checkpoint step 1800

.gitattributes

@@ -48,3 +48,4 @@ checkpoint-1400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-1500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-1600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-1700/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1800/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-1800/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/qwen3-30b-a3b-base
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/qwen3-30b-a3b-base
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# 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 0.20.0

checkpoint-1800/adapter_config.json

@@ -0,0 +1,57 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3MoeForCausalLM",
+    "parent_library": "transformers.models.qwen3_moe.modeling_qwen3_moe",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/qwen3-30b-a3b-base",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.20.0",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "down_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "target_parameters": [
+    "mlp.experts.gate_up_proj",
+    "mlp.experts.down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": true,
+  "velora_config": null
+}

checkpoint-1800/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1d2ae9fa0797c5f6e9f3f1fd5ff53c9f12c200dc1a05cd82c60729edd18c74d
+size 5140199640

checkpoint-1800/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56c492f1b7e7aadb4be5765df5743236b8b8957887ba6b7cb017c429207f523d
+size 2612400547

checkpoint-1800/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d873a4f9239c98d6624b353e6bee56153a0bc656a3d9a559f175392e2d9f793b
+size 1465

checkpoint-1800/tokenizer.json

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

checkpoint-1800/tokenizer_config.json

@@ -0,0 +1,225 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": false,
+  "model_max_length": 32768,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    }
+  }
+}

checkpoint-1800/trainer_state.json

@@ -0,0 +1,1323 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6945533033485669,
+  "eval_steps": 150,
+  "global_step": 1800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.003858629463047594,
+      "grad_norm": 0.9612510204315186,
+      "learning_rate": 1.8e-05,
+      "loss": 1.0067429542541504,
+      "step": 10
+    },
+    {
+      "epoch": 0.007717258926095188,
+      "grad_norm": 0.6660895347595215,
+      "learning_rate": 3.8e-05,
+      "loss": 0.8466403007507324,
+      "step": 20
+    },
+    {
+      "epoch": 0.011575888389142782,
+      "grad_norm": 0.5681023001670837,
+      "learning_rate": 5.8e-05,
+      "loss": 0.7557645797729492,
+      "step": 30
+    },
+    {
+      "epoch": 0.015434517852190376,
+      "grad_norm": 0.7179134488105774,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 0.7409078121185303,
+      "step": 40
+    },
+    {
+      "epoch": 0.019293147315237968,
+      "grad_norm": 0.5565946102142334,
+      "learning_rate": 9.8e-05,
+      "loss": 0.7274651050567627,
+      "step": 50
+    },
+    {
+      "epoch": 0.023151776778285563,
+      "grad_norm": 0.5450749397277832,
+      "learning_rate": 0.000118,
+      "loss": 0.741389274597168,
+      "step": 60
+    },
+    {
+      "epoch": 0.027010406241333156,
+      "grad_norm": 0.4871410131454468,
+      "learning_rate": 0.000138,
+      "loss": 0.725303316116333,
+      "step": 70
+    },
+    {
+      "epoch": 0.03086903570438075,
+      "grad_norm": 0.5452415347099304,
+      "learning_rate": 0.00015800000000000002,
+      "loss": 0.724397611618042,
+      "step": 80
+    },
+    {
+      "epoch": 0.03472766516742835,
+      "grad_norm": 0.438076376914978,
+      "learning_rate": 0.00017800000000000002,
+      "loss": 0.7216084480285645,
+      "step": 90
+    },
+    {
+      "epoch": 0.038586294630475935,
+      "grad_norm": 0.3792989253997803,
+      "learning_rate": 0.00019800000000000002,
+      "loss": 0.7241204738616943,
+      "step": 100
+    },
+    {
+      "epoch": 0.04244492409352353,
+      "grad_norm": 0.31958940625190735,
+      "learning_rate": 0.0001999935634368633,
+      "loss": 0.7156620502471924,
+      "step": 110
+    },
+    {
+      "epoch": 0.04630355355657113,
+      "grad_norm": 0.3532995283603668,
+      "learning_rate": 0.00019997131465276176,
+      "loss": 0.716402530670166,
+      "step": 120
+    },
+    {
+      "epoch": 0.05016218301961872,
+      "grad_norm": 0.3720763921737671,
+      "learning_rate": 0.0001999331777190454,
+      "loss": 0.725121021270752,
+      "step": 130
+    },
+    {
+      "epoch": 0.05402081248266631,
+      "grad_norm": 0.327168345451355,
+      "learning_rate": 0.0001998791586967059,
+      "loss": 0.711461877822876,
