Upload folder using huggingface_hub

21_128_e3_3e-5/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "ibm-granite/granite-3.3-8b-instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "q_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

21_128_e3_3e-5/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23548eaffe3ed5a8f66e5343e7b3283c36a59e2ebb005f17be6c814c352f5f26
+size 791751704

21_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
+}

21_128_e3_3e-5/all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.681814355403866e+18,
+    "train_loss": 0.5136630487768618,
+    "train_runtime": 798.9244,
+    "train_samples": 11658,
+    "train_samples_per_second": 43.776,
+    "train_steps_per_second": 1.371
+}

21_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 %}

21_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
+}

21_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
+  }
+}

21_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
+}

21_128_e3_3e-5/train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.681814355403866e+18,
+    "train_loss": 0.5136630487768618,
+    "train_runtime": 798.9244,
+    "train_samples": 11658,
+    "train_samples_per_second": 43.776,
+    "train_steps_per_second": 1.371
+}

21_128_e3_3e-5/trainer_state.json

@@ -0,0 +1,1576 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1095,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013717421124828532,
+      "grad_norm": 3.106865882873535,
+      "learning_rate": 2.181818181818182e-06,
+      "loss": 1.4689,
+      "step": 5
+    },
+    {
+      "epoch": 0.027434842249657063,
+      "grad_norm": 2.0553035736083984,
+      "learning_rate": 4.90909090909091e-06,
+      "loss": 1.4574,
+      "step": 10
+    },
+    {
+      "epoch": 0.0411522633744856,
+      "grad_norm": 0.8481558561325073,
+      "learning_rate": 7.636363636363636e-06,
+      "loss": 1.3442,
+      "step": 15
+    },
+    {
+      "epoch": 0.05486968449931413,
+      "grad_norm": 0.4872903525829315,
+      "learning_rate": 1.0363636363636364e-05,
+      "loss": 1.2727,
+      "step": 20
+    },
+    {
+      "epoch": 0.06858710562414266,
+      "grad_norm": 0.5174750685691833,
+      "learning_rate": 1.309090909090909e-05,
+      "loss": 1.2754,
+      "step": 25
+    },
+    {
+      "epoch": 0.0823045267489712,
+      "grad_norm": 0.42355358600616455,
+      "learning_rate": 1.5818181818181818e-05,
+      "loss": 1.2302,
+      "step": 30
+    },
+    {
+      "epoch": 0.09602194787379972,
+      "grad_norm": 0.3771427571773529,
+      "learning_rate": 1.8545454545454545e-05,
+      "loss": 1.2124,
+      "step": 35
+    },
+    {
+      "epoch": 0.10973936899862825,
+      "grad_norm": 0.387548565864563,
+      "learning_rate": 2.1272727272727273e-05,
+      "loss": 1.1857,
+      "step": 40
+    },
+    {
+      "epoch": 0.12345679012345678,
+      "grad_norm": 0.3364452123641968,
+      "learning_rate": 2.4e-05,
+      "loss": 1.1696,
+      "step": 45
+    },
+    {
+      "epoch": 0.13717421124828533,
+      "grad_norm": 0.35074296593666077,
+      "learning_rate": 2.6727272727272728e-05,
+      "loss": 1.176,
+      "step": 50
+    },
+    {
+      "epoch": 0.15089163237311384,
+      "grad_norm": 0.3759289085865021,
+      "learning_rate": 2.9454545454545456e-05,
+      "loss": 1.151,
+      "step": 55
+    },
+    {
+      "epoch": 0.1646090534979424,
+      "grad_norm": 0.4880169928073883,
+      "learning_rate": 2.999890501283416e-05,
+      "loss": 1.1684,
+      "step": 60
+    },
+    {
+      "epoch": 0.17832647462277093,
+      "grad_norm": 0.4521220028400421,
+      "learning_rate": 2.9994456901461047e-05,
+      "loss": 1.1263,
+      "step": 65
+    },
+    {
+      "epoch": 0.19204389574759945,
+      "grad_norm": 0.3896968364715576,
+      "learning_rate": 2.9986588243108745e-05,
+      "loss": 1.0748,
+      "step": 70
+    },
+    {
+      "epoch": 0.205761316872428,
+      "grad_norm": 0.3835393190383911,
+      "learning_rate": 2.997530083278163e-05,
+      "loss": 1.0911,
+      "step": 75
+    },
+    {
+      "epoch": 0.2194787379972565,
+      "grad_norm": 0.3998050093650818,
+      "learning_rate": 2.996059724537237e-05,
+      "loss": 1.0702,
+      "step": 80
+    },
+    {
+      "epoch": 0.23319615912208505,
+      "grad_norm": 0.4182651937007904,
+      "learning_rate": 2.9942480835074575e-05,
+      "loss": 1.136,
+      "step": 85
+    },
+    {
+      "epoch": 0.24691358024691357,
+      "grad_norm": 0.3868694603443146,
+      "learning_rate": 2.9920955734617622e-05,
+      "loss": 1.0517,
+      "step": 90
+    },
+    {
+      "epoch": 0.2606310013717421,
+      "grad_norm": 0.41545096039772034,
+      "learning_rate": 2.9896026854323896e-05,
+      "loss": 1.0053,
+      "step": 95
+    },
+    {
+      "epoch": 0.27434842249657065,
+      "grad_norm": 0.4710679054260254,
+      "learning_rate": 2.986769988098864e-05,
+      "loss": 1.0253,
+      "step": 100
+    },
+    {
+      "epoch": 0.2880658436213992,
+      "grad_norm": 0.48391249775886536,
+      "learning_rate": 2.9835981276582676e-05,
+      "loss": 1.0411,
+      "step": 105
+    },
