Upload folder using huggingface_hub

114_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": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "gate_proj",
+    "down_proj",
+    "up_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

114_128_e3_3e-5/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac7c7c172f6e3f3e7c756d53475dbaf5da283ee903b3e002c3970f0f4dd8412a
+size 791751704

114_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
+}

114_128_e3_3e-5/all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.588195891859161e+18,
+    "train_loss": 0.5233303028088744,
+    "train_runtime": 763.0963,
+    "train_samples": 11877,
+    "train_samples_per_second": 46.693,
+    "train_steps_per_second": 1.462
+}

114_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 %}

114_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
+}

114_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
+  }
+}

114_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
+}

114_128_e3_3e-5/train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.588195891859161e+18,
+    "train_loss": 0.5233303028088744,
+    "train_runtime": 763.0963,
+    "train_samples": 11877,
+    "train_samples_per_second": 46.693,
+    "train_steps_per_second": 1.462
+}

114_128_e3_3e-5/trainer_state.json

@@ -0,0 +1,1604 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1116,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013458950201884253,
+      "grad_norm": 3.0752313137054443,
+      "learning_rate": 2.1428571428571427e-06,
+      "loss": 1.4984,
+      "step": 5
+    },
+    {
+      "epoch": 0.026917900403768506,
+      "grad_norm": 2.1783666610717773,
+      "learning_rate": 4.821428571428572e-06,
+      "loss": 1.4337,
+      "step": 10
+    },
+    {
+      "epoch": 0.040376850605652756,
+      "grad_norm": 0.9253767132759094,
+      "learning_rate": 7.5e-06,
+      "loss": 1.3598,
+      "step": 15
+    },
+    {
+      "epoch": 0.05383580080753701,
+      "grad_norm": 0.5464652180671692,
+      "learning_rate": 1.0178571428571429e-05,
+      "loss": 1.3055,
+      "step": 20
+    },
+    {
+      "epoch": 0.06729475100942127,
+      "grad_norm": 0.6478655338287354,
+      "learning_rate": 1.2857142857142857e-05,
+      "loss": 1.2978,
+      "step": 25
+    },
+    {
+      "epoch": 0.08075370121130551,
+      "grad_norm": 0.37856778502464294,
+      "learning_rate": 1.553571428571429e-05,
+      "loss": 1.2722,
+      "step": 30
+    },
+    {
+      "epoch": 0.09421265141318977,
+      "grad_norm": 0.42493173480033875,
+      "learning_rate": 1.8214285714285712e-05,
+      "loss": 1.2554,
+      "step": 35
+    },
+    {
+      "epoch": 0.10767160161507403,
+      "grad_norm": 0.42154526710510254,
+      "learning_rate": 2.089285714285714e-05,
+      "loss": 1.2516,
+      "step": 40
+    },
+    {
+      "epoch": 0.12113055181695828,
+      "grad_norm": 0.39978301525115967,
+      "learning_rate": 2.357142857142857e-05,
+      "loss": 1.2492,
+      "step": 45
+    },
+    {
+      "epoch": 0.13458950201884254,
+      "grad_norm": 0.40850532054901123,
+      "learning_rate": 2.625e-05,
+      "loss": 1.2348,
+      "step": 50
+    },
+    {
+      "epoch": 0.1480484522207268,
+      "grad_norm": 0.40462711453437805,
+      "learning_rate": 2.892857142857143e-05,
+      "loss": 1.2002,
+      "step": 55
+    },
+    {
+      "epoch": 0.16150740242261102,
+      "grad_norm": 0.4266829490661621,
+      "learning_rate": 2.9999407089793328e-05,
+      "loss": 1.169,
+      "step": 60
+    },
+    {
+      "epoch": 0.17496635262449528,
+      "grad_norm": 0.4644012451171875,
+      "learning_rate": 2.99957839193835e-05,
+      "loss": 1.1505,
+      "step": 65
+    },
+    {
+      "epoch": 0.18842530282637954,
+      "grad_norm": 0.3546897768974304,
+      "learning_rate": 2.9988867767784412e-05,
+      "loss": 1.1065,
+      "step": 70
+    },
+    {
+      "epoch": 0.2018842530282638,
+      "grad_norm": 0.40191951394081116,
+      "learning_rate": 2.997866015374007e-05,
+      "loss": 1.1793,
+      "step": 75
+    },
+    {
+      "epoch": 0.21534320323014805,
+      "grad_norm": 0.4242837131023407,
+      "learning_rate": 2.996516331877925e-05,
+      "loss": 1.0893,
+      "step": 80
+    },
+    {
+      "epoch": 0.2288021534320323,
+      "grad_norm": 0.43813085556030273,
+      "learning_rate": 2.994838022672324e-05,
+      "loss": 1.0731,
+      "step": 85
+    },
+    {
+      "epoch": 0.24226110363391656,
+      "grad_norm": 0.42297857999801636,
+      "learning_rate": 2.9928314563035015e-05,
+      "loss": 1.1296,
+      "step": 90
+    },
+    {
+      "epoch": 0.2557200538358008,
+      "grad_norm": 0.5580310821533203,
+      "learning_rate": 2.9904970734009933e-05,
+      "loss": 1.103,
+      "step": 95
+    },
+    {
+      "epoch": 0.2691790040376851,
+      "grad_norm": 0.42303964495658875,
+      "learning_rate": 2.9878353865808144e-05,
+      "loss": 1.0259,
+      "step": 100
+    },
+    {
+      "epoch": 0.28263795423956933,
+      "grad_norm": 0.43702319264411926,
+      "learning_rate": 2.9848469803328896e-05,
+      "loss": 1.062,
+      "step": 105
+    },
+    {
+      "epoch": 0.2960969044414536,
+      "grad_norm": 0.5819391012191772,
