_token_accuracy": 0.8396952480077744,
+      "num_tokens": 6336790.0,
+      "step": 570
+    },
+    {
+      "entropy": 0.6823922500014306,
+      "epoch": 1.141732283464567,
+      "grad_norm": 0.55078125,
+      "learning_rate": 0.0001424009067098931,
+      "loss": 0.6488718032836914,
+      "mean_token_accuracy": 0.8208951652050018,
+      "num_tokens": 6450761.0,
+      "step": 580
+    },
+    {
+      "entropy": 0.6331134095788002,
+      "epoch": 1.1614173228346456,
+      "grad_norm": 0.482421875,
+      "learning_rate": 0.00014046643408282305,
+      "loss": 0.5916334629058838,
+      "mean_token_accuracy": 0.8340157747268677,
+      "num_tokens": 6562060.0,
+      "step": 590
+    },
+    {
+      "entropy": 0.6203767985105515,
+      "epoch": 1.1811023622047245,
+      "grad_norm": 0.45703125,
+      "learning_rate": 0.00013851367921340017,
+      "loss": 0.5833216667175293,
+      "mean_token_accuracy": 0.8345949351787567,
+      "num_tokens": 6676922.0,
+      "step": 600
+    },
+    {
+      "epoch": 1.1811023622047245,
+      "eval_entropy": 0.7756788493306549,
+      "eval_loss": 0.8351659178733826,
+      "eval_mean_token_accuracy": 0.7810865651678156,
+      "eval_num_tokens": 6676922.0,
+      "eval_runtime": 15.9481,
+      "eval_samples_per_second": 26.774,
+      "eval_steps_per_second": 3.386,
+      "step": 600
+    },
+    {
+      "entropy": 0.645186324417591,
+      "epoch": 1.2007874015748032,
+      "grad_norm": 0.498046875,
+      "learning_rate": 0.0001365435243325051,
+      "loss": 0.6237170219421386,
+      "mean_token_accuracy": 0.8277532249689102,
+      "num_tokens": 6783497.0,
+      "step": 610
+    },
+    {
+      "entropy": 0.6759833052754403,
+      "epoch": 1.220472440944882,
+      "grad_norm": 0.546875,
+      "learning_rate": 0.00013455685953213194,
+      "loss": 0.6462036609649658,
+      "mean_token_accuracy": 0.8247299671173096,
+      "num_tokens": 6894014.0,
+      "step": 620
+    },
+    {
+      "entropy": 0.6737162366509437,
+      "epoch": 1.2401574803149606,
+      "grad_norm": 0.48828125,
+      "learning_rate": 0.0001325545823632554,
+      "loss": 0.6107028484344482,
+      "mean_token_accuracy": 0.8260864973068237,
+      "num_tokens": 6997350.0,
+      "step": 630
+    },
+    {
+      "entropy": 0.6702337503433228,
+      "epoch": 1.2598425196850394,
+      "grad_norm": 0.451171875,
+      "learning_rate": 0.00013053759743032823,
+      "loss": 0.6504123210906982,
+      "mean_token_accuracy": 0.818900191783905,
+      "num_tokens": 7109067.0,
+      "step": 640
+    },
+    {
+      "entropy": 0.7739008516073227,
+      "epoch": 1.279527559055118,
+      "grad_norm": 0.56640625,
+      "learning_rate": 0.00012850681598259195,
+      "loss": 0.7173595905303956,
+      "mean_token_accuracy": 0.7997365325689316,
+      "num_tokens": 7218739.0,
+      "step": 650
+    },
+    {
+      "epoch": 1.279527559055118,
+      "eval_entropy": 0.7500080190323017,
+      "eval_loss": 0.8297256231307983,
+      "eval_mean_token_accuracy": 0.7822851461392862,
+      "eval_num_tokens": 7218739.0,
+      "eval_runtime": 15.9417,
+      "eval_samples_per_second": 26.785,
+      "eval_steps_per_second": 3.387,
+      "step": 650
+    },
+    {
+      "entropy": 0.7080179423093795,
+      "epoch": 1.2992125984251968,
+      "grad_norm": 0.53125,
+      "learning_rate": 0.0001264631555023856,
+      "loss": 0.661363172531128,
+      "mean_token_accuracy": 0.8172380715608597,
+      "num_tokens": 7334561.0,
+      "step": 660
+    },
+    {
+      "entropy": 0.6184108316898346,
+      "epoch": 1.3188976377952755,
+      "grad_norm": 0.78515625,
