Model save

README.md

@@ -1,27 +1,19 @@
 ---
 library_name: peft
 tags:
-- liuhaotian/llava-v1.5-13b_10.0
 - generated_from_trainer
 base_model: liuhaotian/llava-v1.5-13b
 model-index:
-- name: liuhaotian/llava-v1.5-13b_10.0
+- name: llava_13b_city_synthetic
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# liuhaotian/llava-v1.5-13b_10.0
+# llava_13b_city_synthetic
 
-This model is a fine-tuned version of [liuhaotian/llava-v1.5-13b_10.0](https://huggingface.co/liuhaotian/llava-v1.5-13b_10.0) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- eval_loss: 0.0018
-- eval_runtime: 55.1141
-- eval_samples_per_second: 15.731
-- eval_steps_per_second: 0.508
-- epoch: 9.0
-- step: 252
+This model is a fine-tuned version of [liuhaotian/llava-v1.5-13b](https://huggingface.co/liuhaotian/llava-v1.5-13b) on an unknown dataset.
 
 ## Model description
 
@@ -45,13 +37,13 @@ The following hyperparameters were used during training:
 - eval_batch_size: 4
 - seed: 42
 - distributed_type: multi-GPU
-- num_devices: 8
-- total_train_batch_size: 32
-- total_eval_batch_size: 32
+- num_devices: 4
+- total_train_batch_size: 16
+- total_eval_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.03
-- num_epochs: 10.0
+- num_epochs: 20.0
 
 ### Framework versions
 

adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "up_proj",
+    "v_proj",
+    "o_proj",
     "down_proj",
     "q_proj",
-    "up_proj",
     "k_proj",
-    "o_proj",
-    "v_proj",
     "gate_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5220f27e3577f427604e1d37873608404b0dd12581a0c11e8759f49344a77bb0
+oid sha256:b60faa828dec524e825e23fcf16a9976ea8f5e326aeb85e50efc593f4a293061
 size 1001466944

config.json

@@ -0,0 +1,63 @@
+{
+  "_name_or_path": "liuhaotian/llava-v1.5-13b",
+  "architectures": [
+    "LlavaLlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "freeze_mm_mlp_adapter": false,
+  "freeze_mm_vision_resampler": false,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "image_aspect_ratio": "pad",
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_length": 4096,
+  "max_position_embeddings": 4096,
+  "mm_hidden_size": 1024,
+  "mm_patch_merge_type": "flat",
+  "mm_projector_lr": 2e-05,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_resampler_type": null,
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "openai/clip-vit-large-patch14-336",
+  "model_type": "llava_llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": [
+      "mm_projector"
+    ],
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "tokenizer_model_max_length": 2048,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.2",
+  "tune_mm_mlp_adapter": false,
+  "tune_mm_vision_resampler": false,
+  "unfreeze_mm_vision_tower": false,
+  "use_cache": true,
+  "use_mm_proj": true,
+  "vocab_size": 32000
+}

non_lora_trainables.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d68ddfe6ce0358ed97665d43ab246ef5884bd28da1ad884819ce894242a22ee8
+size 62937264

num_examples=100/llava-v1.5-13b_1.0/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: liuhaotian/llava-v1.5-13b
+---
+
+# 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 0.10.0

num_examples=100/llava-v1.5-13b_1.0/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "liuhaotian/llava-v1.5-13b",
+  "bias": "none",
+  "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": 256,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "v_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "k_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

num_examples=100/llava-v1.5-13b_1.0/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b60faa828dec524e825e23fcf16a9976ea8f5e326aeb85e50efc593f4a293061
+size 1001466944

num_examples=100/llava-v1.5-13b_1.0/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

num_examples=100/llava-v1.5-13b_1.0/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

num_examples=100/llava-v1.5-13b_1.0/tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

num_examples=100/llava-v1.5-13b_1.0/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecfec25df92e2fa743e00b5933b37cc854d2d087fcb1327cb7e9c80ebff881a8
+size 6776

