checkpoint-1380 (step 1380, resume push)

.gitattributes

@@ -37,3 +37,4 @@ checkpoint-1220/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-1230/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-1250/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-1350/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1380/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-1380/README.md

@@ -0,0 +1,209 @@
+---
+base_model: unsloth/gemma-4-31B-it-unsloth-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/gemma-4-31B-it-unsloth-bnb-4bit
+- 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-1380/adapter_config.json

@@ -0,0 +1,40 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/gemma-4-31B-it-unsloth-bnb-4bit",
+  "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": 32,
+  "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": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "^model\\.language_model\\.layers\\.\\d+\\.(self_attn|mlp)\\.(q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_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-1380/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6638206df2b8dd890fe24e329133a6ffd363bb77ec04208b630a1f84505fa76d
+size 489840816

checkpoint-1380/chat_template.jinja

@@ -0,0 +1,18 @@
+{{- bos_token -}}
+{%- for message in messages -%}
+{%- set role = 'model' if message['role'] == 'assistant' else message['role'] -%}
+{{- '<|turn>' + role + '
+' -}}
+{%- if role == 'model' -%}
+{% generation %}{{ message['content'] | trim }}{{ '<turn|>
+' }}{% endgeneration %}
+{%- else -%}
+{{- message['content'] | trim -}}
+{{- '<turn|>
+' -}}
+{%- endif -%}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+{{- '<|turn>model
+' -}}
+{%- endif -%}

checkpoint-1380/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f02373e59d2569a22d0f4831056cd541619c6225221d7964fc7ee0ff8326ffe0
+size 980141567

checkpoint-1380/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af06bd533458373469bda004055f6f3aafaea92902ad549364a820c28aab2588
+size 14645

checkpoint-1380/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1ef648e0d81edf21507f9216ccb45135daf406976d43cadfbb938126f999676
+size 1465

checkpoint-1380/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc8d3a0ce36466ccc1278bf987df5f71db1719b9ca6b4118264f45cb627bfe0f
+size 32169626

checkpoint-1380/tokenizer_config.json

@@ -0,0 +1,96 @@
+{
+  "audio_token": "<|audio|>",
+  "backend": "tokenizers",
+  "boa_token": "<|audio>",
+  "boi_token": "<|image>",
+  "bos_token": "<bos>",
+  "eoa_token": "<audio|>",
+  "eoc_token": "<channel|>",
+  "eoi_token": "<image|>",
+  "eos_token": "<eos>",
+  "eot_token": "<turn|>",
+  "escape_token": "<|\"|>",
+  "etc_token": "<tool_call|>",
+  "etd_token": "<tool|>",
+  "etr_token": "<tool_response|>",
+  "extra_special_tokens": [
+    "<|video|>"
+  ],
+  "image_token": "<|image|>",
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_token": "<|audio|>",
+    "boa_token": "<|audio>",
+    "boi_token": "<|image>",
+    "eoa_token": "<audio|>",
+    "eoc_token": "<channel|>",
+    "eoi_token": "<image|>",
+    "eot_token": "<turn|>",
+    "escape_token": "<|\"|>",
+    "etc_token": "<tool_call|>",
+    "etd_token": "<tool|>",
+    "etr_token": "<tool_response|>",
+    "image_token": "<|image|>",
+    "soc_token": "<|channel>",
+    "sot_token": "<|turn>",
+    "stc_token": "<|tool_call>",
+    "std_token": "<|tool>",
+    "str_token": "<|tool_response>",
+    "think_token": "<|think|>"
+  },
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "processor_class": "Gemma4Processor",
+  "response_schema": {
+    "properties": {
+      "content": {
+        "type": "string"
+      },
+      "role": {
+        "const": "assistant"
+      },
+      "thinking": {
+        "type": "string"
+      },
+      "tool_calls": {
+        "items": {
+          "properties": {
+            "function": {
+              "properties": {
+                "arguments": {
+                  "additionalProperties": {},
+                  "type": "object",
+                  "x-parser": "gemma4-tool-call"
+                },
+                "name": {
+                  "type": "string"
+                }
+              },
+              "type": "object",
+              "x-regex": "call\\:(?P<name>\\w+)(?P<arguments>\\{.*\\})"
+            },
+            "type": {
+              "const": "function"
+            }
+          },
+          "type": "object"
+        },
+        "type": "array",
+        "x-regex-iterator": "<\\|tool_call>(.*?)<tool_call\\|>"
+      }
+    },
+    "type": "object",
+    "x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?P<content>(?:(?!\\<turn\\|\\>)(?!\\<\\|tool_response\\>).)+)?(?:\\<turn\\|\\>|\\<\\|tool_response\\>)?"
+  },
+  "soc_token": "<|channel>",
+  "sot_token": "<|turn>",
+  "stc_token": "<|tool_call>",
+  "std_token": "<|tool>",
+  "str_token": "<|tool_response>",
+  "think_token": "<|think|>",
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>"
+}

checkpoint-1380/trainer_state.json

@@ -0,0 +1,1414 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.2860029532913655,
+  "eval_steps": 200,
+  "global_step": 1380,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 0.6597388138063252,
+      "epoch": 0.002072485168778011,
+      "grad_norm": 8.8125,
+      "learning_rate": 4.990675507666805e-05,
+      "loss": 2.548648643493652,
+      "mean_token_accuracy": 0.6212699495255947,
+      "num_tokens": 68556.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.2319401498883962,
+      "epoch": 0.004144970337556022,
+      "grad_norm": 1.8551321029663086,
+      "learning_rate": 4e-05,
+      "loss": 1.2790006637573241,
+      "mean_token_accuracy": 0.6778201619163156,
+      "num_tokens": 68899.0,
+      "step": 20
+    },
+    {
+      "entropy": 1.0786436698399484,
+      "epoch": 0.006217455506334033,
+      "grad_norm": 1.6974092721939087,
+      "learning_rate": 4.9699544135930385e-05,
+      "loss": 1.078802466392517,
+      "mean_token_accuracy": 0.7033441085368395,