+    {
+      "epoch": 0.3017832647462277,
+      "grad_norm": 0.5029139518737793,
+      "learning_rate": 2.9800878276778313e-05,
+      "loss": 0.94,
+      "step": 110
+    },
+    {
+      "epoch": 0.31550068587105623,
+      "grad_norm": 0.49302148818969727,
+      "learning_rate": 2.976239888929872e-05,
+      "loss": 1.0161,
+      "step": 115
+    },
+    {
+      "epoch": 0.3292181069958848,
+      "grad_norm": 0.5704795122146606,
+      "learning_rate": 2.97205518920912e-05,
+      "loss": 1.0147,
+      "step": 120
+    },
+    {
+      "epoch": 0.3429355281207133,
+      "grad_norm": 0.5088088512420654,
+      "learning_rate": 2.9675346831324778e-05,
+      "loss": 0.9711,
+      "step": 125
+    },
+    {
+      "epoch": 0.35665294924554186,
+      "grad_norm": 0.534210741519928,
+      "learning_rate": 2.962679401921249e-05,
+      "loss": 0.913,
+      "step": 130
+    },
+    {
+      "epoch": 0.37037037037037035,
+      "grad_norm": 0.5042473077774048,
+      "learning_rate": 2.9574904531658977e-05,
+      "loss": 1.01,
+      "step": 135
+    },
+    {
+      "epoch": 0.3840877914951989,
+      "grad_norm": 0.5204794406890869,
+      "learning_rate": 2.9519690205733844e-05,
+      "loss": 0.9121,
+      "step": 140
+    },
+    {
+      "epoch": 0.39780521262002744,
+      "grad_norm": 0.510765790939331,
+      "learning_rate": 2.9461163636971352e-05,
+      "loss": 0.933,
+      "step": 145
+    },
+    {
+      "epoch": 0.411522633744856,
+      "grad_norm": 0.5383373498916626,
+      "learning_rate": 2.9399338176497145e-05,
+      "loss": 0.889,
+      "step": 150
+    },
+    {
+      "epoch": 0.4252400548696845,
+      "grad_norm": 0.5727680921554565,
+      "learning_rate": 2.9334227927982563e-05,
+      "loss": 0.8609,
+      "step": 155
+    },
+    {
+      "epoch": 0.438957475994513,
+      "grad_norm": 0.542536199092865,
+      "learning_rate": 2.9265847744427305e-05,
+      "loss": 0.9212,
+      "step": 160
+    },
+    {
+      "epoch": 0.45267489711934156,
+      "grad_norm": 0.5726959109306335,
+      "learning_rate": 2.9194213224771155e-05,
+      "loss": 0.8392,
+      "step": 165
+    },
+    {
+      "epoch": 0.4663923182441701,
+      "grad_norm": 0.5851187705993652,
+      "learning_rate": 2.9119340710335535e-05,
+      "loss": 0.8463,
+      "step": 170
+    },
+    {
+      "epoch": 0.48010973936899864,
+      "grad_norm": 0.5985710620880127,
+      "learning_rate": 2.9041247281095725e-05,
+      "loss": 0.8925,
+      "step": 175
+    },
+    {
+      "epoch": 0.49382716049382713,
+      "grad_norm": 0.6218758225440979,
+      "learning_rate": 2.8959950751784533e-05,
+      "loss": 0.8125,
+      "step": 180
+    },
+    {
+      "epoch": 0.5075445816186557,
+      "grad_norm": 0.661232590675354,
+      "learning_rate": 2.8875469667828426e-05,
+      "loss": 0.8103,
+      "step": 185
+    },
+    {
+      "epoch": 0.5212620027434842,
+      "grad_norm": 0.6368886828422546,
+      "learning_rate": 2.87878233011169e-05,
+      "loss": 0.827,
+      "step": 190
+    },
+    {
+      "epoch": 0.5349794238683128,
+      "grad_norm": 0.6714680194854736,
+      "learning_rate": 2.8697031645606183e-05,
+      "loss": 0.8288,
+      "step": 195
+    },
+    {
+      "epoch": 0.5486968449931413,
+      "grad_norm": 0.6813381314277649,
+      "learning_rate": 2.860311541275818e-05,
+      "loss": 0.8088,
+      "step": 200
+    },
+    {
+      "epoch": 0.5624142661179699,
+      "grad_norm": 0.7461832165718079,
+      "learning_rate": 2.8506096026815783e-05,
+      "loss": 0.8205,
+      "step": 205
+    },
+    {
+      "epoch": 0.5761316872427984,
+      "grad_norm": 0.6457212567329407,
+      "learning_rate": 2.8405995619915528e-05,
+      "loss": 0.8314,
+      "step": 210
+    },
+    {
+      "epoch": 0.5898491083676269,
+      "grad_norm": 0.7194303870201111,
+      "learning_rate": 2.8302837027038814e-05,
+      "loss": 0.7881,
+      "step": 215
+    },
+    {
+      "epoch": 0.6035665294924554,
+      "grad_norm": 0.7200083136558533,
+      "learning_rate": 2.8196643780802768e-05,
+      "loss": 0.8154,
+      "step": 220
+    },
+    {
+      "epoch": 0.6172839506172839,
+      "grad_norm": 0.69374680519104,
+      "learning_rate": 2.808744010609196e-05,
+      "loss": 0.7565,
+      "step": 225
+    },
+    {
+      "epoch": 0.6310013717421125,
+      "grad_norm": 0.7076025605201721,
+      "learning_rate": 2.79752509145322e-05,
+      "loss": 0.7397,
+      "step": 230
+    },
+    {
+      "epoch": 0.644718792866941,
+      "grad_norm": 0.6978985071182251,
+      "learning_rate": 2.7860101798807693e-05,
+      "loss": 0.7728,
+      "step": 235
+    },
+    {
+      "epoch": 0.6584362139917695,
+      "grad_norm": 0.758421778678894,
+      "learning_rate": 2.7742019026822818e-05,
+      "loss": 0.776,
+      "step": 240
+    },
+    {
+      "epoch": 0.6721536351165981,
+      "grad_norm": 0.7375482320785522,
+      "learning_rate": 2.762102953570984e-05,
+      "loss": 0.7629,
+      "step": 245
+    },
+    {
+      "epoch": 0.6858710562414266,
+      "grad_norm": 0.6563310623168945,
+      "learning_rate": 2.749716092568404e-05,