trainer_state.json

@@ -0,0 +1,1790 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 280,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0,
+      "loss": 1.4877,
+      "step": 1
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 6.309297535714573e-05,
+      "loss": 1.2045,
+      "step": 2
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0001,
+      "loss": 1.176,
+      "step": 3
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00012618595071429146,
+      "loss": 1.1334,
+      "step": 4
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0001464973520717927,
+      "loss": 1.0804,
+      "step": 5
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00016309297535714573,
+      "loss": 1.0285,
+      "step": 6
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00017712437491614223,
+      "loss": 0.9975,
+      "step": 7
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0001892789260714372,
+      "loss": 0.9584,
+      "step": 8
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0002,
+      "loss": 0.9367,
+      "step": 9
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0002,
+      "loss": 0.9542,
+      "step": 10
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0002,
+      "loss": 0.8867,
+      "step": 11
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0002,
+      "loss": 0.8464,
+      "step": 12
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0002,
+      "loss": 0.8221,
+      "step": 13
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0002,
+      "loss": 0.7841,
+      "step": 14
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0002,
+      "loss": 0.7761,
+      "step": 15
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0002,
+      "loss": 0.7351,
+      "step": 16
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0002,
+      "loss": 0.6505,
+      "step": 17
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0002,
+      "loss": 0.7055,
+      "step": 18
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0002,
+      "loss": 0.6137,
+      "step": 19
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0002,
+      "loss": 0.6604,
+      "step": 20
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0002,
+      "loss": 0.5231,
+      "step": 21
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0002,
+      "loss": 0.487,
+      "step": 22
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0002,
+      "loss": 0.451,
+      "step": 23
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0002,
+      "loss": 0.3773,
+      "step": 24
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0002,
+      "loss": 0.428,
+      "step": 25
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0002,
+      "loss": 0.3572,
+      "step": 26
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0002,
+      "loss": 0.401,
+      "step": 27
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0002,
+      "loss": 0.328,
+      "step": 28
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.24994784593582153,
+      "eval_runtime": 54.9388,
+      "eval_samples_per_second": 15.781,
+      "eval_steps_per_second": 0.51,
+      "step": 28
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.0002,
+      "loss": 0.2342,
+      "step": 29
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0002,
+      "loss": 0.2448,
+      "step": 30
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0002,
+      "loss": 0.2244,
+      "step": 31
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.0002,
+      "loss": 0.1932,
+      "step": 32
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.0002,
+      "loss": 0.2106,
+      "step": 33
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.0002,
+      "loss": 0.1943,
+      "step": 34
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.0002,
+      "loss": 0.2357,
+      "step": 35
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.0002,
+      "loss": 0.1552,
+      "step": 36
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.0002,
+      "loss": 0.1553,
+      "step": 37
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.0002,
+      "loss": 0.098,
+      "step": 38
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.0002,
+      "loss": 0.1053,
+      "step": 39
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.0002,
+      "loss": 0.1762,
+      "step": 40
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.0002,
+      "loss": 0.1139,
+      "step": 41
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.0002,
+      "loss": 0.1066,
+      "step": 42
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.0002,
+      "loss": 0.1322,
+      "step": 43
