Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,202 @@
+---
+base_model: google/gemma-3-12b-it
+library_name: peft
+---
+
+# 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 0.14.0

adapter_config.json

@@ -0,0 +1,40 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-3-12b-it",
+  "bias": "none",
+  "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": 48,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "lm_head",
+    "embed_tokens"
+  ],
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj",
+    "down_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:604c3b790b74ce6d0269f7c3a24dce55d8b104b774167a56142363906c4b1104
+size 4301469136

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

chat_template.jinja

@@ -0,0 +1,47 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{'<start_of_turn>model
+'}}
+{%- endif -%}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8d5a78e158d1343eb96c55a70d3c3a10b76e0ad5cf7e51815483ebe349b7905
+size 8341591628

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:328481d74ce23d4f60dedbfde589c06e8f0b8a215e7a1442d471c526f07a1b92
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d39dd723af97f1fe81f5caa6a398fa43ee685546e1d60eac8df498a260d3ead8
+size 1064

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074

trainer_state.json

@@ -0,0 +1,1501 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.5086182537439955,
+  "eval_steps": 300,
+  "global_step": 900,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0028256569652444193,
+      "grad_norm": 125.03303527832031,
+      "learning_rate": 6.666666666666666e-07,
+      "loss": 19.3957,
+      "mean_token_accuracy": 0.443931570649147,
+      "step": 5
+    },
+    {
+      "epoch": 0.005651313930488839,
+      "grad_norm": 179.0009765625,
+      "learning_rate": 1.5e-06,
+      "loss": 19.1611,
+      "mean_token_accuracy": 0.4493979915976524,
+      "step": 10
+    },
+    {
+      "epoch": 0.008476970895733259,
+      "grad_norm": 117.55085754394531,
+      "learning_rate": 2.3333333333333336e-06,
+      "loss": 19.097,
+      "mean_token_accuracy": 0.45788785591721537,
+      "step": 15
+    },
+    {
+      "epoch": 0.011302627860977677,
+      "grad_norm": 109.04960632324219,
+      "learning_rate": 3.1666666666666667e-06,
+      "loss": 19.207,
+      "mean_token_accuracy": 0.4440133422613144,
+      "step": 20
+    },
+    {
+      "epoch": 0.014128284826222097,
+      "grad_norm": 118.16978454589844,
+      "learning_rate": 4e-06,
+      "loss": 17.2711,
+      "mean_token_accuracy": 0.4634488716721535,
+      "step": 25
+    },
+    {
+      "epoch": 0.016953941791466517,
+      "grad_norm": 161.21022033691406,
+      "learning_rate": 4.833333333333333e-06,
+      "loss": 17.7255,
+      "mean_token_accuracy": 0.4570723704993725,
+      "step": 30
+    },
+    {
+      "epoch": 0.019779598756710936,
+      "grad_norm": 111.49407958984375,
+      "learning_rate": 5.666666666666667e-06,
+      "loss": 18.1505,
+      "mean_token_accuracy": 0.46947305351495744,
+      "step": 35
+    },
+    {
+      "epoch": 0.022605255721955354,
+      "grad_norm": 94.02478790283203,
+      "learning_rate": 5.999955686683124e-06,
+      "loss": 16.5811,
+      "mean_token_accuracy": 0.4923714891076088,
+      "step": 40
+    },
+    {
+      "epoch": 0.025430912687199773,
+      "grad_norm": 93.49138641357422,
+      "learning_rate": 5.999684887820798e-06,
+      "loss": 14.6779,
+      "mean_token_accuracy": 0.4900531888008118,
+      "step": 45
+    },
+    {
+      "epoch": 0.028256569652444195,
+      "grad_norm": 89.19295501708984,
+      "learning_rate": 5.9991679308007015e-06,
+      "loss": 15.0693,
+      "mean_token_accuracy": 0.48212875574827196,
+      "step": 50
+    },
+    {
+      "epoch": 0.031082226617688613,
+      "grad_norm": 117.02027130126953,
+      "learning_rate": 5.998404858045021e-06,
+      "loss": 14.6772,
+      "mean_token_accuracy": 0.4899917796254158,
+      "step": 55
+    },
+    {
+      "epoch": 0.033907883582933035,
+      "grad_norm": 72.73108673095703,
+      "learning_rate": 5.997395732172529e-06,
+      "loss": 13.4677,
+      "mean_token_accuracy": 0.4900201290845871,
+      "step": 60
+    },
+    {
+      "epoch": 0.03673354054817745,
+      "grad_norm": 77.72334289550781,
+      "learning_rate": 5.996140635993444e-06,
+      "loss": 13.2612,
+      "mean_token_accuracy": 0.5328952759504318,
+      "step": 65
+    },
+    {
+      "epoch": 0.03955919751342187,
+      "grad_norm": 80.2801284790039,
+      "learning_rate": 5.994639672502639e-06,
+      "loss": 11.504,
+      "mean_token_accuracy": 0.559516441822052,
+      "step": 70
+    },
+    {
+      "epoch": 0.04238485447866629,
+      "grad_norm": 61.040287017822266,
+      "learning_rate": 5.992892964871187e-06,
+      "loss": 11.0794,
+      "mean_token_accuracy": 0.5566341817378998,
+      "step": 75
+    },
+    {
+      "epoch": 0.04521051144391071,
+      "grad_norm": 61.21868896484375,
+      "learning_rate": 5.990900656436255e-06,
+      "loss": 11.9816,
+      "mean_token_accuracy": 0.5282905742526054,
+      "step": 80
+    },
+    {
+      "epoch": 0.04803616840915513,
+      "grad_norm": 114.57307434082031,
+      "learning_rate": 5.988662910689342e-06,
+      "loss": 10.3066,
+      "mean_token_accuracy": 0.5789915665984153,
+      "step": 85
+    },
+    {
+      "epoch": 0.050861825374399545,
+      "grad_norm": 76.79177856445312,
+      "learning_rate": 5.986179911262859e-06,