+      "learning_rate": 2.981532510892707e-05,
+      "loss": 1.0329,
+      "step": 110
+    },
+    {
+      "epoch": 0.30955585464333785,
+      "grad_norm": 0.4956589639186859,
+      "learning_rate": 2.9778927060972075e-05,
+      "loss": 1.041,
+      "step": 115
+    },
+    {
+      "epoch": 0.32301480484522205,
+      "grad_norm": 0.46729394793510437,
+      "learning_rate": 2.9739283652249625e-05,
+      "loss": 1.0239,
+      "step": 120
+    },
+    {
+      "epoch": 0.3364737550471063,
+      "grad_norm": 0.5063794851303101,
+      "learning_rate": 2.9696403588206517e-05,
+      "loss": 0.9778,
+      "step": 125
+    },
+    {
+      "epoch": 0.34993270524899056,
+      "grad_norm": 0.5185872912406921,
+      "learning_rate": 2.9650296285038996e-05,
+      "loss": 0.9994,
+      "step": 130
+    },
+    {
+      "epoch": 0.3633916554508748,
+      "grad_norm": 0.4821980893611908,
+      "learning_rate": 2.9600971867625027e-05,
+      "loss": 0.9737,
+      "step": 135
+    },
+    {
+      "epoch": 0.3768506056527591,
+      "grad_norm": 0.6356862783432007,
+      "learning_rate": 2.95484411673009e-05,
+      "loss": 0.9388,
+      "step": 140
+    },
+    {
+      "epoch": 0.39030955585464333,
+      "grad_norm": 0.5219665169715881,
+      "learning_rate": 2.9492715719482776e-05,
+      "loss": 0.9622,
+      "step": 145
+    },
+    {
+      "epoch": 0.4037685060565276,
+      "grad_norm": 0.5676219463348389,
+      "learning_rate": 2.9433807761133542e-05,
+      "loss": 0.9725,
+      "step": 150
+    },
+    {
+      "epoch": 0.41722745625841184,
+      "grad_norm": 0.6402288675308228,
+      "learning_rate": 2.9371730228075684e-05,
+      "loss": 0.9072,
+      "step": 155
+    },
+    {
+      "epoch": 0.4306864064602961,
+      "grad_norm": 0.6200628876686096,
+      "learning_rate": 2.9306496752150638e-05,
+      "loss": 0.8634,
+      "step": 160
+    },
+    {
+      "epoch": 0.44414535666218036,
+      "grad_norm": 0.6403441429138184,
+      "learning_rate": 2.9238121658225337e-05,
+      "loss": 0.9066,
+      "step": 165
+    },
+    {
+      "epoch": 0.4576043068640646,
+      "grad_norm": 0.6115174889564514,
+      "learning_rate": 2.9166619961046545e-05,
+      "loss": 0.9229,
+      "step": 170
+    },
+    {
+      "epoch": 0.47106325706594887,
+      "grad_norm": 0.5582686066627502,
+      "learning_rate": 2.909200736194372e-05,
+      "loss": 0.898,
+      "step": 175
+    },
+    {
+      "epoch": 0.4845222072678331,
+      "grad_norm": 0.5958764553070068,
+      "learning_rate": 2.9014300245381095e-05,
+      "loss": 0.8523,
+      "step": 180
+    },
+    {
+      "epoch": 0.4979811574697174,
+      "grad_norm": 0.6379088759422302,
+      "learning_rate": 2.8933515675359766e-05,
+      "loss": 0.925,
+      "step": 185
+    },
+    {
+      "epoch": 0.5114401076716016,
+      "grad_norm": 0.6231744289398193,
+      "learning_rate": 2.8849671391670518e-05,
+      "loss": 0.8599,
+      "step": 190
+    },
+    {
+      "epoch": 0.5248990578734859,
+      "grad_norm": 0.7618863582611084,
+      "learning_rate": 2.8762785805998295e-05,
+      "loss": 0.8507,
+      "step": 195
+    },
+    {
+      "epoch": 0.5383580080753702,
+      "grad_norm": 0.6924864649772644,
+      "learning_rate": 2.86728779978791e-05,
+      "loss": 0.842,
+      "step": 200
+    },
+    {
+      "epoch": 0.5518169582772544,
+      "grad_norm": 0.7325058579444885,
+      "learning_rate": 2.8579967710510264e-05,
+      "loss": 0.9124,
+      "step": 205
+    },
+    {
+      "epoch": 0.5652759084791387,
+      "grad_norm": 0.6338002681732178,
+      "learning_rate": 2.8484075346414936e-05,
+      "loss": 0.7816,
+      "step": 210
+    },
+    {
+      "epoch": 0.5787348586810229,
+      "grad_norm": 0.6967992782592773,
+      "learning_rate": 2.838522196296182e-05,
+      "loss": 0.8704,
+      "step": 215
+    },
+    {
+      "epoch": 0.5921938088829072,
+      "grad_norm": 0.6495214104652405,
+      "learning_rate": 2.8283429267741138e-05,
+      "loss": 0.758,
+      "step": 220
+    },
+    {
+      "epoch": 0.6056527590847914,
+      "grad_norm": 0.8025368452072144,
+      "learning_rate": 2.8178719613797747e-05,
+      "loss": 0.8053,
+      "step": 225
+    },
+    {
+      "epoch": 0.6191117092866757,
+      "grad_norm": 0.7716348767280579,
+      "learning_rate": 2.807111599472254e-05,
+      "loss": 0.7815,
+      "step": 230
+    },
+    {
+      "epoch": 0.6325706594885598,
+      "grad_norm": 0.9781221151351929,
+      "learning_rate": 2.7960642039603235e-05,
+      "loss": 0.7556,
+      "step": 235
+    },
+    {
+      "epoch": 0.6460296096904441,
+      "grad_norm": 0.8113903999328613,
+      "learning_rate": 2.7847322007835546e-05,
+      "loss": 0.7919,
+      "step": 240
+    },
+    {
+      "epoch": 0.6594885598923284,
+      "grad_norm": 0.8120785355567932,
+      "learning_rate": 2.773118078379597e-05,
+      "loss": 0.7864,
+      "step": 245
+    },
+    {
+      "epoch": 0.6729475100942126,
+      "grad_norm": 0.7792527675628662,
+      "learning_rate": 2.7612243871377342e-05,
+      "loss": 0.7757,
+      "step": 250
+    },
+    {
+      "epoch": 0.6864064602960969,
+      "grad_norm": 0.712630033493042,
+      "learning_rate": 2.749053738838834e-05,
