Upload folder using huggingface_hub

9_128_e3_3e-5/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "ibm-granite/granite-3.3-8b-instruct",
+  "bias": "none",
+  "corda_config": null,
+  "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": 256,
+  "lora_bias": false,
+  "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": [
+    "v_proj",
+    "up_proj",
+    "down_proj",
+    "o_proj",
+    "k_proj",
+    "gate_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

9_128_e3_3e-5/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a7d4b109e4e9d36739e78f5757eeaf34fd63d04c5f3673d027bd8946e15b25d
+size 791751704

9_128_e3_3e-5/added_tokens.json

@@ -0,0 +1,9 @@
+{
+  "<|end_of_cite|>": 49156,
+  "<|end_of_plugin|>": 49158,
+  "<|end_of_role|>": 49153,
+  "<|start_of_cite|>": 49155,
+  "<|start_of_plugin|>": 49157,
+  "<|start_of_role|>": 49152,
+  "<|tool_call|>": 49154
+}

9_128_e3_3e-5/all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.9997709539779543e+18,
+    "train_loss": 0.49729131393091025,
+    "train_runtime": 968.4082,
+    "train_samples": 14586,
+    "train_samples_per_second": 45.185,
+    "train_steps_per_second": 1.413
+}

9_128_e3_3e-5/chat_template.jinja

@@ -0,0 +1,62 @@
+{# Alias tools -> available_tools #}
+{%- if tools and not available_tools -%}
+    {%- set available_tools = tools -%}
+{%- endif -%}
+{%- if messages[0]['role'] == 'system' %}
+     {%- set system_message = messages[0]['content'] %}
+     {%- set loop_messages = messages[1:] %}
+ {%- else %}
+     {%- set system_message = "Knowledge Cutoff Date: April 2024.
+Today's Date: " + strftime_now('%B %d, %Y') + ".
+You are Granite, developed by IBM." %}
+     {%- if available_tools and documents %}
+         {%- set system_message = system_message + " You are a helpful assistant with access to the following tools. When a tool is required to answer the user's query, respond only with <|tool_call|> followed by a JSON list of tools used. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request.
+Write the response to the user's input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data." %}
+     {%- elif available_tools %}
+         {%- set system_message = system_message + " You are a helpful assistant with access to the following tools. When a tool is required to answer the user's query, respond only with <|tool_call|> followed by a JSON list of tools used. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request." %}
+     {%- elif documents %}
+         {%- set system_message = system_message + " Write the response to the user's input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data." %}
+    {%- elif thinking %}
+    {%- set system_message = system_message + " You are a helpful AI assistant.
+Respond to every user query in a comprehensive and detailed way. You can write down your thoughts and reasoning process before responding. In the thought process, engage in a comprehensive cycle of analysis, summarization, exploration, reassessment, reflection, backtracing, and iteration to develop well-considered thinking process. In the response section, based on various attempts, explorations, and reflections from the thoughts section, systematically present the final solution that you deem correct. The response should summarize the thought process. Write your thoughts between <think></think> and write your response between <response></response> for each user query." %}
+     {%- else %}
+         {%- set system_message = system_message + " You are a helpful AI assistant." %}
+     {%- endif %}
+     {%- if 'citations' in controls and documents %}
+         {%- set system_message = system_message + '
+Use the symbols <|start_of_cite|> and <|end_of_cite|> to indicate when a fact comes from a document in the search result, e.g <|start_of_cite|> {document_id: 1}my fact <|end_of_cite|> for a fact from document 1. Afterwards, list all the citations with their corresponding documents in an ordered list.' %}
+     {%- endif %}
+     {%- if 'hallucinations' in controls and documents %}
+         {%- set system_message = system_message + '
+Finally, after the response is written, include a numbered list of sentences from the response with a corresponding risk value that are hallucinated and not based in the documents.' %}
+     {%- endif %}
+     {%- set loop_messages = messages %}
+ {%- endif %}
+ {{- '<|start_of_role|>system<|end_of_role|>' + system_message + '<|end_of_text|>
+' }}
+ {%- if available_tools %}
+     {{- '<|start_of_role|>available_tools<|end_of_role|>' }}
+     {{- available_tools | tojson(indent=4) }}
+     {{- '<|end_of_text|>
+' }}
+ {%- endif %}
+ {%- if documents %}
+     {%- for document in documents %}
+         {{- '<|start_of_role|>document {"document_id": "' + document['doc_id'] | string + '"}<|end_of_role|>
+' }}
+         {{- document['text'] }}
+         {{- '<|end_of_text|>
+' }}
+              {%- endfor %}
+ {%- endif %}
+ {%- for message in loop_messages %}
+     {{- '<|start_of_role|>' + message['role'] + '<|end_of_role|>' + message['content'] + '<|end_of_text|>
+' }}
+     {%- if loop.last and add_generation_prompt %}
+         {{- '<|start_of_role|>assistant' }}
+             {%- if controls %}
+                 {{- ' ' + controls | tojson()}}
+             {%- endif %}
+         {{- '<|end_of_role|>' }}
+     {%- endif %}
+ {%- endfor %}

9_128_e3_3e-5/config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "GraniteForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attention_multiplier": 0.0078125,
+  "bos_token_id": 0,
+  "embedding_multiplier": 12.0,
+  "eos_token_id": 0,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12800,
+  "logits_scaling": 16.0,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "granite",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "residual_multiplier": 0.22,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.4",
+  "use_cache": true,
+  "vocab_size": 49159
+}

9_128_e3_3e-5/special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "additional_special_tokens": [
+    "<|start_of_role|>",
+    "<|end_of_role|>",
+    "<|tool_call|>",
+    "<|start_of_cite|>",
+    "<|end_of_cite|>",
+    "<|start_of_plugin|>",
+    "<|end_of_plugin|>"
+  ],
+  "bos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_plugin|>",
+  "unk_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

9_128_e3_3e-5/tokenizer_config.json

@@ -0,0 +1,234 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<fim_prefix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<fim_middle>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<fim_suffix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<fim_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<commit_before>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<commit_msg>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "<commit_after>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49152": {
+      "content": "<|start_of_role|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49153": {
+      "content": "<|end_of_role|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49154": {
+      "content": "<|tool_call|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49155": {
+      "content": "<|start_of_cite|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49156": {
+      "content": "<|end_of_cite|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49157": {
+      "content": "<|start_of_plugin|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49158": {
+      "content": "<|end_of_plugin|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|start_of_role|>",
+    "<|end_of_role|>",
+    "<|tool_call|>",
+    "<|start_of_cite|>",
+    "<|end_of_cite|>",
+    "<|start_of_plugin|>",
+    "<|end_of_plugin|>"
+  ],
+  "bos_token": "<|end_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 8192,
+  "pad_token": "<|end_of_plugin|>",
+  "padding_side": "left",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|end_of_text|>",
+  "vocab_size": 49152
+}

9_128_e3_3e-5/train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.9997709539779543e+18,
+    "train_loss": 0.49729131393091025,
+    "train_runtime": 968.4082,
+    "train_samples": 14586,
+    "train_samples_per_second": 45.185,
+    "train_steps_per_second": 1.413
+}