+      "step": 140
+    },
+    {
+      "epoch": 0.05787944194571391,
+      "grad_norm": 0.31293419003486633,
+      "learning_rate": 0.00019980926617082901,
+      "loss": 0.7175386905670166,
+      "step": 150
+    },
+    {
+      "epoch": 0.05787944194571391,
+      "eval_loss": 0.7297696471214294,
+      "eval_runtime": 244.1933,
+      "eval_samples_per_second": 3.419,
+      "eval_steps_per_second": 1.712,
+      "step": 150
+    },
+    {
+      "epoch": 0.0617380714087615,
+      "grad_norm": 0.3199326694011688,
+      "learning_rate": 0.0001997235112492302,
+      "loss": 0.7084239006042481,
+      "step": 160
+    },
+    {
+      "epoch": 0.06559670087180909,
+      "grad_norm": 0.3334254026412964,
+      "learning_rate": 0.00019962190756068907,
+      "loss": 0.7120396614074707,
+      "step": 170
+    },
+    {
+      "epoch": 0.0694553303348567,
+      "grad_norm": 0.32970502972602844,
+      "learning_rate": 0.00019950447125278376,
+      "loss": 0.7141448974609375,
+      "step": 180
+    },
+    {
+      "epoch": 0.07331395979790428,
+      "grad_norm": 0.3339720368385315,
+      "learning_rate": 0.00019937122098932428,
+      "loss": 0.7231975555419922,
+      "step": 190
+    },
+    {
+      "epoch": 0.07717258926095187,
+      "grad_norm": 0.302263081073761,
+      "learning_rate": 0.00019922217794738657,
+      "loss": 0.7377682685852051,
+      "step": 200
+    },
+    {
+      "epoch": 0.08103121872399947,
+      "grad_norm": 0.3148849904537201,
+      "learning_rate": 0.00019905736581394689,
+      "loss": 0.7064791202545166,
+      "step": 210
+    },
+    {
+      "epoch": 0.08488984818704706,
+      "grad_norm": 0.3036375641822815,
+      "learning_rate": 0.00019887681078211707,
+      "loss": 0.7082621097564697,
+      "step": 220
+    },
+    {
+      "epoch": 0.08874847765009465,
+      "grad_norm": 0.353236585855484,
+      "learning_rate": 0.00019868054154698202,
+      "loss": 0.7202902793884277,
+      "step": 230
+    },
+    {
+      "epoch": 0.09260710711314225,
+      "grad_norm": 0.2983817458152771,
+      "learning_rate": 0.0001984685893010392,
+      "loss": 0.6949288845062256,
+      "step": 240
+    },
+    {
+      "epoch": 0.09646573657618984,
+      "grad_norm": 0.3325659930706024,
+      "learning_rate": 0.00019824098772924114,
+      "loss": 0.7241635799407959,
+      "step": 250
+    },
+    {
+      "epoch": 0.10032436603923744,
+      "grad_norm": 0.29093560576438904,
+      "learning_rate": 0.00019799777300364218,
+      "loss": 0.7079925060272216,
+      "step": 260
+    },
+    {
+      "epoch": 0.10418299550228503,
+      "grad_norm": 0.3151165246963501,
+      "learning_rate": 0.0001977389837776497,
+      "loss": 0.7299640655517579,
+      "step": 270
+    },
+    {
+      "epoch": 0.10804162496533262,
+      "grad_norm": 0.30055317282676697,
+      "learning_rate": 0.000197464661179881,
+      "loss": 0.7072536468505859,
+      "step": 280
+    },
+    {
+      "epoch": 0.11190025442838022,
+      "grad_norm": 0.28629517555236816,
+      "learning_rate": 0.00019717484880762685,
+      "loss": 0.7206380844116211,
+      "step": 290
+    },
+    {
+      "epoch": 0.1196175133544754,
+      "grad_norm": 0.31153738498687744,
+      "learning_rate": 0.0001965489414302289,
+      "loss": 0.722527265548706,
+      "step": 310
+    },
+    {
+      "epoch": 0.123476142817523,
+      "grad_norm": 0.2931964695453644,
+      "learning_rate": 0.00019621294589872003,
+      "loss": 0.7037133693695068,
+      "step": 320
+    },
+    {
+      "epoch": 0.1273347722805706,
+      "grad_norm": 0.33466067910194397,
+      "learning_rate": 0.0001958616595241865,
+      "loss": 0.727421760559082,
+      "step": 330
+    },
+    {
+      "epoch": 0.13119340174361818,
+      "grad_norm": 0.28575319051742554,
+      "learning_rate": 0.00019549513813554785,
+      "loss": 0.6994576930999756,
+      "step": 340
+    },
+    {
+      "epoch": 0.13505203120666578,
+      "grad_norm": 0.31457364559173584,
+      "learning_rate": 0.0001951134399829799,
+      "loss": 0.734303331375122,
+      "step": 350
+    },
+    {
+      "epoch": 0.1389106606697134,
+      "grad_norm": 0.30264604091644287,
+      "learning_rate": 0.00019471662572865736,
+      "loss": 0.7409284591674805,
+      "step": 360
+    },
+    {
+      "epoch": 0.14276929013276096,
+      "grad_norm": 0.28342851996421814,
+      "learning_rate": 0.00019430475843711293,
+      "loss": 0.7335753440856934,
+      "step": 370
+    },
+    {
+      "epoch": 0.14662791959580856,
+      "grad_norm": 0.30577903985977173,
+      "learning_rate": 0.00019387790356521463,
+      "loss": 0.7155701637268066,
+      "step": 380
+    },
+    {
+      "epoch": 0.15048654905885617,
