Upload folder using huggingface_hub

126_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": [
+    "down_proj",
+    "v_proj",
+    "o_proj",
+    "up_proj",
+    "q_proj",
+    "k_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

126_128_e3_3e-5/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e9c64a4bcbcb36b4d4c27b00cab38b0058b617fe5f64a6c80ab138a37ac9eae
+size 791751704

126_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
+}

126_128_e3_3e-5/all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.3711430478609777e+18,
+    "train_loss": 0.6045596268238166,
+    "train_runtime": 644.6715,
+    "train_samples": 10395,
+    "train_samples_per_second": 48.373,
+    "train_steps_per_second": 1.512
+}

126_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 %}

126_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
+}

126_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
+  }
+}

126_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
+}

126_128_e3_3e-5/train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.3711430478609777e+18,
+    "train_loss": 0.6045596268238166,
+    "train_runtime": 644.6715,
+    "train_samples": 10395,
+    "train_samples_per_second": 48.373,
+    "train_steps_per_second": 1.512
+}

126_128_e3_3e-5/trainer_state.json

@@ -0,0 +1,1408 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 975,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.015384615384615385,
+      "grad_norm": 3.191135883331299,
+      "learning_rate": 2.4489795918367347e-06,
+      "loss": 1.5896,
+      "step": 5
+    },
+    {
+      "epoch": 0.03076923076923077,
+      "grad_norm": 2.2008650302886963,
+      "learning_rate": 5.510204081632653e-06,
+      "loss": 1.5372,
+      "step": 10
+    },
+    {
+      "epoch": 0.046153846153846156,
+      "grad_norm": 0.8214209079742432,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 1.4147,
+      "step": 15
+    },
+    {
+      "epoch": 0.06153846153846154,
+      "grad_norm": 0.4854404926300049,
+      "learning_rate": 1.163265306122449e-05,
+      "loss": 1.4242,
+      "step": 20
+    },
+    {
+      "epoch": 0.07692307692307693,
+      "grad_norm": 0.4039292633533478,
+      "learning_rate": 1.4693877551020408e-05,
+      "loss": 1.4064,
+      "step": 25
+    },
+    {
+      "epoch": 0.09230769230769231,
+      "grad_norm": 0.4518930912017822,
+      "learning_rate": 1.7755102040816327e-05,
+      "loss": 1.3914,
+      "step": 30
+    },
+    {
+      "epoch": 0.1076923076923077,
+      "grad_norm": 0.4490149915218353,
+      "learning_rate": 2.0816326530612247e-05,
+      "loss": 1.3371,
+      "step": 35
+    },
+    {
+      "epoch": 0.12307692307692308,
+      "grad_norm": 0.45870330929756165,
+      "learning_rate": 2.3877551020408164e-05,
+      "loss": 1.3218,
+      "step": 40
+    },
+    {
+      "epoch": 0.13846153846153847,
+      "grad_norm": 0.40856820344924927,
+      "learning_rate": 2.6938775510204084e-05,
+      "loss": 1.2739,
+      "step": 45
+    },
+    {
+      "epoch": 0.15384615384615385,
+      "grad_norm": 0.4209417402744293,
+      "learning_rate": 3e-05,
+      "loss": 1.2788,
+      "step": 50
+    },
+    {
+      "epoch": 0.16923076923076924,
+      "grad_norm": 0.4109303951263428,
+      "learning_rate": 2.9997841914583366e-05,
+      "loss": 1.2715,
+      "step": 55
+    },
+    {
+      "epoch": 0.18461538461538463,
+      "grad_norm": 0.42402413487434387,
+      "learning_rate": 2.9991368279311155e-05,
+      "loss": 1.2645,
+      "step": 60
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.36688071489334106,
+      "learning_rate": 2.998058095693775e-05,
+      "loss": 1.2513,
+      "step": 65
+    },
+    {
+      "epoch": 0.2153846153846154,
+      "grad_norm": 0.4094462990760803,
+      "learning_rate": 2.996548305145823e-05,
+      "loss": 1.2691,
+      "step": 70
+    },
+    {
+      "epoch": 0.23076923076923078,
+      "grad_norm": 0.4490308463573456,
+      "learning_rate": 2.9946078907215212e-05,
+      "loss": 1.2602,
+      "step": 75
+    },
+    {
+      "epoch": 0.24615384615384617,
+      "grad_norm": 0.4254547953605652,
+      "learning_rate": 2.9922374107648796e-05,
+      "loss": 1.2233,
+      "step": 80
+    },
+    {
+      "epoch": 0.26153846153846155,
+      "grad_norm": 0.45248717069625854,
+      "learning_rate": 2.989437547368994e-05,
+      "loss": 1.1324,
+      "step": 85
+    },
+    {
+      "epoch": 0.27692307692307694,
+      "grad_norm": 0.44229620695114136,
+      "learning_rate": 2.98620910617978e-05,
+      "loss": 1.1777,