+      "learning_rate": 0.00012440753929063826,
+      "loss": 0.6013145923614502,
+      "mean_token_accuracy": 0.8273262619972229,
+      "num_tokens": 7443871.0,
+      "step": 670
+    },
+    {
+      "entropy": 0.71297377794981,
+      "epoch": 1.3385826771653544,
+      "grad_norm": 0.5078125,
+      "learning_rate": 0.00012234089604973303,
+      "loss": 0.6702734470367432,
+      "mean_token_accuracy": 0.8151450455188751,
+      "num_tokens": 7555559.0,
+      "step": 680
+    },
+    {
+      "entropy": 0.6389088705182076,
+      "epoch": 1.358267716535433,
+      "grad_norm": 0.50390625,
+      "learning_rate": 0.0001202641594639305,
+      "loss": 0.6133567810058593,
+      "mean_token_accuracy": 0.8298202604055405,
+      "num_tokens": 7669861.0,
+      "step": 690
+    },
+    {
+      "entropy": 0.7520714432001114,
+      "epoch": 1.3779527559055118,
+      "grad_norm": 0.5390625,
+      "learning_rate": 0.00011817826777754171,
+      "loss": 0.6847642421722412,
+      "mean_token_accuracy": 0.8055585384368896,
+      "num_tokens": 7782831.0,
+      "step": 700
+    },
+    {
+      "epoch": 1.3779527559055118,
+      "eval_entropy": 0.7791200037355777,
+      "eval_loss": 0.8222253322601318,
+      "eval_mean_token_accuracy": 0.7843283326537521,
+      "eval_num_tokens": 7782831.0,
+      "eval_runtime": 15.9494,
+      "eval_samples_per_second": 26.772,
+      "eval_steps_per_second": 3.386,
+      "step": 700
+    },
+    {
+      "entropy": 0.7161616936326027,
+      "epoch": 1.3976377952755905,
+      "grad_norm": 0.421875,
+      "learning_rate": 0.00011608416337104065,
+      "loss": 0.6723262786865234,
+      "mean_token_accuracy": 0.8196182817220687,
+      "num_tokens": 7895511.0,
+      "step": 710
+    },
+    {
+      "entropy": 0.6407245740294456,
+      "epoch": 1.4173228346456692,
+      "grad_norm": 0.443359375,
+      "learning_rate": 0.00011398279233530829,
+      "loss": 0.6370048522949219,
+      "mean_token_accuracy": 0.8265632688999176,
+      "num_tokens": 8006186.0,
+      "step": 720
+    },
+    {
+      "entropy": 0.704089181125164,
+      "epoch": 1.4370078740157481,
+      "grad_norm": 0.51953125,
+      "learning_rate": 0.00011187510404420028,
+      "loss": 0.645330286026001,
+      "mean_token_accuracy": 0.8142861813306809,
+      "num_tokens": 8110444.0,
+      "step": 730
+    },
+    {
+      "entropy": 0.7673430755734444,
+      "epoch": 1.4566929133858268,
+      "grad_norm": 0.7109375,
+      "learning_rate": 0.00010976205072563132,
+      "loss": 0.7298968315124512,
+      "mean_token_accuracy": 0.8080587953329086,
+      "num_tokens": 8220128.0,
+      "step": 740
+    },
+    {
+      "entropy": 0.6395664170384407,
+      "epoch": 1.4763779527559056,
+      "grad_norm": 0.5078125,
+      "learning_rate": 0.00010764458703137024,
+      "loss": 0.6174263477325439,
+      "mean_token_accuracy": 0.8285290688276291,
+      "num_tokens": 8327961.0,
+      "step": 750
+    },
+    {
+      "epoch": 1.4763779527559056,
+      "eval_entropy": 0.7358508281133793,
+      "eval_loss": 0.8263605833053589,
+      "eval_mean_token_accuracy": 0.7838875507866895,
+      "eval_num_tokens": 8327961.0,
+      "eval_runtime": 15.9403,
+      "eval_samples_per_second": 26.787,
+      "eval_steps_per_second": 3.388,
+      "step": 750
+    },
+    {
+      "entropy": 0.701068015396595,
+      "epoch": 1.4960629921259843,
+      "grad_norm": 0.65625,
+      "learning_rate": 0.00010552366960573985,
+      "loss": 0.6718067646026611,
+      "mean_token_accuracy": 0.8166692137718201,
+      "num_tokens": 8432725.0,
+      "step": 760
+    },
+    {
+      "entropy": 0.6750249415636063,
+      "epoch": 1.515748031496063,