+      "loss": 0.7426,
+      "step": 250
+    },
+    {
+      "epoch": 0.6995884773662552,
+      "grad_norm": 0.792753279209137,
+      "learning_rate": 2.737044145374749e-05,
+      "loss": 0.7458,
+      "step": 255
+    },
+    {
+      "epoch": 0.7133058984910837,
+      "grad_norm": 0.7958997488021851,
+      "learning_rate": 2.7240900027243072e-05,
+      "loss": 0.7465,
+      "step": 260
+    },
+    {
+      "epoch": 0.7270233196159122,
+      "grad_norm": 0.8392963409423828,
+      "learning_rate": 2.7108566197260103e-05,
+      "loss": 0.6873,
+      "step": 265
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 0.7651315927505493,
+      "learning_rate": 2.697347015189311e-05,
+      "loss": 0.7016,
+      "step": 270
+    },
+    {
+      "epoch": 0.7544581618655692,
+      "grad_norm": 0.7778927683830261,
+      "learning_rate": 2.683564270935531e-05,
+      "loss": 0.6612,
+      "step": 275
+    },
+    {
+      "epoch": 0.7681755829903978,
+      "grad_norm": 0.8361443281173706,
+      "learning_rate": 2.6695115310948335e-05,
+      "loss": 0.6759,
+      "step": 280
+    },
+    {
+      "epoch": 0.7818930041152263,
+      "grad_norm": 0.8205651640892029,
+      "learning_rate": 2.655192001388982e-05,
+      "loss": 0.6457,
+      "step": 285
+    },
+    {
+      "epoch": 0.7956104252400549,
+      "grad_norm": 0.7632591724395752,
+      "learning_rate": 2.6406089484000465e-05,
+      "loss": 0.7204,
+      "step": 290
+    },
+    {
+      "epoch": 0.8093278463648834,
+      "grad_norm": 0.8065452575683594,
+      "learning_rate": 2.6257656988252314e-05,
+      "loss": 0.6296,
+      "step": 295
+    },
+    {
+      "epoch": 0.823045267489712,
+      "grad_norm": 0.8871366381645203,
+      "learning_rate": 2.6106656387179853e-05,
+      "loss": 0.6288,
+      "step": 300
+    },
+    {
+      "epoch": 0.8367626886145405,
+      "grad_norm": 0.7919726967811584,
+      "learning_rate": 2.5953122127155703e-05,
+      "loss": 0.6996,
+      "step": 305
+    },
+    {
+      "epoch": 0.850480109739369,
+      "grad_norm": 0.7500154376029968,
+      "learning_rate": 2.5797089232532727e-05,
+      "loss": 0.6738,
+      "step": 310
+    },
+    {
+      "epoch": 0.8641975308641975,
+      "grad_norm": 0.8016030192375183,
+      "learning_rate": 2.5638593297654208e-05,
+      "loss": 0.6557,
+      "step": 315
+    },
+    {
+      "epoch": 0.877914951989026,
+      "grad_norm": 0.8199147582054138,
+      "learning_rate": 2.547767047873406e-05,
+      "loss": 0.6848,
+      "step": 320
+    },
+    {
+      "epoch": 0.8916323731138546,
+      "grad_norm": 0.8543243408203125,
+      "learning_rate": 2.5314357485608832e-05,
+      "loss": 0.6676,
+      "step": 325
+    },
+    {
+      "epoch": 0.9053497942386831,
+      "grad_norm": 0.8435254096984863,
+      "learning_rate": 2.514869157336347e-05,
+      "loss": 0.6253,
+      "step": 330
+    },
+    {
+      "epoch": 0.9190672153635117,
+      "grad_norm": 0.8155385851860046,
+      "learning_rate": 2.49807105338326e-05,
+      "loss": 0.6156,
+      "step": 335
+    },
+    {
+      "epoch": 0.9327846364883402,
+      "grad_norm": 0.8313052654266357,
+      "learning_rate": 2.481045268697947e-05,
+      "loss": 0.5689,
+      "step": 340
+    },
+    {
+      "epoch": 0.9465020576131687,
+      "grad_norm": 0.8453279733657837,
+      "learning_rate": 2.4637956872154342e-05,
+      "loss": 0.6183,
+      "step": 345
+    },
+    {
+      "epoch": 0.9602194787379973,
+      "grad_norm": 0.8089984655380249,
+      "learning_rate": 2.446326243923446e-05,
+      "loss": 0.5591,
+      "step": 350
+    },
+    {
+      "epoch": 0.9739368998628258,
+      "grad_norm": 0.9062568545341492,
+      "learning_rate": 2.4286409239647515e-05,
+      "loss": 0.6174,
+      "step": 355
+    },
+    {
+      "epoch": 0.9876543209876543,
+      "grad_norm": 0.9152640700340271,
+      "learning_rate": 2.410743761728067e-05,
+      "loss": 0.5664,
+      "step": 360
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.2532458305358887,
+      "learning_rate": 2.3926388399277344e-05,
+      "loss": 0.5643,
+      "step": 365
+    },
+    {
+      "epoch": 1.0137174211248285,
+      "grad_norm": 1.107286810874939,
+      "learning_rate": 2.3743302886723657e-05,
+      "loss": 0.5225,
+      "step": 370
+    },
+    {
+      "epoch": 1.027434842249657,
+      "grad_norm": 0.956028938293457,
+      "learning_rate": 2.3558222845226783e-05,
+      "loss": 0.5159,
+      "step": 375
+    },
+    {
+      "epoch": 1.0411522633744856,
+      "grad_norm": 0.9799565672874451,
+      "learning_rate": 2.3371190495387375e-05,
+      "loss": 0.4982,
+      "step": 380
+    },
+    {
+      "epoch": 1.0548696844993142,
+      "grad_norm": 0.8768431544303894,
+      "learning_rate": 2.3182248503168173e-05,
+      "loss": 0.5439,
+      "step": 385
+    },
+    {
+      "epoch": 1.0685871056241427,
+      "grad_norm": 0.8403708934783936,
+      "learning_rate": 2.2991439970160965e-05,
+      "loss": 0.4915,
+      "step": 390
+    },
+    {
+      "epoch": 1.0823045267489713,
+      "grad_norm": 0.9563457369804382,
