Upload folder using huggingface_hub

100_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": [
+    "gate_proj",
+    "q_proj",
+    "down_proj",
+    "k_proj",
+    "v_proj",
+    "up_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

100_128_e3_3e-5/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a5277fa823561704e0c6e7497ffd885ed95fb00110e44f7c9f273e59843c178
+size 791751704

100_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
+}

100_128_e3_3e-5/all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.5637608849987338e+18,
+    "train_loss": 0.5088282435960163,
+    "train_runtime": 723.6343,
+    "train_samples": 11046,
+    "train_samples_per_second": 45.794,
+    "train_steps_per_second": 1.434
+}

100_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 %}

100_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
+}

100_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
+  }
+}

100_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
+}

100_128_e3_3e-5/train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.5637608849987338e+18,
+    "train_loss": 0.5088282435960163,
+    "train_runtime": 723.6343,
+    "train_samples": 11046,
+    "train_samples_per_second": 45.794,
+    "train_steps_per_second": 1.434
+}

100_128_e3_3e-5/trainer_state.json

@@ -0,0 +1,1492 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1038,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01447178002894356,
+      "grad_norm": 2.8615591526031494,
+      "learning_rate": 2.307692307692308e-06,
+      "loss": 1.4769,
+      "step": 5
+    },
+    {
+      "epoch": 0.02894356005788712,
+      "grad_norm": 2.151601791381836,
+      "learning_rate": 5.192307692307692e-06,
+      "loss": 1.4719,
+      "step": 10
+    },
+    {
+      "epoch": 0.04341534008683068,
+      "grad_norm": 0.8743847608566284,
+      "learning_rate": 8.076923076923077e-06,
+      "loss": 1.3167,
+      "step": 15
+    },
+    {
+      "epoch": 0.05788712011577424,
+      "grad_norm": 0.49110934138298035,
+      "learning_rate": 1.0961538461538462e-05,
+      "loss": 1.2605,
+      "step": 20
+    },
+    {
+      "epoch": 0.0723589001447178,
+      "grad_norm": 0.3963072896003723,
+      "learning_rate": 1.3846153846153847e-05,
+      "loss": 1.3158,
+      "step": 25
+    },
+    {
+      "epoch": 0.08683068017366136,
+      "grad_norm": 0.39099782705307007,
+      "learning_rate": 1.673076923076923e-05,
+      "loss": 1.212,
+      "step": 30
+    },
+    {
+      "epoch": 0.10130246020260492,
+      "grad_norm": 0.3860986530780792,
+      "learning_rate": 1.9615384615384617e-05,
+      "loss": 1.2278,
+      "step": 35
+    },
+    {
+      "epoch": 0.11577424023154848,
+      "grad_norm": 0.360788494348526,
+      "learning_rate": 2.25e-05,
+      "loss": 1.1546,
+      "step": 40
+    },
+    {
+      "epoch": 0.13024602026049203,
+      "grad_norm": 0.343351274728775,
+      "learning_rate": 2.5384615384615386e-05,
+      "loss": 1.1238,
+      "step": 45
+    },
+    {
+      "epoch": 0.1447178002894356,
+      "grad_norm": 0.35071519017219543,
+      "learning_rate": 2.8269230769230768e-05,
+      "loss": 1.1477,
+      "step": 50
+    },
+    {
+      "epoch": 0.15918958031837915,
+      "grad_norm": 0.4042356610298157,
+      "learning_rate": 2.999969544502334e-05,
+      "loss": 1.1531,
+      "step": 55
+    },
+    {
+      "epoch": 0.1736613603473227,
+      "grad_norm": 0.3548179268836975,
+      "learning_rate": 2.9996269343563534e-05,
+      "loss": 1.1397,
+      "step": 60
+    },
+    {
+      "epoch": 0.18813314037626627,
+      "grad_norm": 0.37136110663414,
+      "learning_rate": 2.9989037319336417e-05,
+      "loss": 1.0947,
+      "step": 65
+    },
+    {
+      "epoch": 0.20260492040520983,
+      "grad_norm": 0.40603527426719666,
+      "learning_rate": 2.9978001207766858e-05,
+      "loss": 1.0931,
+      "step": 70
+    },
+    {
+      "epoch": 0.2170767004341534,
+      "grad_norm": 0.3855189085006714,
+      "learning_rate": 2.9963163809724016e-05,
+      "loss": 1.1052,
+      "step": 75
+    },
+    {
+      "epoch": 0.23154848046309695,
+      "grad_norm": 0.4021053910255432,
+      "learning_rate": 2.99445288908105e-05,
+      "loss": 1.0685,
+      "step": 80
+    },
+    {
+      "epoch": 0.2460202604920405,
+      "grad_norm": 0.4100794494152069,
+      "learning_rate": 2.992210118040671e-05,
+      "loss": 1.0407,
+      "step": 85
+    },
+    {
+      "epoch": 0.26049204052098407,
+      "grad_norm": 0.4250035583972931,
+      "learning_rate": 2.9895886370470525e-05,
+      "loss": 1.0416,
+      "step": 90
+    },
+    {
+      "epoch": 0.27496382054992763,
+      "grad_norm": 0.4670529067516327,
+      "learning_rate": 2.9865891114092777e-05,
+      "loss": 0.9995,
+      "step": 95
+    },
+    {
+      "epoch": 0.2894356005788712,
+      "grad_norm": 0.49352172017097473,