+      "loss": 10.7346,
+      "mean_token_accuracy": 0.5474225521087647,
+      "step": 90
+    },
+    {
+      "epoch": 0.05368748233964397,
+      "grad_norm": 50.477203369140625,
+      "learning_rate": 5.983451861915061e-06,
+      "loss": 11.5344,
+      "mean_token_accuracy": 0.5186601117253303,
+      "step": 95
+    },
+    {
+      "epoch": 0.05651313930488839,
+      "grad_norm": 65.024169921875,
+      "learning_rate": 5.980478986513332e-06,
+      "loss": 10.1865,
+      "mean_token_accuracy": 0.5476699441671371,
+      "step": 100
+    },
+    {
+      "epoch": 0.059338796270132804,
+      "grad_norm": 78.97113037109375,
+      "learning_rate": 5.977261529015807e-06,
+      "loss": 10.5502,
+      "mean_token_accuracy": 0.5594380274415016,
+      "step": 105
+    },
+    {
+      "epoch": 0.062164453235377226,
+      "grad_norm": 63.45710372924805,
+      "learning_rate": 5.9737997534513565e-06,
+      "loss": 10.1732,
+      "mean_token_accuracy": 0.5498600453138351,
+      "step": 110
+    },
+    {
+      "epoch": 0.06499011020062165,
+      "grad_norm": 43.65032958984375,
+      "learning_rate": 5.970093943897915e-06,
+      "loss": 9.483,
+      "mean_token_accuracy": 0.5819845095276832,
+      "step": 115
+    },
+    {
+      "epoch": 0.06781576716586607,
+      "grad_norm": 65.38373565673828,
+      "learning_rate": 5.966144404459178e-06,
+      "loss": 9.8998,
+      "mean_token_accuracy": 0.5803950399160385,
+      "step": 120
+    },
+    {
+      "epoch": 0.07064142413111048,
+      "grad_norm": 51.20427703857422,
+      "learning_rate": 5.96195145923964e-06,
+      "loss": 9.5007,
+      "mean_token_accuracy": 0.5401258394122124,
+      "step": 125
+    },
+    {
+      "epoch": 0.0734670810963549,
+      "grad_norm": 43.631324768066406,
+      "learning_rate": 5.957515452317996e-06,
+      "loss": 9.3663,
+      "mean_token_accuracy": 0.5585527911782264,
+      "step": 130
+    },
+    {
+      "epoch": 0.07629273806159932,
+      "grad_norm": 49.34850311279297,
+      "learning_rate": 5.952836747718916e-06,
+      "loss": 10.0569,
+      "mean_token_accuracy": 0.5572537362575531,
+      "step": 135
+    },
+    {
+      "epoch": 0.07911839502684374,
+      "grad_norm": 56.23272705078125,
+      "learning_rate": 5.947915729383162e-06,
+      "loss": 9.1624,
+      "mean_token_accuracy": 0.6116252914071083,
+      "step": 140
+    },
+    {
+      "epoch": 0.08194405199208817,
+      "grad_norm": 54.321495056152344,
+      "learning_rate": 5.942752801136086e-06,
+      "loss": 9.0426,
+      "mean_token_accuracy": 0.5830309092998505,
+      "step": 145
+    },
+    {
+      "epoch": 0.08476970895733257,
+      "grad_norm": 49.35163116455078,
+      "learning_rate": 5.937348386654492e-06,
+      "loss": 8.7897,
+      "mean_token_accuracy": 0.5833149090409279,
+      "step": 150
+    },
+    {
+      "epoch": 0.087595365922577,
+      "grad_norm": 41.16096878051758,
+      "learning_rate": 5.9317029294318685e-06,
+      "loss": 9.2698,
+      "mean_token_accuracy": 0.5732270866632462,
+      "step": 155
+    },
+    {
+      "epoch": 0.09042102288782142,
+      "grad_norm": 56.901546478271484,
+      "learning_rate": 5.925816892741992e-06,
+      "loss": 8.8971,
+      "mean_token_accuracy": 0.5911598846316337,
+      "step": 160
+    },
+    {
+      "epoch": 0.09324667985306584,
+      "grad_norm": 37.740020751953125,
+      "learning_rate": 5.919690759600914e-06,
+      "loss": 9.3825,
+      "mean_token_accuracy": 0.5646735802292824,
+      "step": 165
+    },
+    {
+      "epoch": 0.09607233681831026,
+      "grad_norm": 43.82129669189453,
+      "learning_rate": 5.913325032727323e-06,
+      "loss": 8.921,
+      "mean_token_accuracy": 0.5748174145817757,
+      "step": 170
+    },
+    {
+      "epoch": 0.09889799378355468,
+      "grad_norm": 43.662750244140625,
+      "learning_rate": 5.906720234501286e-06,
+      "loss": 8.329,
+      "mean_token_accuracy": 0.5832746580243111,
+      "step": 175
+    },
+    {
+      "epoch": 0.10172365074879909,
+      "grad_norm": 63.78599548339844,
+      "learning_rate": 5.899876906921388e-06,
+      "loss": 9.403,
+      "mean_token_accuracy": 0.5746660903096199,
+      "step": 180
+    },
+    {
+      "epoch": 0.10454930771404351,
+      "grad_norm": 38.50173568725586,
+      "learning_rate": 5.892795611560252e-06,
+      "loss": 7.9569,
+      "mean_token_accuracy": 0.6175401106476783,
+      "step": 185
+    },
+    {
+      "epoch": 0.10737496467928793,
+      "grad_norm": 46.76047134399414,
+      "learning_rate": 5.885476929518457e-06,
+      "loss": 8.8664,
+      "mean_token_accuracy": 0.5698649421334266,
+      "step": 190
+    },
+    {
+      "epoch": 0.11020062164453236,
+      "grad_norm": 34.551719665527344,
+      "learning_rate": 5.877921461376848e-06,
+      "loss": 8.9507,
+      "mean_token_accuracy": 0.5774942457675933,
+      "step": 195
+    },
+    {
+      "epoch": 0.11302627860977678,
+      "grad_norm": 46.14909362792969,
+      "learning_rate": 5.8701298271472565e-06,
+      "loss": 8.3937,
+      "mean_token_accuracy": 0.5869078159332275,
+      "step": 200
+    },
+    {
+      "epoch": 0.11585193557502119,
+      "grad_norm": 38.04121017456055,
+      "learning_rate": 5.862102666221617e-06,
+      "loss": 9.1566,
+      "mean_token_accuracy": 0.5589849069714546,
+      "step": 205
+    },
+    {
+      "epoch": 0.11867759254026561,
+      "grad_norm": 47.98865509033203,