+      "loss": 0.7515,
+      "step": 255
+    },
+    {
+      "epoch": 0.6998654104979811,
+      "grad_norm": 0.7548930048942566,
+      "learning_rate": 2.7366088060818154e-05,
+      "loss": 0.7526,
+      "step": 260
+    },
+    {
+      "epoch": 0.7133243606998654,
+      "grad_norm": 0.7331514358520508,
+      "learning_rate": 2.7238923216967666e-05,
+      "loss": 0.7318,
+      "step": 265
+    },
+    {
+      "epoch": 0.7267833109017496,
+      "grad_norm": 0.815104603767395,
+      "learning_rate": 2.7109070781448283e-05,
+      "loss": 0.7221,
+      "step": 270
+    },
+    {
+      "epoch": 0.7402422611036339,
+      "grad_norm": 0.81403648853302,
+      "learning_rate": 2.6976559269049875e-05,
+      "loss": 0.7495,
+      "step": 275
+    },
+    {
+      "epoch": 0.7537012113055181,
+      "grad_norm": 0.8133912086486816,
+      "learning_rate": 2.6841417778479132e-05,
+      "loss": 0.6743,
+      "step": 280
+    },
+    {
+      "epoch": 0.7671601615074024,
+      "grad_norm": 0.8576045036315918,
+      "learning_rate": 2.670367598596963e-05,
+      "loss": 0.7049,
+      "step": 285
+    },
+    {
+      "epoch": 0.7806191117092867,
+      "grad_norm": 0.7764049172401428,
+      "learning_rate": 2.6563364138765137e-05,
+      "loss": 0.6701,
+      "step": 290
+    },
+    {
+      "epoch": 0.7940780619111709,
+      "grad_norm": 0.8644312620162964,
+      "learning_rate": 2.6420513048477503e-05,
+      "loss": 0.7141,
+      "step": 295
+    },
+    {
+      "epoch": 0.8075370121130552,
+      "grad_norm": 0.8128887414932251,
+      "learning_rate": 2.6275154084320622e-05,
+      "loss": 0.7112,
+      "step": 300
+    },
+    {
+      "epoch": 0.8209959623149394,
+      "grad_norm": 0.8293873071670532,
+      "learning_rate": 2.6127319166221923e-05,
+      "loss": 0.6635,
+      "step": 305
+    },
+    {
+      "epoch": 0.8344549125168237,
+      "grad_norm": 0.7972635626792908,
+      "learning_rate": 2.5977040757812997e-05,
+      "loss": 0.6719,
+      "step": 310
+    },
+    {
+      "epoch": 0.847913862718708,
+      "grad_norm": 0.848283052444458,
+      "learning_rate": 2.5824351859300748e-05,
+      "loss": 0.6925,
+      "step": 315
+    },
+    {
+      "epoch": 0.8613728129205922,
+      "grad_norm": 0.8814877867698669,
+      "learning_rate": 2.5669286000220757e-05,
+      "loss": 0.7067,
+      "step": 320
+    },
+    {
+      "epoch": 0.8748317631224765,
+      "grad_norm": 1.021031379699707,
+      "learning_rate": 2.551187723207443e-05,
+      "loss": 0.6467,
+      "step": 325
+    },
+    {
+      "epoch": 0.8882907133243607,
+      "grad_norm": 0.832267701625824,
+      "learning_rate": 2.5352160120851464e-05,
+      "loss": 0.6393,
+      "step": 330
+    },
+    {
+      "epoch": 0.901749663526245,
+      "grad_norm": 0.9228408932685852,
+      "learning_rate": 2.519016973943939e-05,
+      "loss": 0.6378,
+      "step": 335
+    },
+    {
+      "epoch": 0.9152086137281292,
+      "grad_norm": 0.8543319702148438,
+      "learning_rate": 2.5025941659921783e-05,
+      "loss": 0.6153,
+      "step": 340
+    },
+    {
+      "epoch": 0.9286675639300135,
+      "grad_norm": 0.9395829439163208,
+      "learning_rate": 2.485951194576685e-05,
+      "loss": 0.6532,
+      "step": 345
+    },
+    {
+      "epoch": 0.9421265141318977,
+      "grad_norm": 0.9021148681640625,
+      "learning_rate": 2.469091714390811e-05,
+      "loss": 0.6449,
+      "step": 350
+    },
+    {
+      "epoch": 0.955585464333782,
+      "grad_norm": 0.9327398538589478,
+      "learning_rate": 2.4520194276718938e-05,
+      "loss": 0.6128,
+      "step": 355
+    },
+    {
+      "epoch": 0.9690444145356663,
+      "grad_norm": 0.8025656342506409,
+      "learning_rate": 2.4347380833882634e-05,
+      "loss": 0.6273,
+      "step": 360
+    },
+    {
+      "epoch": 0.9825033647375505,
+      "grad_norm": 0.8696247935295105,
+      "learning_rate": 2.417251476415998e-05,
+      "loss": 0.6473,
+      "step": 365
+    },
+    {
+      "epoch": 0.9959623149394348,
+      "grad_norm": 0.8262956142425537,
+      "learning_rate": 2.3995634467055882e-05,
+      "loss": 0.5988,
+      "step": 370
+    },
+    {
+      "epoch": 1.0080753701211305,
+      "grad_norm": 1.0454819202423096,
+      "learning_rate": 2.3816778784387097e-05,
+      "loss": 0.581,
+      "step": 375
+    },
+    {
+      "epoch": 1.0215343203230147,
+      "grad_norm": 0.9129600524902344,
+      "learning_rate": 2.363598699175281e-05,
+      "loss": 0.5028,
+      "step": 380
+    },
+    {
+      "epoch": 1.034993270524899,
+      "grad_norm": 0.8659692406654358,
+      "learning_rate": 2.3453298789909935e-05,
+      "loss": 0.5206,
+      "step": 385
+    },
+    {
+      "epoch": 1.0484522207267832,
+      "grad_norm": 0.9665210247039795,
+      "learning_rate": 2.3268754296055122e-05,
+      "loss": 0.5503,
+      "step": 390
+    },
+    {
+      "epoch": 1.0619111709286675,
+      "grad_norm": 0.910910964012146,
+      "learning_rate": 2.3082394035015212e-05,
+      "loss": 0.5306,
+      "step": 395
+    },
+    {
+      "epoch": 1.0753701211305517,
+      "grad_norm": 0.9324933886528015,
+      "learning_rate": 2.2894258930348284e-05,
+      "loss": 0.5311,