+      "learning_rate": 2.2798808423754288e-05,
+      "loss": 0.5344,
+      "step": 395
+    },
+    {
+      "epoch": 1.0960219478737998,
+      "grad_norm": 0.994430661201477,
+      "learning_rate": 2.2604397807203857e-05,
+      "loss": 0.4886,
+      "step": 400
+    },
+    {
+      "epoch": 1.1097393689986284,
+      "grad_norm": 1.0950026512145996,
+      "learning_rate": 2.2408252469608255e-05,
+      "loss": 0.5039,
+      "step": 405
+    },
+    {
+      "epoch": 1.123456790123457,
+      "grad_norm": 0.8684844374656677,
+      "learning_rate": 2.2210417155791934e-05,
+      "loss": 0.5414,
+      "step": 410
+    },
+    {
+      "epoch": 1.1371742112482854,
+      "grad_norm": 0.8997437953948975,
+      "learning_rate": 2.2010936996098042e-05,
+      "loss": 0.4471,
+      "step": 415
+    },
+    {
+      "epoch": 1.1508916323731138,
+      "grad_norm": 1.0063364505767822,
+      "learning_rate": 2.1809857496093203e-05,
+      "loss": 0.456,
+      "step": 420
+    },
+    {
+      "epoch": 1.1646090534979423,
+      "grad_norm": 0.9689503312110901,
+      "learning_rate": 2.160722452618678e-05,
+      "loss": 0.5293,
+      "step": 425
+    },
+    {
+      "epoch": 1.1783264746227708,
+      "grad_norm": 0.9166932702064514,
+      "learning_rate": 2.1403084311166896e-05,
+      "loss": 0.4858,
+      "step": 430
+    },
+    {
+      "epoch": 1.1920438957475994,
+      "grad_norm": 0.9573662281036377,
+      "learning_rate": 2.1197483419655564e-05,
+      "loss": 0.5091,
+      "step": 435
+    },
+    {
+      "epoch": 1.205761316872428,
+      "grad_norm": 0.8931414484977722,
+      "learning_rate": 2.099046875348543e-05,
+      "loss": 0.4717,
+      "step": 440
+    },
+    {
+      "epoch": 1.2194787379972565,
+      "grad_norm": 0.9017981886863708,
+      "learning_rate": 2.0782087537000525e-05,
+      "loss": 0.4776,
+      "step": 445
+    },
+    {
+      "epoch": 1.233196159122085,
+      "grad_norm": 0.9682060480117798,
+      "learning_rate": 2.0572387306283357e-05,
+      "loss": 0.458,
+      "step": 450
+    },
+    {
+      "epoch": 1.2469135802469136,
+      "grad_norm": 0.9869005084037781,
+      "learning_rate": 2.036141589831098e-05,
+      "loss": 0.52,
+      "step": 455
+    },
+    {
+      "epoch": 1.260631001371742,
+      "grad_norm": 1.0599266290664673,
+      "learning_rate": 2.0149221440042375e-05,
+      "loss": 0.4583,
+      "step": 460
+    },
+    {
+      "epoch": 1.2743484224965707,
+      "grad_norm": 0.8293225765228271,
+      "learning_rate": 1.993585233743969e-05,
+      "loss": 0.4339,
+      "step": 465
+    },
+    {
+      "epoch": 1.2880658436213992,
+      "grad_norm": 1.0139296054840088,
+      "learning_rate": 1.9721357264425844e-05,
+      "loss": 0.4546,
+      "step": 470
+    },
+    {
+      "epoch": 1.3017832647462277,
+      "grad_norm": 0.9689605236053467,
+      "learning_rate": 1.9505785151780973e-05,
+      "loss": 0.4263,
+      "step": 475
+    },
+    {
+      "epoch": 1.3155006858710563,
+      "grad_norm": 0.9394211769104004,
+      "learning_rate": 1.9289185175980338e-05,
+      "loss": 0.4735,
+      "step": 480
+    },
+    {
+      "epoch": 1.3292181069958848,
+      "grad_norm": 1.0727108716964722,
+      "learning_rate": 1.9071606747976112e-05,
+      "loss": 0.3985,
+      "step": 485
+    },
+    {
+      "epoch": 1.3429355281207134,
+      "grad_norm": 0.8843740224838257,
+      "learning_rate": 1.8853099501925742e-05,
+      "loss": 0.4251,
+      "step": 490
+    },
+    {
+      "epoch": 1.356652949245542,
+      "grad_norm": 0.9701921939849854,
+      "learning_rate": 1.863371328386936e-05,
+      "loss": 0.4775,
+      "step": 495
+    },
+    {
+      "epoch": 1.3703703703703702,
+      "grad_norm": 0.9475935101509094,
+      "learning_rate": 1.841349814035885e-05,
+      "loss": 0.4255,
+      "step": 500
+    },
+    {
+      "epoch": 1.3840877914951988,
+      "grad_norm": 0.9424192309379578,
+      "learning_rate": 1.8192504307041224e-05,
+      "loss": 0.4175,
+      "step": 505
+    },
+    {
+      "epoch": 1.3978052126200273,
+      "grad_norm": 0.92666095495224,
+      "learning_rate": 1.7970782197198796e-05,
+      "loss": 0.4293,
+      "step": 510
+    },
+    {
+      "epoch": 1.4115226337448559,
+      "grad_norm": 1.0038453340530396,
+      "learning_rate": 1.774838239024888e-05,
+      "loss": 0.3889,
+      "step": 515
+    },
+    {
+      "epoch": 1.4252400548696844,
+      "grad_norm": 1.072291612625122,
+      "learning_rate": 1.7525355620205574e-05,
+      "loss": 0.4388,
+      "step": 520
+    },
+    {
+      "epoch": 1.438957475994513,
+      "grad_norm": 0.9682796001434326,
+      "learning_rate": 1.730175276410629e-05,
+      "loss": 0.4271,
+      "step": 525
+    },
+    {
+      "epoch": 1.4526748971193415,
+      "grad_norm": 0.9968134164810181,
+      "learning_rate": 1.7077624830405602e-05,
+      "loss": 0.4449,
+      "step": 530
+    },
+    {
+      "epoch": 1.46639231824417,
+      "grad_norm": 0.944649875164032,
+      "learning_rate": 1.685302294733921e-05,
+      "loss": 0.4337,
+      "step": 535
+    },
+    {
+      "epoch": 1.4801097393689986,