9_128_e3_3e-5/trainer_state.json

@@ -0,0 +1,1954 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1368,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.010964912280701754,
+      "grad_norm": 3.24426531791687,
+      "learning_rate": 1.7391304347826088e-06,
+      "loss": 1.4932,
+      "step": 5
+    },
+    {
+      "epoch": 0.021929824561403508,
+      "grad_norm": 2.1502578258514404,
+      "learning_rate": 3.913043478260869e-06,
+      "loss": 1.4498,
+      "step": 10
+    },
+    {
+      "epoch": 0.03289473684210526,
+      "grad_norm": 1.2595070600509644,
+      "learning_rate": 6.086956521739131e-06,
+      "loss": 1.3814,
+      "step": 15
+    },
+    {
+      "epoch": 0.043859649122807015,
+      "grad_norm": 0.7001549005508423,
+      "learning_rate": 8.260869565217392e-06,
+      "loss": 1.3215,
+      "step": 20
+    },
+    {
+      "epoch": 0.05482456140350877,
+      "grad_norm": 0.4792288839817047,
+      "learning_rate": 1.0434782608695653e-05,
+      "loss": 1.2688,
+      "step": 25
+    },
+    {
+      "epoch": 0.06578947368421052,
+      "grad_norm": 0.3867693841457367,
+      "learning_rate": 1.2608695652173912e-05,
+      "loss": 1.2524,
+      "step": 30
+    },
+    {
+      "epoch": 0.07675438596491228,
+      "grad_norm": 0.4167414605617523,
+      "learning_rate": 1.4782608695652174e-05,
+      "loss": 1.2529,
+      "step": 35
+    },
+    {
+      "epoch": 0.08771929824561403,
+      "grad_norm": 0.438427597284317,
+      "learning_rate": 1.6956521739130433e-05,
+      "loss": 1.2756,
+      "step": 40
+    },
+    {
+      "epoch": 0.09868421052631579,
+      "grad_norm": 0.40318217873573303,
+      "learning_rate": 1.9130434782608694e-05,
+      "loss": 1.1826,
+      "step": 45
+    },
+    {
+      "epoch": 0.10964912280701754,
+      "grad_norm": 0.49343574047088623,
+      "learning_rate": 2.1304347826086958e-05,
+      "loss": 1.1891,
+      "step": 50
+    },
+    {
+      "epoch": 0.1206140350877193,
+      "grad_norm": 0.37749776244163513,
+      "learning_rate": 2.347826086956522e-05,
+      "loss": 1.2024,
+      "step": 55
+    },
+    {
+      "epoch": 0.13157894736842105,
+      "grad_norm": 0.3650110960006714,
+      "learning_rate": 2.565217391304348e-05,
+      "loss": 1.195,
+      "step": 60
+    },
+    {
+      "epoch": 0.1425438596491228,
+      "grad_norm": 0.5029582381248474,
+      "learning_rate": 2.782608695652174e-05,
+      "loss": 1.1836,
+      "step": 65
+    },
+    {
+      "epoch": 0.15350877192982457,
+      "grad_norm": 0.36065730452537537,
+      "learning_rate": 3e-05,
+      "loss": 1.1111,
+      "step": 70
+    },
+    {
+      "epoch": 0.16447368421052633,
+      "grad_norm": 0.42705437541007996,
+      "learning_rate": 2.999890332631331e-05,
+      "loss": 1.1878,
+      "step": 75
+    },
+    {
+      "epoch": 0.17543859649122806,
+      "grad_norm": 0.42906564474105835,
+      "learning_rate": 2.999561346561234e-05,
+      "loss": 1.1339,
+      "step": 80
+    },
+    {
+      "epoch": 0.18640350877192982,
+      "grad_norm": 0.3949109613895416,
+      "learning_rate": 2.9990130898950905e-05,
+      "loss": 1.0679,
+      "step": 85
+    },
+    {
+      "epoch": 0.19736842105263158,
+      "grad_norm": 0.46161895990371704,
+      "learning_rate": 2.9982456428007215e-05,
+      "loss": 1.1259,
+      "step": 90
+    },
+    {
+      "epoch": 0.20833333333333334,
+      "grad_norm": 0.472602516412735,
+      "learning_rate": 2.9972591174966656e-05,
+      "loss": 1.0261,
+      "step": 95
+    },
+    {
+      "epoch": 0.21929824561403508,
+      "grad_norm": 0.4412432014942169,
+      "learning_rate": 2.996053658235768e-05,
+      "loss": 1.014,
+      "step": 100
+    },
+    {
+      "epoch": 0.23026315789473684,
+      "grad_norm": 0.41926974058151245,
+      "learning_rate": 2.994629441284089e-05,
+      "loss": 1.0404,
+      "step": 105
+    },
+    {
+      "epoch": 0.2412280701754386,
+      "grad_norm": 0.46813884377479553,
+      "learning_rate": 2.9929866748951292e-05,
+      "loss": 1.0692,
+      "step": 110
+    },
+    {
+      "epoch": 0.25219298245614036,
+      "grad_norm": 0.46364185214042664,
+      "learning_rate": 2.9911255992793788e-05,
+      "loss": 1.0182,
+      "step": 115
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "grad_norm": 0.4689925014972687,
+      "learning_rate": 2.9890464865691914e-05,
+      "loss": 0.9718,
+      "step": 120
+    },
+    {
+      "epoch": 0.2741228070175439,
+      "grad_norm": 0.5339643359184265,
+      "learning_rate": 2.9867496407789935e-05,
+      "loss": 0.9994,
+      "step": 125
+    },
+    {
+      "epoch": 0.2850877192982456,
+      "grad_norm": 0.4611864686012268,
+      "learning_rate": 2.9842353977608316e-05,
+      "loss": 0.9998,
+      "step": 130
+    },
+    {
+      "epoch": 0.29605263157894735,
+      "grad_norm": 0.5565639138221741,
+      "learning_rate": 2.9815041251552594e-05,
+      "loss": 1.0322,
+      "step": 135
+    },
+    {
+      "epoch": 0.30701754385964913,
+      "grad_norm": 0.6286779642105103,
+      "learning_rate": 2.978556222337584e-05,
+      "loss": 1.0102,
+      "step": 140
+    },
+    {
+      "epoch": 0.31798245614035087,
+      "grad_norm": 0.5537821650505066,
+      "learning_rate": 2.9753921203594646e-05,
+      "loss": 0.9312,
+      "step": 145
+    },
+    {
+      "epoch": 0.32894736842105265,
+      "grad_norm": 0.600766658782959,
+      "learning_rate": 2.972012281885886e-05,
+      "loss": 0.9943,
+      "step": 150
+    },
+    {
+      "epoch": 0.3399122807017544,
+      "grad_norm": 0.5232401490211487,
+      "learning_rate": 2.968417201127504e-05,
+      "loss": 0.9611,
+      "step": 155
+    },
+    {
+      "epoch": 0.3508771929824561,
+      "grad_norm": 0.5713093876838684,
+      "learning_rate": 2.9646074037683818e-05,
+      "loss": 0.9487,
+      "step": 160
+    },
+    {
+      "epoch": 0.3618421052631579,
+      "grad_norm": 0.570633590221405,
+      "learning_rate": 2.9605834468891202e-05,
+      "loss": 0.9353,
+      "step": 165
+    },
+    {
+      "epoch": 0.37280701754385964,
+      "grad_norm": 0.6094421744346619,
+      "learning_rate": 2.9563459188854033e-05,
+      "loss": 0.934,
+      "step": 170
+    },
+    {
+      "epoch": 0.38377192982456143,
+      "grad_norm": 0.6095627546310425,
+      "learning_rate": 2.9518954393819587e-05,
+      "loss": 0.9962,
+      "step": 175
+    },
+    {
+      "epoch": 0.39473684210526316,
+      "grad_norm": 0.5608710646629333,
+      "learning_rate": 2.9472326591419556e-05,
+      "loss": 0.901,
+      "step": 180
+    },
+    {
+      "epoch": 0.4057017543859649,
+      "grad_norm": 0.5257043838500977,
+      "learning_rate": 2.9423582599718464e-05,
+      "loss": 0.9036,
+      "step": 185
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 0.7401961088180542,
+      "learning_rate": 2.9372729546216718e-05,
+      "loss": 0.9458,
+      "step": 190
+    },
+    {
+      "epoch": 0.4276315789473684,
+      "grad_norm": 0.6545663475990295,
+      "learning_rate": 2.9319774866808414e-05,
+      "loss": 0.8378,