+      "learning_rate": 5.853840637319504e-06,
+      "loss": 8.3272,
+      "mean_token_accuracy": 0.613035187125206,
+      "step": 210
+    },
+    {
+      "epoch": 0.12150324950551003,
+      "grad_norm": 52.02131271362305,
+      "learning_rate": 5.845344418434068e-06,
+      "loss": 9.2413,
+      "mean_token_accuracy": 0.5741102159023285,
+      "step": 215
+    },
+    {
+      "epoch": 0.12432890647075445,
+      "grad_norm": 46.88343048095703,
+      "learning_rate": 5.8366147067764056e-06,
+      "loss": 8.468,
+      "mean_token_accuracy": 0.5816206842660904,
+      "step": 220
+    },
+    {
+      "epoch": 0.12715456343599887,
+      "grad_norm": 43.369300842285156,
+      "learning_rate": 5.8276522187183435e-06,
+      "loss": 7.4452,
+      "mean_token_accuracy": 0.6464217156171799,
+      "step": 225
+    },
+    {
+      "epoch": 0.1299802204012433,
+      "grad_norm": 46.008766174316406,
+      "learning_rate": 5.818457689733649e-06,
+      "loss": 8.2276,
+      "mean_token_accuracy": 0.6063334688544273,
+      "step": 230
+    },
+    {
+      "epoch": 0.13280587736648772,
+      "grad_norm": 38.97382736206055,
+      "learning_rate": 5.809031874337681e-06,
+      "loss": 8.029,
+      "mean_token_accuracy": 0.6226910144090653,
+      "step": 235
+    },
+    {
+      "epoch": 0.13563153433173214,
+      "grad_norm": 44.3059196472168,
+      "learning_rate": 5.7993755460254685e-06,
+      "loss": 8.4051,
+      "mean_token_accuracy": 0.5975374907255173,
+      "step": 240
+    },
+    {
+      "epoch": 0.13845719129697653,
+      "grad_norm": 56.00782012939453,
+      "learning_rate": 5.789489497208243e-06,
+      "loss": 8.6075,
+      "mean_token_accuracy": 0.5798447385430336,
+      "step": 245
+    },
+    {
+      "epoch": 0.14128284826222096,
+      "grad_norm": 39.610755920410156,
+      "learning_rate": 5.779374539148403e-06,
+      "loss": 7.9846,
+      "mean_token_accuracy": 0.593911099433899,
+      "step": 250
+    },
+    {
+      "epoch": 0.14410850522746538,
+      "grad_norm": 40.99591827392578,
+      "learning_rate": 5.769031501892949e-06,
+      "loss": 8.3259,
+      "mean_token_accuracy": 0.5966995969414711,
+      "step": 255
+    },
+    {
+      "epoch": 0.1469341621927098,
+      "grad_norm": 37.0196533203125,
+      "learning_rate": 5.7584612342053655e-06,
+      "loss": 7.7289,
+      "mean_token_accuracy": 0.6313483536243438,
+      "step": 260
+    },
+    {
+      "epoch": 0.14975981915795422,
+      "grad_norm": 36.436134338378906,
+      "learning_rate": 5.7476646034959705e-06,
+      "loss": 9.042,
+      "mean_token_accuracy": 0.5726025938987732,
+      "step": 265
+    },
+    {
+      "epoch": 0.15258547612319864,
+      "grad_norm": 49.964351654052734,
+      "learning_rate": 5.736642495750733e-06,
+      "loss": 7.8111,
+      "mean_token_accuracy": 0.6032327204942703,
+      "step": 270
+    },
+    {
+      "epoch": 0.15541113308844307,
+      "grad_norm": 37.209232330322266,
+      "learning_rate": 5.725395815458571e-06,
+      "loss": 6.2546,
+      "mean_token_accuracy": 0.6550982385873795,
+      "step": 275
+    },
+    {
+      "epoch": 0.1582367900536875,
+      "grad_norm": 39.0145149230957,
+      "learning_rate": 5.713925485537126e-06,
+      "loss": 8.2466,
+      "mean_token_accuracy": 0.5892508149147033,
+      "step": 280
+    },
+    {
+      "epoch": 0.1610624470189319,
+      "grad_norm": 46.74445724487305,
+      "learning_rate": 5.702232447257029e-06,
+      "loss": 8.1135,
+      "mean_token_accuracy": 0.6003284469246865,
+      "step": 285
+    },
+    {
+      "epoch": 0.16388810398417633,
+      "grad_norm": 61.96944046020508,
+      "learning_rate": 5.6903176601646535e-06,
+      "loss": 8.0814,
+      "mean_token_accuracy": 0.6058224648237228,
+      "step": 290
+    },
+    {
+      "epoch": 0.16671376094942075,
+      "grad_norm": 41.85062026977539,
+      "learning_rate": 5.6781821020033794e-06,
+      "loss": 7.7756,
+      "mean_token_accuracy": 0.6040422543883324,
+      "step": 295
+    },
+    {
+      "epoch": 0.16953941791466515,
+      "grad_norm": 37.07870864868164,
+      "learning_rate": 5.665826768633358e-06,
+      "loss": 7.4973,
+      "mean_token_accuracy": 0.6139729157090187,
+      "step": 300
+    },
+    {
+      "epoch": 0.16953941791466515,
+      "eval_loss": 1.9660394191741943,
+      "eval_mean_token_accuracy": 0.6081940480295172,
+      "eval_runtime": 60.361,
+      "eval_samples_per_second": 26.06,
+      "eval_steps_per_second": 3.264,
+      "step": 300
+    },
+    {
+      "epoch": 0.17236507487990957,
+      "grad_norm": 36.64670181274414,
+      "learning_rate": 5.6532526739497834e-06,
+      "loss": 7.6396,
+      "mean_token_accuracy": 0.6107118725776672,
+      "step": 305
+    },
+    {
+      "epoch": 0.175190731845154,
+      "grad_norm": 54.716243743896484,
+      "learning_rate": 5.640460849799702e-06,
+      "loss": 7.2263,
+      "mean_token_accuracy": 0.6144478976726532,
+      "step": 310
+    },
+    {
+      "epoch": 0.1780163888103984,
+      "grad_norm": 55.097808837890625,
+      "learning_rate": 5.627452345897328e-06,
+      "loss": 7.0887,
+      "mean_token_accuracy": 0.6283742040395737,
+      "step": 315
+    },
+    {
+      "epoch": 0.18084204577564283,
+      "grad_norm": 61.68784713745117,
+      "learning_rate": 5.614228229737906e-06,
+      "loss": 7.8888,
+      "mean_token_accuracy": 0.6202467530965805,
+      "step": 320
+    },
+    {