+      "learning_rate": 2.9832123023808732e-05,
+      "loss": 0.9835,
+      "step": 100
+    },
+    {
+      "epoch": 0.30390738060781475,
+      "grad_norm": 0.4847329556941986,
+      "learning_rate": 2.979459066966608e-05,
+      "loss": 0.9538,
+      "step": 105
+    },
+    {
+      "epoch": 0.3183791606367583,
+      "grad_norm": 0.4724056124687195,
+      "learning_rate": 2.9753303577049967e-05,
+      "loss": 0.9552,
+      "step": 110
+    },
+    {
+      "epoch": 0.33285094066570187,
+      "grad_norm": 0.49951690435409546,
+      "learning_rate": 2.970827222426551e-05,
+      "loss": 0.9723,
+      "step": 115
+    },
+    {
+      "epoch": 0.3473227206946454,
+      "grad_norm": 0.5437686443328857,
+      "learning_rate": 2.9659508039878496e-05,
+      "loss": 0.9296,
+      "step": 120
+    },
+    {
+      "epoch": 0.361794500723589,
+      "grad_norm": 0.547705888748169,
+      "learning_rate": 2.9607023399814915e-05,
+      "loss": 0.8867,
+      "step": 125
+    },
+    {
+      "epoch": 0.37626628075253254,
+      "grad_norm": 0.596917986869812,
+      "learning_rate": 2.955083162422008e-05,
+      "loss": 0.9631,
+      "step": 130
+    },
+    {
+      "epoch": 0.3907380607814761,
+      "grad_norm": 0.5863762497901917,
+      "learning_rate": 2.949094697407803e-05,
+      "loss": 0.953,
+      "step": 135
+    },
+    {
+      "epoch": 0.40520984081041966,
+      "grad_norm": 0.5602851510047913,
+      "learning_rate": 2.942738464759229e-05,
+      "loss": 0.8917,
+      "step": 140
+    },
+    {
+      "epoch": 0.4196816208393632,
+      "grad_norm": 0.5136785507202148,
+      "learning_rate": 2.9360160776328642e-05,
+      "loss": 0.9125,
+      "step": 145
+    },
+    {
+      "epoch": 0.4341534008683068,
+      "grad_norm": 0.5575056672096252,
+      "learning_rate": 2.9289292421121108e-05,
+      "loss": 0.8682,
+      "step": 150
+    },
+    {
+      "epoch": 0.44862518089725034,
+      "grad_norm": 0.6020906567573547,
+      "learning_rate": 2.9214797567742036e-05,
+      "loss": 0.853,
+      "step": 155
+    },
+    {
+      "epoch": 0.4630969609261939,
+      "grad_norm": 0.6466463804244995,
+      "learning_rate": 2.9136695122337492e-05,
+      "loss": 0.8577,
+      "step": 160
+    },
+    {
+      "epoch": 0.47756874095513746,
+      "grad_norm": 0.66497403383255,
+      "learning_rate": 2.9055004906629016e-05,
+      "loss": 0.8777,
+      "step": 165
+    },
+    {
+      "epoch": 0.492040520984081,
+      "grad_norm": 0.6498398780822754,
+      "learning_rate": 2.896974765288306e-05,
+      "loss": 0.8483,
+      "step": 170
+    },
+    {
+      "epoch": 0.5065123010130246,
+      "grad_norm": 0.6811681985855103,
+      "learning_rate": 2.8880944998649318e-05,
+      "loss": 0.8126,
+      "step": 175
+    },
+    {
+      "epoch": 0.5209840810419681,
+      "grad_norm": 0.6576763391494751,
+      "learning_rate": 2.87886194812693e-05,
+      "loss": 0.842,
+      "step": 180
+    },
+    {
+      "epoch": 0.5354558610709117,
+      "grad_norm": 0.6560257077217102,
+      "learning_rate": 2.8692794532156544e-05,
+      "loss": 0.8118,
+      "step": 185
+    },
+    {
+      "epoch": 0.5499276410998553,
+      "grad_norm": 0.6648563742637634,
+      "learning_rate": 2.8593494470849942e-05,
+      "loss": 0.7685,
+      "step": 190
+    },
+    {
+      "epoch": 0.5643994211287988,
+      "grad_norm": 0.6550049781799316,
+      "learning_rate": 2.849074449884164e-05,
+      "loss": 0.8377,
+      "step": 195
+    },
+    {
+      "epoch": 0.5788712011577424,
+      "grad_norm": 0.6944078803062439,
+      "learning_rate": 2.8384570693181143e-05,
+      "loss": 0.7758,
+      "step": 200
+    },
+    {
+      "epoch": 0.5933429811866859,
+      "grad_norm": 0.7304152846336365,
+      "learning_rate": 2.8274999999857125e-05,
+      "loss": 0.8103,
+      "step": 205
+    },
+    {
+      "epoch": 0.6078147612156295,
+      "grad_norm": 0.8426342606544495,
+      "learning_rate": 2.816206022695885e-05,
+      "loss": 0.7471,
+      "step": 210
+    },
+    {
+      "epoch": 0.622286541244573,
+      "grad_norm": 0.7130635380744934,
+      "learning_rate": 2.8045780037618675e-05,
+      "loss": 0.7708,
+      "step": 215
+    },
+    {
+      "epoch": 0.6367583212735166,
+      "grad_norm": 0.7973529696464539,
+      "learning_rate": 2.7926188942737598e-05,
+      "loss": 0.76,
+      "step": 220
+    },
+    {
+      "epoch": 0.6512301013024602,
+      "grad_norm": 0.7135194540023804,
+      "learning_rate": 2.7803317293495654e-05,
+      "loss": 0.7031,
+      "step": 225
+    },
+    {
+      "epoch": 0.6657018813314037,
+      "grad_norm": 0.73508220911026,
+      "learning_rate": 2.7677196273649063e-05,
+      "loss": 0.729,
+      "step": 230
+    },
+    {
+      "epoch": 0.6801736613603473,
+      "grad_norm": 0.753930926322937,
+      "learning_rate": 2.7547857891616045e-05,