+      "step": 195
+    },
+    {
+      "epoch": 0.43859649122807015,
+      "grad_norm": 0.7008340358734131,
+      "learning_rate": 2.926472630469401e-05,
+      "loss": 0.8717,
+      "step": 200
+    },
+    {
+      "epoch": 0.44956140350877194,
+      "grad_norm": 0.6411566138267517,
+      "learning_rate": 2.9207591909248117e-05,
+      "loss": 0.8359,
+      "step": 205
+    },
+    {
+      "epoch": 0.4605263157894737,
+      "grad_norm": 0.6739814281463623,
+      "learning_rate": 2.9148380034842482e-05,
+      "loss": 0.8357,
+      "step": 210
+    },
+    {
+      "epoch": 0.47149122807017546,
+      "grad_norm": 0.6448566317558289,
+      "learning_rate": 2.9087099339624388e-05,
+      "loss": 0.8301,
+      "step": 215
+    },
+    {
+      "epoch": 0.4824561403508772,
+      "grad_norm": 0.7340844869613647,
+      "learning_rate": 2.902375878425062e-05,
+      "loss": 0.8351,
+      "step": 220
+    },
+    {
+      "epoch": 0.4934210526315789,
+      "grad_norm": 0.7562801837921143,
+      "learning_rate": 2.8958367630577235e-05,
+      "loss": 0.8045,
+      "step": 225
+    },
+    {
+      "epoch": 0.5043859649122807,
+      "grad_norm": 0.7216281294822693,
+      "learning_rate": 2.8890935440305247e-05,
+      "loss": 0.8075,
+      "step": 230
+    },
+    {
+      "epoch": 0.5153508771929824,
+      "grad_norm": 0.6866181492805481,
+      "learning_rate": 2.882147207358247e-05,
+      "loss": 0.8269,
+      "step": 235
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 0.7293913960456848,
+      "learning_rate": 2.8749987687561775e-05,
+      "loss": 0.8048,
+      "step": 240
+    },
+    {
+      "epoch": 0.5372807017543859,
+      "grad_norm": 0.7445973753929138,
+      "learning_rate": 2.867649273491585e-05,
+      "loss": 0.8416,
+      "step": 245
+    },
+    {
+      "epoch": 0.5482456140350878,
+      "grad_norm": 0.7006743550300598,
+      "learning_rate": 2.8600997962308786e-05,
+      "loss": 0.7928,
+      "step": 250
+    },
+    {
+      "epoch": 0.5592105263157895,
+      "grad_norm": 0.7185664176940918,
+      "learning_rate": 2.852351440882466e-05,
+      "loss": 0.8392,
+      "step": 255
+    },
+    {
+      "epoch": 0.5701754385964912,
+      "grad_norm": 0.7762722373008728,
+      "learning_rate": 2.8444053404353372e-05,
+      "loss": 0.7783,
+      "step": 260
+    },
+    {
+      "epoch": 0.581140350877193,
+      "grad_norm": 0.800458550453186,
+      "learning_rate": 2.8362626567933958e-05,
+      "loss": 0.7992,
+      "step": 265
+    },
+    {
+      "epoch": 0.5921052631578947,
+      "grad_norm": 0.7102886438369751,
+      "learning_rate": 2.8279245806055592e-05,
+      "loss": 0.7493,
+      "step": 270
+    },
+    {
+      "epoch": 0.6030701754385965,
+      "grad_norm": 0.7695249319076538,
+      "learning_rate": 2.8193923310916624e-05,
+      "loss": 0.7832,
+      "step": 275
+    },
+    {
+      "epoch": 0.6140350877192983,
+      "grad_norm": 0.7752018570899963,
+      "learning_rate": 2.8106671558641753e-05,
+      "loss": 0.7556,
+      "step": 280
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 0.7446553111076355,
+      "learning_rate": 2.8017503307457763e-05,
+      "loss": 0.7318,
+      "step": 285
+    },
+    {
+      "epoch": 0.6359649122807017,
+      "grad_norm": 0.8375803232192993,
+      "learning_rate": 2.7926431595827945e-05,
+      "loss": 0.7435,
+      "step": 290
+    },
+    {
+      "epoch": 0.6469298245614035,
+      "grad_norm": 0.7837749719619751,
+      "learning_rate": 2.783346974054561e-05,
+      "loss": 0.7501,
+      "step": 295
+    },
+    {
+      "epoch": 0.6578947368421053,
+      "grad_norm": 0.7391999363899231,
+      "learning_rate": 2.7738631334786825e-05,
+      "loss": 0.721,
+      "step": 300
+    },
+    {
+      "epoch": 0.668859649122807,
+      "grad_norm": 0.7342454791069031,
+      "learning_rate": 2.7641930246122806e-05,
+      "loss": 0.6731,
+      "step": 305
+    },
+    {
+      "epoch": 0.6798245614035088,
+      "grad_norm": 0.8315247297286987,
+      "learning_rate": 2.7543380614492134e-05,
+      "loss": 0.7283,
+      "step": 310
+    },
+    {
+      "epoch": 0.6907894736842105,
+      "grad_norm": 0.8511914610862732,
+      "learning_rate": 2.7442996850133197e-05,
+      "loss": 0.6996,
+      "step": 315
+    },
+    {
+      "epoch": 0.7017543859649122,
+      "grad_norm": 0.8434128761291504,
+      "learning_rate": 2.7340793631477043e-05,
+      "loss": 0.7237,
+      "step": 320
+    },
+    {
+      "epoch": 0.7127192982456141,
+      "grad_norm": 0.9416542053222656,
+      "learning_rate": 2.7236785903001095e-05,
+      "loss": 0.7171,
+      "step": 325
+    },
+    {
+      "epoch": 0.7236842105263158,
+      "grad_norm": 0.856392502784729,
+      "learning_rate": 2.713098887304389e-05,
+      "loss": 0.709,
+      "step": 330
+    },
+    {
+      "epoch": 0.7346491228070176,
+      "grad_norm": 0.7916982173919678,
+      "learning_rate": 2.702341801158127e-05,
+      "loss": 0.723,
+      "step": 335
+    },
+    {
+      "epoch": 0.7456140350877193,
+      "grad_norm": 0.9043979048728943,
+      "learning_rate": 2.6914089047964342e-05,
+      "loss": 0.6858,
+      "step": 340
+    },
+    {
+      "epoch": 0.756578947368421,
+      "grad_norm": 0.8785055875778198,
+      "learning_rate": 2.6803017968619445e-05,
+      "loss": 0.6559,
+      "step": 345
+    },
+    {
+      "epoch": 0.7675438596491229,
+      "grad_norm": 0.8278961777687073,
+      "learning_rate": 2.6690221014710585e-05,
+      "loss": 0.6677,
+      "step": 350
+    },
+    {
+      "epoch": 0.7785087719298246,
+      "grad_norm": 0.8543934226036072,
+      "learning_rate": 2.6575714679764613e-05,
+      "loss": 0.6494,
+      "step": 355
+    },
+    {
+      "epoch": 0.7894736842105263,
+      "grad_norm": 0.9262869358062744,
+      "learning_rate": 2.6459515707259447e-05,
+      "loss": 0.6293,
+      "step": 360
+    },
+    {
+      "epoch": 0.8004385964912281,
+      "grad_norm": 0.8156819939613342,
+      "learning_rate": 2.634164108817584e-05,
+      "loss": 0.6507,
+      "step": 365
+    },
+    {
+      "epoch": 0.8114035087719298,
+      "grad_norm": 0.9190047383308411,
+      "learning_rate": 2.6222108058512866e-05,
+      "loss": 0.6386,
+      "step": 370
+    },
+    {
+      "epoch": 0.8223684210526315,
+      "grad_norm": 0.863660454750061,
+      "learning_rate": 2.610093409676763e-05,
+      "loss": 0.6369,
+      "step": 375
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 1.0574290752410889,
+      "learning_rate": 2.597813692137952e-05,
+      "loss": 0.62,
+      "step": 380
+    },
+    {
+      "epoch": 0.8442982456140351,
+      "grad_norm": 0.8489395976066589,
+      "learning_rate": 2.5853734488139337e-05,
+      "loss": 0.646,
+      "step": 385
+    },
+    {
+      "epoch": 0.8552631578947368,
+      "grad_norm": 0.9370837807655334,
+      "learning_rate": 2.5727744987563765e-05,
+      "loss": 0.63,
+      "step": 390
+    },
+    {
+      "epoch": 0.8662280701754386,
+      "grad_norm": 0.9266082644462585,