+      "step": 90
+    },
+    {
+      "epoch": 0.2923076923076923,
+      "grad_norm": 0.47411033511161804,
+      "learning_rate": 2.982553016164151e-05,
+      "loss": 1.1322,
+      "step": 95
+    },
+    {
+      "epoch": 0.3076923076923077,
+      "grad_norm": 0.5014300346374512,
+      "learning_rate": 2.9784703293427125e-05,
+      "loss": 1.1336,
+      "step": 100
+    },
+    {
+      "epoch": 0.3230769230769231,
+      "grad_norm": 0.46827614307403564,
+      "learning_rate": 2.9739622204870503e-05,
+      "loss": 1.1823,
+      "step": 105
+    },
+    {
+      "epoch": 0.3384615384615385,
+      "grad_norm": 0.5334767699241638,
+      "learning_rate": 2.9690299867816947e-05,
+      "loss": 1.0821,
+      "step": 110
+    },
+    {
+      "epoch": 0.35384615384615387,
+      "grad_norm": 0.43920257687568665,
+      "learning_rate": 2.9636750474508627e-05,
+      "loss": 1.118,
+      "step": 115
+    },
+    {
+      "epoch": 0.36923076923076925,
+      "grad_norm": 0.555946946144104,
+      "learning_rate": 2.957898943350085e-05,
+      "loss": 1.063,
+      "step": 120
+    },
+    {
+      "epoch": 0.38461538461538464,
+      "grad_norm": 0.5551937818527222,
+      "learning_rate": 2.9517033365228314e-05,
+      "loss": 1.0341,
+      "step": 125
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.5497499108314514,
+      "learning_rate": 2.945090009722268e-05,
+      "loss": 1.1253,
+      "step": 130
+    },
+    {
+      "epoch": 0.4153846153846154,
+      "grad_norm": 0.5459065437316895,
+      "learning_rate": 2.9380608658982763e-05,
+      "loss": 1.0253,
+      "step": 135
+    },
+    {
+      "epoch": 0.4307692307692308,
+      "grad_norm": 0.652377724647522,
+      "learning_rate": 2.930617927649895e-05,
+      "loss": 1.1149,
+      "step": 140
+    },
+    {
+      "epoch": 0.4461538461538462,
+      "grad_norm": 0.618680477142334,
+      "learning_rate": 2.9227633366433227e-05,
+      "loss": 1.1067,
+      "step": 145
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "grad_norm": 0.6362542510032654,
+      "learning_rate": 2.9144993529956657e-05,
+      "loss": 1.0252,
+      "step": 150
+    },
+    {
+      "epoch": 0.47692307692307695,
+      "grad_norm": 0.6453359723091125,
+      "learning_rate": 2.905828354624604e-05,
+      "loss": 1.0505,
+      "step": 155
+    },
+    {
+      "epoch": 0.49230769230769234,
+      "grad_norm": 0.6349513530731201,
+      "learning_rate": 2.896752836564155e-05,
+      "loss": 0.9646,
+      "step": 160
+    },
+    {
+      "epoch": 0.5076923076923077,
+      "grad_norm": 0.6579886078834534,
+      "learning_rate": 2.887275410246742e-05,
+      "loss": 1.0122,
+      "step": 165
+    },
+    {
+      "epoch": 0.5230769230769231,
+      "grad_norm": 0.7696048021316528,
+      "learning_rate": 2.8773988027517678e-05,
+      "loss": 0.953,
+      "step": 170
+    },
+    {
+      "epoch": 0.5384615384615384,
+      "grad_norm": 0.7107468247413635,
+      "learning_rate": 2.867125856020913e-05,
+      "loss": 0.93,
+      "step": 175
+    },
+    {
+      "epoch": 0.5538461538461539,
+      "grad_norm": 0.6523647904396057,
+      "learning_rate": 2.8564595260403804e-05,
+      "loss": 1.0067,
+      "step": 180
+    },
+    {
+      "epoch": 0.5692307692307692,
+      "grad_norm": 0.6959507465362549,
+      "learning_rate": 2.8454028819903277e-05,
+      "loss": 0.9288,
+      "step": 185
+    },
+    {
+      "epoch": 0.5846153846153846,
+      "grad_norm": 0.7379077672958374,
+      "learning_rate": 2.833959105361726e-05,
+      "loss": 0.8966,
+      "step": 190
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.7674935460090637,
+      "learning_rate": 2.822131489040902e-05,
+      "loss": 0.934,
+      "step": 195
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": 0.7664425373077393,
+      "learning_rate": 2.8099234363620284e-05,
+      "loss": 0.9205,
+      "step": 200
+    },
+    {
+      "epoch": 0.6307692307692307,
+      "grad_norm": 0.8975176811218262,
+      "learning_rate": 2.7973384601278323e-05,
+      "loss": 0.8789,
+      "step": 205
+    },
+    {
+      "epoch": 0.6461538461538462,
+      "grad_norm": 0.8107626438140869,
+      "learning_rate": 2.7843801815988043e-05,
+      "loss": 0.9014,
+      "step": 210
+    },
+    {
+      "epoch": 0.6615384615384615,
+      "grad_norm": 0.8643553853034973,
+      "learning_rate": 2.7710523294512002e-05,
+      "loss": 0.8522,
+      "step": 215
+    },
+    {
+      "epoch": 0.676923076923077,
+      "grad_norm": 0.8077470064163208,
+      "learning_rate": 2.7573587387041342e-05,