+      "step": 400
+    },
+    {
+      "epoch": 1.088829071332436,
+      "grad_norm": 0.8836406469345093,
+      "learning_rate": 2.2704390295357056e-05,
+      "loss": 0.5087,
+      "step": 405
+    },
+    {
+      "epoch": 1.1022880215343203,
+      "grad_norm": 0.9519623517990112,
+      "learning_rate": 2.2512829824016773e-05,
+      "loss": 0.5189,
+      "step": 410
+    },
+    {
+      "epoch": 1.1157469717362045,
+      "grad_norm": 1.012231707572937,
+      "learning_rate": 2.2319619581819458e-05,
+      "loss": 0.4829,
+      "step": 415
+    },
+    {
+      "epoch": 1.1292059219380888,
+      "grad_norm": 1.0678762197494507,
+      "learning_rate": 2.2124801996536575e-05,
+      "loss": 0.4753,
+      "step": 420
+    },
+    {
+      "epoch": 1.142664872139973,
+      "grad_norm": 0.8759668469429016,
+      "learning_rate": 2.1928419848902163e-05,
+      "loss": 0.4748,
+      "step": 425
+    },
+    {
+      "epoch": 1.1561238223418573,
+      "grad_norm": 1.0330374240875244,
+      "learning_rate": 2.1730516263218472e-05,
+      "loss": 0.4829,
+      "step": 430
+    },
+    {
+      "epoch": 1.1695827725437415,
+      "grad_norm": 0.9744387269020081,
+      "learning_rate": 2.1531134697886103e-05,
+      "loss": 0.465,
+      "step": 435
+    },
+    {
+      "epoch": 1.1830417227456258,
+      "grad_norm": 1.1334826946258545,
+      "learning_rate": 2.133031893586083e-05,
+      "loss": 0.4784,
+      "step": 440
+    },
+    {
+      "epoch": 1.19650067294751,
+      "grad_norm": 0.9853057265281677,
+      "learning_rate": 2.1128113075039124e-05,
+      "loss": 0.4905,
+      "step": 445
+    },
+    {
+      "epoch": 1.2099596231493943,
+      "grad_norm": 1.0171077251434326,
+      "learning_rate": 2.092456151857455e-05,
+      "loss": 0.4742,
+      "step": 450
+    },
+    {
+      "epoch": 1.2234185733512786,
+      "grad_norm": 0.9706171751022339,
+      "learning_rate": 2.0719708965127073e-05,
+      "loss": 0.4999,
+      "step": 455
+    },
+    {
+      "epoch": 1.2368775235531628,
+      "grad_norm": 0.9746336340904236,
+      "learning_rate": 2.0513600399047545e-05,
+      "loss": 0.4708,
+      "step": 460
+    },
+    {
+      "epoch": 1.250336473755047,
+      "grad_norm": 0.89353346824646,
+      "learning_rate": 2.0306281080499413e-05,
+      "loss": 0.5129,
+      "step": 465
+    },
+    {
+      "epoch": 1.2637954239569313,
+      "grad_norm": 1.0605510473251343,
+      "learning_rate": 2.009779653551983e-05,
+      "loss": 0.459,
+      "step": 470
+    },
+    {
+      "epoch": 1.2772543741588156,
+      "grad_norm": 0.9838437438011169,
+      "learning_rate": 1.9888192546022488e-05,
+      "loss": 0.4356,
+      "step": 475
+    },
+    {
+      "epoch": 1.2907133243606999,
+      "grad_norm": 0.8651937246322632,
+      "learning_rate": 1.9677515139744126e-05,
+      "loss": 0.5075,
+      "step": 480
+    },
+    {
+      "epoch": 1.304172274562584,
+      "grad_norm": 0.8786460757255554,
+      "learning_rate": 1.946581058013717e-05,
+      "loss": 0.4666,
+      "step": 485
+    },
+    {
+      "epoch": 1.3176312247644684,
+      "grad_norm": 0.9619340896606445,
+      "learning_rate": 1.9253125356210547e-05,
+      "loss": 0.4559,
+      "step": 490
+    },
+    {
+      "epoch": 1.3310901749663526,
+      "grad_norm": 1.1055383682250977,
+      "learning_rate": 1.903950617232098e-05,
+      "loss": 0.4476,
+      "step": 495
+    },
+    {
+      "epoch": 1.3445491251682369,
+      "grad_norm": 0.996176540851593,
+      "learning_rate": 1.8824999937917025e-05,
+      "loss": 0.4237,
+      "step": 500
+    },
+    {
+      "epoch": 1.3580080753701211,
+      "grad_norm": 0.9471869468688965,
+      "learning_rate": 1.8609653757238026e-05,
+      "loss": 0.429,
+      "step": 505
+    },
+    {
+      "epoch": 1.3714670255720054,
+      "grad_norm": 0.9920096397399902,
+      "learning_rate": 1.8393514918970315e-05,
+      "loss": 0.4276,
+      "step": 510
+    },
+    {
+      "epoch": 1.3849259757738897,
+      "grad_norm": 1.044312596321106,
+      "learning_rate": 1.8176630885862927e-05,
+      "loss": 0.4489,
+      "step": 515
+    },
+    {
+      "epoch": 1.398384925975774,
+      "grad_norm": 1.028834342956543,
+      "learning_rate": 1.7959049284305056e-05,
+      "loss": 0.4406,
+      "step": 520
+    },
+    {
+      "epoch": 1.4118438761776582,
+      "grad_norm": 1.0623140335083008,
+      "learning_rate": 1.7740817893867613e-05,
+      "loss": 0.4271,
+      "step": 525
+    },
+    {
+      "epoch": 1.4253028263795424,
+      "grad_norm": 1.0849002599716187,
+      "learning_rate": 1.752198463681111e-05,
+      "loss": 0.4157,
+      "step": 530
+    },
+    {
+      "epoch": 1.4387617765814267,
+      "grad_norm": 0.9743526577949524,
+      "learning_rate": 1.7302597567562237e-05,
+      "loss": 0.4222,
+      "step": 535
+    },
+    {
+      "epoch": 1.452220726783311,
+      "grad_norm": 1.1622055768966675,
+      "learning_rate": 1.7082704862161422e-05,
+      "loss": 0.4033,
+      "step": 540
+    },
+    {
+      "epoch": 1.4656796769851952,
+      "grad_norm": 1.0536174774169922,
+      "learning_rate": 1.6862354807683643e-05,
+      "loss": 0.4144,
+      "step": 545
+    },
+    {