+      "grad_norm": 0.28058379888534546,
+      "learning_rate": 0.000193436128951763,
+      "loss": 0.6958878993988037,
+      "step": 390
+    },
+    {
+      "epoch": 0.15434517852190374,
+      "grad_norm": 0.30901074409484863,
+      "learning_rate": 0.0001929795048067095,
+      "loss": 0.7224118709564209,
+      "step": 400
+    },
+    {
+      "epoch": 0.15820380798495134,
+      "grad_norm": 0.28316858410835266,
+      "learning_rate": 0.0001925081036999984,
+      "loss": 0.7156408786773681,
+      "step": 410
+    },
+    {
+      "epoch": 0.16206243744799895,
+      "grad_norm": 0.29417017102241516,
+      "learning_rate": 0.00019202200055003346,
+      "loss": 0.7048601150512696,
+      "step": 420
+    },
+    {
+      "epoch": 0.16592106691104652,
+      "grad_norm": 0.29546213150024414,
+      "learning_rate": 0.00019152127261177126,
+      "loss": 0.7047354698181152,
+      "step": 430
+    },
+    {
+      "epoch": 0.16977969637409412,
+      "grad_norm": 0.2986455261707306,
+      "learning_rate": 0.0001910059994644434,
+      "loss": 0.6936575889587402,
+      "step": 440
+    },
+    {
+      "epoch": 0.17363832583714173,
+      "grad_norm": 0.35280054807662964,
+      "learning_rate": 0.0001904762629989091,
+      "loss": 0.6981217384338378,
+      "step": 450
+    },
+    {
+      "epoch": 0.17363832583714173,
+      "eval_loss": 0.7733834385871887,
+      "eval_runtime": 241.1126,
+      "eval_samples_per_second": 3.463,
+      "eval_steps_per_second": 1.734,
+      "step": 450
+    },
+    {
+      "epoch": 0.1774969553001893,
+      "grad_norm": 0.28504979610443115,
+      "learning_rate": 0.00018993214740464063,
+      "loss": 0.7187217235565185,
+      "step": 460
+    },
+    {
+      "epoch": 0.1813555847632369,
+      "grad_norm": 0.294179230928421,
+      "learning_rate": 0.00018937373915634323,
+      "loss": 0.723856258392334,
+      "step": 470
+    },
+    {
+      "epoch": 0.1852142142262845,
+      "grad_norm": 0.3039489984512329,
+      "learning_rate": 0.00018880112700021205,
+      "loss": 0.7158075332641601,
+      "step": 480
+    },
+    {
+      "epoch": 0.18907284368933208,
+      "grad_norm": 0.3352907598018646,
+      "learning_rate": 0.0001882144019398278,
+      "loss": 0.7123313903808594,
+      "step": 490
+    },
+    {
+      "epoch": 0.19293147315237968,
+      "grad_norm": 0.31155890226364136,
+      "learning_rate": 0.00018761365722169403,
+      "loss": 0.7325988292694092,
+      "step": 500
+    },
+    {
+      "epoch": 0.1967901026154273,
+      "grad_norm": 0.3036295175552368,
+      "learning_rate": 0.00018699898832041757,
+      "loss": 0.7070968627929688,
+      "step": 510
+    },
+    {
+      "epoch": 0.2006487320784749,
+      "grad_norm": 0.2792280316352844,
+      "learning_rate": 0.00018637049292353513,
+      "loss": 0.7023006916046143,
+      "step": 520
+    },
+    {
+      "epoch": 0.20450736154152246,
+      "grad_norm": 0.30598390102386475,
+      "learning_rate": 0.00018572827091598793,
+      "loss": 0.708428144454956,
+      "step": 530
+    },
+    {
+      "epoch": 0.20836599100457007,
+      "grad_norm": 0.28768792748451233,
+      "learning_rate": 0.00018507242436424765,
+      "loss": 0.708616304397583,
+      "step": 540
+    },
+    {
+      "epoch": 0.21222462046761767,
+      "grad_norm": 0.32237133383750916,
+      "learning_rate": 0.00018440305750009483,
+      "loss": 0.7210727214813233,
+      "step": 550
+    },
+    {
+      "epoch": 0.21608324993066524,
+      "grad_norm": 0.2892608940601349,
+      "learning_rate": 0.000183720276704054,
+      "loss": 0.6931821823120117,
+      "step": 560
+    },
+    {
+      "epoch": 0.21994187939371285,
+      "grad_norm": 0.3152562081813812,
+      "learning_rate": 0.00018302419048848667,
+      "loss": 0.7213119506835938,
+      "step": 570
+    },
+    {
+      "epoch": 0.22380050885676045,
+      "grad_norm": 0.31499791145324707,
+      "learning_rate": 0.00018231490948034592,
+      "loss": 0.6939045906066894,
+      "step": 580
+    },
+    {
+      "epoch": 0.22765913831980802,
+      "grad_norm": 0.2861924469470978,
+      "learning_rate": 0.00018159254640359487,
+      "loss": 0.7252971649169921,
+      "step": 590
+    },
+    {
+      "epoch": 0.23537639724590323,
+      "grad_norm": 0.2836938500404358,
+      "learning_rate": 0.00018010903531734363,
+      "loss": 0.6902801513671875,
+      "step": 610
+    },
+    {
+      "epoch": 0.2392350267089508,
+      "grad_norm": 0.3197932243347168,
+      "learning_rate": 0.00017934812307793583,
+      "loss": 0.6933451175689698,
+      "step": 620
+    },
+    {
+      "epoch": 0.2430936561719984,
+      "grad_norm": 0.29024383425712585,
+      "learning_rate": 0.00017857460027263225,