+      "loss": 0.851,
+      "step": 220
+    },
+    {
+      "epoch": 0.6923076923076923,
+      "grad_norm": 0.7755894660949707,
+      "learning_rate": 2.7433033496160713e-05,
+      "loss": 0.8735,
+      "step": 225
+    },
+    {
+      "epoch": 0.7076923076923077,
+      "grad_norm": 0.894898533821106,
+      "learning_rate": 2.7288902065510407e-05,
+      "loss": 0.8731,
+      "step": 230
+    },
+    {
+      "epoch": 0.7230769230769231,
+      "grad_norm": 0.8682807683944702,
+      "learning_rate": 2.71412345681489e-05,
+      "loss": 0.8826,
+      "step": 235
+    },
+    {
+      "epoch": 0.7384615384615385,
+      "grad_norm": 0.8361955285072327,
+      "learning_rate": 2.6990073494619198e-05,
+      "loss": 0.826,
+      "step": 240
+    },
+    {
+      "epoch": 0.7538461538461538,
+      "grad_norm": 0.7905547022819519,
+      "learning_rate": 2.6835462340722422e-05,
+      "loss": 0.7972,
+      "step": 245
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 0.8578044176101685,
+      "learning_rate": 2.667744559500209e-05,
+      "loss": 0.828,
+      "step": 250
+    },
+    {
+      "epoch": 0.7846153846153846,
+      "grad_norm": 0.8790921568870544,
+      "learning_rate": 2.6516068725942815e-05,
+      "loss": 0.846,
+      "step": 255
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.9101660251617432,
+      "learning_rate": 2.6351378168886948e-05,
+      "loss": 0.7741,
+      "step": 260
+    },
+    {
+      "epoch": 0.8153846153846154,
+      "grad_norm": 0.8347858786582947,
+      "learning_rate": 2.618342131267309e-05,
+      "loss": 0.8165,
+      "step": 265
+    },
+    {
+      "epoch": 0.8307692307692308,
+      "grad_norm": 0.9162393808364868,
+      "learning_rate": 2.601224648600017e-05,
+      "loss": 0.7888,
+      "step": 270
+    },
+    {
+      "epoch": 0.8461538461538461,
+      "grad_norm": 0.864322304725647,
+      "learning_rate": 2.5837902943521144e-05,
+      "loss": 0.7808,
+      "step": 275
+    },
+    {
+      "epoch": 0.8615384615384616,
+      "grad_norm": 0.8308318853378296,
+      "learning_rate": 2.566044085167021e-05,
+      "loss": 0.7345,
+      "step": 280
+    },
+    {
+      "epoch": 0.8769230769230769,
+      "grad_norm": 0.8681084513664246,
+      "learning_rate": 2.5479911274227696e-05,
+      "loss": 0.7924,
+      "step": 285
+    },
+    {
+      "epoch": 0.8923076923076924,
+      "grad_norm": 0.8732675909996033,
+      "learning_rate": 2.529636615762671e-05,
+      "loss": 0.7571,
+      "step": 290
+    },
+    {
+      "epoch": 0.9076923076923077,
+      "grad_norm": 0.924938440322876,
+      "learning_rate": 2.5109858316005844e-05,
+      "loss": 0.7808,
+      "step": 295
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 0.9509190917015076,
+      "learning_rate": 2.4920441416012183e-05,
+      "loss": 0.7517,
+      "step": 300
+    },
+    {
+      "epoch": 0.9384615384615385,
+      "grad_norm": 1.0044610500335693,
+      "learning_rate": 2.472816996135899e-05,
+      "loss": 0.7589,
+      "step": 305
+    },
+    {
+      "epoch": 0.9538461538461539,
+      "grad_norm": 0.9878382086753845,
+      "learning_rate": 2.4533099277142578e-05,
+      "loss": 0.7157,
+      "step": 310
+    },
+    {
+      "epoch": 0.9692307692307692,
+      "grad_norm": 0.9564942717552185,
+      "learning_rate": 2.433528549392279e-05,
+      "loss": 0.7266,
+      "step": 315
+    },
+    {
+      "epoch": 0.9846153846153847,
+      "grad_norm": 0.9731267094612122,
+      "learning_rate": 2.4134785531571735e-05,
+      "loss": 0.7104,
+      "step": 320
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.9944301843643188,
+      "learning_rate": 2.393165708289537e-05,
+      "loss": 0.6721,
+      "step": 325
+    },
+    {
+      "epoch": 1.0153846153846153,
+      "grad_norm": 1.0032981634140015,
+      "learning_rate": 2.372595859703275e-05,
+      "loss": 0.6352,
+      "step": 330
+    },
+    {
+      "epoch": 1.0307692307692307,
+      "grad_norm": 0.9027681350708008,
+      "learning_rate": 2.3517749262637542e-05,
+      "loss": 0.5951,
+      "step": 335
+    },
+    {
+      "epoch": 1.0461538461538462,
+      "grad_norm": 0.9905908703804016,
+      "learning_rate": 2.330708899084683e-05,
+      "loss": 0.5574,
+      "step": 340
+    },
+    {
+      "epoch": 1.0615384615384615,
+      "grad_norm": 1.0512447357177734,
+      "learning_rate": 2.3094038398042015e-05,
+      "loss": 0.6123,
+      "step": 345
+    },
+    {
+      "epoch": 1.0769230769230769,
+      "grad_norm": 0.9578827023506165,