+      "grad_norm": 0.949520468711853,
+      "learning_rate": 1.6627998351260496e-05,
+      "loss": 0.4223,
+      "step": 540
+    },
+    {
+      "epoch": 1.4938271604938271,
+      "grad_norm": 0.9722627997398376,
+      "learning_rate": 1.640260237495247e-05,
+      "loss": 0.4536,
+      "step": 545
+    },
+    {
+      "epoch": 1.5075445816186557,
+      "grad_norm": 1.1368709802627563,
+      "learning_rate": 1.6176886435917676e-05,
+      "loss": 0.3889,
+      "step": 550
+    },
+    {
+      "epoch": 1.5212620027434842,
+      "grad_norm": 0.9086707234382629,
+      "learning_rate": 1.5950902024648793e-05,
+      "loss": 0.3921,
+      "step": 555
+    },
+    {
+      "epoch": 1.5349794238683128,
+      "grad_norm": 1.1461021900177002,
+      "learning_rate": 1.5724700692882606e-05,
+      "loss": 0.3492,
+      "step": 560
+    },
+    {
+      "epoch": 1.5486968449931413,
+      "grad_norm": 1.0213220119476318,
+      "learning_rate": 1.549833404183996e-05,
+      "loss": 0.396,
+      "step": 565
+    },
+    {
+      "epoch": 1.5624142661179699,
+      "grad_norm": 0.9958617687225342,
+      "learning_rate": 1.527185371045446e-05,
+      "loss": 0.4026,
+      "step": 570
+    },
+    {
+      "epoch": 1.5761316872427984,
+      "grad_norm": 1.0077898502349854,
+      "learning_rate": 1.5045311363592562e-05,
+      "loss": 0.4052,
+      "step": 575
+    },
+    {
+      "epoch": 1.589849108367627,
+      "grad_norm": 1.0151335000991821,
+      "learning_rate": 1.481875868026774e-05,
+      "loss": 0.3579,
+      "step": 580
+    },
+    {
+      "epoch": 1.6035665294924555,
+      "grad_norm": 0.9512467980384827,
+      "learning_rate": 1.4592247341851426e-05,
+      "loss": 0.3699,
+      "step": 585
+    },
+    {
+      "epoch": 1.617283950617284,
+      "grad_norm": 1.1125658750534058,
+      "learning_rate": 1.436582902028342e-05,
+      "loss": 0.3692,
+      "step": 590
+    },
+    {
+      "epoch": 1.6310013717421126,
+      "grad_norm": 0.9458398818969727,
+      "learning_rate": 1.4139555366284447e-05,
+      "loss": 0.4035,
+      "step": 595
+    },
+    {
+      "epoch": 1.6447187928669411,
+      "grad_norm": 0.9057902097702026,
+      "learning_rate": 1.3913477997573565e-05,
+      "loss": 0.3908,
+      "step": 600
+    },
+    {
+      "epoch": 1.6584362139917697,
+      "grad_norm": 1.0327421426773071,
+      "learning_rate": 1.3687648487093068e-05,
+      "loss": 0.3592,
+      "step": 605
+    },
+    {
+      "epoch": 1.6721536351165982,
+      "grad_norm": 1.0575224161148071,
+      "learning_rate": 1.3462118351243652e-05,
+      "loss": 0.3925,
+      "step": 610
+    },
+    {
+      "epoch": 1.6858710562414267,
+      "grad_norm": 1.074633002281189,
+      "learning_rate": 1.3236939038132438e-05,
+      "loss": 0.4321,
+      "step": 615
+    },
+    {
+      "epoch": 1.6995884773662553,
+      "grad_norm": 0.9927712678909302,
+      "learning_rate": 1.301216191583659e-05,
+      "loss": 0.328,
+      "step": 620
+    },
+    {
+      "epoch": 1.7133058984910838,
+      "grad_norm": 1.0187026262283325,
+      "learning_rate": 1.2787838260685207e-05,
+      "loss": 0.3617,
+      "step": 625
+    },
+    {
+      "epoch": 1.7270233196159122,
+      "grad_norm": 1.0585708618164062,
+      "learning_rate": 1.256401924556211e-05,
+      "loss": 0.3859,
+      "step": 630
+    },
+    {
+      "epoch": 1.7407407407407407,
+      "grad_norm": 1.1495975255966187,
+      "learning_rate": 1.2340755928232249e-05,
+      "loss": 0.3519,
+      "step": 635
+    },
+    {
+      "epoch": 1.7544581618655692,
+      "grad_norm": 1.0765626430511475,
+      "learning_rate": 1.2118099239694373e-05,
+      "loss": 0.3535,
+      "step": 640
+    },
+    {
+      "epoch": 1.7681755829903978,
+      "grad_norm": 0.929316520690918,
+      "learning_rate": 1.1896099972562607e-05,
+      "loss": 0.3702,
+      "step": 645
+    },
+    {
+      "epoch": 1.7818930041152263,
+      "grad_norm": 1.0712732076644897,
+      "learning_rate": 1.1674808769479596e-05,
+      "loss": 0.329,
+      "step": 650
+    },
+    {
+      "epoch": 1.7956104252400549,
+      "grad_norm": 1.0400203466415405,
+      "learning_rate": 1.1454276111563876e-05,
+      "loss": 0.3618,
+      "step": 655
+    },
+    {
+      "epoch": 1.8093278463648834,
+      "grad_norm": 0.9378494024276733,
+      "learning_rate": 1.1234552306894075e-05,
+      "loss": 0.3342,
+      "step": 660
+    },
+    {
+      "epoch": 1.823045267489712,
+      "grad_norm": 0.9590099453926086,
+      "learning_rate": 1.1015687479032615e-05,
+      "loss": 0.3684,
+      "step": 665
+    },
+    {
+      "epoch": 1.8367626886145405,
+      "grad_norm": 0.9713229537010193,
+      "learning_rate": 1.0797731555591448e-05,
+      "loss": 0.3584,
+      "step": 670
+    },
+    {
+      "epoch": 1.850480109739369,
+      "grad_norm": 0.9658066034317017,
+      "learning_rate": 1.0580734256842577e-05,
+      "loss": 0.3256,
+      "step": 675
+    },
+    {
+      "epoch": 1.8641975308641974,
+      "grad_norm": 1.0665819644927979,
+      "learning_rate": 1.036474508437579e-05,
+      "loss": 0.3235,