+      "loss": 0.7269,
+      "step": 235
+    },
+    {
+      "epoch": 0.6946454413892909,
+      "grad_norm": 0.7326066493988037,
+      "learning_rate": 2.741533497235336e-05,
+      "loss": 0.7229,
+      "step": 240
+    },
+    {
+      "epoch": 0.7091172214182344,
+      "grad_norm": 0.7160481214523315,
+      "learning_rate": 2.7279661149025634e-05,
+      "loss": 0.7732,
+      "step": 245
+    },
+    {
+      "epoch": 0.723589001447178,
+      "grad_norm": 0.7680026292800903,
+      "learning_rate": 2.714087085446956e-05,
+      "loss": 0.7357,
+      "step": 250
+    },
+    {
+      "epoch": 0.7380607814761215,
+      "grad_norm": 0.7813519239425659,
+      "learning_rate": 2.6998999312455103e-05,
+      "loss": 0.7377,
+      "step": 255
+    },
+    {
+      "epoch": 0.7525325615050651,
+      "grad_norm": 0.7649766206741333,
+      "learning_rate": 2.685408252874607e-05,
+      "loss": 0.7245,
+      "step": 260
+    },
+    {
+      "epoch": 0.7670043415340086,
+      "grad_norm": 0.8014342188835144,
+      "learning_rate": 2.670615728196211e-05,
+      "loss": 0.7188,
+      "step": 265
+    },
+    {
+      "epoch": 0.7814761215629522,
+      "grad_norm": 0.829677402973175,
+      "learning_rate": 2.655526111424466e-05,
+      "loss": 0.7073,
+      "step": 270
+    },
+    {
+      "epoch": 0.7959479015918958,
+      "grad_norm": 0.7537582516670227,
+      "learning_rate": 2.640143232172904e-05,
+      "loss": 0.6762,
+      "step": 275
+    },
+    {
+      "epoch": 0.8104196816208393,
+      "grad_norm": 0.9482523202896118,
+      "learning_rate": 2.6244709944825263e-05,
+      "loss": 0.6828,
+      "step": 280
+    },
+    {
+      "epoch": 0.8248914616497829,
+      "grad_norm": 0.7638236284255981,
+      "learning_rate": 2.6085133758309887e-05,
+      "loss": 0.6885,
+      "step": 285
+    },
+    {
+      "epoch": 0.8393632416787264,
+      "grad_norm": 0.8016229271888733,
+      "learning_rate": 2.5922744261231543e-05,
+      "loss": 0.6249,
+      "step": 290
+    },
+    {
+      "epoch": 0.85383502170767,
+      "grad_norm": 0.8272259831428528,
+      "learning_rate": 2.5757582666632612e-05,
+      "loss": 0.642,
+      "step": 295
+    },
+    {
+      "epoch": 0.8683068017366136,
+      "grad_norm": 0.774215042591095,
+      "learning_rate": 2.558969089108973e-05,
+      "loss": 0.6935,
+      "step": 300
+    },
+    {
+      "epoch": 0.8827785817655571,
+      "grad_norm": 0.9142395853996277,
+      "learning_rate": 2.541911154407572e-05,
+      "loss": 0.6773,
+      "step": 305
+    },
+    {
+      "epoch": 0.8972503617945007,
+      "grad_norm": 0.902748167514801,
+      "learning_rate": 2.524588791714567e-05,
+      "loss": 0.6534,
+      "step": 310
+    },
+    {
+      "epoch": 0.9117221418234442,
+      "grad_norm": 0.8144389390945435,
+      "learning_rate": 2.5070063972949915e-05,
+      "loss": 0.6364,
+      "step": 315
+    },
+    {
+      "epoch": 0.9261939218523878,
+      "grad_norm": 0.9208300709724426,
+      "learning_rate": 2.489168433407672e-05,
+      "loss": 0.6298,
+      "step": 320
+    },
+    {
+      "epoch": 0.9406657018813314,
+      "grad_norm": 0.8535764217376709,
+      "learning_rate": 2.4710794271727415e-05,
+      "loss": 0.6493,
+      "step": 325
+    },
+    {
+      "epoch": 0.9551374819102749,
+      "grad_norm": 0.8404795527458191,
+      "learning_rate": 2.4527439694227e-05,
+      "loss": 0.5672,
+      "step": 330
+    },
+    {
+      "epoch": 0.9696092619392185,
+      "grad_norm": 1.0010117292404175,
+      "learning_rate": 2.4341667135372972e-05,
+      "loss": 0.6063,
+      "step": 335
+    },
+    {
+      "epoch": 0.984081041968162,
+      "grad_norm": 0.8761574029922485,
+      "learning_rate": 2.4153523742625492e-05,
+      "loss": 0.6009,
+      "step": 340
+    },
+    {
+      "epoch": 0.9985528219971056,
+      "grad_norm": 0.8519713878631592,
+      "learning_rate": 2.396305726514173e-05,
+      "loss": 0.5696,
+      "step": 345
+    },
+    {
+      "epoch": 1.0115774240231548,
+      "grad_norm": 0.8920317888259888,
+      "learning_rate": 2.3770316041657577e-05,
+      "loss": 0.5247,
+      "step": 350
+    },
+    {
+      "epoch": 1.0260492040520983,
+      "grad_norm": 0.9324450492858887,
+      "learning_rate": 2.357534898821967e-05,
+      "loss": 0.5679,
+      "step": 355
+    },
+    {
+      "epoch": 1.0405209840810419,
+      "grad_norm": 0.9909124970436096,
+      "learning_rate": 2.3378205585770943e-05,
+      "loss": 0.5236,
+      "step": 360
+    },
+    {
+      "epoch": 1.0549927641099854,
+      "grad_norm": 0.8417657017707825,
+      "learning_rate": 2.3178935867592783e-05,
+      "loss": 0.5008,
+      "step": 365
+    },
+    {
+      "epoch": 1.069464544138929,
+      "grad_norm": 0.9080502986907959,
+      "learning_rate": 2.2977590406607014e-05,
+      "loss": 0.4836,
+      "step": 370