+      "learning_rate": 2.287865878840673e-05,
+      "loss": 0.6018,
+      "step": 350
+    },
+    {
+      "epoch": 1.0923076923076924,
+      "grad_norm": 1.1320775747299194,
+      "learning_rate": 2.2661012136286932e-05,
+      "loss": 0.592,
+      "step": 355
+    },
+    {
+      "epoch": 1.1076923076923078,
+      "grad_norm": 0.9369445443153381,
+      "learning_rate": 2.2441161068358067e-05,
+      "loss": 0.579,
+      "step": 360
+    },
+    {
+      "epoch": 1.123076923076923,
+      "grad_norm": 1.0818852186203003,
+      "learning_rate": 2.2219168845604614e-05,
+      "loss": 0.5693,
+      "step": 365
+    },
+    {
+      "epoch": 1.1384615384615384,
+      "grad_norm": 1.0641779899597168,
+      "learning_rate": 2.1995099345117035e-05,
+      "loss": 0.5313,
+      "step": 370
+    },
+    {
+      "epoch": 1.1538461538461537,
+      "grad_norm": 0.9953758120536804,
+      "learning_rate": 2.1769017041711508e-05,
+      "loss": 0.5949,
+      "step": 375
+    },
+    {
+      "epoch": 1.1692307692307693,
+      "grad_norm": 1.0875123739242554,
+      "learning_rate": 2.1540986989377635e-05,
+      "loss": 0.5945,
+      "step": 380
+    },
+    {
+      "epoch": 1.1846153846153846,
+      "grad_norm": 1.1269574165344238,
+      "learning_rate": 2.1311074802559464e-05,
+      "loss": 0.5914,
+      "step": 385
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 1.0737024545669556,
+      "learning_rate": 2.107934663727534e-05,
+      "loss": 0.5707,
+      "step": 390
+    },
+    {
+      "epoch": 1.2153846153846155,
+      "grad_norm": 1.0038108825683594,
+      "learning_rate": 2.0845869172081802e-05,
+      "loss": 0.5929,
+      "step": 395
+    },
+    {
+      "epoch": 1.2307692307692308,
+      "grad_norm": 1.0682005882263184,
+      "learning_rate": 2.0610709588887233e-05,
+      "loss": 0.5211,
+      "step": 400
+    },
+    {
+      "epoch": 1.2461538461538462,
+      "grad_norm": 1.027268648147583,
+      "learning_rate": 2.037393555362056e-05,
+      "loss": 0.5378,
+      "step": 405
+    },
+    {
+      "epoch": 1.2615384615384615,
+      "grad_norm": 1.1356418132781982,
+      "learning_rate": 2.013561519676079e-05,
+      "loss": 0.537,
+      "step": 410
+    },
+    {
+      "epoch": 1.2769230769230768,
+      "grad_norm": 1.033194661140442,
+      "learning_rate": 1.989581709373281e-05,
+      "loss": 0.54,
+      "step": 415
+    },
+    {
+      "epoch": 1.2923076923076924,
+      "grad_norm": 1.1161775588989258,
+      "learning_rate": 1.965461024517517e-05,
+      "loss": 0.527,
+      "step": 420
+    },
+    {
+      "epoch": 1.3076923076923077,
+      "grad_norm": 1.2823989391326904,
+      "learning_rate": 1.9412064057085496e-05,
+      "loss": 0.5262,
+      "step": 425
+    },
+    {
+      "epoch": 1.323076923076923,
+      "grad_norm": 1.1141964197158813,
+      "learning_rate": 1.916824832084931e-05,
+      "loss": 0.5473,
+      "step": 430
+    },
+    {
+      "epoch": 1.3384615384615386,
+      "grad_norm": 1.1521342992782593,
+      "learning_rate": 1.892323319315791e-05,
+      "loss": 0.5212,
+      "step": 435
+    },
+    {
+      "epoch": 1.353846153846154,
+      "grad_norm": 1.1139543056488037,
+      "learning_rate": 1.867708917582115e-05,
+      "loss": 0.5125,
+      "step": 440
+    },
+    {
+      "epoch": 1.3692307692307693,
+      "grad_norm": 1.0473060607910156,
+      "learning_rate": 1.8429887095480917e-05,
+      "loss": 0.477,
+      "step": 445
+    },
+    {
+      "epoch": 1.3846153846153846,
+      "grad_norm": 1.2336174249649048,
+      "learning_rate": 1.8181698083231162e-05,
+      "loss": 0.5332,
+      "step": 450
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 1.1250574588775635,
+      "learning_rate": 1.793259355415026e-05,
+      "loss": 0.5502,
+      "step": 455
+    },
+    {
+      "epoch": 1.4153846153846155,
+      "grad_norm": 1.0635682344436646,
+      "learning_rate": 1.768264518675175e-05,
+      "loss": 0.5409,
+      "step": 460
+    },
+    {
+      "epoch": 1.4307692307692308,
+      "grad_norm": 1.1778167486190796,
+      "learning_rate": 1.7431924902359168e-05,
+      "loss": 0.49,
+      "step": 465
+    },
+    {
+      "epoch": 1.4461538461538461,
+      "grad_norm": 1.1598814725875854,
+      "learning_rate": 1.71805048444111e-05,
+      "loss": 0.5484,
+      "step": 470
+    },
+    {
+      "epoch": 1.4615384615384617,
+      "grad_norm": 1.1300697326660156,
+      "learning_rate": 1.692845735770228e-05,
+      "loss": 0.4913,
+      "step": 475
+    },
+    {
+      "epoch": 1.476923076923077,