+      "step": 680
+    },
+    {
+      "epoch": 1.877914951989026,
+      "grad_norm": 0.9527893662452698,
+      "learning_rate": 1.0149813309806345e-05,
+      "loss": 0.3634,
+      "step": 685
+    },
+    {
+      "epoch": 1.8916323731138545,
+      "grad_norm": 1.090286374092102,
+      "learning_rate": 9.935987963535077e-06,
+      "loss": 0.3175,
+      "step": 690
+    },
+    {
+      "epoch": 1.905349794238683,
+      "grad_norm": 0.9725489020347595,
+      "learning_rate": 9.723317823563562e-06,
+      "loss": 0.3969,
+      "step": 695
+    },
+    {
+      "epoch": 1.9190672153635115,
+      "grad_norm": 1.1476311683654785,
+      "learning_rate": 9.511851404366818e-06,
+      "loss": 0.3407,
+      "step": 700
+    },
+    {
+      "epoch": 1.93278463648834,
+      "grad_norm": 0.8596852421760559,
+      "learning_rate": 9.301636945826163e-06,
+      "loss": 0.2975,
+      "step": 705
+    },
+    {
+      "epoch": 1.9465020576131686,
+      "grad_norm": 1.0431839227676392,
+      "learning_rate": 9.092722402224705e-06,
+      "loss": 0.3311,
+      "step": 710
+    },
+    {
+      "epoch": 1.9602194787379972,
+      "grad_norm": 1.2009830474853516,
+      "learning_rate": 8.885155431307938e-06,
+      "loss": 0.3098,
+      "step": 715
+    },
+    {
+      "epoch": 1.9739368998628257,
+      "grad_norm": 1.0051283836364746,
+      "learning_rate": 8.678983383412067e-06,
+      "loss": 0.3255,
+      "step": 720
+    },
+    {
+      "epoch": 1.9876543209876543,
+      "grad_norm": 0.986889660358429,
+      "learning_rate": 8.47425329066237e-06,
+      "loss": 0.3119,
+      "step": 725
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.4370043277740479,
+      "learning_rate": 8.271011856244232e-06,
+      "loss": 0.281,
+      "step": 730
+    },
+    {
+      "epoch": 2.0137174211248285,
+      "grad_norm": 1.057409644126892,
+      "learning_rate": 8.069305443749158e-06,
+      "loss": 0.2804,
+      "step": 735
+    },
+    {
+      "epoch": 2.027434842249657,
+      "grad_norm": 1.1250669956207275,
+      "learning_rate": 7.869180066598258e-06,
+      "loss": 0.2781,
+      "step": 740
+    },
+    {
+      "epoch": 2.0411522633744856,
+      "grad_norm": 1.0327444076538086,
+      "learning_rate": 7.67068137754568e-06,
+      "loss": 0.2454,
+      "step": 745
+    },
+    {
+      "epoch": 2.054869684499314,
+      "grad_norm": 0.9646955728530884,
+      "learning_rate": 7.47385465826421e-06,
+      "loss": 0.269,
+      "step": 750
+    },
+    {
+      "epoch": 2.0685871056241427,
+      "grad_norm": 1.0620466470718384,
+      "learning_rate": 7.278744809015629e-06,
+      "loss": 0.255,
+      "step": 755
+    },
+    {
+      "epoch": 2.0823045267489713,
+      "grad_norm": 1.2195289134979248,
+      "learning_rate": 7.085396338408007e-06,
+      "loss": 0.2654,
+      "step": 760
+    },
+    {
+      "epoch": 2.0960219478738,
+      "grad_norm": 0.9989861249923706,
+      "learning_rate": 6.893853353242378e-06,
+      "loss": 0.2678,
+      "step": 765
+    },
+    {
+      "epoch": 2.1097393689986284,
+      "grad_norm": 0.8964051604270935,
+      "learning_rate": 6.704159548451039e-06,
+      "loss": 0.2376,
+      "step": 770
+    },
+    {
+      "epoch": 2.123456790123457,
+      "grad_norm": 1.1280827522277832,
+      "learning_rate": 6.516358197129864e-06,
+      "loss": 0.26,
+      "step": 775
+    },
+    {
+      "epoch": 2.1371742112482854,
+      "grad_norm": 1.1098802089691162,
+      "learning_rate": 6.330492140666776e-06,
+      "loss": 0.2668,
+      "step": 780
+    },
+    {
+      "epoch": 2.150891632373114,
+      "grad_norm": 0.9676617383956909,
+      "learning_rate": 6.146603778968776e-06,
+      "loss": 0.2561,
+      "step": 785
+    },
+    {
+      "epoch": 2.1646090534979425,
+      "grad_norm": 1.0433140993118286,
+      "learning_rate": 5.964735060789591e-06,
+      "loss": 0.2768,
+      "step": 790
+    },
+    {
+      "epoch": 2.178326474622771,
+      "grad_norm": 1.0165446996688843,
+      "learning_rate": 5.7849274741603635e-06,
+      "loss": 0.2838,
+      "step": 795
+    },
+    {
+      "epoch": 2.1920438957475996,
+      "grad_norm": 0.9863305687904358,
+      "learning_rate": 5.607222036925295e-06,
+      "loss": 0.2647,
+      "step": 800
+    },
+    {
+      "epoch": 2.205761316872428,
+      "grad_norm": 0.9141923785209656,
+      "learning_rate": 5.431659287384682e-06,
+      "loss": 0.2592,
+      "step": 805
+    },
+    {
+      "epoch": 2.2194787379972567,
+      "grad_norm": 1.0824416875839233,
+      "learning_rate": 5.258279275047247e-06,
+      "loss": 0.2606,
+      "step": 810
+    },
+    {
+      "epoch": 2.2331961591220852,
+      "grad_norm": 1.013136863708496,
+      "learning_rate": 5.08712155149405e-06,
+      "loss": 0.264,
+      "step": 815
+    },
+    {
+      "epoch": 2.246913580246914,
+      "grad_norm": 1.0065057277679443,
+      "learning_rate": 4.918225161355908e-06,
+      "loss": 0.2314,
+      "step": 820
+    },
+    {
+      "epoch": 2.260631001371742,
+      "grad_norm": 1.0977758169174194,
+      "learning_rate": 4.751628633406569e-06,