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 0.0002,
+      "loss": 0.1329,
+      "step": 44
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 0.0002,
+      "loss": 0.0722,
+      "step": 45
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 0.0002,
+      "loss": 0.074,
+      "step": 46
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 0.0002,
+      "loss": 0.0945,
+      "step": 47
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 0.0002,
+      "loss": 0.1162,
+      "step": 48
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 0.0002,
+      "loss": 0.1019,
+      "step": 49
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 0.0002,
+      "loss": 0.0557,
+      "step": 50
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 0.0002,
+      "loss": 0.1309,
+      "step": 51
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 0.0002,
+      "loss": 0.052,
+      "step": 52
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 0.0002,
+      "loss": 0.11,
+      "step": 53
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 0.0002,
+      "loss": 0.1602,
+      "step": 54
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 0.0002,
+      "loss": 0.1089,
+      "step": 55
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0002,
+      "loss": 0.0393,
+      "step": 56
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.045933909714221954,
+      "eval_runtime": 55.0131,
+      "eval_samples_per_second": 15.76,
+      "eval_steps_per_second": 0.509,
+      "step": 56
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 0.0002,
+      "loss": 0.0396,
+      "step": 57
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 0.0002,
+      "loss": 0.0315,
+      "step": 58
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 0.0002,
+      "loss": 0.0315,
+      "step": 59
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 0.0002,
+      "loss": 0.0438,
+      "step": 60
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 0.0002,
+      "loss": 0.0254,
+      "step": 61
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 0.0002,
+      "loss": 0.0363,
+      "step": 62
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 0.0002,
+      "loss": 0.0266,
+      "step": 63
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 0.0002,
+      "loss": 0.023,
+      "step": 64
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 0.0002,
+      "loss": 0.0309,
+      "step": 65
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 0.0002,
+      "loss": 0.0305,
+      "step": 66
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 0.0002,
+      "loss": 0.0143,
+      "step": 67
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 0.0002,
+      "loss": 0.0319,
+      "step": 68
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 0.0002,
+      "loss": 0.0377,
+      "step": 69
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 0.0002,
+      "loss": 0.0283,
+      "step": 70
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 0.0002,
+      "loss": 0.0191,
+      "step": 71
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 0.0002,
+      "loss": 0.022,
+      "step": 72
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 0.0002,
+      "loss": 0.0144,
+      "step": 73
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 0.0002,
+      "loss": 0.0382,
+      "step": 74
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 0.0002,
+      "loss": 0.0331,
+      "step": 75
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 0.0002,
+      "loss": 0.0188,
+      "step": 76
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 0.0002,
+      "loss": 0.0122,
+      "step": 77
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 0.0002,
+      "loss": 0.0267,
+      "step": 78
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 0.0002,
+      "loss": 0.0324,
+      "step": 79
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 0.0002,
+      "loss": 0.0273,
+      "step": 80
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 0.0002,
+      "loss": 0.0213,
+      "step": 81
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 0.0002,
+      "loss": 0.0281,
+      "step": 82
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 0.0002,
+      "loss": 0.0302,
+      "step": 83
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0002,
+      "loss": 0.0098,
+      "step": 84
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.014728669077157974,
+      "eval_runtime": 55.0126,
+      "eval_samples_per_second": 15.76,
+      "eval_steps_per_second": 0.509,
+      "step": 84
+    },
+    {
+      "epoch": 3.04,
+      "learning_rate": 0.0002,
+      "loss": 0.0059,
+      "step": 85
+    },
+    {