+      "num_tokens": 54536.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.9887175707146525,
+      "epoch": 0.008289940675112044,
+      "grad_norm": 1.4512412548065186,
+      "learning_rate": 4.959593866556154e-05,
+      "loss": 1.01682710647583,
+      "mean_token_accuracy": 0.7121535470709205,
+      "num_tokens": 124904.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.8816413406282664,
+      "epoch": 0.010362425843890055,
+      "grad_norm": 2.4218170642852783,
+      "learning_rate": 4.949233319519271e-05,
+      "loss": 0.8716130256652832,
+      "mean_token_accuracy": 0.7505482472479343,
+      "num_tokens": 195835.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.8809595944359898,
+      "epoch": 0.012434911012668066,
+      "grad_norm": 1.6672383546829224,
+      "learning_rate": 4.938872772482387e-05,
+      "loss": 0.9053549766540527,
+      "mean_token_accuracy": 0.7492184635251761,
+      "num_tokens": 265339.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.8150073861703276,
+      "epoch": 0.014507396181446076,
+      "grad_norm": 14.46755599975586,
+      "learning_rate": 4.9285122254455033e-05,
+      "loss": 0.8346444129943847,
+      "mean_token_accuracy": 0.7595395758748055,
+      "num_tokens": 336368.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.8175835784524679,
+      "epoch": 0.016579881350224087,
+      "grad_norm": 2.1960630416870117,
+      "learning_rate": 4.91815167840862e-05,
+      "loss": 0.8361362457275391,
+      "mean_token_accuracy": 0.7581128649413585,
+      "num_tokens": 407860.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.8256460943259298,
+      "epoch": 0.0186523665190021,
+      "grad_norm": 1.531234622001648,
+      "learning_rate": 4.9077911313717365e-05,
+      "loss": 0.7942526817321778,
+      "mean_token_accuracy": 0.7586981456726789,
+      "num_tokens": 478153.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.7670522393658757,
+      "epoch": 0.02072485168778011,
+      "grad_norm": 1.4846571683883667,
+      "learning_rate": 4.8974305843348534e-05,
+      "loss": 0.8066231727600097,
+      "mean_token_accuracy": 0.7640550158917904,
+      "num_tokens": 69191.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.7678677449002862,
+      "epoch": 0.02279733685655812,
+      "grad_norm": 2.2768352031707764,
+      "learning_rate": 4.8870700372979696e-05,
+      "loss": 0.7622539043426514,
+      "mean_token_accuracy": 0.7605789495632053,
+      "num_tokens": 70685.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.7928496496751904,
+      "epoch": 0.024869822025336132,
+      "grad_norm": 1.6135530471801758,
+      "learning_rate": 4.876709490261086e-05,
+      "loss": 0.8297886848449707,
+      "mean_token_accuracy": 0.7713910015299916,
+      "num_tokens": 67611.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.8187904762104153,
+      "epoch": 0.026942307194114144,
+      "grad_norm": 1.6927149295806885,
+      "learning_rate": 4.866348943224203e-05,
+      "loss": 0.7997621536254883,
+      "mean_token_accuracy": 0.7677309328690172,
+      "num_tokens": 137341.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.7725600127130747,
+      "epoch": 0.02901479236289215,
+      "grad_norm": 1.4924240112304688,
+      "learning_rate": 4.855988396187319e-05,
+      "loss": 0.7891172885894775,
+      "mean_token_accuracy": 0.7674690783023834,
+      "num_tokens": 207836.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.7419765160419047,
+      "epoch": 0.031087277531670163,
+      "grad_norm": 2.3756399154663086,
+      "learning_rate": 4.845627849150435e-05,
+      "loss": 0.7784533977508545,
+      "mean_token_accuracy": 0.7648058263584971,
+      "num_tokens": 69933.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.8250428622588515,
+      "epoch": 0.033159762700448174,
+      "grad_norm": 1.5159028768539429,
+      "learning_rate": 4.835267302113552e-05,
+      "loss": 0.7961467266082763,
+      "mean_token_accuracy": 0.7633555989712477,
+      "num_tokens": 140048.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.7436810432001948,
+      "epoch": 0.035232247869226185,
+      "grad_norm": 1.6811050176620483,
+      "learning_rate": 4.824906755076668e-05,
+      "loss": 0.7290493011474609,
+      "mean_token_accuracy": 0.7767306372523308,
+      "num_tokens": 211895.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.7125280739739537,
+      "epoch": 0.0373047330380042,
+      "grad_norm": 1.5065526962280273,
+      "learning_rate": 4.8145462080397844e-05,
+      "loss": 0.7759998798370361,
+      "mean_token_accuracy": 0.7708184143528343,
+      "num_tokens": 283257.0,
+      "step": 180
+    },
+    {
+      "entropy": 0.7604576957412064,
+      "epoch": 0.03937721820678221,
+      "grad_norm": 1.7176634073257446,
+      "learning_rate": 4.804185661002901e-05,
+      "loss": 0.7218780040740966,
+      "mean_token_accuracy": 0.7823256257921457,
+      "num_tokens": 353293.0,
+      "step": 190
+    },
+    {
+      "entropy": 0.7666805353015661,
+      "epoch": 0.04144970337556022,
+      "grad_norm": 1.6243501901626587,
+      "learning_rate": 4.7938251139660175e-05,
+      "loss": 0.8028314590454102,
+      "mean_token_accuracy": 0.7595077693462372,
+      "num_tokens": 69595.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.7682002261281013,
+      "epoch": 0.04352218854433823,
+      "grad_norm": 1.4806550741195679,
+      "learning_rate": 4.783464566929134e-05,
+      "loss": 0.7437312126159668,
+      "mean_token_accuracy": 0.7693941719830036,
+      "num_tokens": 140317.0,
+      "step": 210
+    },
+    {
+      "entropy": 0.7393435522913933,
+      "epoch": 0.04559467371311624,
+      "grad_norm": 1.5655195713043213,
+      "learning_rate": 4.7731040198922507e-05,
+      "loss": 0.7613331317901612,
+      "mean_token_accuracy": 0.7660789949819445,
+      "num_tokens": 209078.0,
+      "step": 220
+    },
+    {
+      "entropy": 0.7387663672678173,
+      "epoch": 0.04766715888189425,
+      "grad_norm": 1.7122442722320557,