+      "loss": 0.2322,
+      "step": 825
+    },
+    {
+      "epoch": 2.274348422496571,
+      "grad_norm": 0.9866920709609985,
+      "learning_rate": 4.587369971773419e-06,
+      "loss": 0.2395,
+      "step": 830
+    },
+    {
+      "epoch": 2.288065843621399,
+      "grad_norm": 1.0764834880828857,
+      "learning_rate": 4.425486647268019e-06,
+      "loss": 0.2754,
+      "step": 835
+    },
+    {
+      "epoch": 2.3017832647462275,
+      "grad_norm": 0.9970492720603943,
+      "learning_rate": 4.266015588838185e-06,
+      "loss": 0.2604,
+      "step": 840
+    },
+    {
+      "epoch": 2.315500685871056,
+      "grad_norm": 1.199155330657959,
+      "learning_rate": 4.108993175143772e-06,
+      "loss": 0.252,
+      "step": 845
+    },
+    {
+      "epoch": 2.3292181069958846,
+      "grad_norm": 1.1609810590744019,
+      "learning_rate": 3.954455226257909e-06,
+      "loss": 0.2565,
+      "step": 850
+    },
+    {
+      "epoch": 2.342935528120713,
+      "grad_norm": 0.9952213168144226,
+      "learning_rate": 3.8024369954957174e-06,
+      "loss": 0.2286,
+      "step": 855
+    },
+    {
+      "epoch": 2.3566529492455417,
+      "grad_norm": 0.9645949006080627,
+      "learning_rate": 3.6529731613722955e-06,
+      "loss": 0.2518,
+      "step": 860
+    },
+    {
+      "epoch": 2.3703703703703702,
+      "grad_norm": 0.8817917704582214,
+      "learning_rate": 3.5060978196918303e-06,
+      "loss": 0.237,
+      "step": 865
+    },
+    {
+      "epoch": 2.384087791495199,
+      "grad_norm": 1.1733688116073608,
+      "learning_rate": 3.3618444757696152e-06,
+      "loss": 0.292,
+      "step": 870
+    },
+    {
+      "epoch": 2.3978052126200273,
+      "grad_norm": 0.9009637832641602,
+      "learning_rate": 3.2202460367888293e-06,
+      "loss": 0.2713,
+      "step": 875
+    },
+    {
+      "epoch": 2.411522633744856,
+      "grad_norm": 1.1742184162139893,
+      "learning_rate": 3.081334804293688e-06,
+      "loss": 0.2362,
+      "step": 880
+    },
+    {
+      "epoch": 2.4252400548696844,
+      "grad_norm": 1.013698935508728,
+      "learning_rate": 2.9451424668208195e-06,
+      "loss": 0.2847,
+      "step": 885
+    },
+    {
+      "epoch": 2.438957475994513,
+      "grad_norm": 1.0418685674667358,
+      "learning_rate": 2.8117000926704363e-06,
+      "loss": 0.2095,
+      "step": 890
+    },
+    {
+      "epoch": 2.4526748971193415,
+      "grad_norm": 1.0569798946380615,
+      "learning_rate": 2.6810381228190163e-06,
+      "loss": 0.2389,
+      "step": 895
+    },
+    {
+      "epoch": 2.46639231824417,
+      "grad_norm": 1.0391570329666138,
+      "learning_rate": 2.553186363975074e-06,
+      "loss": 0.2446,
+      "step": 900
+    },
+    {
+      "epoch": 2.4801097393689986,
+      "grad_norm": 0.97417813539505,
+      "learning_rate": 2.4281739817796488e-06,
+      "loss": 0.2754,
+      "step": 905
+    },
+    {
+      "epoch": 2.493827160493827,
+      "grad_norm": 1.0047510862350464,
+      "learning_rate": 2.306029494152996e-06,
+      "loss": 0.244,
+      "step": 910
+    },
+    {
+      "epoch": 2.5075445816186557,
+      "grad_norm": 1.0940197706222534,
+      "learning_rate": 2.1867807647890803e-06,
+      "loss": 0.2473,
+      "step": 915
+    },
+    {
+      "epoch": 2.521262002743484,
+      "grad_norm": 0.9839754104614258,
+      "learning_rate": 2.070454996799261e-06,
+      "loss": 0.2167,
+      "step": 920
+    },
+    {
+      "epoch": 2.5349794238683128,
+      "grad_norm": 0.9579572677612305,
+      "learning_rate": 1.957078726506733e-06,
+      "loss": 0.2748,
+      "step": 925
+    },
+    {
+      "epoch": 2.5486968449931413,
+      "grad_norm": 1.0771347284317017,
+      "learning_rate": 1.8466778173930016e-06,
+      "loss": 0.2283,
+      "step": 930
+    },
+    {
+      "epoch": 2.56241426611797,
+      "grad_norm": 0.9137755632400513,
+      "learning_rate": 1.7392774541979151e-06,
+      "loss": 0.1989,
+      "step": 935
+    },
+    {
+      "epoch": 2.5761316872427984,
+      "grad_norm": 1.064967155456543,
+      "learning_rate": 1.6349021371744833e-06,
+      "loss": 0.2226,
+      "step": 940
+    },
+    {
+      "epoch": 2.589849108367627,
+      "grad_norm": 1.1061336994171143,
+      "learning_rate": 1.533575676499876e-06,
+      "loss": 0.2233,
+      "step": 945
+    },
+    {
+      "epoch": 2.6035665294924555,
+      "grad_norm": 0.9804483652114868,
+      "learning_rate": 1.4353211868438115e-06,
+      "loss": 0.2316,
+      "step": 950
+    },
+    {
+      "epoch": 2.617283950617284,
+      "grad_norm": 0.98353511095047,
+      "learning_rate": 1.340161082095646e-06,
+      "loss": 0.2227,
+      "step": 955
+    },
+    {
+      "epoch": 2.6310013717421126,
+      "grad_norm": 1.0998910665512085,
+      "learning_rate": 1.248117070251264e-06,
+      "loss": 0.2519,
+      "step": 960
+    },
+    {
+      "epoch": 2.644718792866941,
+      "grad_norm": 1.0841447114944458,
+      "learning_rate": 1.159210148461065e-06,
+      "loss": 0.2118,
+      "step": 965
+    },
+    {
+      "epoch": 2.6584362139917697,
+      "grad_norm": 0.9606541395187378,