+      "epoch": 1.4791386271870794,
+      "grad_norm": 0.9392291903495789,
+      "learning_rate": 1.66415957916349e-05,
+      "loss": 0.443,
+      "step": 550
+    },
+    {
+      "epoch": 1.4925975773889637,
+      "grad_norm": 1.070420742034912,
+      "learning_rate": 1.642047629132663e-05,
+      "loss": 0.3982,
+      "step": 555
+    },
+    {
+      "epoch": 1.506056527590848,
+      "grad_norm": 0.9795191287994385,
+      "learning_rate": 1.619904486323037e-05,
+      "loss": 0.4303,
+      "step": 560
+    },
+    {
+      "epoch": 1.5195154777927322,
+      "grad_norm": 0.9967865347862244,
+      "learning_rate": 1.597735013231507e-05,
+      "loss": 0.4006,
+      "step": 565
+    },
+    {
+      "epoch": 1.5329744279946165,
+      "grad_norm": 1.0129674673080444,
+      "learning_rate": 1.5755440781369345e-05,
+      "loss": 0.4451,
+      "step": 570
+    },
+    {
+      "epoch": 1.5464333781965007,
+      "grad_norm": 0.9781271815299988,
+      "learning_rate": 1.5533365540311038e-05,
+      "loss": 0.3587,
+      "step": 575
+    },
+    {
+      "epoch": 1.559892328398385,
+      "grad_norm": 1.069239854812622,
+      "learning_rate": 1.531117317548643e-05,
+      "loss": 0.3884,
+      "step": 580
+    },
+    {
+      "epoch": 1.5733512786002692,
+      "grad_norm": 1.1788475513458252,
+      "learning_rate": 1.5088912478961458e-05,
+      "loss": 0.374,
+      "step": 585
+    },
+    {
+      "epoch": 1.5868102288021535,
+      "grad_norm": 1.0183911323547363,
+      "learning_rate": 1.4866632257807278e-05,
+      "loss": 0.3622,
+      "step": 590
+    },
+    {
+      "epoch": 1.6002691790040378,
+      "grad_norm": 0.981325626373291,
+      "learning_rate": 1.4644381323382539e-05,
+      "loss": 0.415,
+      "step": 595
+    },
+    {
+      "epoch": 1.613728129205922,
+      "grad_norm": 1.0954121351242065,
+      "learning_rate": 1.4422208480614684e-05,
+      "loss": 0.3695,
+      "step": 600
+    },
+    {
+      "epoch": 1.6271870794078063,
+      "grad_norm": 0.9849578142166138,
+      "learning_rate": 1.4200162517282736e-05,
+      "loss": 0.3899,
+      "step": 605
+    },
+    {
+      "epoch": 1.6406460296096905,
+      "grad_norm": 0.9740379452705383,
+      "learning_rate": 1.3978292193303768e-05,
+      "loss": 0.3687,
+      "step": 610
+    },
+    {
+      "epoch": 1.6541049798115748,
+      "grad_norm": 1.0310138463974,
+      "learning_rate": 1.3756646230025555e-05,
+      "loss": 0.4176,
+      "step": 615
+    },
+    {
+      "epoch": 1.667563930013459,
+      "grad_norm": 1.162459373474121,
+      "learning_rate": 1.3535273299527622e-05,
+      "loss": 0.3547,
+      "step": 620
+    },
+    {
+      "epoch": 1.6810228802153433,
+      "grad_norm": 1.4040632247924805,
+      "learning_rate": 1.3314222013933218e-05,
+      "loss": 0.3961,
+      "step": 625
+    },
+    {
+      "epoch": 1.6944818304172276,
+      "grad_norm": 1.0262576341629028,
+      "learning_rate": 1.3093540914734351e-05,
+      "loss": 0.4085,
+      "step": 630
+    },
+    {
+      "epoch": 1.7079407806191118,
+      "grad_norm": 1.1665087938308716,
+      "learning_rate": 1.2873278462132401e-05,
+      "loss": 0.3788,
+      "step": 635
+    },
+    {
+      "epoch": 1.721399730820996,
+      "grad_norm": 0.9853291511535645,
+      "learning_rate": 1.2653483024396535e-05,
+      "loss": 0.4147,
+      "step": 640
+    },
+    {
+      "epoch": 1.7348586810228803,
+      "grad_norm": 0.9819117188453674,
+      "learning_rate": 1.2434202867242372e-05,
+      "loss": 0.3462,
+      "step": 645
+    },
+    {
+      "epoch": 1.7483176312247646,
+      "grad_norm": 1.1457184553146362,
+      "learning_rate": 1.221548614323308e-05,
+      "loss": 0.3546,
+      "step": 650
+    },
+    {
+      "epoch": 1.7617765814266488,
+      "grad_norm": 1.215744137763977,
+      "learning_rate": 1.1997380881205431e-05,
+      "loss": 0.3255,
+      "step": 655
+    },
+    {
+      "epoch": 1.775235531628533,
+      "grad_norm": 1.042707920074463,
+      "learning_rate": 1.1779934975722919e-05,
+      "loss": 0.3436,
+      "step": 660
+    },
+    {
+      "epoch": 1.7886944818304173,
+      "grad_norm": 1.0489780902862549,
+      "learning_rate": 1.1563196176558436e-05,
+      "loss": 0.3795,
+      "step": 665
+    },
+    {
+      "epoch": 1.8021534320323016,
+      "grad_norm": 1.274134874343872,
+      "learning_rate": 1.13472120782087e-05,
+      "loss": 0.358,
+      "step": 670
+    },
+    {
+      "epoch": 1.8156123822341859,
+      "grad_norm": 0.956627368927002,
+      "learning_rate": 1.1132030109442823e-05,
+      "loss": 0.3756,
+      "step": 675
+    },
+    {
+      "epoch": 1.8290713324360701,
+      "grad_norm": 1.0112433433532715,
+      "learning_rate": 1.0917697522887217e-05,
+      "loss": 0.3685,
+      "step": 680
+    },
+    {
+      "epoch": 1.8425302826379544,
+      "grad_norm": 1.1500123739242554,
+      "learning_rate": 1.0704261384649242e-05,
+      "loss": 0.339,
+      "step": 685
+    },
+    {
+      "epoch": 1.8559892328398386,
+      "grad_norm": 1.0089510679244995,
+      "learning_rate": 1.0491768563981747e-05,
+      "loss": 0.3695,
+      "step": 690
+    },
+    {
+      "epoch": 1.8694481830417229,
+      "grad_norm": 0.9519475698471069,