+      "learning_rate": 4.762743472855367e-05,
+      "loss": 0.7724202632904053,
+      "mean_token_accuracy": 0.7625673318281769,
+      "num_tokens": 70251.0,
+      "step": 230
+    },
+    {
+      "entropy": 0.7247329102829099,
+      "epoch": 0.049739644050672265,
+      "grad_norm": 1.8207371234893799,
+      "learning_rate": 4.752382925818483e-05,
+      "loss": 0.7066797733306884,
+      "mean_token_accuracy": 0.782066080160439,
+      "num_tokens": 139095.0,
+      "step": 240
+    },
+    {
+      "entropy": 0.6723151629790663,
+      "epoch": 0.051812129219450276,
+      "grad_norm": 1.4351515769958496,
+      "learning_rate": 4.7420223787816e-05,
+      "loss": 0.7053018569946289,
+      "mean_token_accuracy": 0.7821334384381771,
+      "num_tokens": 209680.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.8154770018532872,
+      "epoch": 0.05388461438822829,
+      "grad_norm": 1.6868013143539429,
+      "learning_rate": 4.731661831744716e-05,
+      "loss": 0.7971642017364502,
+      "mean_token_accuracy": 0.7698610629886389,
+      "num_tokens": 278575.0,
+      "step": 260
+    },
+    {
+      "entropy": 0.6673171075060964,
+      "epoch": 0.0559570995570063,
+      "grad_norm": 1.9865959882736206,
+      "learning_rate": 4.721301284707833e-05,
+      "loss": 0.709796142578125,
+      "mean_token_accuracy": 0.7879142951220274,
+      "num_tokens": 350316.0,
+      "step": 270
+    },
+    {
+      "entropy": 0.7255571869201958,
+      "epoch": 0.0580295847257843,
+      "grad_norm": 1.538944959640503,
+      "learning_rate": 4.710940737670949e-05,
+      "loss": 0.7522840976715088,
+      "mean_token_accuracy": 0.7715948877856136,
+      "num_tokens": 69041.0,
+      "step": 280
+    },
+    {
+      "entropy": 0.7363651756197214,
+      "epoch": 0.060102069894562314,
+      "grad_norm": 1.786579966545105,
+      "learning_rate": 4.7005801906340655e-05,
+      "loss": 0.7095738410949707,
+      "mean_token_accuracy": 0.7872146792709828,
+      "num_tokens": 137384.0,
+      "step": 290
+    },
+    {
+      "entropy": 0.6957077354192733,
+      "epoch": 0.062174555063340325,
+      "grad_norm": 1.565349817276001,
+      "learning_rate": 4.6902196435971824e-05,
+      "loss": 0.7271500110626221,
+      "mean_token_accuracy": 0.7818357802927494,
+      "num_tokens": 205506.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.7745418599806726,
+      "epoch": 0.06424704023211834,
+      "grad_norm": 1.8280259370803833,
+      "learning_rate": 4.6798590965602986e-05,
+      "loss": 0.7450338363647461,
+      "mean_token_accuracy": 0.7677149960771203,
+      "num_tokens": 274438.0,
+      "step": 310
+    },
+    {
+      "entropy": 0.6606647335924208,
+      "epoch": 0.06631952540089635,
+      "grad_norm": 1.8488798141479492,
+      "learning_rate": 4.669498549523415e-05,
+      "loss": 0.6708813667297363,
+      "mean_token_accuracy": 0.7946085242554546,
+      "num_tokens": 346343.0,
+      "step": 320
+    },
+    {
+      "entropy": 0.6250341087579727,
+      "epoch": 0.06839201056967437,
+      "grad_norm": 1.5199235677719116,
+      "learning_rate": 4.659138002486532e-05,
+      "loss": 0.6807006359100342,
+      "mean_token_accuracy": 0.7861586820334197,
+      "num_tokens": 68759.0,
+      "step": 330
+    },
+    {
+      "entropy": 0.726000511739403,
+      "epoch": 0.07046449573845237,
+      "grad_norm": 1.764443278312683,
+      "learning_rate": 4.648777455449648e-05,
+      "loss": 0.7153847694396973,
+      "mean_token_accuracy": 0.7712504647672176,
+      "num_tokens": 69903.0,
+      "step": 340
+    },
+    {
+      "entropy": 0.6995948201045394,
+      "epoch": 0.07253698090723039,
+      "grad_norm": 1.4723390340805054,
+      "learning_rate": 4.638416908412764e-05,
+      "loss": 0.7241292953491211,
+      "mean_token_accuracy": 0.7754306487739087,
+      "num_tokens": 139565.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.7070768253877759,
+      "epoch": 0.0746094660760084,
+      "grad_norm": 2.09631609916687,
+      "learning_rate": 4.628056361375881e-05,
+      "loss": 0.6986414432525635,
+      "mean_token_accuracy": 0.781221623159945,
+      "num_tokens": 211282.0,
+      "step": 360
+    },
+    {
+      "entropy": 0.7351198641583323,
+      "epoch": 0.0766819512447864,
+      "grad_norm": 1.4800150394439697,
+      "learning_rate": 4.617695814338997e-05,
+      "loss": 0.7421191692352295,
+      "mean_token_accuracy": 0.7763467058539391,
+      "num_tokens": 280875.0,
+      "step": 370
+    },
+    {
+      "entropy": 0.7293847506865859,
+      "epoch": 0.07875443641356442,
+      "grad_norm": 1.5986937284469604,
+      "learning_rate": 4.6073352673021135e-05,
+      "loss": 0.7357936382293702,
+      "mean_token_accuracy": 0.7747447842732071,
+      "num_tokens": 351666.0,
+      "step": 380
+    },
+    {
+      "entropy": 0.7266428637318313,
+      "epoch": 0.08082692158234242,
+      "grad_norm": 1.5452651977539062,
+      "learning_rate": 4.5969747202652304e-05,
+      "loss": 0.7276121139526367,
+      "mean_token_accuracy": 0.7778783718124032,
+      "num_tokens": 423595.0,
+      "step": 390
+    },
+    {
+      "entropy": 0.7027492884546518,
+      "epoch": 0.08289940675112044,
+      "grad_norm": 1.6821953058242798,
+      "learning_rate": 4.5866141732283466e-05,
+      "loss": 0.6949647903442383,
+      "mean_token_accuracy": 0.7877286925911904,
+      "num_tokens": 492184.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.7082527220249176,
+      "epoch": 0.08497189191989844,
+      "grad_norm": 3.255920648574829,
+      "learning_rate": 4.576253626191463e-05,
+      "loss": 0.737195348739624,
+      "mean_token_accuracy": 0.782087417319417,
+      "num_tokens": 68961.0,
+      "step": 410
+    },
+    {
+      "entropy": 0.730042477324605,
+      "epoch": 0.08704437708867646,
+      "grad_norm": 1.7037324905395508,
+      "learning_rate": 4.56589307915458e-05,
+      "loss": 0.7140017509460449,
+      "mean_token_accuracy": 0.7823584023863077,