+      "learning_rate": 1.0734605982400603e-06,
+      "loss": 0.2111,
+      "step": 970
+    },
+    {
+      "epoch": 2.672153635116598,
+      "grad_norm": 1.0418294668197632,
+      "learning_rate": 9.908879808412485e-07,
+      "loss": 0.2942,
+      "step": 975
+    },
+    {
+      "epoch": 2.6858710562414267,
+      "grad_norm": 1.0719671249389648,
+      "learning_rate": 9.115111327932718e-07,
+      "loss": 0.2175,
+      "step": 980
+    },
+    {
+      "epoch": 2.6995884773662553,
+      "grad_norm": 0.981621265411377,
+      "learning_rate": 8.353481616034369e-07,
+      "loss": 0.2613,
+      "step": 985
+    },
+    {
+      "epoch": 2.713305898491084,
+      "grad_norm": 1.18305504322052,
+      "learning_rate": 7.624164416269935e-07,
+      "loss": 0.2357,
+      "step": 990
+    },
+    {
+      "epoch": 2.7270233196159124,
+      "grad_norm": 1.00554621219635,
+      "learning_rate": 6.927326101037007e-07,
+      "loss": 0.2671,
+      "step": 995
+    },
+    {
+      "epoch": 2.7407407407407405,
+      "grad_norm": 1.073001742362976,
+      "learning_rate": 6.263125633625067e-07,
+      "loss": 0.1962,
+      "step": 1000
+    },
+    {
+      "epoch": 2.7544581618655695,
+      "grad_norm": 1.155756950378418,
+      "learning_rate": 5.631714531952925e-07,
+      "loss": 0.2379,
+      "step": 1005
+    },
+    {
+      "epoch": 2.7681755829903976,
+      "grad_norm": 0.8633406162261963,
+      "learning_rate": 5.033236834004057e-07,
+      "loss": 0.2273,
+      "step": 1010
+    },
+    {
+      "epoch": 2.7818930041152266,
+      "grad_norm": 0.9453356266021729,
+      "learning_rate": 4.467829064968815e-07,
+      "loss": 0.2475,
+      "step": 1015
+    },
+    {
+      "epoch": 2.7956104252400547,
+      "grad_norm": 1.0707476139068604,
+      "learning_rate": 3.9356202060999767e-07,
+      "loss": 0.209,
+      "step": 1020
+    },
+    {
+      "epoch": 2.8093278463648836,
+      "grad_norm": 0.9674614071846008,
+      "learning_rate": 3.4367316652895996e-07,
+      "loss": 0.2232,
+      "step": 1025
+    },
+    {
+      "epoch": 2.8230452674897117,
+      "grad_norm": 1.1861839294433594,
+      "learning_rate": 2.9712772493732387e-07,
+      "loss": 0.2064,
+      "step": 1030
+    },
+    {
+      "epoch": 2.8367626886145407,
+      "grad_norm": 0.9691592454910278,
+      "learning_rate": 2.5393631381683493e-07,
+      "loss": 0.2669,
+      "step": 1035
+    },
+    {
+      "epoch": 2.850480109739369,
+      "grad_norm": 0.9858601689338684,
+      "learning_rate": 2.1410878602523776e-07,
+      "loss": 0.2328,
+      "step": 1040
+    },
+    {
+      "epoch": 2.8641975308641974,
+      "grad_norm": 0.9588889479637146,
+      "learning_rate": 1.7765422704864088e-07,
+      "loss": 0.2335,
+      "step": 1045
+    },
+    {
+      "epoch": 2.877914951989026,
+      "grad_norm": 0.9827353954315186,
+      "learning_rate": 1.4458095292892436e-07,
+      "loss": 0.2344,
+      "step": 1050
+    },
+    {
+      "epoch": 2.8916323731138545,
+      "grad_norm": 0.96021568775177,
+      "learning_rate": 1.1489650836668419e-07,
+      "loss": 0.2168,
+      "step": 1055
+    },
+    {
+      "epoch": 2.905349794238683,
+      "grad_norm": 1.048067331314087,
+      "learning_rate": 8.860766500012218e-08,
+      "loss": 0.2404,
+      "step": 1060
+    },
+    {
+      "epoch": 2.9190672153635115,
+      "grad_norm": 0.9892206192016602,
+      "learning_rate": 6.572041986029842e-08,
+      "loss": 0.2222,
+      "step": 1065
+    },
+    {
+      "epoch": 2.93278463648834,
+      "grad_norm": 0.9867884516716003,
+      "learning_rate": 4.623999400308054e-08,
+      "loss": 0.2223,
+      "step": 1070
+    },
+    {
+      "epoch": 2.9465020576131686,
+      "grad_norm": 1.0633527040481567,
+      "learning_rate": 3.0170831318119815e-08,
+      "loss": 0.2487,
+      "step": 1075
+    },
+    {
+      "epoch": 2.960219478737997,
+      "grad_norm": 0.97935950756073,
+      "learning_rate": 1.7516597515100374e-08,
+      "loss": 0.2496,
+      "step": 1080
+    },
+    {
+      "epoch": 2.9739368998628257,
+      "grad_norm": 0.9585884809494019,
+      "learning_rate": 8.280179287519785e-09,
+      "loss": 0.2247,
+      "step": 1085
+    },
+    {
+      "epoch": 2.9876543209876543,
+      "grad_norm": 0.981431245803833,
+      "learning_rate": 2.463683654167492e-09,
+      "loss": 0.2549,
+      "step": 1090
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.2818795442581177,
+      "learning_rate": 6.843747847762316e-11,
+      "loss": 0.2225,
+      "step": 1095
+    },
+    {
+      "epoch": 3.0,
+      "step": 1095,
+      "total_flos": 1.681814355403866e+18,
+      "train_loss": 0.5136630487768618,
+      "train_runtime": 798.9244,
+      "train_samples_per_second": 43.776,
+      "train_steps_per_second": 1.371
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1095,
+  "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": 1.681814355403866e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

21_128_e3_3e-5/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9afb5b0eed9286ec6f35c8c379c43c04f39c0ab576cbaa015d13a1d36683df7b
+size 8209