+      "epoch": 0.18366770274088726,
+      "grad_norm": 50.16268539428711,
+      "learning_rate": 5.600789586510113e-06,
+      "loss": 8.1697,
+      "mean_token_accuracy": 0.6052482485771179,
+      "step": 325
+    },
+    {
+      "epoch": 0.18649335970613168,
+      "grad_norm": 34.98442840576172,
+      "learning_rate": 5.587137519007004e-06,
+      "loss": 7.6766,
+      "mean_token_accuracy": 0.610385374724865,
+      "step": 330
+    },
+    {
+      "epoch": 0.1893190166713761,
+      "grad_norm": 54.69295120239258,
+      "learning_rate": 5.5732731475355135e-06,
+      "loss": 7.4116,
+      "mean_token_accuracy": 0.6147442162036896,
+      "step": 335
+    },
+    {
+      "epoch": 0.19214467363662052,
+      "grad_norm": 36.03273391723633,
+      "learning_rate": 5.559197609824526e-06,
+      "loss": 7.7704,
+      "mean_token_accuracy": 0.6110788837075234,
+      "step": 340
+    },
+    {
+      "epoch": 0.19497033060186494,
+      "grad_norm": 45.89215087890625,
+      "learning_rate": 5.544912060931511e-06,
+      "loss": 6.0621,
+      "mean_token_accuracy": 0.6817868202924728,
+      "step": 345
+    },
+    {
+      "epoch": 0.19779598756710937,
+      "grad_norm": 43.32875442504883,
+      "learning_rate": 5.530417673147736e-06,
+      "loss": 7.5385,
+      "mean_token_accuracy": 0.6150149628520012,
+      "step": 350
+    },
+    {
+      "epoch": 0.20062164453235376,
+      "grad_norm": 35.37779998779297,
+      "learning_rate": 5.515715635902064e-06,
+      "loss": 6.6067,
+      "mean_token_accuracy": 0.6687664300203323,
+      "step": 355
+    },
+    {
+      "epoch": 0.20344730149759818,
+      "grad_norm": 44.46392822265625,
+      "learning_rate": 5.500807155663359e-06,
+      "loss": 6.2822,
+      "mean_token_accuracy": 0.6637924790382386,
+      "step": 360
+    },
+    {
+      "epoch": 0.2062729584628426,
+      "grad_norm": 36.08877182006836,
+      "learning_rate": 5.485693455841464e-06,
+      "loss": 6.894,
+      "mean_token_accuracy": 0.6358136102557183,
+      "step": 365
+    },
+    {
+      "epoch": 0.20909861542808703,
+      "grad_norm": 34.14577865600586,
+      "learning_rate": 5.470375776686822e-06,
+      "loss": 7.4445,
+      "mean_token_accuracy": 0.6168029010295868,
+      "step": 370
+    },
+    {
+      "epoch": 0.21192427239333145,
+      "grad_norm": 40.84408950805664,
+      "learning_rate": 5.454855375188691e-06,
+      "loss": 7.0881,
+      "mean_token_accuracy": 0.6331988245248794,
+      "step": 375
+    },
+    {
+      "epoch": 0.21474992935857587,
+      "grad_norm": 47.68820571899414,
+      "learning_rate": 5.439133524971994e-06,
+      "loss": 7.1198,
+      "mean_token_accuracy": 0.6500597685575485,
+      "step": 380
+    },
+    {
+      "epoch": 0.2175755863238203,
+      "grad_norm": 62.971771240234375,
+      "learning_rate": 5.4232115161928125e-06,
+      "loss": 7.3537,
+      "mean_token_accuracy": 0.6475826740264893,
+      "step": 385
+    },
+    {
+      "epoch": 0.2204012432890647,
+      "grad_norm": 47.17545700073242,
+      "learning_rate": 5.407090655432498e-06,
+      "loss": 6.484,
+      "mean_token_accuracy": 0.6483543753623963,
+      "step": 390
+    },
+    {
+      "epoch": 0.22322690025430914,
+      "grad_norm": 47.76310348510742,
+      "learning_rate": 5.390772265590469e-06,
+      "loss": 7.1721,
+      "mean_token_accuracy": 0.6379205271601677,
+      "step": 395
+    },
+    {
+      "epoch": 0.22605255721955356,
+      "grad_norm": 41.001304626464844,
+      "learning_rate": 5.374257685775642e-06,
+      "loss": 7.3882,
+      "mean_token_accuracy": 0.6161196917295456,
+      "step": 400
+    },
+    {
+      "epoch": 0.22887821418479798,
+      "grad_norm": 41.1621208190918,
+      "learning_rate": 5.357548271196545e-06,
+      "loss": 6.6539,
+      "mean_token_accuracy": 0.6448143661022187,
+      "step": 405
+    },
+    {
+      "epoch": 0.23170387115004237,
+      "grad_norm": 56.77714920043945,
+      "learning_rate": 5.34064539305011e-06,
+      "loss": 6.7501,
+      "mean_token_accuracy": 0.6442455291748047,
+      "step": 410
+    },
+    {
+      "epoch": 0.2345295281152868,
+      "grad_norm": 34.29147720336914,
+      "learning_rate": 5.323550438409145e-06,
+      "loss": 7.1571,
+      "mean_token_accuracy": 0.6502243876457214,
+      "step": 415
+    },
+    {
+      "epoch": 0.23735518508053122,
+      "grad_norm": 38.84526824951172,
+      "learning_rate": 5.306264810108515e-06,
+      "loss": 7.4697,
+      "mean_token_accuracy": 0.6136257261037826,
+      "step": 420
+    },
+    {
+      "epoch": 0.24018084204577564,
+      "grad_norm": 39.21842575073242,
+      "learning_rate": 5.288789926630018e-06,
+      "loss": 5.6676,
+      "mean_token_accuracy": 0.6803564548492431,
+      "step": 425
+    },
+    {
+      "epoch": 0.24300649901102006,
+      "grad_norm": 43.55912780761719,
+      "learning_rate": 5.27112722198599e-06,
+      "loss": 7.6674,
+      "mean_token_accuracy": 0.6143711119890213,
+      "step": 430
+    },
+    {
+      "epoch": 0.24583215597626448,
+      "grad_norm": 47.082237243652344,
+      "learning_rate": 5.253278145601618e-06,
+      "loss": 6.9372,
+      "mean_token_accuracy": 0.6543397754430771,
+      "step": 435
+    },
+    {
+      "epoch": 0.2486578129415089,
+      "grad_norm": 71.78733825683594,
+      "learning_rate": 5.235244162196007e-06,
+      "loss": 6.3831,
+      "mean_token_accuracy": 0.6731083989143372,
+      "step": 440