+      "grad_norm": 0.41796875,
+      "learning_rate": 0.00010340025665341684,
+      "loss": 0.6471256256103516,
+      "mean_token_accuracy": 0.8236999034881591,
+      "num_tokens": 8550042.0,
+      "step": 770
+    },
+    {
+      "entropy": 0.6500637173652649,
+      "epoch": 1.5354330708661417,
+      "grad_norm": 0.470703125,
+      "learning_rate": 0.00010127530750652642,
+      "loss": 0.5989052295684815,
+      "mean_token_accuracy": 0.8357917547225953,
+      "num_tokens": 8664499.0,
+      "step": 780
+    },
+    {
+      "entropy": 0.6429416075348854,
+      "epoch": 1.5551181102362204,
+      "grad_norm": 0.69140625,
+      "learning_rate": 9.914978219122791e-05,
+      "loss": 0.6052910327911377,
+      "mean_token_accuracy": 0.8295481771230697,
+      "num_tokens": 8778459.0,
+      "step": 790
+    },
+    {
+      "entropy": 0.6374648019671441,
+      "epoch": 1.574803149606299,
+      "grad_norm": 0.6484375,
+      "learning_rate": 9.702464099398632e-05,
+      "loss": 0.6044469833374023,
+      "mean_token_accuracy": 0.8315474331378937,
+      "num_tokens": 8886361.0,
+      "step": 800
+    },
+    {
+      "epoch": 1.574803149606299,
+      "eval_entropy": 0.7627564834223853,
+      "eval_loss": 0.8170398473739624,
+      "eval_mean_token_accuracy": 0.7843498874593664,
+      "eval_num_tokens": 8886361.0,
+      "eval_runtime": 15.9518,
+      "eval_samples_per_second": 26.768,
+      "eval_steps_per_second": 3.385,
+      "step": 800
+    },
+    {
+      "entropy": 0.6787230268120765,
+      "epoch": 1.594488188976378,
+      "grad_norm": 0.515625,
+      "learning_rate": 9.4900844027727e-05,
+      "loss": 0.6268706321716309,
+      "mean_token_accuracy": 0.8275486946105957,
+      "num_tokens": 8995558.0,
+      "step": 810
+    },
+    {
+      "entropy": 0.7012800723314285,
+      "epoch": 1.6141732283464567,
+      "grad_norm": 0.5390625,
+      "learning_rate": 9.277935079806795e-05,
+      "loss": 0.652205228805542,
+      "mean_token_accuracy": 0.8216399610042572,
+      "num_tokens": 9096245.0,
+      "step": 820
+    },
+    {
+      "entropy": 0.6063105046749115,
+      "epoch": 1.6338582677165354,
+      "grad_norm": 0.8125,
+      "learning_rate": 9.066111976982712e-05,
+      "loss": 0.597124719619751,
+      "mean_token_accuracy": 0.836309888958931,
+      "num_tokens": 9204264.0,
+      "step": 830
+    },
+    {
+      "entropy": 0.6953654140233994,
+      "epoch": 1.6535433070866141,
+      "grad_norm": 0.5,
+      "learning_rate": 8.854710793399947e-05,
+      "loss": 0.6501974105834961,
+      "mean_token_accuracy": 0.8178625762462616,
+      "num_tokens": 9314940.0,
+      "step": 840
+    },
+    {
+      "entropy": 0.6784902378916741,
+      "epoch": 1.673228346456693,
+      "grad_norm": 0.546875,
+      "learning_rate": 8.64382703754003e-05,
+      "loss": 0.636347484588623,
+      "mean_token_accuracy": 0.8207234263420105,
+      "num_tokens": 9429496.0,
+      "step": 850
+    },
+    {
+      "epoch": 1.673228346456693,
+      "eval_entropy": 0.7619620506410245,
+      "eval_loss": 0.8146092295646667,
+      "eval_mean_token_accuracy": 0.7850696554890385,
+      "eval_num_tokens": 9429496.0,
+      "eval_runtime": 15.937,
+      "eval_samples_per_second": 26.793,
+      "eval_steps_per_second": 3.388,
+      "step": 850
+    },
+    {
+      "entropy": 0.6777935117483139,
+      "epoch": 1.6929133858267718,
+      "grad_norm": 0.478515625,
+      "learning_rate": 8.433555984116937e-05,
+      "loss": 0.6113362312316895,
+      "mean_token_accuracy": 0.8263391226530075,
+      "num_tokens": 9544270.0,
+      "step": 860
+    },
+    {