+      "loss": 0.6954158306121826,
+      "step": 630
+    },
+    {
+      "epoch": 0.246952285635046,
+      "grad_norm": 0.29053837060928345,
+      "learning_rate": 0.00017778858983515743,
+      "loss": 0.7062996864318848,
+      "step": 640
+    },
+    {
+      "epoch": 0.2508109150980936,
+      "grad_norm": 0.2862823009490967,
+      "learning_rate": 0.00017699021668385895,
+      "loss": 0.726755428314209,
+      "step": 650
+    },
+    {
+      "epoch": 0.2546695445611412,
+      "grad_norm": 0.31322675943374634,
+      "learning_rate": 0.00017617960770185444,
+      "loss": 0.7403687953948974,
+      "step": 660
+    },
+    {
+      "epoch": 0.25852817402418876,
+      "grad_norm": 0.2916722595691681,
+      "learning_rate": 0.00017535689171686644,
+      "loss": 0.6931378364562988,
+      "step": 670
+    },
+    {
+      "epoch": 0.26238680348723636,
+      "grad_norm": 0.3099428117275238,
+      "learning_rate": 0.00017452219948074814,
+      "loss": 0.7085556983947754,
+      "step": 680
+    },
+    {
+      "epoch": 0.26624543295028397,
+      "grad_norm": 0.30417969822883606,
+      "learning_rate": 0.0001736756636487035,
+      "loss": 0.7230380058288575,
+      "step": 690
+    },
+    {
+      "epoch": 0.27010406241333157,
+      "grad_norm": 0.28197744488716125,
+      "learning_rate": 0.0001728174187582045,
+      "loss": 0.722746467590332,
+      "step": 700
+    },
+    {
+      "epoch": 0.27396269187637917,
+      "grad_norm": 0.30067917704582214,
+      "learning_rate": 0.00017194760120760986,
+      "loss": 0.7116784572601318,
+      "step": 710
+    },
+    {
+      "epoch": 0.2778213213394268,
+      "grad_norm": 0.2828962802886963,
+      "learning_rate": 0.00017106634923448724,
+      "loss": 0.6991414546966552,
+      "step": 720
+    },
+    {
+      "epoch": 0.2816799508024743,
+      "grad_norm": 0.303771436214447,
+      "learning_rate": 0.00017017380289364388,
+      "loss": 0.700380277633667,
+      "step": 730
+    },
+    {
+      "epoch": 0.2855385802655219,
+      "grad_norm": 0.3401305377483368,
+      "learning_rate": 0.00016927010403486786,
+      "loss": 0.717545461654663,
+      "step": 740
+    },
+    {
+      "epoch": 0.2893972097285695,
+      "grad_norm": 0.29057246446609497,
+      "learning_rate": 0.00016835539628038445,
+      "loss": 0.7112515449523926,
+      "step": 750
+    },
+    {
+      "epoch": 0.2893972097285695,
+      "eval_loss": 0.7159802317619324,
+      "eval_runtime": 247.114,
+      "eval_samples_per_second": 3.379,
+      "eval_steps_per_second": 1.692,
+      "step": 750
+    },
+    {
+      "epoch": 0.29325583919161713,
+      "grad_norm": 0.2816619277000427,
+      "learning_rate": 0.0001674298250020307,
+      "loss": 0.7210293769836426,
+      "step": 760
+    },
+    {
+      "epoch": 0.29711446865466473,
+      "grad_norm": 0.35117030143737793,
+      "learning_rate": 0.00016649353729815172,
+      "loss": 0.7004368305206299,
+      "step": 770
+    },
+    {
+      "epoch": 0.30097309811771233,
+      "grad_norm": 0.3049272298812866,
+      "learning_rate": 0.00016554668197022295,
+      "loss": 0.693110990524292,
+      "step": 780
+    },
+    {
+      "epoch": 0.3048317275807599,
+      "grad_norm": 0.33454808592796326,
+      "learning_rate": 0.0001645894094992015,
+      "loss": 0.7131325244903565,
+      "step": 790
+    },
+    {
+      "epoch": 0.3086903570438075,
+      "grad_norm": 0.2931094765663147,
+      "learning_rate": 0.00016362187202161076,
+      "loss": 0.7059287071228028,
+      "step": 800
+    },
+    {
+      "epoch": 0.3125489865068551,
+      "grad_norm": 0.31233930587768555,
+      "learning_rate": 0.00016264422330536154,
+      "loss": 0.7155674934387207,
+      "step": 810
+    },
+    {
+      "epoch": 0.3164076159699027,
+      "grad_norm": 0.30221912264823914,
+      "learning_rate": 0.00016165661872531443,
+      "loss": 0.7006759166717529,
+      "step": 820
+    },
+    {
+      "epoch": 0.3202662454329503,
+      "grad_norm": 0.28081852197647095,
+      "learning_rate": 0.00016065921523858635,
+      "loss": 0.7008425712585449,
+      "step": 830
+    },
+    {
+      "epoch": 0.3241248748959979,
+      "grad_norm": 0.31421926617622375,
+      "learning_rate": 0.00015965217135960607,
+      "loss": 0.7249965190887451,
+      "step": 840
+    },
+    {
+      "epoch": 0.3279835043590455,
+      "grad_norm": 0.2977774143218994,
+      "learning_rate": 0.0001586356471349215,
+      "loss": 0.6932929039001465,
+      "step": 850
+    },
+    {
+      "epoch": 0.33184213382209304,
+      "grad_norm": 0.28536227345466614,
+      "learning_rate": 0.0001576098041177646,
+      "loss": 0.7123911857604981,
+      "step": 860
+    },
+    {