+      "grad_norm": 1.0996512174606323,
+      "learning_rate": 1.667585496756676e-05,
+      "loss": 0.4471,
+      "step": 480
+    },
+    {
+      "epoch": 1.4923076923076923,
+      "grad_norm": 1.250686526298523,
+      "learning_rate": 1.642277035900912e-05,
+      "loss": 0.5164,
+      "step": 485
+    },
+    {
+      "epoch": 1.5076923076923077,
+      "grad_norm": 1.1898046731948853,
+      "learning_rate": 1.6169276355789747e-05,
+      "loss": 0.546,
+      "step": 490
+    },
+    {
+      "epoch": 1.523076923076923,
+      "grad_norm": 1.2050820589065552,
+      "learning_rate": 1.5915445899470185e-05,
+      "loss": 0.4694,
+      "step": 495
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 1.1026623249053955,
+      "learning_rate": 1.5661352028424573e-05,
+      "loss": 0.4641,
+      "step": 500
+    },
+    {
+      "epoch": 1.5538461538461539,
+      "grad_norm": 1.181199312210083,
+      "learning_rate": 1.5407067856823252e-05,
+      "loss": 0.4485,
+      "step": 505
+    },
+    {
+      "epoch": 1.5692307692307692,
+      "grad_norm": 1.0810766220092773,
+      "learning_rate": 1.515266655359455e-05,
+      "loss": 0.4762,
+      "step": 510
+    },
+    {
+      "epoch": 1.5846153846153848,
+      "grad_norm": 1.1683320999145508,
+      "learning_rate": 1.4898221321370785e-05,
+      "loss": 0.4701,
+      "step": 515
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 1.2383395433425903,
+      "learning_rate": 1.4643805375424637e-05,
+      "loss": 0.4816,
+      "step": 520
+    },
+    {
+      "epoch": 1.6153846153846154,
+      "grad_norm": 1.0712422132492065,
+      "learning_rate": 1.438949192260179e-05,
+      "loss": 0.4473,
+      "step": 525
+    },
+    {
+      "epoch": 1.6307692307692307,
+      "grad_norm": 1.1591110229492188,
+      "learning_rate": 1.413535414025608e-05,
+      "loss": 0.4308,
+      "step": 530
+    },
+    {
+      "epoch": 1.646153846153846,
+      "grad_norm": 1.138411283493042,
+      "learning_rate": 1.3881465155193107e-05,
+      "loss": 0.4879,
+      "step": 535
+    },
+    {
+      "epoch": 1.6615384615384614,
+      "grad_norm": 1.1001267433166504,
+      "learning_rate": 1.362789802262834e-05,
+      "loss": 0.4762,
+      "step": 540
+    },
+    {
+      "epoch": 1.676923076923077,
+      "grad_norm": 1.220465898513794,
+      "learning_rate": 1.337472570516591e-05,
+      "loss": 0.4094,
+      "step": 545
+    },
+    {
+      "epoch": 1.6923076923076923,
+      "grad_norm": 1.1158863306045532,
+      "learning_rate": 1.3122021051803974e-05,
+      "loss": 0.4694,
+      "step": 550
+    },
+    {
+      "epoch": 1.7076923076923078,
+      "grad_norm": 1.2002766132354736,
+      "learning_rate": 1.286985677697281e-05,
+      "loss": 0.4276,
+      "step": 555
+    },
+    {
+      "epoch": 1.7230769230769232,
+      "grad_norm": 1.1275635957717896,
+      "learning_rate": 1.2618305439611647e-05,
+      "loss": 0.4689,
+      "step": 560
+    },
+    {
+      "epoch": 1.7384615384615385,
+      "grad_norm": 1.297777533531189,
+      "learning_rate": 1.236743942229017e-05,
+      "loss": 0.4617,
+      "step": 565
+    },
+    {
+      "epoch": 1.7538461538461538,
+      "grad_norm": 1.2170557975769043,
+      "learning_rate": 1.2117330910380846e-05,
+      "loss": 0.4051,
+      "step": 570
+    },
+    {
+      "epoch": 1.7692307692307692,
+      "grad_norm": 1.2399832010269165,
+      "learning_rate": 1.1868051871287964e-05,
+      "loss": 0.4547,
+      "step": 575
+    },
+    {
+      "epoch": 1.7846153846153845,
+      "grad_norm": 1.2813540697097778,
+      "learning_rate": 1.161967403373937e-05,
+      "loss": 0.4369,
+      "step": 580
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 1.2256884574890137,
+      "learning_rate": 1.137226886714695e-05,
+      "loss": 0.4332,
+      "step": 585
+    },
+    {
+      "epoch": 1.8153846153846154,
+      "grad_norm": 1.467110276222229,
+      "learning_rate": 1.1125907561041636e-05,
+      "loss": 0.4539,
+      "step": 590
+    },
+    {
+      "epoch": 1.830769230769231,
+      "grad_norm": 1.1153144836425781,
+      "learning_rate": 1.0880661004589008e-05,
+      "loss": 0.4214,
+      "step": 595
+    },
+    {
+      "epoch": 1.8461538461538463,
+      "grad_norm": 1.177450180053711,
+      "learning_rate": 1.0636599766191336e-05,
+      "loss": 0.4453,
+      "step": 600
+    },
+    {
+      "epoch": 1.8615384615384616,
+      "grad_norm": 1.2653224468231201,
+      "learning_rate": 1.0393794073181874e-05,
+      "loss": 0.4127,
+      "step": 605