+    },
+    {
+      "epoch": 1.0839363241678726,
+      "grad_norm": 0.9842959642410278,
+      "learning_rate": 2.2774220302540945e-05,
+      "loss": 0.5112,
+      "step": 375
+    },
+    {
+      "epoch": 1.0984081041968161,
+      "grad_norm": 1.0712053775787354,
+      "learning_rate": 2.2568877168958696e-05,
+      "loss": 0.5096,
+      "step": 380
+    },
+    {
+      "epoch": 1.1128798842257597,
+      "grad_norm": 0.9379140138626099,
+      "learning_rate": 2.236161312016211e-05,
+      "loss": 0.4919,
+      "step": 385
+    },
+    {
+      "epoch": 1.1273516642547032,
+      "grad_norm": 0.8969681859016418,
+      "learning_rate": 2.215248075796462e-05,
+      "loss": 0.5199,
+      "step": 390
+    },
+    {
+      "epoch": 1.1418234442836468,
+      "grad_norm": 0.8633139133453369,
+      "learning_rate": 2.194153315834135e-05,
+      "loss": 0.4964,
+      "step": 395
+    },
+    {
+      "epoch": 1.1562952243125904,
+      "grad_norm": 0.8779736161231995,
+      "learning_rate": 2.1728823857958914e-05,
+      "loss": 0.4387,
+      "step": 400
+    },
+    {
+      "epoch": 1.170767004341534,
+      "grad_norm": 0.9226593375205994,
+      "learning_rate": 2.151440684058823e-05,
+      "loss": 0.4848,
+      "step": 405
+    },
+    {
+      "epoch": 1.1852387843704775,
+      "grad_norm": 0.8742358684539795,
+      "learning_rate": 2.129833652340397e-05,
+      "loss": 0.4815,
+      "step": 410
+    },
+    {
+      "epoch": 1.199710564399421,
+      "grad_norm": 0.9066572785377502,
+      "learning_rate": 2.1080667743173904e-05,
+      "loss": 0.4618,
+      "step": 415
+    },
+    {
+      "epoch": 1.2141823444283646,
+      "grad_norm": 0.9232774972915649,
+      "learning_rate": 2.086145574234184e-05,
+      "loss": 0.5011,
+      "step": 420
+    },
+    {
+      "epoch": 1.2286541244573081,
+      "grad_norm": 1.0020390748977661,
+      "learning_rate": 2.064075615500754e-05,
+      "loss": 0.4271,
+      "step": 425
+    },
+    {
+      "epoch": 1.2431259044862517,
+      "grad_norm": 0.9579097628593445,
+      "learning_rate": 2.0418624992807297e-05,
+      "loss": 0.4407,
+      "step": 430
+    },
+    {
+      "epoch": 1.2575976845151953,
+      "grad_norm": 1.0055112838745117,
+      "learning_rate": 2.019511863069865e-05,
+      "loss": 0.4931,
+      "step": 435
+    },
+    {
+      "epoch": 1.2720694645441388,
+      "grad_norm": 1.0458002090454102,
+      "learning_rate": 1.9970293792652926e-05,
+      "loss": 0.4336,
+      "step": 440
+    },
+    {
+      "epoch": 1.2865412445730824,
+      "grad_norm": 1.1285804510116577,
+      "learning_rate": 1.9744207537259174e-05,
+      "loss": 0.437,
+      "step": 445
+    },
+    {
+      "epoch": 1.301013024602026,
+      "grad_norm": 0.9937500953674316,
+      "learning_rate": 1.95169172432432e-05,
+      "loss": 0.4032,
+      "step": 450
+    },
+    {
+      "epoch": 1.3154848046309695,
+      "grad_norm": 1.0096193552017212,
+      "learning_rate": 1.9288480594905342e-05,
+      "loss": 0.4451,
+      "step": 455
+    },
+    {
+      "epoch": 1.329956584659913,
+      "grad_norm": 1.0254855155944824,
+      "learning_rate": 1.9058955567480702e-05,
+      "loss": 0.4561,
+      "step": 460
+    },
+    {
+      "epoch": 1.3444283646888566,
+      "grad_norm": 0.88856440782547,
+      "learning_rate": 1.8828400412425527e-05,
+      "loss": 0.3902,
+      "step": 465
+    },
+    {
+      "epoch": 1.3589001447178002,
+      "grad_norm": 0.8858474493026733,
+      "learning_rate": 1.85968736426335e-05,
+      "loss": 0.4195,
+      "step": 470
+    },
+    {
+      "epoch": 1.3733719247467437,
+      "grad_norm": 0.9886773824691772,
+      "learning_rate": 1.8364434017585674e-05,
+      "loss": 0.4278,
+      "step": 475
+    },
+    {
+      "epoch": 1.3878437047756873,
+      "grad_norm": 1.0052309036254883,
+      "learning_rate": 1.813114052843783e-05,
+      "loss": 0.4329,
+      "step": 480
+    },
+    {
+      "epoch": 1.4023154848046309,
+      "grad_norm": 0.8194876313209534,
+      "learning_rate": 1.7897052383049038e-05,
+      "loss": 0.4622,
+      "step": 485
+    },
+    {
+      "epoch": 1.4167872648335744,
+      "grad_norm": 1.045122742652893,
+      "learning_rate": 1.7662228990955207e-05,
+      "loss": 0.4392,
+      "step": 490
+    },
+    {
+      "epoch": 1.431259044862518,
+      "grad_norm": 1.040113091468811,
+      "learning_rate": 1.7426729948291474e-05,
+      "loss": 0.4197,
+      "step": 495
+    },
+    {
+      "epoch": 1.4457308248914615,
+      "grad_norm": 0.9122487306594849,
+      "learning_rate": 1.71906150226672e-05,
+      "loss": 0.3582,
+      "step": 500
+    },
+    {
+      "epoch": 1.460202604920405,
+      "grad_norm": 0.9121474623680115,
+      "learning_rate": 1.6953944137997497e-05,
+      "loss": 0.4533,
+      "step": 505
+    },
+    {