+      "num_tokens": 137630.0,
+      "step": 420
+    },
+    {
+      "entropy": 0.6598193269222975,
+      "epoch": 0.08911686225745447,
+      "grad_norm": 1.8114103078842163,
+      "learning_rate": 4.555532532117696e-05,
+      "loss": 0.6801549434661865,
+      "mean_token_accuracy": 0.7824499621987343,
+      "num_tokens": 205721.0,
+      "step": 430
+    },
+    {
+      "entropy": 0.6710394449532032,
+      "epoch": 0.09118934742623248,
+      "grad_norm": 1.6750438213348389,
+      "learning_rate": 4.545171985080812e-05,
+      "loss": 0.6884138584136963,
+      "mean_token_accuracy": 0.7796468544751406,
+      "num_tokens": 275604.0,
+      "step": 440
+    },
+    {
+      "entropy": 0.6683231407776475,
+      "epoch": 0.09326183259501049,
+      "grad_norm": 4.430294990539551,
+      "learning_rate": 4.534811438043929e-05,
+      "loss": 0.6381510734558106,
+      "mean_token_accuracy": 0.8033638086169959,
+      "num_tokens": 347194.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.6776463004760445,
+      "epoch": 0.0953343177637885,
+      "grad_norm": 2.0065362453460693,
+      "learning_rate": 4.524450891007045e-05,
+      "loss": 0.7055120468139648,
+      "mean_token_accuracy": 0.7787912800908089,
+      "num_tokens": 418052.0,
+      "step": 460
+    },
+    {
+      "entropy": 0.7017317101359367,
+      "epoch": 0.09740680293256651,
+      "grad_norm": 1.8958861827850342,
+      "learning_rate": 4.514090343970162e-05,
+      "loss": 0.7303417682647705,
+      "mean_token_accuracy": 0.7812308793887496,
+      "num_tokens": 488415.0,
+      "step": 470
+    },
+    {
+      "entropy": 0.7091405378654599,
+      "epoch": 0.09947928810134453,
+      "grad_norm": 19.853466033935547,
+      "learning_rate": 4.5037297969332784e-05,
+      "loss": 0.6662539005279541,
+      "mean_token_accuracy": 0.7855507833883166,
+      "num_tokens": 70219.0,
+      "step": 480
+    },
+    {
+      "entropy": 0.672448315937072,
+      "epoch": 0.10155177327012253,
+      "grad_norm": 1.5199726819992065,
+      "learning_rate": 4.4933692498963946e-05,
+      "loss": 0.6813668727874755,
+      "mean_token_accuracy": 0.7893076185137033,
+      "num_tokens": 70268.0,
+      "step": 490
+    },
+    {
+      "entropy": 0.6648079196922481,
+      "epoch": 0.10362425843890055,
+      "grad_norm": 1.6414028406143188,
+      "learning_rate": 4.4830087028595115e-05,
+      "loss": 0.6589033603668213,
+      "mean_token_accuracy": 0.7939360909163952,
+      "num_tokens": 140943.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.6688623799011111,
+      "epoch": 0.10569674360767856,
+      "grad_norm": 1.9084100723266602,
+      "learning_rate": 4.472648155822628e-05,
+      "loss": 0.7010292053222656,
+      "mean_token_accuracy": 0.7834952095523476,
+      "num_tokens": 211102.0,
+      "step": 510
+    },
+    {
+      "entropy": 0.6870146187953651,
+      "epoch": 0.10776922877645657,
+      "grad_norm": 1.3491404056549072,
+      "learning_rate": 4.462287608785744e-05,
+      "loss": 0.6879950046539307,
+      "mean_token_accuracy": 0.7922510616481304,
+      "num_tokens": 69328.0,
+      "step": 520
+    },
+    {
+      "entropy": 0.7129757734015584,
+      "epoch": 0.10984171394523458,
+      "grad_norm": 2.1514997482299805,
+      "learning_rate": 4.451927061748861e-05,
+      "loss": 0.7187893390655518,
+      "mean_token_accuracy": 0.775782386213541,
+      "num_tokens": 139443.0,
+      "step": 530
+    },
+    {
+      "entropy": 0.6893678920343518,
+      "epoch": 0.1119141991140126,
+      "grad_norm": 1.7353824377059937,
+      "learning_rate": 4.441566514711977e-05,
+      "loss": 0.6905662059783936,
+      "mean_token_accuracy": 0.7856925368309021,
+      "num_tokens": 209644.0,
+      "step": 540
+    },
+    {
+      "entropy": 0.6872515428811312,
+      "epoch": 0.1139866842827906,
+      "grad_norm": 1.6228446960449219,
+      "learning_rate": 4.431205967675093e-05,
+      "loss": 0.668769359588623,
+      "mean_token_accuracy": 0.7955817665904761,
+      "num_tokens": 281194.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.6489416746422648,
+      "epoch": 0.1160591694515686,
+      "grad_norm": 2.0254833698272705,
+      "learning_rate": 4.42084542063821e-05,
+      "loss": 0.6596323013305664,
+      "mean_token_accuracy": 0.7954790510237217,
+      "num_tokens": 351822.0,
+      "step": 560
+    },
+    {
+      "entropy": 0.6674875200260431,
+      "epoch": 0.11813165462034662,
+      "grad_norm": 1.439931035041809,
+      "learning_rate": 4.4104848736013263e-05,
+      "loss": 0.6615776538848877,
+      "mean_token_accuracy": 0.7966180466115474,
+      "num_tokens": 422625.0,
+      "step": 570
+    },
+    {
+      "entropy": 0.6334569159895181,
+      "epoch": 0.12020413978912463,
+      "grad_norm": 2.2282028198242188,
+      "learning_rate": 4.4001243265644426e-05,
+      "loss": 0.6483668804168701,
+      "mean_token_accuracy": 0.797807352989912,
+      "num_tokens": 492300.0,
+      "step": 580
+    },
+    {
+      "entropy": 0.6936957992613315,
+      "epoch": 0.12227662495790265,
+      "grad_norm": 1.643386721611023,
+      "learning_rate": 4.3897637795275594e-05,
+      "loss": 0.6917550086975097,
+      "mean_token_accuracy": 0.7832328652963042,
+      "num_tokens": 72501.0,
+      "step": 590
+    },
+    {
+      "entropy": 0.6695835535414517,
+      "epoch": 0.12434911012668065,
+      "grad_norm": 1.569928765296936,
+      "learning_rate": 4.379403232490676e-05,
+      "loss": 0.6677763938903809,
+      "mean_token_accuracy": 0.7877933101728558,
+      "num_tokens": 139382.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.6616535548120737,
+      "epoch": 0.12642159529545866,
+      "grad_norm": 3.1185977458953857,
+      "learning_rate": 4.369042685453792e-05,
+      "loss": 0.6709516048431396,
+      "mean_token_accuracy": 0.7996543843299151,
+      "num_tokens": 208905.0,
+      "step": 610
+    },
+    {
+      "entropy": 0.6468584710732103,
+      "epoch": 0.1284940804642367,