+      "epoch": 0.33570076328514065,
+      "grad_norm": 0.2825419008731842,
+      "learning_rate": 0.00015657480534237561,
+      "loss": 0.6955167293548584,
+      "step": 870
+    },
+    {
+      "epoch": 0.33955939274818825,
+      "grad_norm": 0.2923476994037628,
+      "learning_rate": 0.00015553081529809281,
+      "loss": 0.6951467990875244,
+      "step": 880
+    },
+    {
+      "epoch": 0.34341802221123585,
+      "grad_norm": 0.290323406457901,
+      "learning_rate": 0.00015447799990321066,
+      "loss": 0.6957611083984375,
+      "step": 890
+    },
+    {
+      "epoch": 0.34727665167428345,
+      "grad_norm": 0.29604029655456543,
+      "learning_rate": 0.00015341652647861084,
+      "loss": 0.7186079025268555,
+      "step": 900
+    },
+    {
+      "epoch": 0.34727665167428345,
+      "eval_loss": 0.7107371687889099,
+      "eval_runtime": 261.1674,
+      "eval_samples_per_second": 3.197,
+      "eval_steps_per_second": 1.601,
+      "step": 900
+    },
+    {
+      "epoch": 0.35113528113733106,
+      "grad_norm": 0.27018797397613525,
+      "learning_rate": 0.00015234656372117042,
+      "loss": 0.7154855728149414,
+      "step": 910
+    },
+    {
+      "epoch": 0.3549939106003786,
+      "grad_norm": 0.26977527141571045,
+      "learning_rate": 0.00015126828167695146,
+      "loss": 0.699330997467041,
+      "step": 920
+    },
+    {
+      "epoch": 0.3588525400634262,
+      "grad_norm": 0.30887559056282043,
+      "learning_rate": 0.00015018185171417604,
+      "loss": 0.6892439842224121,
+      "step": 930
+    },
+    {
+      "epoch": 0.3627111695264738,
+      "grad_norm": 0.31451812386512756,
+      "learning_rate": 0.00014908744649599104,
+      "loss": 0.7145347595214844,
+      "step": 940
+    },
+    {
+      "epoch": 0.3665697989895214,
+      "grad_norm": 0.2898563742637634,
+      "learning_rate": 0.00014798523995302758,
+      "loss": 0.7055789947509765,
+      "step": 950
+    },
+    {
+      "epoch": 0.370428428452569,
+      "grad_norm": 0.26642370223999023,
+      "learning_rate": 0.00014687540725575845,
+      "loss": 0.6984900951385498,
+      "step": 960
+    },
+    {
+      "epoch": 0.3742870579156166,
+      "grad_norm": 0.32259368896484375,
+      "learning_rate": 0.0001457581247866591,
+      "loss": 0.6736190795898438,
+      "step": 970
+    },
+    {
+      "epoch": 0.37814568737866416,
+      "grad_norm": 0.2674982249736786,
+      "learning_rate": 0.00014463357011217532,
+      "loss": 0.6823287010192871,
+      "step": 980
+    },
+    {
+      "epoch": 0.38200431684171177,
+      "grad_norm": 0.295978307723999,
+      "learning_rate": 0.0001435019219545034,
+      "loss": 0.7077735900878906,
+      "step": 990
+    },
+    {
+      "epoch": 0.38586294630475937,
+      "grad_norm": 0.3013753294944763,
+      "learning_rate": 0.0001423633601631862,
+      "loss": 0.7043970108032227,
+      "step": 1000
+    },
+    {
+      "epoch": 0.38972157576780697,
+      "grad_norm": 0.26629018783569336,
+      "learning_rate": 0.00014121806568653025,
+      "loss": 0.6968683719635009,
+      "step": 1010
+    },
+    {
+      "epoch": 0.3935802052308546,
+      "grad_norm": 0.2660974860191345,
+      "learning_rate": 0.00014006622054284806,
+      "loss": 0.6901365756988526,
+      "step": 1020
+    },
+    {
+      "epoch": 0.3974388346939022,
+      "grad_norm": 0.2733144760131836,
+      "learning_rate": 0.0001389080077915307,
+      "loss": 0.6891340255737305,
+      "step": 1030
+    },
+    {
+      "epoch": 0.4012974641569498,
+      "grad_norm": 0.30119362473487854,
+      "learning_rate": 0.00013774361150395442,
+      "loss": 0.687501335144043,
+      "step": 1040
+    },
+    {
+      "epoch": 0.4051560936199973,
+      "grad_norm": 0.29165130853652954,
+      "learning_rate": 0.00013657321673422691,
+      "loss": 0.7198416233062744,
+      "step": 1050
+    },
+    {
+      "epoch": 0.4051560936199973,
+      "eval_loss": 0.7047804594039917,
+      "eval_runtime": 261.4782,
+      "eval_samples_per_second": 3.193,
+      "eval_steps_per_second": 1.599,
+      "step": 1050
+    },
+    {
+      "epoch": 0.40901472308304493,
+      "grad_norm": 0.2916712760925293,
+      "learning_rate": 0.00013539700948977717,
+      "loss": 0.6978848934173584,
+      "step": 1060
+    },
+    {
+      "epoch": 0.41287335254609253,
+      "grad_norm": 0.29535216093063354,
+      "learning_rate": 0.0001342151767017938,
+      "loss": 0.6890017986297607,
+      "step": 1070
+    },
+    {
+      "epoch": 0.41673198200914013,
+      "grad_norm": 0.28752076625823975,
+      "learning_rate": 0.00013302790619551674,
+      "loss": 0.717583703994751,
+      "step": 1080
+    },
+    {
+      "epoch": 0.42059061147218774,
+      "grad_norm": 0.32082512974739075,