+      "learning_rate": 2.5600186842235476e-05,
+      "loss": 0.6068,
+      "step": 395
+    },
+    {
+      "epoch": 0.8771929824561403,
+      "grad_norm": 0.8708203434944153,
+      "learning_rate": 2.5471078704109335e-05,
+      "loss": 0.6095,
+      "step": 400
+    },
+    {
+      "epoch": 0.8881578947368421,
+      "grad_norm": 0.7840025424957275,
+      "learning_rate": 2.5340439451785065e-05,
+      "loss": 0.6108,
+      "step": 405
+    },
+    {
+      "epoch": 0.8991228070175439,
+      "grad_norm": 0.9310855865478516,
+      "learning_rate": 2.5208288187746717e-05,
+      "loss": 0.632,
+      "step": 410
+    },
+    {
+      "epoch": 0.9100877192982456,
+      "grad_norm": 0.8249394297599792,
+      "learning_rate": 2.5074644235569487e-05,
+      "loss": 0.5878,
+      "step": 415
+    },
+    {
+      "epoch": 0.9210526315789473,
+      "grad_norm": 0.9249837398529053,
+      "learning_rate": 2.4939527137094137e-05,
+      "loss": 0.5976,
+      "step": 420
+    },
+    {
+      "epoch": 0.9320175438596491,
+      "grad_norm": 0.8325455188751221,
+      "learning_rate": 2.480295664956954e-05,
+      "loss": 0.6374,
+      "step": 425
+    },
+    {
+      "epoch": 0.9429824561403509,
+      "grad_norm": 0.9041548371315002,
+      "learning_rate": 2.4664952742763697e-05,
+      "loss": 0.5983,
+      "step": 430
+    },
+    {
+      "epoch": 0.9539473684210527,
+      "grad_norm": 0.9164990186691284,
+      "learning_rate": 2.4525535596043712e-05,
+      "loss": 0.5942,
+      "step": 435
+    },
+    {
+      "epoch": 0.9649122807017544,
+      "grad_norm": 0.8874028325080872,
+      "learning_rate": 2.438472559542509e-05,
+      "loss": 0.6187,
+      "step": 440
+    },
+    {
+      "epoch": 0.9758771929824561,
+      "grad_norm": 1.0253710746765137,
+      "learning_rate": 2.4242543330590828e-05,
+      "loss": 0.5603,
+      "step": 445
+    },
+    {
+      "epoch": 0.9868421052631579,
+      "grad_norm": 0.826774537563324,
+      "learning_rate": 2.4099009591880734e-05,
+      "loss": 0.5702,
+      "step": 450
+    },
+    {
+      "epoch": 0.9978070175438597,
+      "grad_norm": 0.8926154971122742,
+      "learning_rate": 2.3954145367251397e-05,
+      "loss": 0.6038,
+      "step": 455
+    },
+    {
+      "epoch": 1.0087719298245614,
+      "grad_norm": 0.884126603603363,
+      "learning_rate": 2.3807971839207258e-05,
+      "loss": 0.5823,
+      "step": 460
+    },
+    {
+      "epoch": 1.019736842105263,
+      "grad_norm": 0.8890111446380615,
+      "learning_rate": 2.3660510381703226e-05,
+      "loss": 0.5096,
+      "step": 465
+    },
+    {
+      "epoch": 1.030701754385965,
+      "grad_norm": 0.8804746866226196,
+      "learning_rate": 2.3511782557019344e-05,
+      "loss": 0.4853,
+      "step": 470
+    },
+    {
+      "epoch": 1.0416666666666667,
+      "grad_norm": 0.8731418251991272,
+      "learning_rate": 2.336181011260785e-05,
+      "loss": 0.5108,
+      "step": 475
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "grad_norm": 0.9769871234893799,
+      "learning_rate": 2.321061497791321e-05,
+      "loss": 0.4927,
+      "step": 480
+    },
+    {
+      "epoch": 1.0635964912280702,
+      "grad_norm": 0.8549882173538208,
+      "learning_rate": 2.3058219261165537e-05,
+      "loss": 0.4572,
+      "step": 485
+    },
+    {
+      "epoch": 1.0745614035087718,
+      "grad_norm": 0.9094993472099304,
+      "learning_rate": 2.2904645246147823e-05,
+      "loss": 0.4869,
+      "step": 490
+    },
+    {
+      "epoch": 1.0855263157894737,
+      "grad_norm": 0.9365506172180176,
+      "learning_rate": 2.274991538893757e-05,
+      "loss": 0.4958,
+      "step": 495
+    },
+    {
+      "epoch": 1.0964912280701755,
+      "grad_norm": 0.8872578740119934,
+      "learning_rate": 2.2594052314623165e-05,
+      "loss": 0.5302,
+      "step": 500
+    },
+    {
+      "epoch": 1.1074561403508771,
+      "grad_norm": 0.8636729121208191,
+      "learning_rate": 2.243707881399559e-05,
+      "loss": 0.4744,
+      "step": 505
+    },
+    {
+      "epoch": 1.118421052631579,
+      "grad_norm": 0.9333797097206116,
+      "learning_rate": 2.2279017840215868e-05,
+      "loss": 0.4918,
+      "step": 510
+    },
+    {
+      "epoch": 1.1293859649122808,
+      "grad_norm": 1.0834002494812012,
+      "learning_rate": 2.2119892505458773e-05,
+      "loss": 0.4844,
+      "step": 515
+    },
+    {
+      "epoch": 1.1403508771929824,
+      "grad_norm": 1.0561366081237793,
+      "learning_rate": 2.1959726077533307e-05,
+      "loss": 0.4558,
+      "step": 520
+    },
+    {
+      "epoch": 1.1513157894736843,
+      "grad_norm": 0.9655598402023315,
+      "learning_rate": 2.1798541976480402e-05,
+      "loss": 0.4829,
+      "step": 525
+    },
+    {
+      "epoch": 1.162280701754386,
+      "grad_norm": 0.977446436882019,
+      "learning_rate": 2.163636377114837e-05,
+      "loss": 0.4453,
+      "step": 530
+    },
+    {
+      "epoch": 1.1732456140350878,
+      "grad_norm": 0.9137710928916931,
+      "learning_rate": 2.147321517574659e-05,
+      "loss": 0.4608,
+      "step": 535
+    },
+    {
+      "epoch": 1.1842105263157894,
+      "grad_norm": 0.9051221013069153,
+      "learning_rate": 2.1309120046377944e-05,
+      "loss": 0.4626,
+      "step": 540
+    },
+    {
+      "epoch": 1.1951754385964912,
+      "grad_norm": 1.0096217393875122,
+      "learning_rate": 2.1144102377550495e-05,
+      "loss": 0.4817,
+      "step": 545
+    },
+    {
+      "epoch": 1.206140350877193,
+      "grad_norm": 1.0037966966629028,
+      "learning_rate": 2.0978186298668944e-05,
+      "loss": 0.4779,
+      "step": 550
+    },
+    {
+      "epoch": 1.2171052631578947,
+      "grad_norm": 0.9060343503952026,
+      "learning_rate": 2.0811396070506343e-05,
+      "loss": 0.4081,
+      "step": 555
+    },
+    {
+      "epoch": 1.2280701754385965,
+      "grad_norm": 1.028432846069336,
+      "learning_rate": 2.0643756081656616e-05,
+      "loss": 0.4355,
+      "step": 560
+    },
+    {
+      "epoch": 1.2390350877192982,
+      "grad_norm": 1.0631004571914673,
+      "learning_rate": 2.0475290844968372e-05,
+      "loss": 0.4498,
+      "step": 565
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.9762498736381531,
+      "learning_rate": 2.0306024993960587e-05,
+      "loss": 0.4403,
+      "step": 570
+    },
+    {
+      "epoch": 1.2609649122807016,
+      "grad_norm": 1.0591838359832764,
+      "learning_rate": 2.0135983279220557e-05,
+      "loss": 0.445,
+      "step": 575
+    },
+    {
+      "epoch": 1.2719298245614035,
+      "grad_norm": 0.8875951766967773,
+      "learning_rate": 1.9965190564784848e-05,
+      "loss": 0.4249,
+      "step": 580
+    },
+    {
+      "epoch": 1.2828947368421053,
+      "grad_norm": 0.9278407692909241,
+      "learning_rate": 1.979367182450357e-05,
+      "loss": 0.4918,
+      "step": 585
+    },
+    {
+      "epoch": 1.293859649122807,
+      "grad_norm": 0.9412364363670349,
+      "learning_rate": 1.962145213838862e-05,
+      "loss": 0.4205,
+      "step": 590
+    },
+    {
+      "epoch": 1.3048245614035088,