+      "epoch": 3.07,
+      "learning_rate": 0.0002,
+      "loss": 0.012,
+      "step": 86
+    },
+    {
+      "epoch": 3.11,
+      "learning_rate": 0.0002,
+      "loss": 0.01,
+      "step": 87
+    },
+    {
+      "epoch": 3.14,
+      "learning_rate": 0.0002,
+      "loss": 0.0105,
+      "step": 88
+    },
+    {
+      "epoch": 3.18,
+      "learning_rate": 0.0002,
+      "loss": 0.0161,
+      "step": 89
+    },
+    {
+      "epoch": 3.21,
+      "learning_rate": 0.0002,
+      "loss": 0.0127,
+      "step": 90
+    },
+    {
+      "epoch": 3.25,
+      "learning_rate": 0.0002,
+      "loss": 0.0119,
+      "step": 91
+    },
+    {
+      "epoch": 3.29,
+      "learning_rate": 0.0002,
+      "loss": 0.0062,
+      "step": 92
+    },
+    {
+      "epoch": 3.32,
+      "learning_rate": 0.0002,
+      "loss": 0.0094,
+      "step": 93
+    },
+    {
+      "epoch": 3.36,
+      "learning_rate": 0.0002,
+      "loss": 0.0058,
+      "step": 94
+    },
+    {
+      "epoch": 3.39,
+      "learning_rate": 0.0002,
+      "loss": 0.0077,
+      "step": 95
+    },
+    {
+      "epoch": 3.43,
+      "learning_rate": 0.0002,
+      "loss": 0.0114,
+      "step": 96
+    },
+    {
+      "epoch": 3.46,
+      "learning_rate": 0.0002,
+      "loss": 0.0112,
+      "step": 97
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 0.0002,
+      "loss": 0.0139,
+      "step": 98
+    },
+    {
+      "epoch": 3.54,
+      "learning_rate": 0.0002,
+      "loss": 0.0141,
+      "step": 99
+    },
+    {
+      "epoch": 3.57,
+      "learning_rate": 0.0002,
+      "loss": 0.01,
+      "step": 100
+    },
+    {
+      "epoch": 3.61,
+      "learning_rate": 0.0002,
+      "loss": 0.0183,
+      "step": 101
+    },
+    {
+      "epoch": 3.64,
+      "learning_rate": 0.0002,
+      "loss": 0.007,
+      "step": 102
+    },
+    {
+      "epoch": 3.68,
+      "learning_rate": 0.0002,
+      "loss": 0.0169,
+      "step": 103
+    },
+    {
+      "epoch": 3.71,
+      "learning_rate": 0.0002,
+      "loss": 0.0127,
+      "step": 104
+    },
+    {
+      "epoch": 3.75,
+      "learning_rate": 0.0002,
+      "loss": 0.0169,
+      "step": 105
+    },
+    {
+      "epoch": 3.79,
+      "learning_rate": 0.0002,
+      "loss": 0.0137,
+      "step": 106
+    },
+    {
+      "epoch": 3.82,
+      "learning_rate": 0.0002,
+      "loss": 0.0072,
+      "step": 107
+    },
+    {
+      "epoch": 3.86,
+      "learning_rate": 0.0002,
+      "loss": 0.0094,
+      "step": 108
+    },
+    {
+      "epoch": 3.89,
+      "learning_rate": 0.0002,
+      "loss": 0.0084,
+      "step": 109
+    },
+    {
+      "epoch": 3.93,
+      "learning_rate": 0.0002,
+      "loss": 0.0184,
+      "step": 110
+    },
+    {
+      "epoch": 3.96,
+      "learning_rate": 0.0002,
+      "loss": 0.0049,
+      "step": 111
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.0002,
+      "loss": 0.0049,
+      "step": 112
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.008617790415883064,
+      "eval_runtime": 55.0998,
+      "eval_samples_per_second": 15.735,
+      "eval_steps_per_second": 0.508,
+      "step": 112
+    },
+    {
+      "epoch": 4.04,
+      "learning_rate": 0.0002,
+      "loss": 0.0063,
+      "step": 113
+    },
+    {
+      "epoch": 4.07,
+      "learning_rate": 0.0002,
+      "loss": 0.0056,
+      "step": 114
+    },
+    {
+      "epoch": 4.11,
+      "learning_rate": 0.0002,
+      "loss": 0.0066,
+      "step": 115
+    },
+    {
+      "epoch": 4.14,
+      "learning_rate": 0.0002,
+      "loss": 0.0047,
+      "step": 116
+    },
+    {
+      "epoch": 4.18,
+      "learning_rate": 0.0002,
+      "loss": 0.0066,
+      "step": 117
+    },
+    {
+      "epoch": 4.21,
+      "learning_rate": 0.0002,
+      "loss": 0.0058,
+      "step": 118
+    },
+    {
+      "epoch": 4.25,
+      "learning_rate": 0.0002,
+      "loss": 0.0125,
+      "step": 119
+    },
+    {
+      "epoch": 4.29,
+      "learning_rate": 0.0002,
+      "loss": 0.0081,
+      "step": 120
+    },
+    {
+      "epoch": 4.32,
+      "learning_rate": 0.0002,
+      "loss": 0.0074,
+      "step": 121
+    },
+    {
+      "epoch": 4.36,
+      "learning_rate": 0.0002,
+      "loss": 0.0057,
+      "step": 122
+    },
+    {
+      "epoch": 4.39,
+      "learning_rate": 0.0002,
+      "loss": 0.0069,
+      "step": 123
+    },
+    {
+      "epoch": 4.43,
+      "learning_rate": 0.0002,
+      "loss": 0.0032,
+      "step": 124
+    },
+    {
+      "epoch": 4.46,
+      "learning_rate": 0.0002,
+      "loss": 0.003,
+      "step": 125
+    },
+    {
+      "epoch": 4.5,
+      "learning_rate": 0.0002,
+      "loss": 0.0067,
+      "step": 126
+    },
+    {