+    },
+    {
+      "epoch": 1.876923076923077,
+      "grad_norm": 1.1197375059127808,
+      "learning_rate": 1.0152313791617299e-05,
+      "loss": 0.422,
+      "step": 610
+    },
+    {
+      "epoch": 1.8923076923076922,
+      "grad_norm": 1.1471089124679565,
+      "learning_rate": 9.912228406174155e-06,
+      "loss": 0.4434,
+      "step": 615
+    },
+    {
+      "epoch": 1.9076923076923076,
+      "grad_norm": 1.133317470550537,
+      "learning_rate": 9.67360700015498e-06,
+      "loss": 0.4197,
+      "step": 620
+    },
+    {
+      "epoch": 1.9230769230769231,
+      "grad_norm": 1.1511826515197754,
+      "learning_rate": 9.436518235609969e-06,
+      "loss": 0.4271,
+      "step": 625
+    },
+    {
+      "epoch": 1.9384615384615385,
+      "grad_norm": 1.30781090259552,
+      "learning_rate": 9.201030333579816e-06,
+      "loss": 0.3939,
+      "step": 630
+    },
+    {
+      "epoch": 1.953846153846154,
+      "grad_norm": 1.1271767616271973,
+      "learning_rate": 8.96721105446548e-06,
+      "loss": 0.3711,
+      "step": 635
+    },
+    {
+      "epoch": 1.9692307692307693,
+      "grad_norm": 1.098168134689331,
+      "learning_rate": 8.735127678530473e-06,
+      "loss": 0.3663,
+      "step": 640
+    },
+    {
+      "epoch": 1.9846153846153847,
+      "grad_norm": 1.142554521560669,
+      "learning_rate": 8.504846986541336e-06,
+      "loss": 0.3951,
+      "step": 645
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.1693685054779053,
+      "learning_rate": 8.276435240551819e-06,
+      "loss": 0.3729,
+      "step": 650
+    },
+    {
+      "epoch": 2.0153846153846153,
+      "grad_norm": 1.2102603912353516,
+      "learning_rate": 8.04995816483632e-06,
+      "loss": 0.3402,
+      "step": 655
+    },
+    {
+      "epoch": 2.0307692307692307,
+      "grad_norm": 1.119484782218933,
+      "learning_rate": 7.82548092697809e-06,
+      "loss": 0.314,
+      "step": 660
+    },
+    {
+      "epoch": 2.046153846153846,
+      "grad_norm": 1.3012409210205078,
+      "learning_rate": 7.603068119117569e-06,
+      "loss": 0.3415,
+      "step": 665
+    },
+    {
+      "epoch": 2.0615384615384613,
+      "grad_norm": 1.1300331354141235,
+      "learning_rate": 7.3827837393663725e-06,
+      "loss": 0.3379,
+      "step": 670
+    },
+    {
+      "epoch": 2.076923076923077,
+      "grad_norm": 2.4324357509613037,
+      "learning_rate": 7.164691173392167e-06,
+      "loss": 0.3203,
+      "step": 675
+    },
+    {
+      "epoch": 2.0923076923076924,
+      "grad_norm": 1.119283676147461,
+      "learning_rate": 6.9488531761797625e-06,
+      "loss": 0.3326,
+      "step": 680
+    },
+    {
+      "epoch": 2.1076923076923078,
+      "grad_norm": 1.340505838394165,
+      "learning_rate": 6.73533185397372e-06,
+      "loss": 0.3345,
+      "step": 685
+    },
+    {
+      "epoch": 2.123076923076923,
+      "grad_norm": 1.2588993310928345,
+      "learning_rate": 6.524188646407571e-06,
+      "loss": 0.3304,
+      "step": 690
+    },
+    {
+      "epoch": 2.1384615384615384,
+      "grad_norm": 1.0824459791183472,
+      "learning_rate": 6.315484308824933e-06,
+      "loss": 0.3243,
+      "step": 695
+    },
+    {
+      "epoch": 2.1538461538461537,
+      "grad_norm": 1.2945126295089722,
+      "learning_rate": 6.109278894797447e-06,
+      "loss": 0.3171,
+      "step": 700
+    },
+    {
+      "epoch": 2.169230769230769,
+      "grad_norm": 1.2287533283233643,
+      "learning_rate": 5.905631738844694e-06,
+      "loss": 0.2892,
+      "step": 705
+    },
+    {
+      "epoch": 2.184615384615385,
+      "grad_norm": 1.2344982624053955,
+      "learning_rate": 5.704601439360997e-06,
+      "loss": 0.3165,
+      "step": 710
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 1.204910159111023,
+      "learning_rate": 5.506245841754031e-06,
+      "loss": 0.3033,
+      "step": 715
+    },
+    {
+      "epoch": 2.2153846153846155,
+      "grad_norm": 1.114548921585083,
+      "learning_rate": 5.310622021800134e-06,
+      "loss": 0.2886,
+      "step": 720
+    },
+    {
+      "epoch": 2.230769230769231,
+      "grad_norm": 1.2904489040374756,
+      "learning_rate": 5.117786269221036e-06,
+      "loss": 0.2853,
+      "step": 725
+    },
+    {
+      "epoch": 2.246153846153846,
+      "grad_norm": 1.241295337677002,
+      "learning_rate": 4.927794071486797e-06,
+      "loss": 0.336,
+      "step": 730
+    },
+    {
+      "epoch": 2.2615384615384615,
+      "grad_norm": 1.2287375926971436,
+      "learning_rate": 4.740700097849584e-06,
+      "loss": 0.322,