+      "grad_norm": 0.9890954494476318,
+      "learning_rate": 1.9448556688946403e-05,
+      "loss": 0.39,
+      "step": 595
+    },
+    {
+      "epoch": 1.3157894736842106,
+      "grad_norm": 0.9949614405632019,
+      "learning_rate": 1.927501075749559e-05,
+      "loss": 0.4633,
+      "step": 600
+    },
+    {
+      "epoch": 1.3267543859649122,
+      "grad_norm": 1.0368655920028687,
+      "learning_rate": 1.910083972047037e-05,
+      "loss": 0.4534,
+      "step": 605
+    },
+    {
+      "epoch": 1.337719298245614,
+      "grad_norm": 0.9379305839538574,
+      "learning_rate": 1.8926069045709845e-05,
+      "loss": 0.4698,
+      "step": 610
+    },
+    {
+      "epoch": 1.3486842105263157,
+      "grad_norm": 1.0334619283676147,
+      "learning_rate": 1.875072428873405e-05,
+      "loss": 0.4549,
+      "step": 615
+    },
+    {
+      "epoch": 1.3596491228070176,
+      "grad_norm": 0.9264979362487793,
+      "learning_rate": 1.857483108900713e-05,
+      "loss": 0.3994,
+      "step": 620
+    },
+    {
+      "epoch": 1.3706140350877192,
+      "grad_norm": 1.0656267404556274,
+      "learning_rate": 1.839841516618824e-05,
+      "loss": 0.4177,
+      "step": 625
+    },
+    {
+      "epoch": 1.381578947368421,
+      "grad_norm": 0.9710007309913635,
+      "learning_rate": 1.82215023163708e-05,
+      "loss": 0.3933,
+      "step": 630
+    },
+    {
+      "epoch": 1.3925438596491229,
+      "grad_norm": 0.9420899748802185,
+      "learning_rate": 1.8044118408310428e-05,
+      "loss": 0.4383,
+      "step": 635
+    },
+    {
+      "epoch": 1.4035087719298245,
+      "grad_norm": 1.0052410364151,
+      "learning_rate": 1.7866289379642388e-05,
+      "loss": 0.4166,
+      "step": 640
+    },
+    {
+      "epoch": 1.4144736842105263,
+      "grad_norm": 0.9635876417160034,
+      "learning_rate": 1.768804123308886e-05,
+      "loss": 0.4246,
+      "step": 645
+    },
+    {
+      "epoch": 1.4254385964912282,
+      "grad_norm": 0.965676486492157,
+      "learning_rate": 1.75094000326568e-05,
+      "loss": 0.4121,
+      "step": 650
+    },
+    {
+      "epoch": 1.4364035087719298,
+      "grad_norm": 1.079981803894043,
+      "learning_rate": 1.7330391899826706e-05,
+      "loss": 0.3998,
+      "step": 655
+    },
+    {
+      "epoch": 1.4473684210526316,
+      "grad_norm": 1.0700271129608154,
+      "learning_rate": 1.7151043009733123e-05,
+      "loss": 0.3892,
+      "step": 660
+    },
+    {
+      "epoch": 1.4583333333333333,
+      "grad_norm": 1.0209262371063232,
+      "learning_rate": 1.697137958733718e-05,
+      "loss": 0.4353,
+      "step": 665
+    },
+    {
+      "epoch": 1.469298245614035,
+      "grad_norm": 1.0594371557235718,
+      "learning_rate": 1.6791427903591916e-05,
+      "loss": 0.4037,
+      "step": 670
+    },
+    {
+      "epoch": 1.4802631578947367,
+      "grad_norm": 0.9944431185722351,
+      "learning_rate": 1.661121427160085e-05,
+      "loss": 0.3986,
+      "step": 675
+    },
+    {
+      "epoch": 1.4912280701754386,
+      "grad_norm": 1.0131406784057617,
+      "learning_rate": 1.643076504277042e-05,
+      "loss": 0.3945,
+      "step": 680
+    },
+    {
+      "epoch": 1.5021929824561404,
+      "grad_norm": 0.9437420964241028,
+      "learning_rate": 1.6250106602956753e-05,
+      "loss": 0.3663,
+      "step": 685
+    },
+    {
+      "epoch": 1.513157894736842,
+      "grad_norm": 1.0365841388702393,
+      "learning_rate": 1.6069265368607488e-05,
+      "loss": 0.3574,
+      "step": 690
+    },
+    {
+      "epoch": 1.5241228070175439,
+      "grad_norm": 1.088201642036438,
+      "learning_rate": 1.588826778289904e-05,
+      "loss": 0.3995,
+      "step": 695
+    },
+    {
+      "epoch": 1.5350877192982457,
+      "grad_norm": 0.9893851280212402,
+      "learning_rate": 1.5707140311870037e-05,
+      "loss": 0.3423,
+      "step": 700
+    },
+    {
+      "epoch": 1.5460526315789473,
+      "grad_norm": 1.1008005142211914,
+      "learning_rate": 1.5525909440551317e-05,
+      "loss": 0.338,
+      "step": 705
+    },
+    {
+      "epoch": 1.557017543859649,
+      "grad_norm": 1.01732337474823,
+      "learning_rate": 1.5344601669093258e-05,
+      "loss": 0.3854,
+      "step": 710
+    },
+    {
+      "epoch": 1.567982456140351,
+      "grad_norm": 0.9191359281539917,
+      "learning_rate": 1.5163243508890813e-05,
+      "loss": 0.3588,
+      "step": 715
+    },
+    {
+      "epoch": 1.5789473684210527,
+      "grad_norm": 0.9609974026679993,
+      "learning_rate": 1.4981861478706945e-05,
+      "loss": 0.3751,
+      "step": 720
+    },
+    {
+      "epoch": 1.5899122807017543,
+      "grad_norm": 0.9675068259239197,
+      "learning_rate": 1.4800482100794941e-05,
+      "loss": 0.3855,
+      "step": 725
+    },
+    {
+      "epoch": 1.6008771929824561,
+      "grad_norm": 1.0315802097320557,
+      "learning_rate": 1.4619131897020278e-05,
+      "loss": 0.3914,
+      "step": 730
+    },
+    {
+      "epoch": 1.611842105263158,
+      "grad_norm": 0.908302366733551,
+      "learning_rate": 1.4437837384982504e-05,
+      "loss": 0.3664,
+      "step": 735
+    },
+    {
+      "epoch": 1.6228070175438596,
+      "grad_norm": 0.9855623245239258,
+      "learning_rate": 1.4256625074137738e-05,
+      "loss": 0.397,
+      "step": 740
+    },
+    {
+      "epoch": 1.6337719298245614,
+      "grad_norm": 0.9747766256332397,
+      "learning_rate": 1.4075521461922372e-05,
+      "loss": 0.3444,
+      "step": 745
+    },
+    {
+      "epoch": 1.6447368421052633,
+      "grad_norm": 1.0947595834732056,
+      "learning_rate": 1.3894553029878557e-05,
+      "loss": 0.3417,
+      "step": 750
+    },
+    {
+      "epoch": 1.655701754385965,
+      "grad_norm": 0.957144558429718,
+      "learning_rate": 1.3713746239781964e-05,
+      "loss": 0.3931,
+      "step": 755
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 1.0409021377563477,
+      "learning_rate": 1.3533127529772469e-05,
+      "loss": 0.3473,
+      "step": 760
+    },
+    {
+      "epoch": 1.6776315789473686,
+      "grad_norm": 1.0445263385772705,
+      "learning_rate": 1.3352723310488275e-05,
+      "loss": 0.3278,
+      "step": 765
+    },
+    {
+      "epoch": 1.6885964912280702,
+      "grad_norm": 1.1239886283874512,
+      "learning_rate": 1.3172559961204103e-05,
+      "loss": 0.3277,
+      "step": 770
+    },
+    {
+      "epoch": 1.6995614035087718,
+      "grad_norm": 1.0442458391189575,
+      "learning_rate": 1.2992663825973866e-05,
+      "loss": 0.3905,
+      "step": 775
+    },
+    {
+      "epoch": 1.7105263157894737,
+      "grad_norm": 0.9254198670387268,
+      "learning_rate": 1.2813061209778617e-05,
+      "loss": 0.3257,
+      "step": 780
+    },
+    {
+      "epoch": 1.7214912280701755,
+      "grad_norm": 0.9384222626686096,
+      "learning_rate": 1.2633778374680117e-05,
+      "loss": 0.296,
+      "step": 785
+    },
+    {
+      "epoch": 1.7324561403508771,
+      "grad_norm": 0.9774355888366699,
+      "learning_rate": 1.2454841535980735e-05,
+      "loss": 0.352,