+    },
+    {
+      "epoch": 0.2514834699067533,
+      "grad_norm": 41.5792121887207,
+      "learning_rate": 5.217026751661978e-06,
+      "loss": 5.9193,
+      "mean_token_accuracy": 0.6984533488750457,
+      "step": 445
+    },
+    {
+      "epoch": 0.25430912687199775,
+      "grad_norm": 32.45619201660156,
+      "learning_rate": 5.198627408944628e-06,
+      "loss": 6.1931,
+      "mean_token_accuracy": 0.6726161792874337,
+      "step": 450
+    },
+    {
+      "epoch": 0.25713478383724214,
+      "grad_norm": 54.69667434692383,
+      "learning_rate": 5.180047643918653e-06,
+      "loss": 5.6802,
+      "mean_token_accuracy": 0.700816172361374,
+      "step": 455
+    },
+    {
+      "epoch": 0.2599604408024866,
+      "grad_norm": 52.139469146728516,
+      "learning_rate": 5.161288981264445e-06,
+      "loss": 7.4401,
+      "mean_token_accuracy": 0.6105516791343689,
+      "step": 460
+    },
+    {
+      "epoch": 0.262786097767731,
+      "grad_norm": 38.770294189453125,
+      "learning_rate": 5.142352960342976e-06,
+      "loss": 6.3299,
+      "mean_token_accuracy": 0.6778733760118485,
+      "step": 465
+    },
+    {
+      "epoch": 0.26561175473297544,
+      "grad_norm": 44.44423294067383,
+      "learning_rate": 5.123241135069471e-06,
+      "loss": 6.3576,
+      "mean_token_accuracy": 0.6793156564235687,
+      "step": 470
+    },
+    {
+      "epoch": 0.26843741169821983,
+      "grad_norm": 52.27141189575195,
+      "learning_rate": 5.103955073785902e-06,
+      "loss": 5.4571,
+      "mean_token_accuracy": 0.7010635808110237,
+      "step": 475
+    },
+    {
+      "epoch": 0.2712630686634643,
+      "grad_norm": 41.901485443115234,
+      "learning_rate": 5.084496359132275e-06,
+      "loss": 6.2462,
+      "mean_token_accuracy": 0.6626246273517609,
+      "step": 480
+    },
+    {
+      "epoch": 0.2740887256287087,
+      "grad_norm": 39.49611282348633,
+      "learning_rate": 5.064866587916764e-06,
+      "loss": 6.3324,
+      "mean_token_accuracy": 0.6691112801432609,
+      "step": 485
+    },
+    {
+      "epoch": 0.27691438259395307,
+      "grad_norm": 41.7744140625,
+      "learning_rate": 5.045067370984676e-06,
+      "loss": 7.2696,
+      "mean_token_accuracy": 0.6365453451871872,
+      "step": 490
+    },
+    {
+      "epoch": 0.2797400395591975,
+      "grad_norm": 49.72770690917969,
+      "learning_rate": 5.02510033308626e-06,
+      "loss": 6.5657,
+      "mean_token_accuracy": 0.6508561789989471,
+      "step": 495
+    },
+    {
+      "epoch": 0.2825656965244419,
+      "grad_norm": 32.61491394042969,
+      "learning_rate": 5.004967112743376e-06,
+      "loss": 6.6128,
+      "mean_token_accuracy": 0.6579498335719108,
+      "step": 500
+    },
+    {
+      "epoch": 0.28539135348968636,
+      "grad_norm": 49.389400482177734,
+      "learning_rate": 4.984669362115039e-06,
+      "loss": 6.7253,
+      "mean_token_accuracy": 0.6457798436284066,
+      "step": 505
+    },
+    {
+      "epoch": 0.28821701045493076,
+      "grad_norm": 51.6247673034668,
+      "learning_rate": 4.964208746861841e-06,
+      "loss": 6.2031,
+      "mean_token_accuracy": 0.6751710534095764,
+      "step": 510
+    },
+    {
+      "epoch": 0.2910426674201752,
+      "grad_norm": 28.600732803344727,
+      "learning_rate": 4.943586946009259e-06,
+      "loss": 6.6904,
+      "mean_token_accuracy": 0.6619319871068001,
+      "step": 515
+    },
+    {
+      "epoch": 0.2938683243854196,
+      "grad_norm": 43.22124481201172,
+      "learning_rate": 4.92280565180988e-06,
+      "loss": 6.7604,
+      "mean_token_accuracy": 0.6478939458727837,
+      "step": 520
+    },
+    {
+      "epoch": 0.29669398135066405,
+      "grad_norm": 41.86116027832031,
+      "learning_rate": 4.901866569604527e-06,
+      "loss": 6.0308,
+      "mean_token_accuracy": 0.6734458118677139,
+      "step": 525
+    },
+    {
+      "epoch": 0.29951963831590844,
+      "grad_norm": 41.02956771850586,
+      "learning_rate": 4.8807714176823205e-06,
+      "loss": 7.0681,
+      "mean_token_accuracy": 0.6355025738477706,
+      "step": 530
+    },
+    {
+      "epoch": 0.3023452952811529,
+      "grad_norm": 44.11521530151367,
+      "learning_rate": 4.859521927139664e-06,
+      "loss": 6.1855,
+      "mean_token_accuracy": 0.6703523576259613,
+      "step": 535
+    },
+    {
+      "epoch": 0.3051709522463973,
+      "grad_norm": 32.89723587036133,
+      "learning_rate": 4.838119841738205e-06,
+      "loss": 6.0888,
+      "mean_token_accuracy": 0.6834497556090355,
+      "step": 540
+    },
+    {
+      "epoch": 0.3079966092116417,
+      "grad_norm": 32.18568420410156,
+      "learning_rate": 4.816566917761719e-06,
+      "loss": 6.9014,
+      "mean_token_accuracy": 0.6485872358083725,
+      "step": 545
+    },
+    {
+      "epoch": 0.31082226617688613,
+      "grad_norm": 46.209686279296875,
+      "learning_rate": 4.794864923872006e-06,
+      "loss": 6.1183,
+      "mean_token_accuracy": 0.6952649801969528,
+      "step": 550
+    },
+    {
+      "epoch": 0.3136479231421305,
+      "grad_norm": 42.59083938598633,
+      "learning_rate": 4.773015640963735e-06,
+      "loss": 6.1898,
+      "mean_token_accuracy": 0.6966498523950577,
+      "step": 555
+    },
+    {
+      "epoch": 0.316473580107375,
+      "grad_norm": 34.99408721923828,
+      "learning_rate": 4.751020862018315e-06,
+      "loss": 6.4017,
+      "mean_token_accuracy": 0.6635166749358177,