+      "learning_rate": 1.0280265722990908e-05,
+      "loss": 0.3131,
+      "step": 695
+    },
+    {
+      "epoch": 1.8829071332436071,
+      "grad_norm": 1.0374550819396973,
+      "learning_rate": 1.0069799306389485e-05,
+      "loss": 0.3499,
+      "step": 700
+    },
+    {
+      "epoch": 1.8963660834454914,
+      "grad_norm": 1.0632023811340332,
+      "learning_rate": 9.860415531297881e-06,
+      "loss": 0.3641,
+      "step": 705
+    },
+    {
+      "epoch": 1.9098250336473757,
+      "grad_norm": 1.0659719705581665,
+      "learning_rate": 9.652160377095124e-06,
+      "loss": 0.3514,
+      "step": 710
+    },
+    {
+      "epoch": 1.92328398384926,
+      "grad_norm": 1.0319280624389648,
+      "learning_rate": 9.445079575322101e-06,
+      "loss": 0.3452,
+      "step": 715
+    },
+    {
+      "epoch": 1.9367429340511442,
+      "grad_norm": 1.0388810634613037,
+      "learning_rate": 9.239218599639171e-06,
+      "loss": 0.3118,
+      "step": 720
+    },
+    {
+      "epoch": 1.9502018842530284,
+      "grad_norm": 1.2116721868515015,
+      "learning_rate": 9.03462265584046e-06,
+      "loss": 0.3204,
+      "step": 725
+    },
+    {
+      "epoch": 1.9636608344549125,
+      "grad_norm": 0.9888458251953125,
+      "learning_rate": 8.831336671926924e-06,
+      "loss": 0.3384,
+      "step": 730
+    },
+    {
+      "epoch": 1.9771197846567967,
+      "grad_norm": 1.0948323011398315,
+      "learning_rate": 8.629405288240461e-06,
+      "loss": 0.3339,
+      "step": 735
+    },
+    {
+      "epoch": 1.990578734858681,
+      "grad_norm": 1.034177303314209,
+      "learning_rate": 8.428872847661139e-06,
+      "loss": 0.3397,
+      "step": 740
+    },
+    {
+      "epoch": 2.0026917900403767,
+      "grad_norm": 1.0161848068237305,
+      "learning_rate": 8.229783385869807e-06,
+      "loss": 0.2892,
+      "step": 745
+    },
+    {
+      "epoch": 2.016150740242261,
+      "grad_norm": 0.9847546815872192,
+      "learning_rate": 8.03218062167811e-06,
+      "loss": 0.2684,
+      "step": 750
+    },
+    {
+      "epoch": 2.029609690444145,
+      "grad_norm": 1.037643551826477,
+      "learning_rate": 7.836107947428115e-06,
+      "loss": 0.2738,
+      "step": 755
+    },
+    {
+      "epoch": 2.0430686406460294,
+      "grad_norm": 0.9790061712265015,
+      "learning_rate": 7.641608419463621e-06,
+      "loss": 0.2516,
+      "step": 760
+    },
+    {
+      "epoch": 2.0565275908479137,
+      "grad_norm": 1.055986762046814,
+      "learning_rate": 7.448724748675273e-06,
+      "loss": 0.2795,
+      "step": 765
+    },
+    {
+      "epoch": 2.069986541049798,
+      "grad_norm": 1.1355167627334595,
+      "learning_rate": 7.257499291121473e-06,
+      "loss": 0.2552,
+      "step": 770
+    },
+    {
+      "epoch": 2.083445491251682,
+      "grad_norm": 1.2173607349395752,
+      "learning_rate": 7.0679740387272896e-06,
+      "loss": 0.2839,
+      "step": 775
+    },
+    {
+      "epoch": 2.0969044414535665,
+      "grad_norm": 1.068787693977356,
+      "learning_rate": 6.880190610063272e-06,
+      "loss": 0.2611,
+      "step": 780
+    },
+    {
+      "epoch": 2.1103633916554507,
+      "grad_norm": 1.1237651109695435,
+      "learning_rate": 6.694190241206277e-06,
+      "loss": 0.2429,
+      "step": 785
+    },
+    {
+      "epoch": 2.123822341857335,
+      "grad_norm": 0.9666768908500671,
+      "learning_rate": 6.510013776684281e-06,
+      "loss": 0.2425,
+      "step": 790
+    },
+    {
+      "epoch": 2.1372812920592192,
+      "grad_norm": 1.2128291130065918,
+      "learning_rate": 6.327701660507191e-06,
+      "loss": 0.2687,
+      "step": 795
+    },
+    {
+      "epoch": 2.1507402422611035,
+      "grad_norm": 1.1535621881484985,
+      "learning_rate": 6.147293927285537e-06,
+      "loss": 0.2516,
+      "step": 800
+    },
+    {
+      "epoch": 2.1641991924629878,
+      "grad_norm": 1.020655870437622,
+      "learning_rate": 5.968830193439195e-06,
+      "loss": 0.3045,
+      "step": 805
+    },
+    {
+      "epoch": 2.177658142664872,
+      "grad_norm": 1.008294701576233,
+      "learning_rate": 5.7923496484978115e-06,
+      "loss": 0.2294,
+      "step": 810
+    },
+    {
+      "epoch": 2.1911170928667563,
+      "grad_norm": 1.109133005142212,
+      "learning_rate": 5.617891046495046e-06,
+      "loss": 0.2588,
+      "step": 815
+    },
+    {
+      "epoch": 2.2045760430686405,
+      "grad_norm": 1.0411441326141357,
+      "learning_rate": 5.44549269745842e-06,
+      "loss": 0.2404,
+      "step": 820
+    },
+    {
+      "epoch": 2.218034993270525,
+      "grad_norm": 1.0516759157180786,
+      "learning_rate": 5.275192458996682e-06,
+      "loss": 0.2592,
+      "step": 825
+    },
+    {
+      "epoch": 2.231493943472409,
+      "grad_norm": 1.0372799634933472,
+      "learning_rate": 5.1070277279864926e-06,
+      "loss": 0.2667,
+      "step": 830
+    },
+    {
+      "epoch": 2.2449528936742933,
+      "grad_norm": 0.9258303046226501,
+      "learning_rate": 4.941035432360333e-06,
+      "loss": 0.2391,
+      "step": 835
+    },
+    {
+      "epoch": 2.2584118438761775,
+      "grad_norm": 1.1755911111831665,
+      "learning_rate": 4.777252022997327e-06,