+      "step": 790
+    },
+    {
+      "epoch": 1.743421052631579,
+      "grad_norm": 1.020918369293213,
+      "learning_rate": 1.2276276858390137e-05,
+      "loss": 0.358,
+      "step": 795
+    },
+    {
+      "epoch": 1.7543859649122808,
+      "grad_norm": 0.9767550826072693,
+      "learning_rate": 1.209811045219944e-05,
+      "loss": 0.3411,
+      "step": 800
+    },
+    {
+      "epoch": 1.7653508771929824,
+      "grad_norm": 1.097368597984314,
+      "learning_rate": 1.1920368369463245e-05,
+      "loss": 0.292,
+      "step": 805
+    },
+    {
+      "epoch": 1.776315789473684,
+      "grad_norm": 0.9820191264152527,
+      "learning_rate": 1.1743076600190237e-05,
+      "loss": 0.3215,
+      "step": 810
+    },
+    {
+      "epoch": 1.787280701754386,
+      "grad_norm": 1.0999784469604492,
+      "learning_rate": 1.1566261068542843e-05,
+      "loss": 0.3386,
+      "step": 815
+    },
+    {
+      "epoch": 1.7982456140350878,
+      "grad_norm": 0.9196261167526245,
+      "learning_rate": 1.138994762904653e-05,
+      "loss": 0.3284,
+      "step": 820
+    },
+    {
+      "epoch": 1.8092105263157894,
+      "grad_norm": 1.006937861442566,
+      "learning_rate": 1.1214162062809253e-05,
+      "loss": 0.3159,
+      "step": 825
+    },
+    {
+      "epoch": 1.8201754385964912,
+      "grad_norm": 1.019486427307129,
+      "learning_rate": 1.1038930073751678e-05,
+      "loss": 0.2926,
+      "step": 830
+    },
+    {
+      "epoch": 1.831140350877193,
+      "grad_norm": 1.008124589920044,
+      "learning_rate": 1.0864277284848672e-05,
+      "loss": 0.3207,
+      "step": 835
+    },
+    {
+      "epoch": 1.8421052631578947,
+      "grad_norm": 1.1085612773895264,
+      "learning_rate": 1.0690229234382621e-05,
+      "loss": 0.3469,
+      "step": 840
+    },
+    {
+      "epoch": 1.8530701754385965,
+      "grad_norm": 0.9389194250106812,
+      "learning_rate": 1.0516811372209143e-05,
+      "loss": 0.3348,
+      "step": 845
+    },
+    {
+      "epoch": 1.8640350877192984,
+      "grad_norm": 1.0715816020965576,
+      "learning_rate": 1.0344049056035741e-05,
+      "loss": 0.3444,
+      "step": 850
+    },
+    {
+      "epoch": 1.875,
+      "grad_norm": 1.0719966888427734,
+      "learning_rate": 1.0171967547713901e-05,
+      "loss": 0.3256,
+      "step": 855
+    },
+    {
+      "epoch": 1.8859649122807016,
+      "grad_norm": 1.1906548738479614,
+      "learning_rate": 1.0000592009545247e-05,
+      "loss": 0.3298,
+      "step": 860
+    },
+    {
+      "epoch": 1.8969298245614035,
+      "grad_norm": 1.0440380573272705,
+      "learning_rate": 9.829947500602217e-06,
+      "loss": 0.3008,
+      "step": 865
+    },
+    {
+      "epoch": 1.9078947368421053,
+      "grad_norm": 1.051279902458191,
+      "learning_rate": 9.660058973063838e-06,
+      "loss": 0.3,
+      "step": 870
+    },
+    {
+      "epoch": 1.918859649122807,
+      "grad_norm": 0.9557648301124573,
+      "learning_rate": 9.49095126856715e-06,
+      "loss": 0.2851,
+      "step": 875
+    },
+    {
+      "epoch": 1.9298245614035088,
+      "grad_norm": 0.9850110411643982,
+      "learning_rate": 9.322649114574791e-06,
+      "loss": 0.326,
+      "step": 880
+    },
+    {
+      "epoch": 1.9407894736842106,
+      "grad_norm": 0.9415509700775146,
+      "learning_rate": 9.155177120759248e-06,
+      "loss": 0.2783,
+      "step": 885
+    },
+    {
+      "epoch": 1.9517543859649122,
+      "grad_norm": 1.0071932077407837,
+      "learning_rate": 8.988559775404372e-06,
+      "loss": 0.3124,
+      "step": 890
+    },
+    {
+      "epoch": 1.962719298245614,
+      "grad_norm": 0.9348342418670654,
+      "learning_rate": 8.822821441824622e-06,
+      "loss": 0.2995,
+      "step": 895
+    },
+    {
+      "epoch": 1.973684210526316,
+      "grad_norm": 1.0431472063064575,
+      "learning_rate": 8.657986354802565e-06,
+      "loss": 0.2858,
+      "step": 900
+    },
+    {
+      "epoch": 1.9846491228070176,
+      "grad_norm": 1.0253784656524658,
+      "learning_rate": 8.494078617045218e-06,
+      "loss": 0.3137,
+      "step": 905
+    },
+    {
+      "epoch": 1.9956140350877192,
+      "grad_norm": 1.0688952207565308,
+      "learning_rate": 8.331122195659646e-06,
+      "loss": 0.3184,
+      "step": 910
+    },
+    {
+      "epoch": 2.0065789473684212,
+      "grad_norm": 0.9592809081077576,
+      "learning_rate": 8.169140918648447e-06,
+      "loss": 0.2948,
+      "step": 915
+    },
+    {
+      "epoch": 2.017543859649123,
+      "grad_norm": 1.105006217956543,
+      "learning_rate": 8.008158471425512e-06,
+      "loss": 0.2397,
+      "step": 920
+    },
+    {
+      "epoch": 2.0285087719298245,
+      "grad_norm": 1.1872037649154663,
+      "learning_rate": 7.848198393352689e-06,
+      "loss": 0.2636,
+      "step": 925
+    },
+    {
+      "epoch": 2.039473684210526,
+      "grad_norm": 1.0474228858947754,
+      "learning_rate": 7.689284074297794e-06,
+      "loss": 0.278,
+      "step": 930
+    },
+    {
+      "epoch": 2.050438596491228,
+      "grad_norm": 1.014209508895874,
+      "learning_rate": 7.531438751214437e-06,
+      "loss": 0.2296,
+      "step": 935
+    },
+    {
+      "epoch": 2.06140350877193,
+      "grad_norm": 0.9980344176292419,
+      "learning_rate": 7.374685504744278e-06,
+      "loss": 0.2419,
+      "step": 940
+    },
+    {
+      "epoch": 2.0723684210526314,
+      "grad_norm": 1.115631103515625,
+      "learning_rate": 7.219047255842076e-06,
+      "loss": 0.2399,
+      "step": 945
+    },
+    {
+      "epoch": 2.0833333333333335,
+      "grad_norm": 0.9669972062110901,
+      "learning_rate": 7.064546762424118e-06,
+      "loss": 0.2333,
+      "step": 950
+    },
+    {
+      "epoch": 2.094298245614035,
+      "grad_norm": 0.9526334404945374,
+      "learning_rate": 6.911206616040505e-06,
+      "loss": 0.2582,
+      "step": 955
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "grad_norm": 1.1515368223190308,
+      "learning_rate": 6.759049238571732e-06,
+      "loss": 0.2427,
+      "step": 960
+    },
+    {
+      "epoch": 2.116228070175439,
+      "grad_norm": 0.8898414969444275,
+      "learning_rate": 6.608096878950069e-06,
+      "loss": 0.2768,
+      "step": 965
+    },
+    {
+      "epoch": 2.1271929824561404,
+      "grad_norm": 1.1969611644744873,
+      "learning_rate": 6.458371609906287e-06,
+      "loss": 0.2201,
+      "step": 970
+    },
+    {
+      "epoch": 2.138157894736842,
+      "grad_norm": 0.8385275602340698,
+      "learning_rate": 6.309895324742081e-06,
+      "loss": 0.207,
+      "step": 975
+    },
+    {
+      "epoch": 2.1491228070175437,
+      "grad_norm": 1.0890440940856934,
+      "learning_rate": 6.1626897341288055e-06,
+      "loss": 0.2293,
+      "step": 980
+    },
+    {
+      "epoch": 2.1600877192982457,
+      "grad_norm": 1.135362148284912,
+      "learning_rate": 6.016776362932819e-06,
+      "loss": 0.2618,
+      "step": 985
+    },
+    {
+      "epoch": 2.1710526315789473,
+      "grad_norm": 0.9805251359939575,
+      "learning_rate": 5.872176547068081e-06,