+      "entropy": 0.6014138415455819,
+      "epoch": 1.7125984251968505,
+      "grad_norm": 0.53125,
+      "learning_rate": 8.22399263103314e-05,
+      "loss": 0.6068051338195801,
+      "mean_token_accuracy": 0.8325248181819915,
+      "num_tokens": 9654198.0,
+      "step": 870
+    },
+    {
+      "entropy": 0.6414325833320618,
+      "epoch": 1.7322834645669292,
+      "grad_norm": 0.69140625,
+      "learning_rate": 8.015231656460712e-05,
+      "loss": 0.6324831008911133,
+      "mean_token_accuracy": 0.834089708328247,
+      "num_tokens": 9769457.0,
+      "step": 880
+    },
+    {
+      "entropy": 0.6839869737625122,
+      "epoch": 1.7519685039370079,
+      "grad_norm": 0.5390625,
+      "learning_rate": 7.807367376066889e-05,
+      "loss": 0.6296841144561768,
+      "mean_token_accuracy": 0.8278504878282547,
+      "num_tokens": 9875831.0,
+      "step": 890
+    },
+    {
+      "entropy": 0.6922678858041763,
+      "epoch": 1.7716535433070866,
+      "grad_norm": 0.48046875,
+      "learning_rate": 7.60049370040338e-05,
+      "loss": 0.6325759887695312,
+      "mean_token_accuracy": 0.8210694164037704,
+      "num_tokens": 9991758.0,
+      "step": 900
+    },
+    {
+      "epoch": 1.7716535433070866,
+      "eval_entropy": 0.7464290934580343,
+      "eval_loss": 0.8118129372596741,
+      "eval_mean_token_accuracy": 0.7863925894101461,
+      "eval_num_tokens": 9991758.0,
+      "eval_runtime": 15.9375,
+      "eval_samples_per_second": 26.792,
+      "eval_steps_per_second": 3.388,
+      "step": 900
+    },
+    {
+      "entropy": 0.7232977166771889,
+      "epoch": 1.7913385826771653,
+      "grad_norm": 0.50390625,
+      "learning_rate": 7.394704092478742e-05,
+      "loss": 0.6871041774749755,
+      "mean_token_accuracy": 0.8109384387731552,
+      "num_tokens": 10106255.0,
+      "step": 910
+    },
+    {
+      "entropy": 0.639159494638443,
+      "epoch": 1.811023622047244,
+      "grad_norm": 0.51953125,
+      "learning_rate": 7.190091525532921e-05,
+      "loss": 0.5977220058441162,
+      "mean_token_accuracy": 0.8346921026706695,
+      "num_tokens": 10218066.0,
+      "step": 920
+    },
+    {
+      "entropy": 0.6970785558223724,
+      "epoch": 1.8307086614173227,
+      "grad_norm": 0.625,
+      "learning_rate": 6.98674844103308e-05,
+      "loss": 0.6659546852111816,
+      "mean_token_accuracy": 0.8177712321281433,
+      "num_tokens": 10326991.0,
+      "step": 930
+    },
+    {
+      "entropy": 0.705052088201046,
+      "epoch": 1.8503937007874016,
+      "grad_norm": 0.52734375,
+      "learning_rate": 6.784766706909662e-05,
+      "loss": 0.6586481094360351,
+      "mean_token_accuracy": 0.8198566019535065,
+      "num_tokens": 10432558.0,
+      "step": 940
+    },
+    {
+      "entropy": 0.6612584158778191,
+      "epoch": 1.8700787401574803,
+      "grad_norm": 0.65625,
+      "learning_rate": 6.58423757605158e-05,
+      "loss": 0.6631102561950684,
+      "mean_token_accuracy": 0.8250136137008667,
+      "num_tokens": 10541702.0,
+      "step": 950
+    },
+    {
+      "epoch": 1.8700787401574803,
+      "eval_entropy": 0.7582799510823356,
+      "eval_loss": 0.8087909817695618,
+      "eval_mean_token_accuracy": 0.7858658830324808,
+      "eval_num_tokens": 10541702.0,
+      "eval_runtime": 15.9386,
+      "eval_samples_per_second": 26.79,
+      "eval_steps_per_second": 3.388,
+      "step": 950
+    },
+    {
+      "entropy": 0.7153135001659393,
+      "epoch": 1.889763779527559,
+      "grad_norm": 0.52734375,
+      "learning_rate": 6.38525164507927e-05,
+      "loss": 0.6485848426818848,
+      "mean_token_accuracy": 0.8191622495651245,
+      "num_tokens": 10652431.0,