+      "grad_norm": 1.3366657495498657,
+      "learning_rate": 4.358682138416909e-05,
+      "loss": 0.6417848587036132,
+      "mean_token_accuracy": 0.7978057712316513,
+      "num_tokens": 277955.0,
+      "step": 620
+    },
+    {
+      "entropy": 0.673513944633305,
+      "epoch": 0.1305665656330147,
+      "grad_norm": 1.906376838684082,
+      "learning_rate": 4.348321591380025e-05,
+      "loss": 0.6771799087524414,
+      "mean_token_accuracy": 0.7926665464416146,
+      "num_tokens": 348217.0,
+      "step": 630
+    },
+    {
+      "entropy": 0.6405081307515502,
+      "epoch": 0.1326390508017927,
+      "grad_norm": 1.432870626449585,
+      "learning_rate": 4.337961044343142e-05,
+      "loss": 0.6618150234222412,
+      "mean_token_accuracy": 0.7943162884563207,
+      "num_tokens": 417786.0,
+      "step": 640
+    },
+    {
+      "entropy": 0.6624415351077915,
+      "epoch": 0.1347115359705707,
+      "grad_norm": 2.131091594696045,
+      "learning_rate": 4.327600497306258e-05,
+      "loss": 0.6451473712921143,
+      "mean_token_accuracy": 0.7957137264311314,
+      "num_tokens": 71332.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.6276063132099807,
+      "epoch": 0.13678402113934873,
+      "grad_norm": 1.8273603916168213,
+      "learning_rate": 4.317239950269374e-05,
+      "loss": 0.636332893371582,
+      "mean_token_accuracy": 0.8046804212033749,
+      "num_tokens": 141457.0,
+      "step": 660
+    },
+    {
+      "entropy": 0.6453790031373501,
+      "epoch": 0.13885650630812674,
+      "grad_norm": 1.611478328704834,
+      "learning_rate": 4.306879403232491e-05,
+      "loss": 0.6900195598602294,
+      "mean_token_accuracy": 0.7854223992675543,
+      "num_tokens": 211039.0,
+      "step": 670
+    },
+    {
+      "entropy": 0.6989213732071221,
+      "epoch": 0.14092899147690474,
+      "grad_norm": 1.3673732280731201,
+      "learning_rate": 4.2965188561956074e-05,
+      "loss": 0.6821016788482666,
+      "mean_token_accuracy": 0.7841938553377986,
+      "num_tokens": 69243.0,
+      "step": 680
+    },
+    {
+      "entropy": 0.6732430781237781,
+      "epoch": 0.14300147664568275,
+      "grad_norm": 1.7757006883621216,
+      "learning_rate": 4.2861583091587236e-05,
+      "loss": 0.6844731330871582,
+      "mean_token_accuracy": 0.7879077158868313,
+      "num_tokens": 139807.0,
+      "step": 690
+    },
+    {
+      "entropy": 0.6312349032610655,
+      "epoch": 0.14507396181446078,
+      "grad_norm": 2.0880074501037598,
+      "learning_rate": 4.2757977621218405e-05,
+      "loss": 0.671199893951416,
+      "mean_token_accuracy": 0.7832676794379949,
+      "num_tokens": 209193.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.6698089136742056,
+      "epoch": 0.14714644698323878,
+      "grad_norm": 4.582449436187744,
+      "learning_rate": 4.265437215084957e-05,
+      "loss": 0.6485928535461426,
+      "mean_token_accuracy": 0.7927296923473477,
+      "num_tokens": 277252.0,
+      "step": 710
+    },
+    {
+      "entropy": 0.6736472038552165,
+      "epoch": 0.1492189321520168,
+      "grad_norm": 12.003286361694336,
+      "learning_rate": 4.255076668048073e-05,
+      "loss": 0.7059356212615967,
+      "mean_token_accuracy": 0.7752311144024133,
+      "num_tokens": 348557.0,
+      "step": 720
+    },
+    {
+      "entropy": 0.6616889594122768,
+      "epoch": 0.1512914173207948,
+      "grad_norm": 41.21874237060547,
+      "learning_rate": 4.24471612101119e-05,
+      "loss": 0.6478518486022949,
+      "mean_token_accuracy": 0.79735719114542,
+      "num_tokens": 70589.0,
+      "step": 730
+    },
+    {
+      "entropy": 0.6093726826831698,
+      "epoch": 0.1533639024895728,
+      "grad_norm": 1.696491003036499,
+      "learning_rate": 4.234355573974306e-05,
+      "loss": 0.6148743629455566,
+      "mean_token_accuracy": 0.7994868841022253,
+      "num_tokens": 139657.0,
+      "step": 740
+    },
+    {
+      "entropy": 0.6621177848428488,
+      "epoch": 0.15543638765835083,
+      "grad_norm": 6.0005340576171875,
+      "learning_rate": 4.223995026937422e-05,
+      "loss": 0.6670567512512207,
+      "mean_token_accuracy": 0.7841767473146319,
+      "num_tokens": 209670.0,
+      "step": 750
+    },
+    {
+      "entropy": 0.632575509045273,
+      "epoch": 0.15750887282712883,
+      "grad_norm": 1.5963951349258423,
+      "learning_rate": 4.213634479900539e-05,
+      "loss": 0.6246257781982422,
+      "mean_token_accuracy": 0.8050273135304451,
+      "num_tokens": 279337.0,
+      "step": 760
+    },
+    {
+      "entropy": 0.6313233209773899,
+      "epoch": 0.15958135799590684,
+      "grad_norm": 1.5304876565933228,
+      "learning_rate": 4.2032739328636554e-05,
+      "loss": 0.6431151866912842,
+      "mean_token_accuracy": 0.7896010477095843,
+      "num_tokens": 350155.0,
+      "step": 770
+    },
+    {
+      "entropy": 0.6548214767128229,
+      "epoch": 0.16165384316468484,
+      "grad_norm": 2.67743182182312,
+      "learning_rate": 4.1929133858267716e-05,
+      "loss": 0.6790497303009033,
+      "mean_token_accuracy": 0.7878863928839565,
+      "num_tokens": 419565.0,
+      "step": 780
+    },
+    {
+      "entropy": 0.6505418440327049,
+      "epoch": 0.16372632833346287,
+      "grad_norm": 242.05491638183594,
+      "learning_rate": 4.1825528387898885e-05,
+      "loss": 0.6433857917785645,
+      "mean_token_accuracy": 0.795454365387559,
+      "num_tokens": 489012.0,
+      "step": 790
+    },
+    {
+      "entropy": 0.6476001624949277,
+      "epoch": 0.16579881350224088,
+      "grad_norm": 1.4300724267959595,
+      "learning_rate": 4.172192291753005e-05,
+      "loss": 0.6319501399993896,
+      "mean_token_accuracy": 0.7924936018884182,
+      "num_tokens": 558867.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.6442388415336608,
+      "epoch": 0.16787129867101888,
+      "grad_norm": 4.613394260406494,
+      "learning_rate": 4.1618317447161216e-05,
+      "loss": 0.6678831577301025,
+      "mean_token_accuracy": 0.7943335395306349,