+      "loss": 0.2504,
+      "step": 990
+    },
+    {
+      "epoch": 2.182017543859649,
+      "grad_norm": 1.0886223316192627,
+      "learning_rate": 5.72891143037635e-06,
+      "loss": 0.2292,
+      "step": 995
+    },
+    {
+      "epoch": 2.192982456140351,
+      "grad_norm": 1.105898380279541,
+      "learning_rate": 5.58700196153546e-06,
+      "loss": 0.2667,
+      "step": 1000
+    },
+    {
+      "epoch": 2.2039473684210527,
+      "grad_norm": 1.1456786394119263,
+      "learning_rate": 5.44646889099612e-06,
+      "loss": 0.245,
+      "step": 1005
+    },
+    {
+      "epoch": 2.2149122807017543,
+      "grad_norm": 0.9122210741043091,
+      "learning_rate": 5.307332767947734e-06,
+      "loss": 0.2418,
+      "step": 1010
+    },
+    {
+      "epoch": 2.2258771929824563,
+      "grad_norm": 0.9057987928390503,
+      "learning_rate": 5.169613937313649e-06,
+      "loss": 0.2205,
+      "step": 1015
+    },
+    {
+      "epoch": 2.236842105263158,
+      "grad_norm": 1.0202924013137817,
+      "learning_rate": 5.033332536776216e-06,
+      "loss": 0.2406,
+      "step": 1020
+    },
+    {
+      "epoch": 2.2478070175438596,
+      "grad_norm": 1.0220569372177124,
+      "learning_rate": 4.8985084938322395e-06,
+      "loss": 0.21,
+      "step": 1025
+    },
+    {
+      "epoch": 2.2587719298245617,
+      "grad_norm": 1.172656536102295,
+      "learning_rate": 4.765161522879077e-06,
+      "loss": 0.2407,
+      "step": 1030
+    },
+    {
+      "epoch": 2.2697368421052633,
+      "grad_norm": 1.0824159383773804,
+      "learning_rate": 4.633311122331957e-06,
+      "loss": 0.2471,
+      "step": 1035
+    },
+    {
+      "epoch": 2.280701754385965,
+      "grad_norm": 0.9344537258148193,
+      "learning_rate": 4.502976571772872e-06,
+      "loss": 0.2209,
+      "step": 1040
+    },
+    {
+      "epoch": 2.2916666666666665,
+      "grad_norm": 0.9334734678268433,
+      "learning_rate": 4.374176929131424e-06,
+      "loss": 0.2639,
+      "step": 1045
+    },
+    {
+      "epoch": 2.3026315789473686,
+      "grad_norm": 1.0213098526000977,
+      "learning_rate": 4.2469310278981335e-06,
+      "loss": 0.232,
+      "step": 1050
+    },
+    {
+      "epoch": 2.31359649122807,
+      "grad_norm": 1.0980297327041626,
+      "learning_rate": 4.121257474370557e-06,
+      "loss": 0.2138,
+      "step": 1055
+    },
+    {
+      "epoch": 2.324561403508772,
+      "grad_norm": 0.9363732933998108,
+      "learning_rate": 3.997174644932599e-06,
+      "loss": 0.2171,
+      "step": 1060
+    },
+    {
+      "epoch": 2.3355263157894735,
+      "grad_norm": 1.0077205896377563,
+      "learning_rate": 3.874700683367457e-06,
+      "loss": 0.1983,
+      "step": 1065
+    },
+    {
+      "epoch": 2.3464912280701755,
+      "grad_norm": 1.0382026433944702,
+      "learning_rate": 3.7538534982045913e-06,
+      "loss": 0.2531,
+      "step": 1070
+    },
+    {
+      "epoch": 2.357456140350877,
+      "grad_norm": 1.0411885976791382,
+      "learning_rate": 3.634650760101076e-06,
+      "loss": 0.2479,
+      "step": 1075
+    },
+    {
+      "epoch": 2.3684210526315788,
+      "grad_norm": 1.1133902072906494,
+      "learning_rate": 3.5171098992577515e-06,
+      "loss": 0.2474,
+      "step": 1080
+    },
+    {
+      "epoch": 2.379385964912281,
+      "grad_norm": 0.8952088356018066,
+      "learning_rate": 3.4012481028705067e-06,
+      "loss": 0.2177,
+      "step": 1085
+    },
+    {
+      "epoch": 2.3903508771929824,
+      "grad_norm": 0.9758759140968323,
+      "learning_rate": 3.2870823126171317e-06,
+      "loss": 0.2088,
+      "step": 1090
+    },
+    {
+      "epoch": 2.401315789473684,
+      "grad_norm": 1.0291149616241455,
+      "learning_rate": 3.1746292221800317e-06,
+      "loss": 0.2448,
+      "step": 1095
+    },
+    {
+      "epoch": 2.412280701754386,
+      "grad_norm": 1.018467903137207,
+      "learning_rate": 3.063905274805251e-06,
+      "loss": 0.2409,
+      "step": 1100
+    },
+    {
+      "epoch": 2.4232456140350878,
+      "grad_norm": 1.0696269273757935,
+      "learning_rate": 2.9549266608980595e-06,
+      "loss": 0.2103,
+      "step": 1105
+    },
+    {
+      "epoch": 2.4342105263157894,
+      "grad_norm": 0.9848340153694153,
+      "learning_rate": 2.847709315655566e-06,
+      "loss": 0.2107,
+      "step": 1110
+    },
+    {
+      "epoch": 2.4451754385964914,
+      "grad_norm": 1.0225777626037598,
+      "learning_rate": 2.7422689167365967e-06,
+      "loss": 0.2342,
+      "step": 1115
+    },
+    {
+      "epoch": 2.456140350877193,
+      "grad_norm": 0.9974656701087952,
+      "learning_rate": 2.6386208819693037e-06,
+      "loss": 0.2256,
+      "step": 1120
+    },
+    {
+      "epoch": 2.4671052631578947,
+      "grad_norm": 0.9634082913398743,
+      "learning_rate": 2.536780367096666e-06,
+      "loss": 0.2291,
+      "step": 1125
+    },
+    {
+      "epoch": 2.4780701754385963,
+      "grad_norm": 0.882702648639679,
+      "learning_rate": 2.4367622635604035e-06,
+      "loss": 0.2352,
+      "step": 1130
+    },
+    {
+      "epoch": 2.4890350877192984,
+      "grad_norm": 0.9883916974067688,
+      "learning_rate": 2.3385811963234903e-06,
+      "loss": 0.2155,
+      "step": 1135
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 1.12102210521698,
+      "learning_rate": 2.2422515217316653e-06,
+      "loss": 0.2392,
+      "step": 1140
+    },
+    {
+      "epoch": 2.5109649122807016,
+      "grad_norm": 1.0628376007080078,
+      "learning_rate": 2.147787325414173e-06,
+      "loss": 0.2314,
+      "step": 1145
+    },
+    {
+      "epoch": 2.5219298245614032,
+      "grad_norm": 0.9789189100265503,
+      "learning_rate": 2.055202420224136e-06,
+      "loss": 0.2343,
+      "step": 1150
+    },
+    {
+      "epoch": 2.5328947368421053,
+      "grad_norm": 0.9841337203979492,
+      "learning_rate": 1.964510344218797e-06,
+      "loss": 0.2197,
+      "step": 1155
+    },
+    {
+      "epoch": 2.543859649122807,
+      "grad_norm": 1.084327220916748,
+      "learning_rate": 1.8757243586799376e-06,
+      "loss": 0.2286,
+      "step": 1160
+    },
+    {
+      "epoch": 2.5548245614035086,
+      "grad_norm": 0.9269506931304932,
+      "learning_rate": 1.7888574461747687e-06,
+      "loss": 0.2097,
+      "step": 1165
+    },
+    {
+      "epoch": 2.5657894736842106,
+      "grad_norm": 1.0006529092788696,
+      "learning_rate": 1.7039223086575827e-06,
+      "loss": 0.2224,
+      "step": 1170
+    },
+    {
+      "epoch": 2.5767543859649122,
+      "grad_norm": 1.046647310256958,
+      "learning_rate": 1.6209313656124247e-06,
+      "loss": 0.2647,
+      "step": 1175
+    },
+    {
+      "epoch": 2.587719298245614,
+      "grad_norm": 0.8911044597625732,
+      "learning_rate": 1.5398967522370978e-06,
+      "loss": 0.2204,
+      "step": 1180
+    },
+    {
+      "epoch": 2.598684210526316,
+      "grad_norm": 1.0781792402267456,
+      "learning_rate": 1.4608303176686965e-06,
+      "loss": 0.2057,
+      "step": 1185
+    },
+    {