+      "step": 735
+    },
+    {
+      "epoch": 2.276923076923077,
+      "grad_norm": 1.2263306379318237,
+      "learning_rate": 4.556558183612854e-06,
+      "loss": 0.2966,
+      "step": 740
+    },
+    {
+      "epoch": 2.292307692307692,
+      "grad_norm": 1.2219051122665405,
+      "learning_rate": 4.375421314640586e-06,
+      "loss": 0.2969,
+      "step": 745
+    },
+    {
+      "epoch": 2.3076923076923075,
+      "grad_norm": 1.0307724475860596,
+      "learning_rate": 4.197341612110815e-06,
+      "loss": 0.2875,
+      "step": 750
+    },
+    {
+      "epoch": 2.3230769230769233,
+      "grad_norm": 1.1877847909927368,
+      "learning_rate": 4.0223703175180805e-06,
+      "loss": 0.3148,
+      "step": 755
+    },
+    {
+      "epoch": 2.3384615384615386,
+      "grad_norm": 1.30415678024292,
+      "learning_rate": 3.850557777928945e-06,
+      "loss": 0.3157,
+      "step": 760
+    },
+    {
+      "epoch": 2.353846153846154,
+      "grad_norm": 1.2754899263381958,
+      "learning_rate": 3.6819534314948737e-06,
+      "loss": 0.3304,
+      "step": 765
+    },
+    {
+      "epoch": 2.3692307692307693,
+      "grad_norm": 1.31760835647583,
+      "learning_rate": 3.516605793226715e-06,
+      "loss": 0.2785,
+      "step": 770
+    },
+    {
+      "epoch": 2.3846153846153846,
+      "grad_norm": 1.368857502937317,
+      "learning_rate": 3.354562441034695e-06,
+      "loss": 0.3498,
+      "step": 775
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 1.2310904264450073,
+      "learning_rate": 3.195870002038186e-06,
+      "loss": 0.3047,
+      "step": 780
+    },
+    {
+      "epoch": 2.4153846153846152,
+      "grad_norm": 1.2456750869750977,
+      "learning_rate": 3.0405741391489648e-06,
+      "loss": 0.2946,
+      "step": 785
+    },
+    {
+      "epoch": 2.430769230769231,
+      "grad_norm": 1.1788861751556396,
+      "learning_rate": 2.888719537931952e-06,
+      "loss": 0.2875,
+      "step": 790
+    },
+    {
+      "epoch": 2.4461538461538463,
+      "grad_norm": 1.2730480432510376,
+      "learning_rate": 2.7403498937472053e-06,
+      "loss": 0.2942,
+      "step": 795
+    },
+    {
+      "epoch": 2.4615384615384617,
+      "grad_norm": 1.1647406816482544,
+      "learning_rate": 2.595507899176767e-06,
+      "loss": 0.27,
+      "step": 800
+    },
+    {
+      "epoch": 2.476923076923077,
+      "grad_norm": 1.198189616203308,
+      "learning_rate": 2.4542352317401346e-06,
+      "loss": 0.2756,
+      "step": 805
+    },
+    {
+      "epoch": 2.4923076923076923,
+      "grad_norm": 1.2865256071090698,
+      "learning_rate": 2.3165725419017485e-06,
+      "loss": 0.2888,
+      "step": 810
+    },
+    {
+      "epoch": 2.5076923076923077,
+      "grad_norm": 1.0661184787750244,
+      "learning_rate": 2.182559441374069e-06,
+      "loss": 0.3119,
+      "step": 815
+    },
+    {
+      "epoch": 2.523076923076923,
+      "grad_norm": 1.054689645767212,
+      "learning_rate": 2.0522344917194692e-06,
+      "loss": 0.2733,
+      "step": 820
+    },
+    {
+      "epoch": 2.5384615384615383,
+      "grad_norm": 1.1389565467834473,
+      "learning_rate": 1.9256351932543927e-06,
+      "loss": 0.2558,
+      "step": 825
+    },
+    {
+      "epoch": 2.5538461538461537,
+      "grad_norm": 1.2306803464889526,
+      "learning_rate": 1.8027979742588086e-06,
+      "loss": 0.2736,
+      "step": 830
+    },
+    {
+      "epoch": 2.569230769230769,
+      "grad_norm": 1.164689302444458,
+      "learning_rate": 1.6837581804941681e-06,
+      "loss": 0.2723,
+      "step": 835
+    },
+    {
+      "epoch": 2.5846153846153848,
+      "grad_norm": 1.1324998140335083,
+      "learning_rate": 1.5685500650328716e-06,
+      "loss": 0.2947,
+      "step": 840
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 1.088495135307312,
+      "learning_rate": 1.457206778402092e-06,
+      "loss": 0.3083,
+      "step": 845
+    },
+    {
+      "epoch": 2.6153846153846154,
+      "grad_norm": 1.170236349105835,
+      "learning_rate": 1.3497603590449131e-06,
+      "loss": 0.2784,
+      "step": 850
+    },
+    {
+      "epoch": 2.6307692307692307,
+      "grad_norm": 1.5001955032348633,
+      "learning_rate": 1.2462417241014296e-06,
+      "loss": 0.263,
+      "step": 855
+    },
+    {
+      "epoch": 2.646153846153846,
+      "grad_norm": 1.0977262258529663,
+      "learning_rate": 1.1466806605124885e-06,
+      "loss": 0.2946,
+      "step": 860
+    },
+    {
+      "epoch": 2.6615384615384614,
+      "grad_norm": 1.170884370803833,