+      "epoch": 4.54,
+      "learning_rate": 0.0002,
+      "loss": 0.006,
+      "step": 127
+    },
+    {
+      "epoch": 4.57,
+      "learning_rate": 0.0002,
+      "loss": 0.0047,
+      "step": 128
+    },
+    {
+      "epoch": 4.61,
+      "learning_rate": 0.0002,
+      "loss": 0.0049,
+      "step": 129
+    },
+    {
+      "epoch": 4.64,
+      "learning_rate": 0.0002,
+      "loss": 0.0024,
+      "step": 130
+    },
+    {
+      "epoch": 4.68,
+      "learning_rate": 0.0002,
+      "loss": 0.0056,
+      "step": 131
+    },
+    {
+      "epoch": 4.71,
+      "learning_rate": 0.0002,
+      "loss": 0.0033,
+      "step": 132
+    },
+    {
+      "epoch": 4.75,
+      "learning_rate": 0.0002,
+      "loss": 0.0057,
+      "step": 133
+    },
+    {
+      "epoch": 4.79,
+      "learning_rate": 0.0002,
+      "loss": 0.0024,
+      "step": 134
+    },
+    {
+      "epoch": 4.82,
+      "learning_rate": 0.0002,
+      "loss": 0.0036,
+      "step": 135
+    },
+    {
+      "epoch": 4.86,
+      "learning_rate": 0.0002,
+      "loss": 0.0041,
+      "step": 136
+    },
+    {
+      "epoch": 4.89,
+      "learning_rate": 0.0002,
+      "loss": 0.0029,
+      "step": 137
+    },
+    {
+      "epoch": 4.93,
+      "learning_rate": 0.0002,
+      "loss": 0.0046,
+      "step": 138
+    },
+    {
+      "epoch": 4.96,
+      "learning_rate": 0.0002,
+      "loss": 0.0024,
+      "step": 139
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0002,
+      "loss": 0.0024,
+      "step": 140
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.003972133155912161,
+      "eval_runtime": 55.133,
+      "eval_samples_per_second": 15.726,
+      "eval_steps_per_second": 0.508,
+      "step": 140
+    },
+    {
+      "epoch": 5.04,
+      "learning_rate": 0.0002,
+      "loss": 0.0024,
+      "step": 141
+    },
+    {
+      "epoch": 5.07,
+      "learning_rate": 0.0002,
+      "loss": 0.0033,
+      "step": 142
+    },
+    {
+      "epoch": 5.11,
+      "learning_rate": 0.0002,
+      "loss": 0.0019,
+      "step": 143
+    },
+    {
+      "epoch": 5.14,
+      "learning_rate": 0.0002,
+      "loss": 0.0033,
+      "step": 144
+    },
+    {
+      "epoch": 5.18,
+      "learning_rate": 0.0002,
+      "loss": 0.0036,
+      "step": 145
+    },
+    {
+      "epoch": 5.21,
+      "learning_rate": 0.0002,
+      "loss": 0.0044,
+      "step": 146
+    },
+    {
+      "epoch": 5.25,
+      "learning_rate": 0.0002,
+      "loss": 0.0038,
+      "step": 147
+    },
+    {
+      "epoch": 5.29,
+      "learning_rate": 0.0002,
+      "loss": 0.0042,
+      "step": 148
+    },
+    {
+      "epoch": 5.32,
+      "learning_rate": 0.0002,
+      "loss": 0.0021,
+      "step": 149
+    },
+    {
+      "epoch": 5.36,
+      "learning_rate": 0.0002,
+      "loss": 0.002,
+      "step": 150
+    },
+    {
+      "epoch": 5.39,
+      "learning_rate": 0.0002,
+      "loss": 0.0022,
+      "step": 151
+    },
+    {
+      "epoch": 5.43,
+      "learning_rate": 0.0002,
+      "loss": 0.0045,
+      "step": 152
+    },
+    {
+      "epoch": 5.46,
+      "learning_rate": 0.0002,
+      "loss": 0.0018,
+      "step": 153
+    },
+    {
+      "epoch": 5.5,
+      "learning_rate": 0.0002,
+      "loss": 0.0093,
+      "step": 154
+    },
+    {
+      "epoch": 5.54,
+      "learning_rate": 0.0002,
+      "loss": 0.002,
+      "step": 155
+    },
+    {
+      "epoch": 5.57,
+      "learning_rate": 0.0002,
+      "loss": 0.0026,
+      "step": 156
+    },
+    {
+      "epoch": 5.61,
+      "learning_rate": 0.0002,
+      "loss": 0.0025,
+      "step": 157
+    },
+    {
+      "epoch": 5.64,
+      "learning_rate": 0.0002,
+      "loss": 0.0028,
+      "step": 158
+    },
+    {
+      "epoch": 5.68,
+      "learning_rate": 0.0002,
+      "loss": 0.0031,
+      "step": 159
+    },
+    {
+      "epoch": 5.71,
+      "learning_rate": 0.0002,
+      "loss": 0.0078,
+      "step": 160
+    },
+    {
+      "epoch": 5.75,
+      "learning_rate": 0.0002,
+      "loss": 0.0031,
+      "step": 161
+    },
+    {
+      "epoch": 5.79,
+      "learning_rate": 0.0002,
+      "loss": 0.002,
+      "step": 162
+    },
+    {
+      "epoch": 5.82,
+      "learning_rate": 0.0002,
+      "loss": 0.0027,
+      "step": 163
+    },
+    {
+      "epoch": 5.86,
+      "learning_rate": 0.0002,
+      "loss": 0.0041,
+      "step": 164
+    },
+    {
+      "epoch": 5.89,
+      "learning_rate": 0.0002,
+      "loss": 0.0047,
+      "step": 165
+    },
+    {
+      "epoch": 5.93,
+      "learning_rate": 0.0002,
+      "loss": 0.0064,
+      "step": 166
+    },
+    {
+      "epoch": 5.96,
+      "learning_rate": 0.0002,
+      "loss": 0.0053,
+      "step": 167