+      "epoch": 1.4746743849493487,
+      "grad_norm": 1.1198792457580566,
+      "learning_rate": 1.6716777359295062e-05,
+      "loss": 0.4043,
+      "step": 510
+    },
+    {
+      "epoch": 1.4891461649782922,
+      "grad_norm": 1.1610769033432007,
+      "learning_rate": 1.6479174877426162e-05,
+      "loss": 0.3728,
+      "step": 515
+    },
+    {
+      "epoch": 1.5036179450072358,
+      "grad_norm": 1.0011494159698486,
+      "learning_rate": 1.6241196993834743e-05,
+      "loss": 0.3767,
+      "step": 520
+    },
+    {
+      "epoch": 1.5180897250361793,
+      "grad_norm": 0.9614905714988708,
+      "learning_rate": 1.6002904105238463e-05,
+      "loss": 0.4222,
+      "step": 525
+    },
+    {
+      "epoch": 1.532561505065123,
+      "grad_norm": 0.9750561118125916,
+      "learning_rate": 1.5764356688300488e-05,
+      "loss": 0.404,
+      "step": 530
+    },
+    {
+      "epoch": 1.5470332850940665,
+      "grad_norm": 1.0076310634613037,
+      "learning_rate": 1.5525615284281083e-05,
+      "loss": 0.384,
+      "step": 535
+    },
+    {
+      "epoch": 1.56150506512301,
+      "grad_norm": 1.05535888671875,
+      "learning_rate": 1.5286740483672733e-05,
+      "loss": 0.4183,
+      "step": 540
+    },
+    {
+      "epoch": 1.5759768451519536,
+      "grad_norm": 1.0437225103378296,
+      "learning_rate": 1.5047792910822832e-05,
+      "loss": 0.3849,
+      "step": 545
+    },
+    {
+      "epoch": 1.5904486251808971,
+      "grad_norm": 0.9838964939117432,
+      "learning_rate": 1.480883320854772e-05,
+      "loss": 0.3863,
+      "step": 550
+    },
+    {
+      "epoch": 1.6049204052098407,
+      "grad_norm": 0.9237931966781616,
+      "learning_rate": 1.4569922022742089e-05,
+      "loss": 0.3446,
+      "step": 555
+    },
+    {
+      "epoch": 1.6193921852387843,
+      "grad_norm": 0.9070779085159302,
+      "learning_rate": 1.4331119986987567e-05,
+      "loss": 0.4088,
+      "step": 560
+    },
+    {
+      "epoch": 1.6338639652677278,
+      "grad_norm": 1.0813218355178833,
+      "learning_rate": 1.4092487707164462e-05,
+      "loss": 0.3562,
+      "step": 565
+    },
+    {
+      "epoch": 1.6483357452966714,
+      "grad_norm": 1.0317497253417969,
+      "learning_rate": 1.3854085746070485e-05,
+      "loss": 0.3555,
+      "step": 570
+    },
+    {
+      "epoch": 1.662807525325615,
+      "grad_norm": 0.966826319694519,
+      "learning_rate": 1.3615974608050472e-05,
+      "loss": 0.3373,
+      "step": 575
+    },
+    {
+      "epoch": 1.6772793053545585,
+      "grad_norm": 0.9833858609199524,
+      "learning_rate": 1.3378214723640877e-05,
+      "loss": 0.3715,
+      "step": 580
+    },
+    {
+      "epoch": 1.691751085383502,
+      "grad_norm": 1.0183324813842773,
+      "learning_rate": 1.3140866434233045e-05,
+      "loss": 0.3186,
+      "step": 585
+    },
+    {
+      "epoch": 1.7062228654124456,
+      "grad_norm": 0.9344832301139832,
+      "learning_rate": 1.2903989976759103e-05,
+      "loss": 0.3716,
+      "step": 590
+    },
+    {
+      "epoch": 1.7206946454413892,
+      "grad_norm": 1.143686056137085,
+      "learning_rate": 1.2667645468404314e-05,
+      "loss": 0.3997,
+      "step": 595
+    },
+    {
+      "epoch": 1.7351664254703327,
+      "grad_norm": 0.957192063331604,
+      "learning_rate": 1.24318928913499e-05,
+      "loss": 0.3533,
+      "step": 600
+    },
+    {
+      "epoch": 1.7496382054992763,
+      "grad_norm": 1.083905577659607,
+      "learning_rate": 1.2196792077550044e-05,
+      "loss": 0.365,
+      "step": 605
+    },
+    {
+      "epoch": 1.7641099855282198,
+      "grad_norm": 1.013757586479187,
+      "learning_rate": 1.1962402693547109e-05,
+      "loss": 0.3662,
+      "step": 610
+    },
+    {
+      "epoch": 1.7785817655571634,
+      "grad_norm": 1.0887141227722168,
+      "learning_rate": 1.1728784225328738e-05,
+      "loss": 0.3515,
+      "step": 615
+    },
+    {
+      "epoch": 1.793053545586107,
+      "grad_norm": 1.0151911973953247,
+      "learning_rate": 1.1495995963230854e-05,
+      "loss": 0.3184,
+      "step": 620
+    },
+    {
+      "epoch": 1.8075253256150505,
+      "grad_norm": 1.1136406660079956,
+      "learning_rate": 1.1264096986890305e-05,
+      "loss": 0.3591,
+      "step": 625
+    },
+    {
+      "epoch": 1.821997105643994,
+      "grad_norm": 0.9611531496047974,
+      "learning_rate": 1.103314615025092e-05,
+      "loss": 0.3499,
+      "step": 630
+    },
+    {
+      "epoch": 1.8364688856729376,
+      "grad_norm": 1.1233144998550415,
+      "learning_rate": 1.0803202066626935e-05,
+      "loss": 0.348,
+      "step": 635
+    },
+    {
+      "epoch": 1.8509406657018812,
+      "grad_norm": 1.031089186668396,
+      "learning_rate": 1.0574323093827411e-05,
+      "loss": 0.3487,
+      "step": 640
+    },
+    {
+      "epoch": 1.8654124457308248,
+      "grad_norm": 1.002594232559204,