+      "num_tokens": 628948.0,
+      "step": 810
+    },
+    {
+      "entropy": 0.6203080628067255,
+      "epoch": 0.16994378383979689,
+      "grad_norm": 2.5130362510681152,
+      "learning_rate": 4.151471197679238e-05,
+      "loss": 0.6110039710998535,
+      "mean_token_accuracy": 0.810325526073575,
+      "num_tokens": 71301.0,
+      "step": 820
+    },
+    {
+      "entropy": 0.6230071322061121,
+      "epoch": 0.17201626900857492,
+      "grad_norm": 2.210916519165039,
+      "learning_rate": 4.141110650642354e-05,
+      "loss": 0.6246025085449218,
+      "mean_token_accuracy": 0.8011124541983008,
+      "num_tokens": 70397.0,
+      "step": 830
+    },
+    {
+      "entropy": 0.6719645065255463,
+      "epoch": 0.17408875417735292,
+      "grad_norm": 5.696254730224609,
+      "learning_rate": 4.130750103605471e-05,
+      "loss": 0.6632156372070312,
+      "mean_token_accuracy": 0.7947734523564577,
+      "num_tokens": 69253.0,
+      "step": 840
+    },
+    {
+      "entropy": 0.6387658508494496,
+      "epoch": 0.17616123934613093,
+      "grad_norm": 4.031402587890625,
+      "learning_rate": 4.120389556568587e-05,
+      "loss": 0.6373042106628418,
+      "mean_token_accuracy": 0.7951240029186011,
+      "num_tokens": 139555.0,
+      "step": 850
+    },
+    {
+      "entropy": 0.6169766587205231,
+      "epoch": 0.17823372451490893,
+      "grad_norm": 2.1127257347106934,
+      "learning_rate": 4.1100290095317034e-05,
+      "loss": 0.6043564796447753,
+      "mean_token_accuracy": 0.8086937755346298,
+      "num_tokens": 210401.0,
+      "step": 860
+    },
+    {
+      "entropy": 0.6277017027139664,
+      "epoch": 0.18030620968368696,
+      "grad_norm": 2.3066794872283936,
+      "learning_rate": 4.09966846249482e-05,
+      "loss": 0.6512989521026611,
+      "mean_token_accuracy": 0.7987392786890268,
+      "num_tokens": 281474.0,
+      "step": 870
+    },
+    {
+      "entropy": 0.6503841457888484,
+      "epoch": 0.18237869485246497,
+      "grad_norm": 1.473809003829956,
+      "learning_rate": 4.089307915457936e-05,
+      "loss": 0.6600662231445312,
+      "mean_token_accuracy": 0.7932868717238307,
+      "num_tokens": 69648.0,
+      "step": 880
+    },
+    {
+      "entropy": 0.6581103558652103,
+      "epoch": 0.18445118002124297,
+      "grad_norm": 2.077177047729492,
+      "learning_rate": 4.078947368421053e-05,
+      "loss": 0.6385226249694824,
+      "mean_token_accuracy": 0.7958818433806301,
+      "num_tokens": 139222.0,
+      "step": 890
+    },
+    {
+      "entropy": 0.6336492419242858,
+      "epoch": 0.18652366519002098,
+      "grad_norm": 2.0784988403320312,
+      "learning_rate": 4.0685868213841696e-05,
+      "loss": 0.6557448863983154,
+      "mean_token_accuracy": 0.7972610833123326,
+      "num_tokens": 209900.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.6921999044716358,
+      "epoch": 0.188596150358799,
+      "grad_norm": 1.454811453819275,
+      "learning_rate": 4.058226274347286e-05,
+      "loss": 0.6755734443664551,
+      "mean_token_accuracy": 0.7822293974459171,
+      "num_tokens": 280946.0,
+      "step": 910
+    },
+    {
+      "entropy": 0.6405132696032524,
+      "epoch": 0.190668635527577,
+      "grad_norm": 6.370351314544678,
+      "learning_rate": 4.047865727310402e-05,
+      "loss": 0.6447234630584717,
+      "mean_token_accuracy": 0.7998423084616662,
+      "num_tokens": 350251.0,
+      "step": 920
+    },
+    {
+      "entropy": 0.6748547056689859,
+      "epoch": 0.19274112069635502,
+      "grad_norm": 1.61223566532135,
+      "learning_rate": 4.037505180273519e-05,
+      "loss": 0.6716421604156494,
+      "mean_token_accuracy": 0.7944653522223234,
+      "num_tokens": 418408.0,
+      "step": 930
+    },
+    {
+      "entropy": 0.652656842302531,
+      "epoch": 0.19481360586513302,
+      "grad_norm": 12.04974365234375,
+      "learning_rate": 4.027144633236635e-05,
+      "loss": 0.675056791305542,
+      "mean_token_accuracy": 0.7908035142347216,
+      "num_tokens": 486615.0,
+      "step": 940
+    },
+    {
+      "entropy": 0.6370473764836788,
+      "epoch": 0.19688609103391103,
+      "grad_norm": 1.5487881898880005,
+      "learning_rate": 4.0167840861997514e-05,
+      "loss": 0.6400912284851075,
+      "mean_token_accuracy": 0.7931933244690299,
+      "num_tokens": 555657.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.6333246235735714,
+      "epoch": 0.19895857620268906,
+      "grad_norm": 2.4830243587493896,
+      "learning_rate": 4.006423539162868e-05,
+      "loss": 0.6166810512542724,
+      "mean_token_accuracy": 0.8014374598860741,
+      "num_tokens": 626425.0,
+      "step": 960
+    },
+    {
+      "entropy": 0.5938723726198077,
+      "epoch": 0.20103106137146706,
+      "grad_norm": 1.842581868171692,
+      "learning_rate": 3.9960629921259845e-05,
+      "loss": 0.6217962741851807,
+      "mean_token_accuracy": 0.8008956335484981,
+      "num_tokens": 696747.0,
+      "step": 970
+    },
+    {
+      "entropy": 0.6409877292811871,
+      "epoch": 0.20310354654024507,
+      "grad_norm": 2.0318474769592285,
+      "learning_rate": 3.985702445089101e-05,
+      "loss": 0.6548454761505127,
+      "mean_token_accuracy": 0.7928589731454849,
+      "num_tokens": 68262.0,
+      "step": 980
+    },
+    {
+      "entropy": 0.6127532176207751,
+      "epoch": 0.20517603170902307,
+      "grad_norm": 14.585939407348633,
+      "learning_rate": 3.9753418980522176e-05,
+      "loss": 0.6044599056243897,
+      "mean_token_accuracy": 0.8128338549286127,
+      "num_tokens": 139011.0,
+      "step": 990
+    },
+    {
+      "entropy": 0.6201622080989182,
+      "epoch": 0.2072485168778011,
+      "grad_norm": 1.8208625316619873,
+      "learning_rate": 3.964981351015334e-05,
+      "loss": 0.6481419086456299,
+      "mean_token_accuracy": 0.7962232168763876,
+      "num_tokens": 207368.0,
+      "step": 1000
+    },
+    {
+      "entropy": 0.6494233716279268,
+      "epoch": 0.2093210020465791,