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 0.0002,
+      "loss": 0.0027,
+      "step": 168
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.0036148722283542156,
+      "eval_runtime": 55.1196,
+      "eval_samples_per_second": 15.729,
+      "eval_steps_per_second": 0.508,
+      "step": 168
+    },
+    {
+      "epoch": 6.04,
+      "learning_rate": 0.0002,
+      "loss": 0.0021,
+      "step": 169
+    },
+    {
+      "epoch": 6.07,
+      "learning_rate": 0.0002,
+      "loss": 0.0049,
+      "step": 170
+    },
+    {
+      "epoch": 6.11,
+      "learning_rate": 0.0002,
+      "loss": 0.003,
+      "step": 171
+    },
+    {
+      "epoch": 6.14,
+      "learning_rate": 0.0002,
+      "loss": 0.008,
+      "step": 172
+    },
+    {
+      "epoch": 6.18,
+      "learning_rate": 0.0002,
+      "loss": 0.0048,
+      "step": 173
+    },
+    {
+      "epoch": 6.21,
+      "learning_rate": 0.0002,
+      "loss": 0.0033,
+      "step": 174
+    },
+    {
+      "epoch": 6.25,
+      "learning_rate": 0.0002,
+      "loss": 0.0049,
+      "step": 175
+    },
+    {
+      "epoch": 6.29,
+      "learning_rate": 0.0002,
+      "loss": 0.0043,
+      "step": 176
+    },
+    {
+      "epoch": 6.32,
+      "learning_rate": 0.0002,
+      "loss": 0.0072,
+      "step": 177
+    },
+    {
+      "epoch": 6.36,
+      "learning_rate": 0.0002,
+      "loss": 0.0048,
+      "step": 178
+    },
+    {
+      "epoch": 6.39,
+      "learning_rate": 0.0002,
+      "loss": 0.0027,
+      "step": 179
+    },
+    {
+      "epoch": 6.43,
+      "learning_rate": 0.0002,
+      "loss": 0.0013,
+      "step": 180
+    },
+    {
+      "epoch": 6.46,
+      "learning_rate": 0.0002,
+      "loss": 0.0017,
+      "step": 181
+    },
+    {
+      "epoch": 6.5,
+      "learning_rate": 0.0002,
+      "loss": 0.0029,
+      "step": 182
+    },
+    {
+      "epoch": 6.54,
+      "learning_rate": 0.0002,
+      "loss": 0.0055,
+      "step": 183
+    },
+    {
+      "epoch": 6.57,
+      "learning_rate": 0.0002,
+      "loss": 0.0058,
+      "step": 184
+    },
+    {
+      "epoch": 6.61,
+      "learning_rate": 0.0002,
+      "loss": 0.0032,
+      "step": 185
+    },
+    {
+      "epoch": 6.64,
+      "learning_rate": 0.0002,
+      "loss": 0.0022,
+      "step": 186
+    },
+    {
+      "epoch": 6.68,
+      "learning_rate": 0.0002,
+      "loss": 0.0024,
+      "step": 187
+    },
+    {
+      "epoch": 6.71,
+      "learning_rate": 0.0002,
+      "loss": 0.0013,
+      "step": 188
+    },
+    {
+      "epoch": 6.75,
+      "learning_rate": 0.0002,
+      "loss": 0.003,
+      "step": 189
+    },
+    {
+      "epoch": 6.79,
+      "learning_rate": 0.0002,
+      "loss": 0.0018,
+      "step": 190
+    },
+    {
+      "epoch": 6.82,
+      "learning_rate": 0.0002,
+      "loss": 0.0016,
+      "step": 191
+    },
+    {
+      "epoch": 6.86,
+      "learning_rate": 0.0002,
+      "loss": 0.0047,
+      "step": 192
+    },
+    {
+      "epoch": 6.89,
+      "learning_rate": 0.0002,
+      "loss": 0.0036,
+      "step": 193
+    },
+    {
+      "epoch": 6.93,
+      "learning_rate": 0.0002,
+      "loss": 0.0046,
+      "step": 194
+    },
+    {
+      "epoch": 6.96,
+      "learning_rate": 0.0002,
+      "loss": 0.0011,
+      "step": 195
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 0.0002,
+      "loss": 0.0013,
+      "step": 196
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.0022535445168614388,
+      "eval_runtime": 55.0753,
+      "eval_samples_per_second": 15.742,
+      "eval_steps_per_second": 0.508,
+      "step": 196
+    },
+    {
+      "epoch": 7.04,
+      "learning_rate": 0.0002,
+      "loss": 0.0006,
+      "step": 197
+    },
+    {
+      "epoch": 7.07,
+      "learning_rate": 0.0002,
+      "loss": 0.0027,
+      "step": 198
+    },
+    {
+      "epoch": 7.11,
+      "learning_rate": 0.0002,
+      "loss": 0.0016,
+      "step": 199
+    },
+    {
+      "epoch": 7.14,
+      "learning_rate": 0.0002,
+      "loss": 0.0051,
+      "step": 200
+    },
+    {
+      "epoch": 7.18,
+      "learning_rate": 0.0002,
+      "loss": 0.0051,
+      "step": 201
+    },
+    {
+      "epoch": 7.21,
+      "learning_rate": 0.0002,
+      "loss": 0.0015,
+      "step": 202
+    },
+    {
+      "epoch": 7.25,
+      "learning_rate": 0.0002,
+      "loss": 0.0014,
+      "step": 203
+    },
+    {
+      "epoch": 7.29,
+      "learning_rate": 0.0002,
+      "loss": 0.003,
+      "step": 204
+    },
+    {
+      "epoch": 7.32,
+      "learning_rate": 0.0002,
+      "loss": 0.001,
+      "step": 205
+    },
+    {
+      "epoch": 7.36,
+      "learning_rate": 0.0002,
+      "loss": 0.0034,