+      "step": 560
+    },
+    {
+      "epoch": 0.31929923707261937,
+      "grad_norm": 44.781253814697266,
+      "learning_rate": 4.728882391956751e-06,
+      "loss": 6.294,
+      "mean_token_accuracy": 0.6908501267433167,
+      "step": 565
+    },
+    {
+      "epoch": 0.3221248940378638,
+      "grad_norm": 38.54107666015625,
+      "learning_rate": 4.706602047491535e-06,
+      "loss": 6.3961,
+      "mean_token_accuracy": 0.6642886430025101,
+      "step": 570
+    },
+    {
+      "epoch": 0.3249505510031082,
+      "grad_norm": 39.30413055419922,
+      "learning_rate": 4.68418165697756e-06,
+      "loss": 7.0987,
+      "mean_token_accuracy": 0.6421632379293442,
+      "step": 575
+    },
+    {
+      "epoch": 0.32777620796835266,
+      "grad_norm": 32.5236930847168,
+      "learning_rate": 4.66162306026209e-06,
+      "loss": 6.3601,
+      "mean_token_accuracy": 0.6777586549520492,
+      "step": 580
+    },
+    {
+      "epoch": 0.33060186493359706,
+      "grad_norm": 44.02008056640625,
+      "learning_rate": 4.638928108533771e-06,
+      "loss": 6.7745,
+      "mean_token_accuracy": 0.6339758485555649,
+      "step": 585
+    },
+    {
+      "epoch": 0.3334275218988415,
+      "grad_norm": 42.38660430908203,
+      "learning_rate": 4.616098664170726e-06,
+      "loss": 6.7977,
+      "mean_token_accuracy": 0.6368318185210228,
+      "step": 590
+    },
+    {
+      "epoch": 0.3362531788640859,
+      "grad_norm": 56.86142349243164,
+      "learning_rate": 4.5931366005877205e-06,
+      "loss": 6.5369,
+      "mean_token_accuracy": 0.6513374149799347,
+      "step": 595
+    },
+    {
+      "epoch": 0.3390788358293303,
+      "grad_norm": 46.34036636352539,
+      "learning_rate": 4.570043802082435e-06,
+      "loss": 6.975,
+      "mean_token_accuracy": 0.6324821501970291,
+      "step": 600
+    },
+    {
+      "epoch": 0.3390788358293303,
+      "eval_loss": 1.6515789031982422,
+      "eval_mean_token_accuracy": 0.6573993170321896,
+      "eval_runtime": 60.1378,
+      "eval_samples_per_second": 26.157,
+      "eval_steps_per_second": 3.276,
+      "step": 600
+    },
+    {
+      "epoch": 0.34190449279457474,
+      "grad_norm": 34.469337463378906,
+      "learning_rate": 4.546822163680829e-06,
+      "loss": 5.6408,
+      "mean_token_accuracy": 0.6926419764757157,
+      "step": 605
+    },
+    {
+      "epoch": 0.34473014975981914,
+      "grad_norm": 54.577877044677734,
+      "learning_rate": 4.523473590981639e-06,
+      "loss": 5.1717,
+      "mean_token_accuracy": 0.708769902586937,
+      "step": 610
+    },
+    {
+      "epoch": 0.3475558067250636,
+      "grad_norm": 42.55693817138672,
+      "learning_rate": 4.5e-06,
+      "loss": 6.131,
+      "mean_token_accuracy": 0.6689537853002548,
+      "step": 615
+    },
+    {
+      "epoch": 0.350381463690308,
+      "grad_norm": 32.82284927368164,
+      "learning_rate": 4.476403317010212e-06,
+      "loss": 6.4724,
+      "mean_token_accuracy": 0.6572571873664856,
+      "step": 620
+    },
+    {
+      "epoch": 0.35320712065555243,
+      "grad_norm": 40.628170013427734,
+      "learning_rate": 4.452685478387672e-06,
+      "loss": 7.2712,
+      "mean_token_accuracy": 0.6308314383029938,
+      "step": 625
+    },
+    {
+      "epoch": 0.3560327776207968,
+      "grad_norm": 32.64014434814453,
+      "learning_rate": 4.4288484304499706e-06,
+      "loss": 5.8603,
+      "mean_token_accuracy": 0.6960221052169799,
+      "step": 630
+    },
+    {
+      "epoch": 0.3588584345860413,
+      "grad_norm": 45.46329116821289,
+      "learning_rate": 4.404894129297172e-06,
+      "loss": 6.1867,
+      "mean_token_accuracy": 0.6657388493418693,
+      "step": 635
+    },
+    {
+      "epoch": 0.36168409155128567,
+      "grad_norm": 105.43537139892578,
+      "learning_rate": 4.380824540651301e-06,
+      "loss": 6.4694,
+      "mean_token_accuracy": 0.6702811747789383,
+      "step": 640
+    },
+    {
+      "epoch": 0.3645097485165301,
+      "grad_norm": 41.170921325683594,
+      "learning_rate": 4.356641639695022e-06,
+      "loss": 6.4786,
+      "mean_token_accuracy": 0.6519061028957367,
+      "step": 645
+    },
+    {
+      "epoch": 0.3673354054817745,
+      "grad_norm": 33.53129959106445,
+      "learning_rate": 4.332347410909566e-06,
+      "loss": 6.4479,
+      "mean_token_accuracy": 0.6696308821439743,
+      "step": 650
+    },
+    {
+      "epoch": 0.3701610624470189,
+      "grad_norm": 44.768699645996094,
+      "learning_rate": 4.307943847911868e-06,
+      "loss": 6.6492,
+      "mean_token_accuracy": 0.6501506567001343,
+      "step": 655
+    },
+    {
+      "epoch": 0.37298671941226336,
+      "grad_norm": 38.888816833496094,
+      "learning_rate": 4.283432953290981e-06,
+      "loss": 6.7759,
+      "mean_token_accuracy": 0.6582424193620682,
+      "step": 660
+    },
+    {
+      "epoch": 0.37581237637750775,
+      "grad_norm": 42.18849563598633,
+      "learning_rate": 4.258816738443731e-06,
+      "loss": 6.0352,
+      "mean_token_accuracy": 0.672022745013237,
+      "step": 665
+    },
+    {
+      "epoch": 0.3786380333427522,
+      "grad_norm": 32.39656066894531,
+      "learning_rate": 4.234097223409664e-06,
+      "loss": 6.2633,
+      "mean_token_accuracy": 0.6928743287920952,
+      "step": 670
+    },
+    {
+      "epoch": 0.3814636903079966,
+      "grad_norm": 38.409385681152344,
+      "learning_rate": 4.209276436705276e-06,
+      "loss": 6.2866,