+      "loss": 0.2527,
+      "step": 840
+    },
+    {
+      "epoch": 2.271870794078062,
+      "grad_norm": 1.105994701385498,
+      "learning_rate": 4.615713465718867e-06,
+      "loss": 0.2515,
+      "step": 845
+    },
+    {
+      "epoch": 2.285329744279946,
+      "grad_norm": 0.8996428847312927,
+      "learning_rate": 4.456455233390751e-06,
+      "loss": 0.241,
+      "step": 850
+    },
+    {
+      "epoch": 2.2987886944818303,
+      "grad_norm": 1.1105486154556274,
+      "learning_rate": 4.299512298133546e-06,
+      "loss": 0.264,
+      "step": 855
+    },
+    {
+      "epoch": 2.3122476446837146,
+      "grad_norm": 1.2268627882003784,
+      "learning_rate": 4.144919123642947e-06,
+      "loss": 0.2624,
+      "step": 860
+    },
+    {
+      "epoch": 2.325706594885599,
+      "grad_norm": 0.9800828695297241,
+      "learning_rate": 3.992709657621739e-06,
+      "loss": 0.2343,
+      "step": 865
+    },
+    {
+      "epoch": 2.339165545087483,
+      "grad_norm": 1.017320990562439,
+      "learning_rate": 3.842917324325107e-06,
+      "loss": 0.2542,
+      "step": 870
+    },
+    {
+      "epoch": 2.3526244952893673,
+      "grad_norm": 1.0729082822799683,
+      "learning_rate": 3.6955750172208763e-06,
+      "loss": 0.237,
+      "step": 875
+    },
+    {
+      "epoch": 2.3660834454912516,
+      "grad_norm": 1.084944486618042,
+      "learning_rate": 3.550715091766307e-06,
+      "loss": 0.2621,
+      "step": 880
+    },
+    {
+      "epoch": 2.379542395693136,
+      "grad_norm": 0.9496181011199951,
+      "learning_rate": 3.4083693583030306e-06,
+      "loss": 0.2545,
+      "step": 885
+    },
+    {
+      "epoch": 2.39300134589502,
+      "grad_norm": 1.161161184310913,
+      "learning_rate": 3.268569075071722e-06,
+      "loss": 0.2765,
+      "step": 890
+    },
+    {
+      "epoch": 2.4064602960969044,
+      "grad_norm": 0.9627789855003357,
+      "learning_rate": 3.131344941347937e-06,
+      "loss": 0.2462,
+      "step": 895
+    },
+    {
+      "epoch": 2.4199192462987886,
+      "grad_norm": 1.2099794149398804,
+      "learning_rate": 2.996727090700794e-06,
+      "loss": 0.2499,
+      "step": 900
+    },
+    {
+      "epoch": 2.433378196500673,
+      "grad_norm": 1.0534799098968506,
+      "learning_rate": 2.86474508437579e-06,
+      "loss": 0.2512,
+      "step": 905
+    },
+    {
+      "epoch": 2.446837146702557,
+      "grad_norm": 1.0375821590423584,
+      "learning_rate": 2.7354279048033524e-06,
+      "loss": 0.2511,
+      "step": 910
+    },
+    {
+      "epoch": 2.4602960969044414,
+      "grad_norm": 1.0421950817108154,
+      "learning_rate": 2.6088039492344707e-06,
+      "loss": 0.2354,
+      "step": 915
+    },
+    {
+      "epoch": 2.4737550471063257,
+      "grad_norm": 1.1523044109344482,
+      "learning_rate": 2.4849010235048513e-06,
+      "loss": 0.2284,
+      "step": 920
+    },
+    {
+      "epoch": 2.48721399730821,
+      "grad_norm": 1.1341627836227417,
+      "learning_rate": 2.3637463359288914e-06,
+      "loss": 0.2504,
+      "step": 925
+    },
+    {
+      "epoch": 2.500672947510094,
+      "grad_norm": 0.9502524137496948,
+      "learning_rate": 2.2453664913249505e-06,
+      "loss": 0.2227,
+      "step": 930
+    },
+    {
+      "epoch": 2.5141318977119784,
+      "grad_norm": 1.028257131576538,
+      "learning_rate": 2.1297874851730575e-06,
+      "loss": 0.2582,
+      "step": 935
+    },
+    {
+      "epoch": 2.5275908479138627,
+      "grad_norm": 1.0402718782424927,
+      "learning_rate": 2.017034697906489e-06,
+      "loss": 0.2202,
+      "step": 940
+    },
+    {
+      "epoch": 2.541049798115747,
+      "grad_norm": 1.1237322092056274,
+      "learning_rate": 1.9071328893383667e-06,
+      "loss": 0.2334,
+      "step": 945
+    },
+    {
+      "epoch": 2.554508748317631,
+      "grad_norm": 1.2287625074386597,
+      "learning_rate": 1.8001061932245654e-06,
+      "loss": 0.2297,
+      "step": 950
+    },
+    {
+      "epoch": 2.5679676985195155,
+      "grad_norm": 1.1148390769958496,
+      "learning_rate": 1.6959781119640894e-06,
+      "loss": 0.2182,
+      "step": 955
+    },
+    {
+      "epoch": 2.5814266487213997,
+      "grad_norm": 0.9711121916770935,
+      "learning_rate": 1.594771511438095e-06,
+      "loss": 0.2381,
+      "step": 960
+    },
+    {
+      "epoch": 2.594885598923284,
+      "grad_norm": 1.0648611783981323,
+      "learning_rate": 1.4965086159886694e-06,
+      "loss": 0.224,
+      "step": 965
+    },
+    {
+      "epoch": 2.608344549125168,
+      "grad_norm": 0.9992756247520447,
+      "learning_rate": 1.401211003538519e-06,
+      "loss": 0.2303,
+      "step": 970
+    },
+    {
+      "epoch": 2.6218034993270525,
+      "grad_norm": 1.1501433849334717,
+      "learning_rate": 1.308899600852585e-06,
+      "loss": 0.2614,
+      "step": 975
+    },
+    {
+      "epoch": 2.6352624495289367,
+      "grad_norm": 1.0796678066253662,
+      "learning_rate": 1.2195946789426531e-06,
+      "loss": 0.2378,
+      "step": 980
+    },
+    {
+      "epoch": 2.648721399730821,
+      "grad_norm": 0.9840754866600037,
+      "learning_rate": 1.13331584861597e-06,
+      "loss": 0.2067,
+      "step": 985
+    },
+    {