+      "grad_norm": 2.095757246017456,
+      "learning_rate": 3.954620803978451e-05,
+      "loss": 0.6731655120849609,
+      "mean_token_accuracy": 0.7879340261220932,
+      "num_tokens": 274548.0,
+      "step": 1010
+    },
+    {
+      "entropy": 0.6554611946456135,
+      "epoch": 0.2113934872153571,
+      "grad_norm": 1.5424741506576538,
+      "learning_rate": 3.944260256941566e-05,
+      "loss": 0.6161803245544434,
+      "mean_token_accuracy": 0.8044503800570965,
+      "num_tokens": 70077.0,
+      "step": 1020
+    },
+    {
+      "entropy": 0.58364950818941,
+      "epoch": 0.21346597238413512,
+      "grad_norm": 3.1126465797424316,
+      "learning_rate": 3.933899709904683e-05,
+      "loss": 0.6338560104370117,
+      "mean_token_accuracy": 0.79702756293118,
+      "num_tokens": 139893.0,
+      "step": 1030
+    },
+    {
+      "entropy": 0.5846088617108762,
+      "epoch": 0.21553845755291315,
+      "grad_norm": 1.5168766975402832,
+      "learning_rate": 3.9235391628678e-05,
+      "loss": 0.6250156879425048,
+      "mean_token_accuracy": 0.7956931252032519,
+      "num_tokens": 211100.0,
+      "step": 1040
+    },
+    {
+      "entropy": 0.6478412504307925,
+      "epoch": 0.21761094272169115,
+      "grad_norm": 1.6615567207336426,
+      "learning_rate": 3.9131786158309155e-05,
+      "loss": 0.6174096584320068,
+      "mean_token_accuracy": 0.8027971796691418,
+      "num_tokens": 282358.0,
+      "step": 1050
+    },
+    {
+      "entropy": 0.6292086754925549,
+      "epoch": 0.21968342789046916,
+      "grad_norm": 5.6696391105651855,
+      "learning_rate": 3.9028180687940324e-05,
+      "loss": 0.6396576404571533,
+      "mean_token_accuracy": 0.805364703014493,
+      "num_tokens": 353387.0,
+      "step": 1060
+    },
+    {
+      "entropy": 0.6447535171173513,
+      "epoch": 0.22175591305924716,
+      "grad_norm": 1.925402045249939,
+      "learning_rate": 3.892457521757149e-05,
+      "loss": 0.6467451572418212,
+      "mean_token_accuracy": 0.7975434828549623,
+      "num_tokens": 68804.0,
+      "step": 1070
+    },
+    {
+      "entropy": 0.6303643623366952,
+      "epoch": 0.2238283982280252,
+      "grad_norm": 1.8096734285354614,
+      "learning_rate": 3.8820969747202655e-05,
+      "loss": 0.6381072521209716,
+      "mean_token_accuracy": 0.794750172458589,
+      "num_tokens": 137683.0,
+      "step": 1080
+    },
+    {
+      "entropy": 0.6708084937185049,
+      "epoch": 0.2259008833968032,
+      "grad_norm": 2.2711029052734375,
+      "learning_rate": 3.871736427683382e-05,
+      "loss": 0.6552023410797119,
+      "mean_token_accuracy": 0.7935653693974019,
+      "num_tokens": 206142.0,
+      "step": 1090
+    },
+    {
+      "entropy": 0.611713959928602,
+      "epoch": 0.2279733685655812,
+      "grad_norm": 6.44283390045166,
+      "learning_rate": 3.8613758806464987e-05,
+      "loss": 0.6246577262878418,
+      "mean_token_accuracy": 0.8030017718672753,
+      "num_tokens": 275500.0,
+      "step": 1100
+    },
+    {
+      "entropy": 0.6367465043906122,
+      "epoch": 0.2300458537343592,
+      "grad_norm": 4.7516093254089355,
+      "learning_rate": 3.851015333609615e-05,
+      "loss": 0.666812801361084,
+      "mean_token_accuracy": 0.8059824664145708,
+      "num_tokens": 343087.0,
+      "step": 1110
+    },
+    {
+      "entropy": 0.6423371199518442,
+      "epoch": 0.2321183389031372,
+      "grad_norm": 1.9025523662567139,
+      "learning_rate": 3.840654786572731e-05,
+      "loss": 0.6421233654022217,
+      "mean_token_accuracy": 0.7951819008216262,
+      "num_tokens": 68969.0,
+      "step": 1120
+    },
+    {
+      "entropy": 0.6140216056257486,
+      "epoch": 0.23419082407191524,
+      "grad_norm": 2.387733221054077,
+      "learning_rate": 3.830294239535848e-05,
+      "loss": 0.6032763481140136,
+      "mean_token_accuracy": 0.8053653921931982,
+      "num_tokens": 71586.0,
+      "step": 1130
+    },
+    {
+      "entropy": 0.6140187031589448,
+      "epoch": 0.23626330924069325,
+      "grad_norm": 1.670482873916626,
+      "learning_rate": 3.819933692498964e-05,
+      "loss": 0.6106282711029053,
+      "mean_token_accuracy": 0.8058054704219103,
+      "num_tokens": 70310.0,
+      "step": 1140
+    },
+    {
+      "entropy": 0.5762817421928048,
+      "epoch": 0.23833579440947125,
+      "grad_norm": 23.664371490478516,
+      "learning_rate": 3.8095731454620804e-05,
+      "loss": 0.6104034423828125,
+      "mean_token_accuracy": 0.8093477137386799,
+      "num_tokens": 70607.0,
+      "step": 1150
+    },
+    {
+      "entropy": 0.6225127806887031,
+      "epoch": 0.24040827957824926,
+      "grad_norm": 5.779444217681885,
+      "learning_rate": 3.7992125984251966e-05,
+      "loss": 0.6293696403503418,
+      "mean_token_accuracy": 0.7947902269661427,
+      "num_tokens": 140872.0,
+      "step": 1160
+    },
+    {
+      "entropy": 0.6353272215463222,
+      "epoch": 0.2424807647470273,
+      "grad_norm": 1.9873942136764526,
+      "learning_rate": 3.7888520513883135e-05,
+      "loss": 0.6285487174987793,
+      "mean_token_accuracy": 0.8022656626999378,
+      "num_tokens": 69502.0,
+      "step": 1170
+    },
+    {
+      "entropy": 0.626314930897206,
+      "epoch": 0.2445532499158053,
+      "grad_norm": 7.768356800079346,
+      "learning_rate": 3.7784915043514304e-05,
+      "loss": 0.6211750507354736,
+      "mean_token_accuracy": 0.8071904622018338,
+      "num_tokens": 69962.0,
+      "step": 1180
+    },
+    {
+      "entropy": 0.6255401530303061,
+      "epoch": 0.2466257350845833,
+      "grad_norm": 1.888361930847168,
+      "learning_rate": 3.768130957314546e-05,
+      "loss": 0.6480055332183838,
+      "mean_token_accuracy": 0.7934892239049077,
+      "num_tokens": 140682.0,
+      "step": 1190
+    },
+    {
+      "entropy": 0.6203898694366217,
+      "epoch": 0.2486982202533613,
+      "grad_norm": 1.921849250793457,
+      "learning_rate": 3.757770410277663e-05,
+      "loss": 0.6031047344207764,