+      "learning_rate": 1.0346567319345555e-05,
+      "loss": 0.3193,
+      "step": 645
+    },
+    {
+      "epoch": 1.8798842257597683,
+      "grad_norm": 1.0564950704574585,
+      "learning_rate": 1.0119992545616598e-05,
+      "loss": 0.3566,
+      "step": 650
+    },
+    {
+      "epoch": 1.8943560057887119,
+      "grad_norm": 1.000454306602478,
+      "learning_rate": 9.894656275348055e-06,
+      "loss": 0.3382,
+      "step": 655
+    },
+    {
+      "epoch": 1.9088277858176554,
+      "grad_norm": 1.0865637063980103,
+      "learning_rate": 9.670615696926027e-06,
+      "loss": 0.3485,
+      "step": 660
+    },
+    {
+      "epoch": 1.923299565846599,
+      "grad_norm": 1.095211386680603,
+      "learning_rate": 9.447927669901284e-06,
+      "loss": 0.3472,
+      "step": 665
+    },
+    {
+      "epoch": 1.9377713458755426,
+      "grad_norm": 1.0050318241119385,
+      "learning_rate": 9.226648710558835e-06,
+      "loss": 0.3029,
+      "step": 670
+    },
+    {
+      "epoch": 1.9522431259044861,
+      "grad_norm": 1.0745723247528076,
+      "learning_rate": 9.00683497757453e-06,
+      "loss": 0.3134,
+      "step": 675
+    },
+    {
+      "epoch": 1.9667149059334297,
+      "grad_norm": 1.003501057624817,
+      "learning_rate": 8.788542257762545e-06,
+      "loss": 0.3097,
+      "step": 680
+    },
+    {
+      "epoch": 1.9811866859623732,
+      "grad_norm": 1.0636464357376099,
+      "learning_rate": 8.571825951917102e-06,
+      "loss": 0.3292,
+      "step": 685
+    },
+    {
+      "epoch": 1.9956584659913168,
+      "grad_norm": 0.9520276784896851,
+      "learning_rate": 8.3567410607523e-06,
+      "loss": 0.3262,
+      "step": 690
+    },
+    {
+      "epoch": 2.008683068017366,
+      "grad_norm": 0.8568843603134155,
+      "learning_rate": 8.143342170943348e-06,
+      "loss": 0.2801,
+      "step": 695
+    },
+    {
+      "epoch": 2.0231548480463095,
+      "grad_norm": 0.9544357657432556,
+      "learning_rate": 7.93168344127299e-06,
+      "loss": 0.2748,
+      "step": 700
+    },
+    {
+      "epoch": 2.037626628075253,
+      "grad_norm": 1.0312806367874146,
+      "learning_rate": 7.721818588886448e-06,
+      "loss": 0.2547,
+      "step": 705
+    },
+    {
+      "epoch": 2.0520984081041966,
+      "grad_norm": 0.9142753481864929,
+      "learning_rate": 7.513800875658483e-06,
+      "loss": 0.2405,
+      "step": 710
+    },
+    {
+      "epoch": 2.06657018813314,
+      "grad_norm": 0.9384972453117371,
+      "learning_rate": 7.3076830946760155e-06,
+      "loss": 0.264,
+      "step": 715
+    },
+    {
+      "epoch": 2.0810419681620838,
+      "grad_norm": 1.0117454528808594,
+      "learning_rate": 7.103517556839661e-06,
+      "loss": 0.2544,
+      "step": 720
+    },
+    {
+      "epoch": 2.0955137481910273,
+      "grad_norm": 1.193626880645752,
+      "learning_rate": 6.901356077587722e-06,
+      "loss": 0.2339,
+      "step": 725
+    },
+    {
+      "epoch": 2.109985528219971,
+      "grad_norm": 0.9370549917221069,
+      "learning_rate": 6.7012499637458315e-06,
+      "loss": 0.2566,
+      "step": 730
+    },
+    {
+      "epoch": 2.1244573082489144,
+      "grad_norm": 0.9933248162269592,
+      "learning_rate": 6.503250000505784e-06,
+      "loss": 0.2411,
+      "step": 735
+    },
+    {
+      "epoch": 2.138929088277858,
+      "grad_norm": 1.091636061668396,
+      "learning_rate": 6.30740643853663e-06,
+      "loss": 0.265,
+      "step": 740
+    },
+    {
+      "epoch": 2.1534008683068016,
+      "grad_norm": 0.9325742721557617,
+      "learning_rate": 6.113768981231543e-06,
+      "loss": 0.2355,
+      "step": 745
+    },
+    {
+      "epoch": 2.167872648335745,
+      "grad_norm": 0.9898898005485535,
+      "learning_rate": 5.922386772093526e-06,
+      "loss": 0.2558,
+      "step": 750
+    },
+    {
+      "epoch": 2.1823444283646887,
+      "grad_norm": 1.1324542760849,
+      "learning_rate": 5.733308382263186e-06,
+      "loss": 0.2265,
+      "step": 755
+    },
+    {
+      "epoch": 2.1968162083936322,
+      "grad_norm": 0.9923890233039856,
+      "learning_rate": 5.546581798191842e-06,
+      "loss": 0.2478,
+      "step": 760
+    },
+    {
+      "epoch": 2.211287988422576,
+      "grad_norm": 1.0704679489135742,
+      "learning_rate": 5.362254409462939e-06,
+      "loss": 0.2546,
+      "step": 765
+    },
+    {
+      "epoch": 2.2257597684515193,
+      "grad_norm": 1.0624035596847534,
+      "learning_rate": 5.180372996765025e-06,
+      "loss": 0.249,
+      "step": 770
+    },
+    {
+      "epoch": 2.240231548480463,
+      "grad_norm": 0.9799182415008545,
+      "learning_rate": 5.000983720019187e-06,
+      "loss": 0.2121,
+      "step": 775
+    },
+    {
+      "epoch": 2.2547033285094065,
+      "grad_norm": 1.0059958696365356,
+      "learning_rate": 4.824132106664077e-06,