+      "learning_rate": 0.00013183538666038648,
+      "loss": 0.7101277351379395,
+      "step": 1090
+    },
+    {
+      "epoch": 0.42444924093523534,
+      "grad_norm": 0.27900826930999756,
+      "learning_rate": 0.00013063780762005654,
+      "loss": 0.6807409286499023,
+      "step": 1100
+    },
+    {
+      "epoch": 0.4283078703982829,
+      "grad_norm": 0.3178718090057373,
+      "learning_rate": 0.0001294353594022728,
+      "loss": 0.686630392074585,
+      "step": 1110
+    },
+    {
+      "epoch": 0.4321664998613305,
+      "grad_norm": 0.2647388279438019,
+      "learning_rate": 0.00012822823310862524,
+      "loss": 0.670403003692627,
+      "step": 1120
+    },
+    {
+      "epoch": 0.4360251293243781,
+      "grad_norm": 0.28969231247901917,
+      "learning_rate": 0.00012701662058417688,
+      "loss": 0.6713655948638916,
+      "step": 1130
+    },
+    {
+      "epoch": 0.4398837587874257,
+      "grad_norm": 0.28609490394592285,
+      "learning_rate": 0.00012580071438697427,
+      "loss": 0.6948023319244385,
+      "step": 1140
+    },
+    {
+      "epoch": 0.4437423882504733,
+      "grad_norm": 0.27543318271636963,
+      "learning_rate": 0.0001245807077574449,
+      "loss": 0.7000330924987793,
+      "step": 1150
+    },
+    {
+      "epoch": 0.4476010177135209,
+      "grad_norm": 0.28665491938591003,
+      "learning_rate": 0.00012335679458768607,
+      "loss": 0.6907845497131347,
+      "step": 1160
+    },
+    {
+      "epoch": 0.45145964717656845,
+      "grad_norm": 0.26809993386268616,
+      "learning_rate": 0.00012212916939064998,
+      "loss": 0.6751095294952393,
+      "step": 1170
+    },
+    {
+      "epoch": 0.45531827663961605,
+      "grad_norm": 0.28608420491218567,
+      "learning_rate": 0.00012089802726923061,
+      "loss": 0.6977941513061523,
+      "step": 1180
+    },
+    {
+      "epoch": 0.45917690610266365,
+      "grad_norm": 0.2964702844619751,
+      "learning_rate": 0.00011966356388525646,
+      "loss": 0.685225248336792,
+      "step": 1190
+    },
+    {
+      "epoch": 0.46689416502875886,
+      "grad_norm": 0.3035467863082886,
+      "learning_rate": 0.00011718545858497087,
+      "loss": 0.6892534732818604,
+      "step": 1210
+    },
+    {
+      "epoch": 0.47075279449180646,
+      "grad_norm": 0.2953267991542816,
+      "learning_rate": 0.00011594221050671095,
+      "loss": 0.6970641136169433,
+      "step": 1220
+    },
+    {
+      "epoch": 0.47461142395485406,
+      "grad_norm": 0.2962872087955475,
+      "learning_rate": 0.00011469642877940779,
+      "loss": 0.6811253547668457,
+      "step": 1230
+    },
+    {
+      "epoch": 0.4784700534179016,
+      "grad_norm": 0.2830030024051666,
+      "learning_rate": 0.00011344831139151972,
+      "loss": 0.6688879489898681,
+      "step": 1240
+    },
+    {
+      "epoch": 0.4823286828809492,
+      "grad_norm": 0.29539620876312256,
+      "learning_rate": 0.00011219805670270496,
+      "loss": 0.700579833984375,
+      "step": 1250
+    },
+    {
+      "epoch": 0.4861873123439968,
+      "grad_norm": 0.29297176003456116,
+      "learning_rate": 0.00011094586341229656,
+      "loss": 0.6867257118225097,
+      "step": 1260
+    },
+    {
+      "epoch": 0.4900459418070444,
+      "grad_norm": 0.29863327741622925,
+      "learning_rate": 0.00010969193052772396,
+      "loss": 0.71397385597229,
+      "step": 1270
+    },
+    {
+      "epoch": 0.493904571270092,
+      "grad_norm": 0.2799651622772217,
+      "learning_rate": 0.00010843645733288519,
+      "loss": 0.7007513046264648,
+      "step": 1280
+    },
+    {
+      "epoch": 0.4977632007331396,
+      "grad_norm": 0.2826097905635834,
+      "learning_rate": 0.00010717964335647535,
+      "loss": 0.6815872669219971,
+      "step": 1290
+    },
+    {
+      "epoch": 0.5016218301961872,
+      "grad_norm": 0.27504852414131165,
+      "learning_rate": 0.00010592168834027598,
+      "loss": 0.6807018280029297,
+      "step": 1300
+    },
+    {
+      "epoch": 0.5054804596592348,
+      "grad_norm": 0.28094950318336487,
+      "learning_rate": 0.00010466279220741078,
+      "loss": 0.6823868751525879,
+      "step": 1310
+    },
+    {
+      "epoch": 0.5093390891222824,
+      "grad_norm": 0.2797650694847107,
+      "learning_rate": 0.00010340315503057243,
+      "loss": 0.674619722366333,
+      "step": 1320
+    },
+    {
+      "epoch": 0.5131977185853299,
+      "grad_norm": 0.28894102573394775,
+      "learning_rate": 0.00010214297700022549,
+      "loss": 0.7022358417510987,
+      "step": 1330
+    },
+    {
+      "epoch": 0.5170563480483775,
+      "grad_norm": 0.29386165738105774,
+      "learning_rate": 0.00010088245839279082,
+      "loss": 0.67178316116333,