+      "step": 206
+    },
+    {
+      "epoch": 7.39,
+      "learning_rate": 0.0002,
+      "loss": 0.0024,
+      "step": 207
+    },
+    {
+      "epoch": 7.43,
+      "learning_rate": 0.0002,
+      "loss": 0.0086,
+      "step": 208
+    },
+    {
+      "epoch": 7.46,
+      "learning_rate": 0.0002,
+      "loss": 0.0037,
+      "step": 209
+    },
+    {
+      "epoch": 7.5,
+      "learning_rate": 0.0002,
+      "loss": 0.0017,
+      "step": 210
+    },
+    {
+      "epoch": 7.54,
+      "learning_rate": 0.0002,
+      "loss": 0.0037,
+      "step": 211
+    },
+    {
+      "epoch": 7.57,
+      "learning_rate": 0.0002,
+      "loss": 0.0052,
+      "step": 212
+    },
+    {
+      "epoch": 7.61,
+      "learning_rate": 0.0002,
+      "loss": 0.0021,
+      "step": 213
+    },
+    {
+      "epoch": 7.64,
+      "learning_rate": 0.0002,
+      "loss": 0.0029,
+      "step": 214
+    },
+    {
+      "epoch": 7.68,
+      "learning_rate": 0.0002,
+      "loss": 0.0021,
+      "step": 215
+    },
+    {
+      "epoch": 7.71,
+      "learning_rate": 0.0002,
+      "loss": 0.0034,
+      "step": 216
+    },
+    {
+      "epoch": 7.75,
+      "learning_rate": 0.0002,
+      "loss": 0.0068,
+      "step": 217
+    },
+    {
+      "epoch": 7.79,
+      "learning_rate": 0.0002,
+      "loss": 0.0065,
+      "step": 218
+    },
+    {
+      "epoch": 7.82,
+      "learning_rate": 0.0002,
+      "loss": 0.0057,
+      "step": 219
+    },
+    {
+      "epoch": 7.86,
+      "learning_rate": 0.0002,
+      "loss": 0.0027,
+      "step": 220
+    },
+    {
+      "epoch": 7.89,
+      "learning_rate": 0.0002,
+      "loss": 0.0036,
+      "step": 221
+    },
+    {
+      "epoch": 7.93,
+      "learning_rate": 0.0002,
+      "loss": 0.0061,
+      "step": 222
+    },
+    {
+      "epoch": 7.96,
+      "learning_rate": 0.0002,
+      "loss": 0.003,
+      "step": 223
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 0.0002,
+      "loss": 0.0046,
+      "step": 224
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.003041429677978158,
+      "eval_runtime": 55.3071,
+      "eval_samples_per_second": 15.676,
+      "eval_steps_per_second": 0.506,
+      "step": 224
+    },
+    {
+      "epoch": 8.04,
+      "learning_rate": 0.0002,
+      "loss": 0.0024,
+      "step": 225
+    },
+    {
+      "epoch": 8.07,
+      "learning_rate": 0.0002,
+      "loss": 0.004,
+      "step": 226
+    },
+    {
+      "epoch": 8.11,
+      "learning_rate": 0.0002,
+      "loss": 0.0026,
+      "step": 227
+    },
+    {
+      "epoch": 8.14,
+      "learning_rate": 0.0002,
+      "loss": 0.0033,
+      "step": 228
+    },
+    {
+      "epoch": 8.18,
+      "learning_rate": 0.0002,
+      "loss": 0.004,
+      "step": 229
+    },
+    {
+      "epoch": 8.21,
+      "learning_rate": 0.0002,
+      "loss": 0.0014,
+      "step": 230
+    },
+    {
+      "epoch": 8.25,
+      "learning_rate": 0.0002,
+      "loss": 0.0052,
+      "step": 231
+    },
+    {
+      "epoch": 8.29,
+      "learning_rate": 0.0002,
+      "loss": 0.0025,
+      "step": 232
+    },
+    {
+      "epoch": 8.32,
+      "learning_rate": 0.0002,
+      "loss": 0.0028,
+      "step": 233
+    },
+    {
+      "epoch": 8.36,
+      "learning_rate": 0.0002,
+      "loss": 0.0051,
+      "step": 234
+    },
+    {
+      "epoch": 8.39,
+      "learning_rate": 0.0002,
+      "loss": 0.0016,
+      "step": 235
+    },
+    {
+      "epoch": 8.43,
+      "learning_rate": 0.0002,
+      "loss": 0.0015,
+      "step": 236
+    },
+    {
+      "epoch": 8.46,
+      "learning_rate": 0.0002,
+      "loss": 0.0024,
+      "step": 237
+    },
+    {
+      "epoch": 8.5,
+      "learning_rate": 0.0002,
+      "loss": 0.0018,
+      "step": 238
+    },
+    {
+      "epoch": 8.54,
+      "learning_rate": 0.0002,
+      "loss": 0.0036,
+      "step": 239
+    },
+    {
+      "epoch": 8.57,
+      "learning_rate": 0.0002,
+      "loss": 0.0053,
+      "step": 240
+    },
+    {
+      "epoch": 8.61,
+      "learning_rate": 0.0002,
+      "loss": 0.0026,
+      "step": 241
+    },
+    {
+      "epoch": 8.64,
+      "learning_rate": 0.0002,
+      "loss": 0.0041,
+      "step": 242
+    },
+    {
+      "epoch": 8.68,
+      "learning_rate": 0.0002,
+      "loss": 0.0022,
+      "step": 243
+    },
+    {
+      "epoch": 8.71,
+      "learning_rate": 0.0002,
+      "loss": 0.0067,
+      "step": 244
+    },
+    {
+      "epoch": 8.75,
+      "learning_rate": 0.0002,
+      "loss": 0.0017,
+      "step": 245
+    },
+    {
+      "epoch": 8.79,
+      "learning_rate": 0.0002,
+      "loss": 0.0031,
+      "step": 246
+    },
+    {
+      "epoch": 8.82,
+      "learning_rate": 0.0002,