+      "epoch": 2.6621803499327052,
+      "grad_norm": 1.0878918170928955,
+      "learning_rate": 1.0500820561688374e-06,
+      "loss": 0.2493,
+      "step": 990
+    },
+    {
+      "epoch": 2.6756393001345895,
+      "grad_norm": 1.0143786668777466,
+      "learning_rate": 9.699115792260953e-07,
+      "loss": 0.2794,
+      "step": 995
+    },
+    {
+      "epoch": 2.6890982503364738,
+      "grad_norm": 0.9427611827850342,
+      "learning_rate": 8.928220227275086e-07,
+      "loss": 0.2217,
+      "step": 1000
+    },
+    {
+      "epoch": 2.702557200538358,
+      "grad_norm": 0.859058678150177,
+      "learning_rate": 8.18830315061801e-07,
+      "loss": 0.234,
+      "step": 1005
+    },
+    {
+      "epoch": 2.7160161507402423,
+      "grad_norm": 1.073665976524353,
+      "learning_rate": 7.479527043492984e-07,
+      "loss": 0.2283,
+      "step": 1010
+    },
+    {
+      "epoch": 2.7294751009421265,
+      "grad_norm": 0.9376751184463501,
+      "learning_rate": 6.802047548739409e-07,
+      "loss": 0.2149,
+      "step": 1015
+    },
+    {
+      "epoch": 2.742934051144011,
+      "grad_norm": 1.0619603395462036,
+      "learning_rate": 6.156013436654617e-07,
+      "loss": 0.2196,
+      "step": 1020
+    },
+    {
+      "epoch": 2.756393001345895,
+      "grad_norm": 1.0922032594680786,
+      "learning_rate": 5.541566572324786e-07,
+      "loss": 0.2506,
+      "step": 1025
+    },
+    {
+      "epoch": 2.7698519515477793,
+      "grad_norm": 0.9645392298698425,
+      "learning_rate": 4.958841884472409e-07,
+      "loss": 0.2263,
+      "step": 1030
+    },
+    {
+      "epoch": 2.7833109017496636,
+      "grad_norm": 1.0580124855041504,
+      "learning_rate": 4.407967335826585e-07,
+      "loss": 0.238,
+      "step": 1035
+    },
+    {
+      "epoch": 2.796769851951548,
+      "grad_norm": 0.9725550413131714,
+      "learning_rate": 3.889063895023287e-07,
+      "loss": 0.2219,
+      "step": 1040
+    },
+    {
+      "epoch": 2.810228802153432,
+      "grad_norm": 1.1302412748336792,
+      "learning_rate": 3.4022455100414184e-07,
+      "loss": 0.2501,
+      "step": 1045
+    },
+    {
+      "epoch": 2.8236877523553163,
+      "grad_norm": 1.0760953426361084,
+      "learning_rate": 2.947619083180525e-07,
+      "loss": 0.2394,
+      "step": 1050
+    },
+    {
+      "epoch": 2.8371467025572006,
+      "grad_norm": 0.933612048625946,
+      "learning_rate": 2.5252844475856906e-07,
+      "loss": 0.2242,
+      "step": 1055
+    },
+    {
+      "epoch": 2.850605652759085,
+      "grad_norm": 0.9729613065719604,
+      "learning_rate": 2.1353343453248408e-07,
+      "loss": 0.2393,
+      "step": 1060
+    },
+    {
+      "epoch": 2.864064602960969,
+      "grad_norm": 0.9166622757911682,
+      "learning_rate": 1.777854407023083e-07,
+      "loss": 0.2305,
+      "step": 1065
+    },
+    {
+      "epoch": 2.8775235531628534,
+      "grad_norm": 1.0187324285507202,
+      "learning_rate": 1.4529231330588644e-07,
+      "loss": 0.234,
+      "step": 1070
+    },
+    {
+      "epoch": 2.8909825033647376,
+      "grad_norm": 1.0369611978530884,
+      "learning_rate": 1.160611876325679e-07,
+      "loss": 0.2439,
+      "step": 1075
+    },
+    {
+      "epoch": 2.904441453566622,
+      "grad_norm": 0.990728497505188,
+      "learning_rate": 9.009848265634669e-08,
+      "loss": 0.2445,
+      "step": 1080
+    },
+    {
+      "epoch": 2.917900403768506,
+      "grad_norm": 0.9160698056221008,
+      "learning_rate": 6.740989962628896e-08,
+      "loss": 0.2144,
+      "step": 1085
+    },
+    {
+      "epoch": 2.9313593539703904,
+      "grad_norm": 0.9574612975120544,
+      "learning_rate": 4.800042081458456e-08,
+      "loss": 0.2556,
+      "step": 1090
+    },
+    {
+      "epoch": 2.9448183041722746,
+      "grad_norm": 0.9852089881896973,
+      "learning_rate": 3.187430842245709e-08,
+      "loss": 0.1979,
+      "step": 1095
+    },
+    {
+      "epoch": 2.958277254374159,
+      "grad_norm": 1.0726145505905151,
+      "learning_rate": 1.9035103644222675e-08,
+      "loss": 0.2175,
+      "step": 1100
+    },
+    {
+      "epoch": 2.971736204576043,
+      "grad_norm": 1.0176410675048828,
+      "learning_rate": 9.485625889660288e-09,
+      "loss": 0.2454,
+      "step": 1105
+    },
+    {
+      "epoch": 2.9851951547779274,
+      "grad_norm": 0.9855303168296814,
+      "learning_rate": 3.2279721648870162e-09,
+      "loss": 0.2047,
+      "step": 1110
+    },
+    {
+      "epoch": 2.9986541049798117,
+      "grad_norm": 0.9880240559577942,
+      "learning_rate": 2.6351661186974074e-10,
+      "loss": 0.207,
+      "step": 1115
+    },
+    {
+      "epoch": 3.0,
+      "step": 1116,
+      "total_flos": 1.588195891859161e+18,
+      "train_loss": 0.5233303028088744,
+      "train_runtime": 763.0963,
+      "train_samples_per_second": 46.693,
+      "train_steps_per_second": 1.462
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1116,
+  "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": 1.588195891859161e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

114_128_e3_3e-5/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c41217719c6d1d217723d447eb155007d3770cf78b2860f69350f31c79a17326
+size 8273