+      "step": 960
+    },
+    {
+      "entropy": 0.6808911249041557,
+      "epoch": 1.909448818897638,
+      "grad_norm": 0.578125,
+      "learning_rate": 6.187898813414251e-05,
+      "loss": 0.6528217315673828,
+      "mean_token_accuracy": 0.8256954222917556,
+      "num_tokens": 10766036.0,
+      "step": 970
+    },
+    {
+      "entropy": 0.6457046732306481,
+      "epoch": 1.9291338582677167,
+      "grad_norm": 0.65625,
+      "learning_rate": 5.99226824266365e-05,
+      "loss": 0.6104453086853028,
+      "mean_token_accuracy": 0.8297607868909835,
+      "num_tokens": 10869598.0,
+      "step": 980
+    },
+    {
+      "entropy": 0.6919459193944931,
+      "epoch": 1.9488188976377954,
+      "grad_norm": 0.640625,
+      "learning_rate": 5.7984483163380764e-05,
+      "loss": 0.6459432601928711,
+      "mean_token_accuracy": 0.8180149614810943,
+      "num_tokens": 10983085.0,
+      "step": 990
+    },
+    {
+      "entropy": 0.6444254025816918,
+      "epoch": 1.968503937007874,
+      "grad_norm": 0.578125,
+      "learning_rate": 5.606526599921026e-05,
+      "loss": 0.6290760517120362,
+      "mean_token_accuracy": 0.8319308578968048,
+      "num_tokens": 11090966.0,
+      "step": 1000
+    },
+    {
+      "epoch": 1.968503937007874,
+      "eval_entropy": 0.7388938731617398,
+      "eval_loss": 0.8063948154449463,
+      "eval_mean_token_accuracy": 0.786332004600101,
+      "eval_num_tokens": 11090966.0,
+      "eval_runtime": 15.9242,
+      "eval_samples_per_second": 26.814,
+      "eval_steps_per_second": 3.391,
+      "step": 1000
+    },
+    {
+      "entropy": 0.716805949807167,
+      "epoch": 1.9881889763779528,
+      "grad_norm": 0.51953125,
+      "learning_rate": 5.416589801307874e-05,
+      "loss": 0.6740987300872803,
+      "mean_token_accuracy": 0.8161014556884766,
+      "num_tokens": 11204584.0,
+      "step": 1010
+    },
+    {
+      "entropy": 0.6367674544453621,
+      "epoch": 2.0078740157480315,
+      "grad_norm": 0.38671875,
+      "learning_rate": 5.2287237316322676e-05,
+      "loss": 0.5608503341674804,
+      "mean_token_accuracy": 0.843386459350586,
+      "num_tokens": 11314232.0,
+      "step": 1020
+    },
+    {
+      "entropy": 0.5910033389925957,
+      "epoch": 2.02755905511811,
+      "grad_norm": 0.515625,
+      "learning_rate": 5.043013266497751e-05,
+      "loss": 0.5252383708953857,
+      "mean_token_accuracy": 0.8537230730056763,
+      "num_tokens": 11422130.0,
+      "step": 1030
+    },
+    {
+      "entropy": 0.5933422192931175,
+      "epoch": 2.047244094488189,
+      "grad_norm": 0.45703125,
+      "learning_rate": 4.85954230763197e-05,
+      "loss": 0.5412720680236817,
+      "mean_token_accuracy": 0.8524353206157684,
+      "num_tokens": 11538400.0,
+      "step": 1040
+    },
+    {
+      "entropy": 0.5587056159973145,
+      "epoch": 2.0669291338582676,
+      "grad_norm": 0.482421875,
+      "learning_rate": 4.6783937449808856e-05,
+      "loss": 0.4972053050994873,
+      "mean_token_accuracy": 0.8567238092422486,
+      "num_tokens": 11645829.0,
+      "step": 1050
+    },
+    {
+      "epoch": 2.0669291338582676,
+      "eval_entropy": 0.6584087091463583,
+      "eval_loss": 0.8380542993545532,
+      "eval_mean_token_accuracy": 0.7845212673699414,
+      "eval_num_tokens": 11645829.0,
+      "eval_runtime": 15.9414,
+      "eval_samples_per_second": 26.786,
+      "eval_steps_per_second": 3.387,
+      "step": 1050
+    },
+    {
+      "entropy": 0.5155777037143707,
+      "epoch": 2.0866141732283463,
+      "grad_norm": 0.5546875,
+      "learning_rate": 4.499649419260133e-05,
+      "loss": 0.46482577323913576,