+      "mean_token_accuracy": 0.6808415204286575,
+      "step": 675
+    },
+    {
+      "epoch": 0.38428934727324104,
+      "grad_norm": 41.57419204711914,
+      "learning_rate": 4.184356415157556e-06,
+      "loss": 5.9778,
+      "mean_token_accuracy": 0.7001727074384689,
+      "step": 680
+    },
+    {
+      "epoch": 0.38711500423848544,
+      "grad_norm": 34.73065185546875,
+      "learning_rate": 4.159339203736831e-06,
+      "loss": 6.0301,
+      "mean_token_accuracy": 0.6711145430803299,
+      "step": 685
+    },
+    {
+      "epoch": 0.3899406612037299,
+      "grad_norm": 40.23607635498047,
+      "learning_rate": 4.134226855388963e-06,
+      "loss": 5.7109,
+      "mean_token_accuracy": 0.7057820171117782,
+      "step": 690
+    },
+    {
+      "epoch": 0.3927663181689743,
+      "grad_norm": 38.31148910522461,
+      "learning_rate": 4.10902143086688e-06,
+      "loss": 6.6394,
+      "mean_token_accuracy": 0.6580009430646896,
+      "step": 695
+    },
+    {
+      "epoch": 0.39559197513421873,
+      "grad_norm": 50.16755676269531,
+      "learning_rate": 4.08372499856146e-06,
+      "loss": 5.611,
+      "mean_token_accuracy": 0.7013431131839752,
+      "step": 700
+    },
+    {
+      "epoch": 0.3984176320994631,
+      "grad_norm": 30.385122299194336,
+      "learning_rate": 4.0583396343318025e-06,
+      "loss": 6.5846,
+      "mean_token_accuracy": 0.6525479450821876,
+      "step": 705
+    },
+    {
+      "epoch": 0.4012432890647075,
+      "grad_norm": 40.52418518066406,
+      "learning_rate": 4.032867421334884e-06,
+      "loss": 5.4611,
+      "mean_token_accuracy": 0.698312160372734,
+      "step": 710
+    },
+    {
+      "epoch": 0.40406894602995197,
+      "grad_norm": 39.72053146362305,
+      "learning_rate": 4.0073104498546036e-06,
+      "loss": 5.9016,
+      "mean_token_accuracy": 0.6850436985492706,
+      "step": 715
+    },
+    {
+      "epoch": 0.40689460299519636,
+      "grad_norm": 38.679527282714844,
+      "learning_rate": 3.981670817130255e-06,
+      "loss": 6.0392,
+      "mean_token_accuracy": 0.6699395298957824,
+      "step": 720
+    },
+    {
+      "epoch": 0.4097202599604408,
+      "grad_norm": 42.41149139404297,
+      "learning_rate": 3.955950627184426e-06,
+      "loss": 6.2423,
+      "mean_token_accuracy": 0.6726677268743515,
+      "step": 725
+    },
+    {
+      "epoch": 0.4125459169256852,
+      "grad_norm": 36.73404312133789,
+      "learning_rate": 3.930151990650336e-06,
+      "loss": 5.0402,
+      "mean_token_accuracy": 0.7204348385334015,
+      "step": 730
+    },
+    {
+      "epoch": 0.41537157389092966,
+      "grad_norm": 33.893760681152344,
+      "learning_rate": 3.904277024598638e-06,
+      "loss": 5.5147,
+      "mean_token_accuracy": 0.6979331076145172,
+      "step": 735
+    },
+    {
+      "epoch": 0.41819723085617405,
+      "grad_norm": 47.56764602661133,
+      "learning_rate": 3.878327852363686e-06,
+      "loss": 5.7995,
+      "mean_token_accuracy": 0.7078070282936096,
+      "step": 740
+    },
+    {
+      "epoch": 0.4210228878214185,
+      "grad_norm": 31.648059844970703,
+      "learning_rate": 3.852306603369294e-06,
+      "loss": 6.8761,
+      "mean_token_accuracy": 0.665014611184597,
+      "step": 745
+    },
+    {
+      "epoch": 0.4238485447866629,
+      "grad_norm": 38.39750289916992,
+      "learning_rate": 3.826215412953991e-06,
+      "loss": 6.0653,
+      "mean_token_accuracy": 0.6770342886447906,
+      "step": 750
+    },
+    {
+      "epoch": 0.42667420175190734,
+      "grad_norm": 30.88237190246582,
+      "learning_rate": 3.800056422195792e-06,
+      "loss": 6.535,
+      "mean_token_accuracy": 0.6590037375688553,
+      "step": 755
+    },
+    {
+      "epoch": 0.42949985871715174,
+      "grad_norm": 63.2603874206543,
+      "learning_rate": 3.773831777736499e-06,
+      "loss": 6.5161,
+      "mean_token_accuracy": 0.6474016666412353,
+      "step": 760
+    },
+    {
+      "epoch": 0.43232551568239613,
+      "grad_norm": 50.654457092285156,
+      "learning_rate": 3.747543631605547e-06,
+      "loss": 6.7369,
+      "mean_token_accuracy": 0.6452984467148781,
+      "step": 765
+    },
+    {
+      "epoch": 0.4351511726476406,
+      "grad_norm": 37.10031509399414,
+      "learning_rate": 3.721194141043398e-06,
+      "loss": 6.2939,
+      "mean_token_accuracy": 0.6634088665246963,
+      "step": 770
+    },
+    {
+      "epoch": 0.437976829612885,
+      "grad_norm": 32.4448356628418,
+      "learning_rate": 3.694785468324526e-06,
+      "loss": 5.3857,
+      "mean_token_accuracy": 0.7086734473705292,
+      "step": 775
+    },
+    {
+      "epoch": 0.4408024865781294,
+      "grad_norm": 37.90336990356445,
+      "learning_rate": 3.6683197805799684e-06,
+      "loss": 5.5692,
+      "mean_token_accuracy": 0.691333469748497,
+      "step": 780
+    },
+    {
+      "epoch": 0.4436281435433738,
+      "grad_norm": 33.28772735595703,
+      "learning_rate": 3.641799249619492e-06,
+      "loss": 5.7555,
+      "mean_token_accuracy": 0.6938249558210373,
+      "step": 785
+    },
+    {
+      "epoch": 0.44645380050861827,
+      "grad_norm": 40.561336517333984,
+      "learning_rate": 3.6152260517533743e-06,
+      "loss": 6.5292,
+      "mean_token_accuracy": 0.6575401365756989,
+      "step": 790
+    },
+    {
+      "epoch": 0.44927945747386266,
+      "grad_norm": 34.72788619995117,
+      "learning_rate": 3.588602367613805e-06,
+      "loss": 5.6275,