+      "mean_token_accuracy": 0.8058484740555286,
+      "num_tokens": 211645.0,
+      "step": 1200
+    },
+    {
+      "entropy": 0.610185282304883,
+      "epoch": 0.2507707054221393,
+      "grad_norm": 1.7859575748443604,
+      "learning_rate": 3.74740986324078e-05,
+      "loss": 0.604803466796875,
+      "mean_token_accuracy": 0.8043402170762419,
+      "num_tokens": 278656.0,
+      "step": 1210
+    },
+    {
+      "entropy": 0.6415552173741161,
+      "epoch": 0.2528431905909173,
+      "grad_norm": 8.131621360778809,
+      "learning_rate": 3.737049316203895e-05,
+      "loss": 0.6561008930206299,
+      "mean_token_accuracy": 0.7935157649219036,
+      "num_tokens": 349616.0,
+      "step": 1220
+    },
+    {
+      "entropy": 0.635531363915652,
+      "epoch": 0.25491567575969537,
+      "grad_norm": 2.340214490890503,
+      "learning_rate": 3.726688769167012e-05,
+      "loss": 0.6464750289916992,
+      "mean_token_accuracy": 0.79804602060467,
+      "num_tokens": 420849.0,
+      "step": 1230
+    },
+    {
+      "entropy": 0.5969384836964309,
+      "epoch": 0.2569881609284734,
+      "grad_norm": 83.84396362304688,
+      "learning_rate": 3.7686567164179105e-06,
+      "loss": 0.5905964374542236,
+      "mean_token_accuracy": 0.802092020958662,
+      "num_tokens": 72388.0,
+      "step": 1240
+    },
+    {
+      "entropy": 0.6049651755951345,
+      "epoch": 0.2590606460972514,
+      "grad_norm": 1.7408950328826904,
+      "learning_rate": 3.7059676750932446e-05,
+      "loss": 0.6098982334136963,
+      "mean_token_accuracy": 0.8154445670545101,
+      "num_tokens": 69334.0,
+      "step": 1250
+    },
+    {
+      "entropy": 0.5929268936160952,
+      "epoch": 0.2611331312660294,
+      "grad_norm": 2.4479739665985107,
+      "learning_rate": 3.6956071280563615e-05,
+      "loss": 0.615260124206543,
+      "mean_token_accuracy": 0.7975582104176283,
+      "num_tokens": 139535.0,
+      "step": 1260
+    },
+    {
+      "entropy": 0.6156681244261563,
+      "epoch": 0.2632056164348074,
+      "grad_norm": 7.5904541015625,
+      "learning_rate": 3.6852465810194784e-05,
+      "loss": 0.6417912006378174,
+      "mean_token_accuracy": 0.8050157245248556,
+      "num_tokens": 209990.0,
+      "step": 1270
+    },
+    {
+      "entropy": 0.6125300782732666,
+      "epoch": 0.2652781016035854,
+      "grad_norm": 1.5859016180038452,
+      "learning_rate": 3.6748860339825946e-05,
+      "loss": 0.5806515216827393,
+      "mean_token_accuracy": 0.8106319297105073,
+      "num_tokens": 280797.0,
+      "step": 1280
+    },
+    {
+      "entropy": 0.6261352578178048,
+      "epoch": 0.2673505867723634,
+      "grad_norm": 2.6306662559509277,
+      "learning_rate": 3.664525486945711e-05,
+      "loss": 0.655699634552002,
+      "mean_token_accuracy": 0.7938036229461432,
+      "num_tokens": 352252.0,
+      "step": 1290
+    },
+    {
+      "entropy": 0.6153189892880618,
+      "epoch": 0.2694230719411414,
+      "grad_norm": 1.740610122680664,
+      "learning_rate": 3.654164939908827e-05,
+      "loss": 0.6046313762664794,
+      "mean_token_accuracy": 0.8039134848862887,
+      "num_tokens": 69275.0,
+      "step": 1300
+    },
+    {
+      "entropy": 0.6278093876317143,
+      "epoch": 0.2714955571099194,
+      "grad_norm": 3.1143393516540527,
+      "learning_rate": 3.643804392871944e-05,
+      "loss": 0.6498140811920166,
+      "mean_token_accuracy": 0.7957121979445219,
+      "num_tokens": 68169.0,
+      "step": 1310
+    },
+    {
+      "entropy": 0.5825623633340001,
+      "epoch": 0.27356804227869747,
+      "grad_norm": 2.6731808185577393,
+      "learning_rate": 3.63344384583506e-05,
+      "loss": 0.5718067169189454,
+      "mean_token_accuracy": 0.8134741004556417,
+      "num_tokens": 137759.0,
+      "step": 1320
+    },
+    {
+      "entropy": 0.5590585919097066,
+      "epoch": 0.27564052744747547,
+      "grad_norm": 2.4920592308044434,
+      "learning_rate": 3.6230832987981764e-05,
+      "loss": 0.5690700054168701,
+      "mean_token_accuracy": 0.8109207771718502,
+      "num_tokens": 205720.0,
+      "step": 1330
+    },
+    {
+      "entropy": 0.5923157716169953,
+      "epoch": 0.2777130126162535,
+      "grad_norm": 1.862938404083252,
+      "learning_rate": 3.612722751761293e-05,
+      "loss": 0.6129358291625977,
+      "mean_token_accuracy": 0.8040174718946218,
+      "num_tokens": 276786.0,
+      "step": 1340
+    },
+    {
+      "entropy": 0.6135842848569155,
+      "epoch": 0.2797854977850315,
+      "grad_norm": 1.5477619171142578,
+      "learning_rate": 3.60236220472441e-05,
+      "loss": 0.6216057777404785,
+      "mean_token_accuracy": 0.7960212029516697,
+      "num_tokens": 346466.0,
+      "step": 1350
+    },
+    {
+      "entropy": 0.6067129975184798,
+      "epoch": 0.2818579829538095,
+      "grad_norm": 1.7471277713775635,
+      "learning_rate": 3.592001657687526e-05,
+      "loss": 0.5627388954162598,
+      "mean_token_accuracy": 0.8164898995310068,
+      "num_tokens": 69745.0,
+      "step": 1360
+    },
+    {
+      "entropy": 0.6310206063091754,
+      "epoch": 0.2839304681225875,
+      "grad_norm": 11.98818302154541,
+      "learning_rate": 3.5816411106506426e-05,
+      "loss": 0.6550020694732666,
+      "mean_token_accuracy": 0.791220530308783,
+      "num_tokens": 138493.0,
+      "step": 1370
+    },
+    {
+      "entropy": 0.5850912119727582,
+      "epoch": 0.2860029532913655,
+      "grad_norm": 5.830422401428223,
+      "learning_rate": 3.5712805636137595e-05,
+      "loss": 0.5944633483886719,
+      "mean_token_accuracy": 0.8132860399782658,
+      "num_tokens": 208664.0,
+      "step": 1380
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 4826,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 10,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.7357298830115876e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1380/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ec1e27ad3033c3112711a0fad2b6e99f6c35317a6bc4c41f77fe069b615c237
+size 5777