+      "mean_token_accuracy": 0.8648948520421982,
+      "num_tokens": 11760076.0,
+      "step": 1060
+    },
+    {
+      "entropy": 0.5826122924685478,
+      "epoch": 2.106299212598425,
+      "grad_norm": 0.390625,
+      "learning_rate": 4.323390084980353e-05,
+      "loss": 0.5252526760101318,
+      "mean_token_accuracy": 0.8463617414236069,
+      "num_tokens": 11875367.0,
+      "step": 1070
+    },
+    {
+      "entropy": 0.569524523615837,
+      "epoch": 2.1259842519685037,
+      "grad_norm": 0.578125,
+      "learning_rate": 4.1496953739633124e-05,
+      "loss": 0.4987020969390869,
+      "mean_token_accuracy": 0.8567680090665817,
+      "num_tokens": 11983766.0,
+      "step": 1080
+    },
+    {
+      "entropy": 0.5740523621439934,
+      "epoch": 2.145669291338583,
+      "grad_norm": 0.6015625,
+      "learning_rate": 3.978643759365202e-05,
+      "loss": 0.5137018680572509,
+      "mean_token_accuracy": 0.8519427388906479,
+      "num_tokens": 12092559.0,
+      "step": 1090
+    },
+    {
+      "entropy": 0.5408509276807308,
+      "epoch": 2.1653543307086616,
+      "grad_norm": 0.54296875,
+      "learning_rate": 3.810312520223419e-05,
+      "loss": 0.5046960830688476,
+      "mean_token_accuracy": 0.8586939305067063,
+      "num_tokens": 12207307.0,
+      "step": 1100
+    },
+    {
+      "epoch": 2.1653543307086616,
+      "eval_entropy": 0.6570906854338117,
+      "eval_loss": 0.8393341898918152,
+      "eval_mean_token_accuracy": 0.7835258808400896,
+      "eval_num_tokens": 12207307.0,
+      "eval_runtime": 15.9395,
+      "eval_samples_per_second": 26.789,
+      "eval_steps_per_second": 3.388,
+      "step": 1100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1524,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.7210353781014733e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3f0e55ef6f28af070d9ef917c7e02ff815b9b702bccb82471082d69e77b490b
+size 5713

checkpoint-1150/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-Math-1.5B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Math-1.5B-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-1150/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Math-1.5B-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": 0.05,
+  "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": [
+    "down_proj",
+    "v_proj",
+    "o_proj",
+    "q_proj",
+    "up_proj",
+    "k_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-1150/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34912f66e3f8ef3a006a793ea9a4a5fa140325760b401db19f0db3d684510ade
+size 73911504

checkpoint-1150/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'Please reason step by step, and put your final answer within \\boxed{}.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nPlease reason step by step, and put your final answer within \\boxed{}.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoint-1150/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4b1aebff74b8ad7a098b69f0c01185ec1315c45fc61beab31d9cda304c20b3e
+size 75481221

checkpoint-1150/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2b64e0e2cfb04dc2c8f321cf94ccb9f7b00504aabf05b33d0aeea70f07c0b6c
+size 14581

checkpoint-1150/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:accb2a528fca29d8797540258b7417dc4e9ad92752b163e17dc7de1effb4163c
+size 1465

checkpoint-1150/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

checkpoint-1150/tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "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,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|fim_pad|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}