+      "loss": 0.0034,
+      "step": 247
+    },
+    {
+      "epoch": 8.86,
+      "learning_rate": 0.0002,
+      "loss": 0.0012,
+      "step": 248
+    },
+    {
+      "epoch": 8.89,
+      "learning_rate": 0.0002,
+      "loss": 0.0061,
+      "step": 249
+    },
+    {
+      "epoch": 8.93,
+      "learning_rate": 0.0002,
+      "loss": 0.0043,
+      "step": 250
+    },
+    {
+      "epoch": 8.96,
+      "learning_rate": 0.0002,
+      "loss": 0.0107,
+      "step": 251
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 0.0002,
+      "loss": 0.0052,
+      "step": 252
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 0.001832196139730513,
+      "eval_runtime": 55.1141,
+      "eval_samples_per_second": 15.731,
+      "eval_steps_per_second": 0.508,
+      "step": 252
+    },
+    {
+      "epoch": 9.04,
+      "learning_rate": 0.0002,
+      "loss": 0.0006,
+      "step": 253
+    },
+    {
+      "epoch": 9.07,
+      "learning_rate": 0.0002,
+      "loss": 0.0046,
+      "step": 254
+    },
+    {
+      "epoch": 9.11,
+      "learning_rate": 0.0002,
+      "loss": 0.0034,
+      "step": 255
+    },
+    {
+      "epoch": 9.14,
+      "learning_rate": 0.0002,
+      "loss": 0.0008,
+      "step": 256
+    },
+    {
+      "epoch": 9.18,
+      "learning_rate": 0.0002,
+      "loss": 0.0031,
+      "step": 257
+    },
+    {
+      "epoch": 9.21,
+      "learning_rate": 0.0002,
+      "loss": 0.0013,
+      "step": 258
+    },
+    {
+      "epoch": 9.25,
+      "learning_rate": 0.0002,
+      "loss": 0.0053,
+      "step": 259
+    },
+    {
+      "epoch": 9.29,
+      "learning_rate": 0.0002,
+      "loss": 0.0053,
+      "step": 260
+    },
+    {
+      "epoch": 9.32,
+      "learning_rate": 0.0002,
+      "loss": 0.0035,
+      "step": 261
+    },
+    {
+      "epoch": 9.36,
+      "learning_rate": 0.0002,
+      "loss": 0.0029,
+      "step": 262
+    },
+    {
+      "epoch": 9.39,
+      "learning_rate": 0.0002,
+      "loss": 0.0071,
+      "step": 263
+    },
+    {
+      "epoch": 9.43,
+      "learning_rate": 0.0002,
+      "loss": 0.0015,
+      "step": 264
+    },
+    {
+      "epoch": 9.46,
+      "learning_rate": 0.0002,
+      "loss": 0.0011,
+      "step": 265
+    },
+    {
+      "epoch": 9.5,
+      "learning_rate": 0.0002,
+      "loss": 0.0014,
+      "step": 266
+    },
+    {
+      "epoch": 9.54,
+      "learning_rate": 0.0002,
+      "loss": 0.0025,
+      "step": 267
+    },
+    {
+      "epoch": 9.57,
+      "learning_rate": 0.0002,
+      "loss": 0.0034,
+      "step": 268
+    },
+    {
+      "epoch": 9.61,
+      "learning_rate": 0.0002,
+      "loss": 0.0044,
+      "step": 269
+    },
+    {
+      "epoch": 9.64,
+      "learning_rate": 0.0002,
+      "loss": 0.0014,
+      "step": 270
+    },
+    {
+      "epoch": 9.68,
+      "learning_rate": 0.0002,
+      "loss": 0.0031,
+      "step": 271
+    },
+    {
+      "epoch": 9.71,
+      "learning_rate": 0.0002,
+      "loss": 0.0035,
+      "step": 272
+    },
+    {
+      "epoch": 9.75,
+      "learning_rate": 0.0002,
+      "loss": 0.0016,
+      "step": 273
+    },
+    {
+      "epoch": 9.79,
+      "learning_rate": 0.0002,
+      "loss": 0.0046,
+      "step": 274
+    },
+    {
+      "epoch": 9.82,
+      "learning_rate": 0.0002,
+      "loss": 0.0049,
+      "step": 275
+    },
+    {
+      "epoch": 9.86,
+      "learning_rate": 0.0002,
+      "loss": 0.0048,
+      "step": 276
+    },
+    {
+      "epoch": 9.89,
+      "learning_rate": 0.0002,
+      "loss": 0.0021,
+      "step": 277
+    },
+    {
+      "epoch": 9.93,
+      "learning_rate": 0.0002,
+      "loss": 0.0058,
+      "step": 278
+    },
+    {
+      "epoch": 9.96,
+      "learning_rate": 0.0002,
+      "loss": 0.0015,
+      "step": 279
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0002,
+      "loss": 0.0021,
+      "step": 280
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 0.0019397155847400427,
+      "eval_runtime": 55.177,
+      "eval_samples_per_second": 15.713,
+      "eval_steps_per_second": 0.507,
+      "step": 280
+    },
+    {
+      "epoch": 10.0,
+      "step": 280,
+      "total_flos": 8.284116092306063e+17,
+      "train_loss": 0.09758472924399289,
+      "train_runtime": 3375.4555,
+      "train_samples_per_second": 2.569,
+      "train_steps_per_second": 0.083
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 280,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 50000,
+  "total_flos": 8.284116092306063e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68e5def49be81ce98744b69e9706019b126bc09f3d46c48bde14fdc51231e864
+oid sha256:ecfec25df92e2fa743e00b5933b37cc854d2d087fcb1327cb7e9c80ebff881a8
 size 6776