+      "step": 1340
+    },
+    {
+      "epoch": 0.5209149775114251,
+      "grad_norm": 0.28537702560424805,
+      "learning_rate": 9.96217995388162e-05,
+      "loss": 0.6890518188476562,
+      "step": 1350
+    },
+    {
+      "epoch": 0.5209149775114251,
+      "eval_loss": 0.6932345032691956,
+      "eval_runtime": 269.3818,
+      "eval_samples_per_second": 3.1,
+      "eval_steps_per_second": 1.552,
+      "step": 1350
+    },
+    {
+      "epoch": 0.5247736069744727,
+      "grad_norm": 0.3049728274345398,
+      "learning_rate": 9.83612007911384e-05,
+      "loss": 0.6744989871978759,
+      "step": 1360
+    },
+    {
+      "epoch": 0.5286322364375203,
+      "grad_norm": 0.33253172039985657,
+      "learning_rate": 9.710086249304164e-05,
+      "loss": 0.6773325443267822,
+      "step": 1370
+    },
+    {
+      "epoch": 0.5324908659005679,
+      "grad_norm": 0.27811330556869507,
+      "learning_rate": 9.584098494641772e-05,
+      "loss": 0.6876926898956299,
+      "step": 1380
+    },
+    {
+      "epoch": 0.5363494953636155,
+      "grad_norm": 0.29328352212905884,
+      "learning_rate": 9.458176837993246e-05,
+      "loss": 0.689525842666626,
+      "step": 1390
+    },
+    {
+      "epoch": 0.5402081248266631,
+      "grad_norm": 0.27268341183662415,
+      "learning_rate": 9.332341291720408e-05,
+      "loss": 0.6747959136962891,
+      "step": 1400
+    },
+    {
+      "epoch": 0.5440667542897107,
+      "grad_norm": 0.28394851088523865,
+      "learning_rate": 9.206611854499805e-05,
+      "loss": 0.6711764335632324,
+      "step": 1410
+    },
+    {
+      "epoch": 0.5479253837527583,
+      "grad_norm": 0.28641200065612793,
+      "learning_rate": 9.081008508144388e-05,
+      "loss": 0.6956794261932373,
+      "step": 1420
+    },
+    {
+      "epoch": 0.551784013215806,
+      "grad_norm": 0.2705199718475342,
+      "learning_rate": 8.955551214427856e-05,
+      "loss": 0.7046959400177002,
+      "step": 1430
+    },
+    {
+      "epoch": 0.5556426426788535,
+      "grad_norm": 0.26797372102737427,
+      "learning_rate": 8.830259911912173e-05,
+      "loss": 0.6727779865264892,
+      "step": 1440
+    },
+    {
+      "epoch": 0.5595012721419012,
+      "grad_norm": 0.2805560529232025,
+      "learning_rate": 8.705154512778821e-05,
+      "loss": 0.6727550506591797,
+      "step": 1450
+    },
+    {
+      "epoch": 0.5633599016049486,
+      "grad_norm": 0.28046268224716187,
+      "learning_rate": 8.580254899664195e-05,
+      "loss": 0.6817981243133545,
+      "step": 1460
+    },
+    {
+      "epoch": 0.5672185310679962,
+      "grad_norm": 0.27203667163848877,
+      "learning_rate": 8.455580922499716e-05,
+      "loss": 0.6813424110412598,
+      "step": 1470
+    },
+    {
+      "epoch": 0.5710771605310438,
+      "grad_norm": 0.29054710268974304,
+      "learning_rate": 8.331152395357141e-05,
+      "loss": 0.6807193279266357,
+      "step": 1480
+    },
+    {
+      "epoch": 0.5749357899940915,
+      "grad_norm": 0.32792478799819946,
+      "learning_rate": 8.206989093299572e-05,
+      "loss": 0.6816314220428467,
+      "step": 1490
+    },
+    {
+      "epoch": 0.578794419457139,
+      "grad_norm": 0.2703556418418884,
+      "learning_rate": 8.083110749238659e-05,
+      "loss": 0.6654800415039063,
+      "step": 1500
+    },
+    {
+      "epoch": 0.578794419457139,
+      "eval_loss": 0.6862806081771851,
+      "eval_runtime": 245.6426,
+      "eval_samples_per_second": 3.399,
+      "eval_steps_per_second": 1.702,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5826530489201867,
+      "grad_norm": 0.27336329221725464,
+      "learning_rate": 7.959537050798512e-05,
+      "loss": 0.6732516288757324,
+      "step": 1510
+    },
+    {
+      "epoch": 0.5865116783832343,
+      "grad_norm": 0.27847999334335327,
+      "learning_rate": 7.836287637186801e-05,
+      "loss": 0.68833327293396,
+      "step": 1520
+    },
+    {
+      "epoch": 0.5903703078462819,
+      "grad_norm": 0.25630271434783936,
+      "learning_rate": 7.713382096073545e-05,
+      "loss": 0.6711580276489257,
+      "step": 1530
+    },
+    {
+      "epoch": 0.5942289373093295,
+      "grad_norm": 0.2752869427204132,
+      "learning_rate": 7.59083996047812e-05,
+      "loss": 0.6594626426696777,
+      "step": 1540
+    },
+    {
+      "epoch": 0.5980875667723771,
+      "grad_norm": 0.27679699659347534,
+      "learning_rate": 7.468680705664914e-05,
+      "loss": 0.6733936309814453,
+      "step": 1550
+    },
+    {
+      "epoch": 0.6019461962354247,
+      "grad_norm": 0.2734837830066681,
+      "learning_rate": 7.346923746048202e-05,
+      "loss": 0.6738894939422607,
+      "step": 1560
+    },
+    {