+      "epoch": 2.6096491228070176,
+      "grad_norm": 0.9152336716651917,
+      "learning_rate": 1.3837436232509904e-06,
+      "loss": 0.184,
+      "step": 1190
+    },
+    {
+      "epoch": 2.620614035087719,
+      "grad_norm": 0.9757503867149353,
+      "learning_rate": 1.3086479408438912e-06,
+      "loss": 0.2129,
+      "step": 1195
+    },
+    {
+      "epoch": 2.6315789473684212,
+      "grad_norm": 0.9043612480163574,
+      "learning_rate": 1.235554251175256e-06,
+      "loss": 0.2095,
+      "step": 1200
+    },
+    {
+      "epoch": 2.642543859649123,
+      "grad_norm": 0.9414308071136475,
+      "learning_rate": 1.1644732422352295e-06,
+      "loss": 0.2267,
+      "step": 1205
+    },
+    {
+      "epoch": 2.6535087719298245,
+      "grad_norm": 0.9960950613021851,
+      "learning_rate": 1.0954153077134322e-06,
+      "loss": 0.219,
+      "step": 1210
+    },
+    {
+      "epoch": 2.6644736842105265,
+      "grad_norm": 1.0561095476150513,
+      "learning_rate": 1.0283905454791414e-06,
+      "loss": 0.2317,
+      "step": 1215
+    },
+    {
+      "epoch": 2.675438596491228,
+      "grad_norm": 1.1242793798446655,
+      "learning_rate": 9.634087561047845e-07,
+      "loss": 0.2123,
+      "step": 1220
+    },
+    {
+      "epoch": 2.68640350877193,
+      "grad_norm": 0.9190773367881775,
+      "learning_rate": 9.004794414328221e-07,
+      "loss": 0.2026,
+      "step": 1225
+    },
+    {
+      "epoch": 2.6973684210526314,
+      "grad_norm": 1.0502454042434692,
+      "learning_rate": 8.396118031863914e-07,
+      "loss": 0.2091,
+      "step": 1230
+    },
+    {
+      "epoch": 2.7083333333333335,
+      "grad_norm": 1.0512956380844116,
+      "learning_rate": 7.80814741623791e-07,
+      "loss": 0.2127,
+      "step": 1235
+    },
+    {
+      "epoch": 2.719298245614035,
+      "grad_norm": 0.9547901749610901,
+      "learning_rate": 7.240968542370574e-07,
+      "loss": 0.2145,
+      "step": 1240
+    },
+    {
+      "epoch": 2.7302631578947367,
+      "grad_norm": 1.1893854141235352,
+      "learning_rate": 6.694664344948109e-07,
+      "loss": 0.2187,
+      "step": 1245
+    },
+    {
+      "epoch": 2.7412280701754383,
+      "grad_norm": 1.0072098970413208,
+      "learning_rate": 6.169314706295637e-07,
+      "loss": 0.2259,
+      "step": 1250
+    },
+    {
+      "epoch": 2.7521929824561404,
+      "grad_norm": 1.034569263458252,
+      "learning_rate": 5.664996444696475e-07,
+      "loss": 0.2316,
+      "step": 1255
+    },
+    {
+      "epoch": 2.763157894736842,
+      "grad_norm": 0.9266517758369446,
+      "learning_rate": 5.181783303159604e-07,
+      "loss": 0.1944,
+      "step": 1260
+    },
+    {
+      "epoch": 2.7741228070175437,
+      "grad_norm": 1.055025339126587,
+      "learning_rate": 4.719745938636649e-07,
+      "loss": 0.2327,
+      "step": 1265
+    },
+    {
+      "epoch": 2.7850877192982457,
+      "grad_norm": 0.9898583292961121,
+      "learning_rate": 4.2789519116902875e-07,
+      "loss": 0.2329,
+      "step": 1270
+    },
+    {
+      "epoch": 2.7960526315789473,
+      "grad_norm": 0.9521634578704834,
+      "learning_rate": 3.8594656766152535e-07,
+      "loss": 0.2464,
+      "step": 1275
+    },
+    {
+      "epoch": 2.807017543859649,
+      "grad_norm": 0.9560325145721436,
+      "learning_rate": 3.461348572013678e-07,
+      "loss": 0.2082,
+      "step": 1280
+    },
+    {
+      "epoch": 2.817982456140351,
+      "grad_norm": 1.0245527029037476,
+      "learning_rate": 3.084658811825947e-07,
+      "loss": 0.2245,
+      "step": 1285
+    },
+    {
+      "epoch": 2.8289473684210527,
+      "grad_norm": 0.8283141255378723,
+      "learning_rate": 2.7294514768184563e-07,
+      "loss": 0.1987,
+      "step": 1290
+    },
+    {
+      "epoch": 2.8399122807017543,
+      "grad_norm": 1.0773205757141113,
+      "learning_rate": 2.3957785065295447e-07,
+      "loss": 0.2309,
+      "step": 1295
+    },
+    {
+      "epoch": 2.8508771929824563,
+      "grad_norm": 1.1377276182174683,
+      "learning_rate": 2.083688691674762e-07,
+      "loss": 0.2134,
+      "step": 1300
+    },
+    {
+      "epoch": 2.861842105263158,
+      "grad_norm": 0.9509216547012329,
+      "learning_rate": 1.793227667012498e-07,
+      "loss": 0.1915,
+      "step": 1305
+    },
+    {
+      "epoch": 2.8728070175438596,
+      "grad_norm": 0.9714044332504272,
+      "learning_rate": 1.5244379046710666e-07,
+      "loss": 0.2193,
+      "step": 1310
+    },
+    {
+      "epoch": 2.8837719298245617,
+      "grad_norm": 0.9448513388633728,
+      "learning_rate": 1.2773587079384751e-07,
+      "loss": 0.2162,
+      "step": 1315
+    },
+    {
+      "epoch": 2.8947368421052633,
+      "grad_norm": 1.0036886930465698,
+      "learning_rate": 1.052026205515172e-07,
+      "loss": 0.2082,
+      "step": 1320
+    },
+    {
+      "epoch": 2.905701754385965,
+      "grad_norm": 0.9712037444114685,
+      "learning_rate": 8.48473346231321e-08,
+      "loss": 0.1992,
+      "step": 1325
+    },
+    {
+      "epoch": 2.9166666666666665,
+      "grad_norm": 0.9526965022087097,
+      "learning_rate": 6.667298942288736e-08,
+      "loss": 0.1852,
+      "step": 1330
+    },
+    {
+      "epoch": 2.9276315789473686,
+      "grad_norm": 1.0061296224594116,
+      "learning_rate": 5.068224246093489e-08,
+      "loss": 0.2312,
+      "step": 1335
+    },
+    {
+      "epoch": 2.93859649122807,
+      "grad_norm": 1.0219966173171997,
+      "learning_rate": 3.687743195479931e-08,
+      "loss": 0.2381,
+      "step": 1340
+    },
+    {
+      "epoch": 2.949561403508772,
+      "grad_norm": 0.9002558588981628,
+      "learning_rate": 2.5260576487471376e-08,
+      "loss": 0.2042,
+      "step": 1345
+    },
+    {
+      "epoch": 2.9605263157894735,
+      "grad_norm": 0.9882487058639526,
+      "learning_rate": 1.583337471224744e-08,
+      "loss": 0.2274,
+      "step": 1350
+    },
+    {
+      "epoch": 2.9714912280701755,
+      "grad_norm": 0.9593895673751831,
+      "learning_rate": 8.597205104343142e-09,
+      "loss": 0.2385,
+      "step": 1355
+    },
+    {
+      "epoch": 2.982456140350877,
+      "grad_norm": 1.0448355674743652,
+      "learning_rate": 3.5531257593313103e-09,
+      "loss": 0.1949,
+      "step": 1360
+    },
+    {
+      "epoch": 2.9934210526315788,
+      "grad_norm": 0.876778244972229,
+      "learning_rate": 7.018742384257149e-10,
+      "loss": 0.2007,
+      "step": 1365
+    },
+    {
+      "epoch": 3.0,
+      "step": 1368,
+      "total_flos": 1.9997709539779543e+18,
+      "train_loss": 0.49729131393091025,
+      "train_runtime": 968.4082,
+      "train_samples_per_second": 45.185,
+      "train_steps_per_second": 1.413
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1368,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 20000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.9997709539779543e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

9_128_e3_3e-5/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5963cd6698a5ec7b1040432901131b384d0bcbbcc0530e055deea332af67c160
+size 8209