+      "learning_rate": 1.0511058164486891e-06,
+      "loss": 0.2731,
+      "step": 865
+    },
+    {
+      "epoch": 2.676923076923077,
+      "grad_norm": 1.1168737411499023,
+      "learning_rate": 9.595446930669782e-07,
+      "loss": 0.2932,
+      "step": 870
+    },
+    {
+      "epoch": 2.6923076923076925,
+      "grad_norm": 0.9551454782485962,
+      "learning_rate": 8.720236365973699e-07,
+      "loss": 0.2856,
+      "step": 875
+    },
+    {
+      "epoch": 2.707692307692308,
+      "grad_norm": 1.2225338220596313,
+      "learning_rate": 7.88567830761952e-07,
+      "loss": 0.2927,
+      "step": 880
+    },
+    {
+      "epoch": 2.723076923076923,
+      "grad_norm": 1.1854199171066284,
+      "learning_rate": 7.09201289528384e-07,
+      "loss": 0.293,
+      "step": 885
+    },
+    {
+      "epoch": 2.7384615384615385,
+      "grad_norm": 1.2780221700668335,
+      "learning_rate": 6.339468502000356e-07,
+      "loss": 0.2686,
+      "step": 890
+    },
+    {
+      "epoch": 2.753846153846154,
+      "grad_norm": 1.1779381036758423,
+      "learning_rate": 5.628261668446394e-07,
+      "loss": 0.2651,
+      "step": 895
+    },
+    {
+      "epoch": 2.769230769230769,
+      "grad_norm": 1.2358449697494507,
+      "learning_rate": 4.958597040634738e-07,
+      "loss": 0.2698,
+      "step": 900
+    },
+    {
+      "epoch": 2.7846153846153845,
+      "grad_norm": 1.1855942010879517,
+      "learning_rate": 4.330667311027708e-07,
+      "loss": 0.2722,
+      "step": 905
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 1.2545822858810425,
+      "learning_rate": 3.744653163090911e-07,
+      "loss": 0.3136,
+      "step": 910
+    },
+    {
+      "epoch": 2.815384615384615,
+      "grad_norm": 1.0530261993408203,
+      "learning_rate": 3.2007232193025757e-07,
+      "loss": 0.3026,
+      "step": 915
+    },
+    {
+      "epoch": 2.830769230769231,
+      "grad_norm": 1.1272757053375244,
+      "learning_rate": 2.699033992633254e-07,
+      "loss": 0.2677,
+      "step": 920
+    },
+    {
+      "epoch": 2.8461538461538463,
+      "grad_norm": 1.1116807460784912,
+      "learning_rate": 2.2397298415101407e-07,
+      "loss": 0.2729,
+      "step": 925
+    },
+    {
+      "epoch": 2.8615384615384616,
+      "grad_norm": 1.3207794427871704,
+      "learning_rate": 1.8229429282786036e-07,
+      "loss": 0.2904,
+      "step": 930
+    },
+    {
+      "epoch": 2.876923076923077,
+      "grad_norm": 1.1643859148025513,
+      "learning_rate": 1.4487931811732192e-07,
+      "loss": 0.2849,
+      "step": 935
+    },
+    {
+      "epoch": 2.8923076923076922,
+      "grad_norm": 1.3089182376861572,
+      "learning_rate": 1.1173882598090435e-07,
+      "loss": 0.2775,
+      "step": 940
+    },
+    {
+      "epoch": 2.9076923076923076,
+      "grad_norm": 1.2784730195999146,
+      "learning_rate": 8.288235242030928e-08,
+      "loss": 0.3089,
+      "step": 945
+    },
+    {
+      "epoch": 2.9230769230769234,
+      "grad_norm": 1.116310477256775,
+      "learning_rate": 5.831820073350591e-08,
+      "loss": 0.2679,
+      "step": 950
+    },
+    {
+      "epoch": 2.9384615384615387,
+      "grad_norm": 1.16549813747406,
+      "learning_rate": 3.8053439125500525e-08,
+      "loss": 0.2813,
+      "step": 955
+    },
+    {
+      "epoch": 2.953846153846154,
+      "grad_norm": 1.0756598711013794,
+      "learning_rate": 2.2093898674490076e-08,
+      "loss": 0.2442,
+      "step": 960
+    },
+    {
+      "epoch": 2.9692307692307693,
+      "grad_norm": 1.2326387166976929,
+      "learning_rate": 1.044417165400935e-08,
+      "loss": 0.2909,
+      "step": 965
+    },
+    {
+      "epoch": 2.9846153846153847,
+      "grad_norm": 1.189927101135254,
+      "learning_rate": 3.107610211524614e-09,
+      "loss": 0.306,
+      "step": 970
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.2568256855010986,
+      "learning_rate": 8.632540387021327e-11,
+      "loss": 0.2946,
+      "step": 975
+    },
+    {
+      "epoch": 3.0,
+      "step": 975,
+      "total_flos": 1.3711430478609777e+18,
+      "train_loss": 0.6045596268238166,
+      "train_runtime": 644.6715,
+      "train_samples_per_second": 48.373,
+      "train_steps_per_second": 1.512
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 975,
+  "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": 1.3711430478609777e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

126_128_e3_3e-5/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f484ff76685ec9041bb488e3667b2482461a65c37bd096c5e5d1c2807bc2a739
+size 8273