+      "loss": 0.2623,
+      "step": 780
+    },
+    {
+      "epoch": 2.26917510853835,
+      "grad_norm": 0.9355487823486328,
+      "learning_rate": 4.649863040101444e-06,
+      "loss": 0.2591,
+      "step": 785
+    },
+    {
+      "epoch": 2.2836468885672936,
+      "grad_norm": 0.997829794883728,
+      "learning_rate": 4.478220748305115e-06,
+      "loss": 0.2574,
+      "step": 790
+    },
+    {
+      "epoch": 2.298118668596237,
+      "grad_norm": 1.1089993715286255,
+      "learning_rate": 4.309248792596333e-06,
+      "loss": 0.2547,
+      "step": 795
+    },
+    {
+      "epoch": 2.3125904486251807,
+      "grad_norm": 1.0383670330047607,
+      "learning_rate": 4.142990056588239e-06,
+      "loss": 0.2666,
+      "step": 800
+    },
+    {
+      "epoch": 2.3270622286541243,
+      "grad_norm": 1.0983021259307861,
+      "learning_rate": 3.979486735302431e-06,
+      "loss": 0.2373,
+      "step": 805
+    },
+    {
+      "epoch": 2.341534008683068,
+      "grad_norm": 1.0168687105178833,
+      "learning_rate": 3.818780324460189e-06,
+      "loss": 0.236,
+      "step": 810
+    },
+    {
+      "epoch": 2.3560057887120114,
+      "grad_norm": 1.141767144203186,
+      "learning_rate": 3.6609116099512447e-06,
+      "loss": 0.2579,
+      "step": 815
+    },
+    {
+      "epoch": 2.370477568740955,
+      "grad_norm": 1.2768852710723877,
+      "learning_rate": 3.5059206574826792e-06,
+      "loss": 0.2325,
+      "step": 820
+    },
+    {
+      "epoch": 2.384949348769899,
+      "grad_norm": 1.079278826713562,
+      "learning_rate": 3.3538468024105845e-06,
+      "loss": 0.2321,
+      "step": 825
+    },
+    {
+      "epoch": 2.399421128798842,
+      "grad_norm": 0.9278891682624817,
+      "learning_rate": 3.2047286397571075e-06,
+      "loss": 0.2215,
+      "step": 830
+    },
+    {
+      "epoch": 2.413892908827786,
+      "grad_norm": 1.0415856838226318,
+      "learning_rate": 3.0586040144153436e-06,
+      "loss": 0.251,
+      "step": 835
+    },
+    {
+      "epoch": 2.428364688856729,
+      "grad_norm": 0.9795122742652893,
+      "learning_rate": 2.9155100115446637e-06,
+      "loss": 0.2485,
+      "step": 840
+    },
+    {
+      "epoch": 2.442836468885673,
+      "grad_norm": 1.066709280014038,
+      "learning_rate": 2.7754829471587916e-06,
+      "loss": 0.2241,
+      "step": 845
+    },
+    {
+      "epoch": 2.4573082489146163,
+      "grad_norm": 0.9052194356918335,
+      "learning_rate": 2.6385583589091446e-06,
+      "loss": 0.2108,
+      "step": 850
+    },
+    {
+      "epoch": 2.4717800289435603,
+      "grad_norm": 1.0657882690429688,
+      "learning_rate": 2.5047709970656635e-06,
+      "loss": 0.2308,
+      "step": 855
+    },
+    {
+      "epoch": 2.4862518089725034,
+      "grad_norm": 1.0150898694992065,
+      "learning_rate": 2.3741548156975e-06,
+      "loss": 0.2489,
+      "step": 860
+    },
+    {
+      "epoch": 2.5007235890014474,
+      "grad_norm": 0.9340193271636963,
+      "learning_rate": 2.2467429640557903e-06,
+      "loss": 0.2236,
+      "step": 865
+    },
+    {
+      "epoch": 2.5151953690303905,
+      "grad_norm": 0.9725841283798218,
+      "learning_rate": 2.1225677781606318e-06,
+      "loss": 0.2457,
+      "step": 870
+    },
+    {
+      "epoch": 2.5296671490593345,
+      "grad_norm": 1.0327273607254028,
+      "learning_rate": 2.0016607725945136e-06,
+      "loss": 0.241,
+      "step": 875
+    },
+    {
+      "epoch": 2.5441389290882777,
+      "grad_norm": 1.0046991109848022,
+      "learning_rate": 1.884052632504159e-06,
+      "loss": 0.2365,
+      "step": 880
+    },
+    {
+      "epoch": 2.5586107091172217,
+      "grad_norm": 1.0558056831359863,
+      "learning_rate": 1.7697732058129279e-06,
+      "loss": 0.2009,
+      "step": 885
+    },
+    {
+      "epoch": 2.5730824891461648,
+      "grad_norm": 0.8913899660110474,
+      "learning_rate": 1.6588514956456585e-06,
+      "loss": 0.2313,
+      "step": 890
+    },
+    {
+      "epoch": 2.587554269175109,
+      "grad_norm": 0.8961359858512878,
+      "learning_rate": 1.551315652967928e-06,
+      "loss": 0.2315,
+      "step": 895
+    },
+    {
+      "epoch": 2.602026049204052,
+      "grad_norm": 1.0485143661499023,
+      "learning_rate": 1.4471929694415897e-06,
+      "loss": 0.2327,
+      "step": 900
+    },
+    {
+      "epoch": 2.616497829232996,
+      "grad_norm": 0.9162960052490234,
+      "learning_rate": 1.3465098704983736e-06,
+      "loss": 0.2108,
+      "step": 905
+    },
+    {
+      "epoch": 2.630969609261939,
+      "grad_norm": 1.1274350881576538,
+      "learning_rate": 1.2492919086333627e-06,
+      "loss": 0.2173,
+      "step": 910
+    },
+    {
+      "epoch": 2.645441389290883,
+      "grad_norm": 0.985431969165802,
+      "learning_rate": 1.1555637569199661e-06,
+      "loss": 0.2507,
+      "step": 915
+    },