+      "mean_token_accuracy": 0.6937674105167388,
+      "step": 795
+    },
+    {
+      "epoch": 0.4521051144391071,
+      "grad_norm": 51.351802825927734,
+      "learning_rate": 3.56193038197595e-06,
+      "loss": 5.8965,
+      "mean_token_accuracy": 0.7013622283935547,
+      "step": 800
+    },
+    {
+      "epoch": 0.4549307714043515,
+      "grad_norm": 34.20261001586914,
+      "learning_rate": 3.5352122835786555e-06,
+      "loss": 6.2313,
+      "mean_token_accuracy": 0.6691349744796753,
+      "step": 805
+    },
+    {
+      "epoch": 0.45775642836959596,
+      "grad_norm": 32.29352951049805,
+      "learning_rate": 3.508450264944848e-06,
+      "loss": 6.0912,
+      "mean_token_accuracy": 0.6840269297361374,
+      "step": 810
+    },
+    {
+      "epoch": 0.46058208533484035,
+      "grad_norm": 39.749229431152344,
+      "learning_rate": 3.481646522201602e-06,
+      "loss": 5.9559,
+      "mean_token_accuracy": 0.6829979822039605,
+      "step": 815
+    },
+    {
+      "epoch": 0.46340774230008475,
+      "grad_norm": 39.798587799072266,
+      "learning_rate": 3.4548032548999336e-06,
+      "loss": 6.161,
+      "mean_token_accuracy": 0.6791020795702934,
+      "step": 820
+    },
+    {
+      "epoch": 0.4662333992653292,
+      "grad_norm": 51.893211364746094,
+      "learning_rate": 3.4279226658342925e-06,
+      "loss": 6.3016,
+      "mean_token_accuracy": 0.6657601609826088,
+      "step": 825
+    },
+    {
+      "epoch": 0.4690590562305736,
+      "grad_norm": 50.02108383178711,
+      "learning_rate": 3.4010069608618056e-06,
+      "loss": 6.0286,
+      "mean_token_accuracy": 0.6940437912940979,
+      "step": 830
+    },
+    {
+      "epoch": 0.47188471319581804,
+      "grad_norm": 55.37822723388672,
+      "learning_rate": 3.374058348721255e-06,
+      "loss": 6.2305,
+      "mean_token_accuracy": 0.6752733439207077,
+      "step": 835
+    },
+    {
+      "epoch": 0.47471037016106243,
+      "grad_norm": 39.274688720703125,
+      "learning_rate": 3.347079040851833e-06,
+      "loss": 6.4344,
+      "mean_token_accuracy": 0.6463314086198807,
+      "step": 840
+    },
+    {
+      "epoch": 0.4775360271263069,
+      "grad_norm": 33.772884368896484,
+      "learning_rate": 3.3200712512116598e-06,
+      "loss": 4.5399,
+      "mean_token_accuracy": 0.7319628089666367,
+      "step": 845
+    },
+    {
+      "epoch": 0.4803616840915513,
+      "grad_norm": 47.047767639160156,
+      "learning_rate": 3.293037196096113e-06,
+      "loss": 6.0456,
+      "mean_token_accuracy": 0.664868313074112,
+      "step": 850
+    },
+    {
+      "epoch": 0.4831873410567957,
+      "grad_norm": 41.05727767944336,
+      "learning_rate": 3.2659790939559453e-06,
+      "loss": 5.7682,
+      "mean_token_accuracy": 0.7045676440000535,
+      "step": 855
+    },
+    {
+      "epoch": 0.4860129980220401,
+      "grad_norm": 37.37389373779297,
+      "learning_rate": 3.238899165215245e-06,
+      "loss": 5.2326,
+      "mean_token_accuracy": 0.7269378632307053,
+      "step": 860
+    },
+    {
+      "epoch": 0.48883865498728457,
+      "grad_norm": 39.5576286315918,
+      "learning_rate": 3.211799632089216e-06,
+      "loss": 5.1324,
+      "mean_token_accuracy": 0.7152336061000824,
+      "step": 865
+    },
+    {
+      "epoch": 0.49166431195252897,
+      "grad_norm": 41.0853157043457,
+      "learning_rate": 3.1846827184018294e-06,
+      "loss": 5.7599,
+      "mean_token_accuracy": 0.6923278480768204,
+      "step": 870
+    },
+    {
+      "epoch": 0.49448996891777336,
+      "grad_norm": 51.03715896606445,
+      "learning_rate": 3.157550649403322e-06,
+      "loss": 4.9395,
+      "mean_token_accuracy": 0.7514464080333709,
+      "step": 875
+    },
+    {
+      "epoch": 0.4973156258830178,
+      "grad_norm": 37.161231994628906,
+      "learning_rate": 3.1304056515876024e-06,
+      "loss": 7.0247,
+      "mean_token_accuracy": 0.6437601447105408,
+      "step": 880
+    },
+    {
+      "epoch": 0.5001412828482622,
+      "grad_norm": 47.0338134765625,
+      "learning_rate": 3.1032499525095303e-06,
+      "loss": 5.647,
+      "mean_token_accuracy": 0.6982032418251037,
+      "step": 885
+    },
+    {
+      "epoch": 0.5029669398135066,
+      "grad_norm": 32.64208221435547,
+      "learning_rate": 3.076085780602128e-06,
+      "loss": 5.6704,
+      "mean_token_accuracy": 0.6939798533916474,
+      "step": 890
+    },
+    {
+      "epoch": 0.5057925967787511,
+      "grad_norm": 32.635005950927734,
+      "learning_rate": 3.048915364993708e-06,
+      "loss": 5.2166,
+      "mean_token_accuracy": 0.7231873899698258,
+      "step": 895
+    },
+    {
+      "epoch": 0.5086182537439955,
+      "grad_norm": 29.856887817382812,
+      "learning_rate": 3.0217409353249512e-06,
+      "loss": 5.9994,
+      "mean_token_accuracy": 0.6912487387657166,
+      "step": 900
+    },
+    {
+      "epoch": 0.5086182537439955,
+      "eval_loss": 1.5281765460968018,
+      "eval_mean_token_accuracy": 0.6797472610691477,
+      "eval_runtime": 60.4506,
+      "eval_samples_per_second": 26.021,
+      "eval_steps_per_second": 3.259,
+      "step": 900
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1770,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 300,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.657153711785286e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bd56f5e149cf0b150f90ab3dcb1fdb48f7680a084d366beb4c63c4d56318225
+size 5624