+      "epoch": 0.6058048256984723,
+      "grad_norm": 0.27832263708114624,
+      "learning_rate": 7.225588432106633e-05,
+      "loss": 0.6458727359771729,
+      "step": 1570
+    },
+    {
+      "epoch": 0.6096634551615198,
+      "grad_norm": 0.28797298669815063,
+      "learning_rate": 7.104694047307963e-05,
+      "loss": 0.6783483982086181,
+      "step": 1580
+    },
+    {
+      "epoch": 0.6135220846245674,
+      "grad_norm": 0.27791404724121094,
+      "learning_rate": 6.984259805044342e-05,
+      "loss": 0.6734447479248047,
+      "step": 1590
+    },
+    {
+      "epoch": 0.617380714087615,
+      "grad_norm": 0.26526719331741333,
+      "learning_rate": 6.864304845578826e-05,
+      "loss": 0.671996021270752,
+      "step": 1600
+    },
+    {
+      "epoch": 0.6212393435506626,
+      "grad_norm": 0.28982335329055786,
+      "learning_rate": 6.74484823300345e-05,
+      "loss": 0.6816313743591309,
+      "step": 1610
+    },
+    {
+      "epoch": 0.6250979730137102,
+      "grad_norm": 0.262482613325119,
+      "learning_rate": 6.625908952209418e-05,
+      "loss": 0.6751953601837158,
+      "step": 1620
+    },
+    {
+      "epoch": 0.6289566024767578,
+      "grad_norm": 0.39887505769729614,
+      "learning_rate": 6.507505905869914e-05,
+      "loss": 0.6822636127471924,
+      "step": 1630
+    },
+    {
+      "epoch": 0.6328152319398054,
+      "grad_norm": 0.2669890224933624,
+      "learning_rate": 6.389657911435943e-05,
+      "loss": 0.6915277957916259,
+      "step": 1640
+    },
+    {
+      "epoch": 0.636673861402853,
+      "grad_norm": 0.2670292556285858,
+      "learning_rate": 6.272383698145723e-05,
+      "loss": 0.652358102798462,
+      "step": 1650
+    },
+    {
+      "epoch": 0.636673861402853,
+      "eval_loss": 0.6799824237823486,
+      "eval_runtime": 238.2058,
+      "eval_samples_per_second": 3.505,
+      "eval_steps_per_second": 1.755,
+      "step": 1650
+    },
+    {
+      "epoch": 0.6405324908659006,
+      "grad_norm": 0.27272072434425354,
+      "learning_rate": 6.15570190404811e-05,
+      "loss": 0.6684075832366944,
+      "step": 1660
+    },
+    {
+      "epoch": 0.6443911203289482,
+      "grad_norm": 0.25919416546821594,
+      "learning_rate": 6.039631073040507e-05,
+      "loss": 0.6651289463043213,
+      "step": 1670
+    },
+    {
+      "epoch": 0.6482497497919958,
+      "grad_norm": 0.27560484409332275,
+      "learning_rate": 5.924189651921728e-05,
+      "loss": 0.6770682811737061,
+      "step": 1680
+    },
+    {
+      "epoch": 0.6521083792550434,
+      "grad_norm": 0.29968157410621643,
+      "learning_rate": 5.8093959874603176e-05,
+      "loss": 0.6616378784179687,
+      "step": 1690
+    },
+    {
+      "epoch": 0.6598256381811385,
+      "grad_norm": 0.2539561092853546,
+      "learning_rate": 5.581824797953925e-05,
+      "loss": 0.6652106761932373,
+      "step": 1710
+    },
+    {
+      "epoch": 0.6636842676441861,
+      "grad_norm": 0.2645578980445862,
+      "learning_rate": 5.4690834401347034e-05,
+      "loss": 0.6816202163696289,
+      "step": 1720
+    },
+    {
+      "epoch": 0.6675428971072337,
+      "grad_norm": 0.2860375642776489,
+      "learning_rate": 5.357062167676426e-05,
+      "loss": 0.6432219982147217,
+      "step": 1730
+    },
+    {
+      "epoch": 0.6714015265702813,
+      "grad_norm": 0.29771652817726135,
+      "learning_rate": 5.2457787837933715e-05,
+      "loss": 0.6574324131011963,
+      "step": 1740
+    },
+    {
+      "epoch": 0.6752601560333289,
+      "grad_norm": 0.26455527544021606,
+      "learning_rate": 5.135250974429342e-05,
+      "loss": 0.6606158256530762,
+      "step": 1750
+    },
+    {
+      "epoch": 0.6791187854963765,
+      "grad_norm": 0.2809986174106598,
+      "learning_rate": 5.02549630544688e-05,
+      "loss": 0.6675248622894288,
+      "step": 1760
+    },
+    {
+      "epoch": 0.6829774149594241,
+      "grad_norm": 0.2710455060005188,
+      "learning_rate": 4.916532219835592e-05,
+      "loss": 0.6551553249359131,
+      "step": 1770
+    },
+    {
+      "epoch": 0.6868360444224717,
+      "grad_norm": 0.3084876239299774,
+      "learning_rate": 4.808376034939965e-05,
+      "loss": 0.6641845703125,
+      "step": 1780
+    },
+    {
+      "epoch": 0.6906946738855193,
+      "grad_norm": 0.2739737033843994,
+      "learning_rate": 4.701044939707181e-05,
+      "loss": 0.640526533126831,
+      "step": 1790
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2592,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.157629021565309e+19,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1800/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36e6279f3948829ea711876c2172486c9470f648c9ce969627b2e58872c6b5f7
+size 5713