+    {
+      "epoch": 2.659913169319826,
+      "grad_norm": 1.1033589839935303,
+      "learning_rate": 1.0653492027481287e-06,
+      "loss": 0.2499,
+      "step": 920
+    },
+    {
+      "epoch": 2.67438494934877,
+      "grad_norm": 1.0592963695526123,
+      "learning_rate": 9.786711417872856e-07,
+      "loss": 0.206,
+      "step": 925
+    },
+    {
+      "epoch": 2.6888567293777133,
+      "grad_norm": 0.9840250611305237,
+      "learning_rate": 8.955515721756447e-07,
+      "loss": 0.2617,
+      "step": 930
+    },
+    {
+      "epoch": 2.7033285094066573,
+      "grad_norm": 1.0350570678710938,
+      "learning_rate": 8.160115889372516e-07,
+      "loss": 0.2367,
+      "step": 935
+    },
+    {
+      "epoch": 2.7178002894356004,
+      "grad_norm": 1.0183647871017456,
+      "learning_rate": 7.400713786282515e-07,
+      "loss": 0.2267,
+      "step": 940
+    },
+    {
+      "epoch": 2.7322720694645444,
+      "grad_norm": 1.0445044040679932,
+      "learning_rate": 6.677502142137298e-07,
+      "loss": 0.2399,
+      "step": 945
+    },
+    {
+      "epoch": 2.7467438494934875,
+      "grad_norm": 0.9031018018722534,
+      "learning_rate": 5.990664501763787e-07,
+      "loss": 0.2224,
+      "step": 950
+    },
+    {
+      "epoch": 2.7612156295224315,
+      "grad_norm": 1.159313440322876,
+      "learning_rate": 5.340375178583129e-07,
+      "loss": 0.2573,
+      "step": 955
+    },
+    {
+      "epoch": 2.7756874095513746,
+      "grad_norm": 0.9514290690422058,
+      "learning_rate": 4.726799210371252e-07,
+      "loss": 0.2086,
+      "step": 960
+    },
+    {
+      "epoch": 2.7901591895803186,
+      "grad_norm": 1.0977853536605835,
+      "learning_rate": 4.150092317373905e-07,
+      "loss": 0.2176,
+      "step": 965
+    },
+    {
+      "epoch": 2.8046309696092617,
+      "grad_norm": 1.1040443181991577,
+      "learning_rate": 3.610400862786067e-07,
+      "loss": 0.2101,
+      "step": 970
+    },
+    {
+      "epoch": 2.8191027496382057,
+      "grad_norm": 1.138049840927124,
+      "learning_rate": 3.1078618156063164e-07,
+      "loss": 0.229,
+      "step": 975
+    },
+    {
+      "epoch": 2.833574529667149,
+      "grad_norm": 0.9003154039382935,
+      "learning_rate": 2.6426027158752475e-07,
+      "loss": 0.2277,
+      "step": 980
+    },
+    {
+      "epoch": 2.848046309696093,
+      "grad_norm": 0.8005179762840271,
+      "learning_rate": 2.2147416423069665e-07,
+      "loss": 0.222,
+      "step": 985
+    },
+    {
+      "epoch": 2.862518089725036,
+      "grad_norm": 0.9654896259307861,
+      "learning_rate": 1.8243871823217127e-07,
+      "loss": 0.2311,
+      "step": 990
+    },
+    {
+      "epoch": 2.87698986975398,
+      "grad_norm": 1.1691473722457886,
+      "learning_rate": 1.4716384044873022e-07,
+      "loss": 0.2333,
+      "step": 995
+    },
+    {
+      "epoch": 2.891461649782923,
+      "grad_norm": 1.1127536296844482,
+      "learning_rate": 1.1565848333764395e-07,
+      "loss": 0.2079,
+      "step": 1000
+    },
+    {
+      "epoch": 2.905933429811867,
+      "grad_norm": 1.0087896585464478,
+      "learning_rate": 8.793064268460605e-08,
+      "loss": 0.196,
+      "step": 1005
+    },
+    {
+      "epoch": 2.92040520984081,
+      "grad_norm": 1.018527626991272,
+      "learning_rate": 6.398735557448299e-08,
+      "loss": 0.2531,
+      "step": 1010
+    },
+    {
+      "epoch": 2.934876989869754,
+      "grad_norm": 0.934693455696106,
+      "learning_rate": 4.383469860535616e-08,
+      "loss": 0.2462,
+      "step": 1015
+    },
+    {
+      "epoch": 2.9493487698986973,
+      "grad_norm": 1.020354986190796,
+      "learning_rate": 2.7477786346337132e-08,
+      "loss": 0.2525,
+      "step": 1020
+    },
+    {
+      "epoch": 2.9638205499276413,
+      "grad_norm": 1.1043814420700073,
+      "learning_rate": 1.492077003953596e-08,
+      "loss": 0.2506,
+      "step": 1025
+    },
+    {
+      "epoch": 2.9782923299565844,
+      "grad_norm": 1.0787711143493652,
+      "learning_rate": 6.1668365465089586e-09,
+      "loss": 0.2287,
+      "step": 1030
+    },
+    {
+      "epoch": 2.9927641099855284,
+      "grad_norm": 1.0761783123016357,
+      "learning_rate": 1.2182075394590041e-09,
+      "loss": 0.225,
+      "step": 1035
+    },
+    {
+      "epoch": 3.0,
+      "step": 1038,
+      "total_flos": 1.5637608849987338e+18,
+      "train_loss": 0.5088282435960163,
+      "train_runtime": 723.6343,
+      "train_samples_per_second": 45.794,
+      "train_steps_per_second": 1.434
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1038,
+  "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": 1.5637608849987338e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

100_128_e3_3e-5/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9da26090bc48be6239bced80c604db89301099a3c516ff967eaac5ca8c0b1ee
+size 8273