Upload folder using huggingface_hub

129_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",
+    "down_proj",
+    "k_proj",
+    "up_proj",
+    "gate_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

129_128_e3_3e-5/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:688f0f18db1fefd59fb9b16265ff94b2f225ec94bd05308bac045188e23ea4dc
+size 791751704

129_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
+}

129_128_e3_3e-5/all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.442704717057622e+18,
+    "train_loss": 0.35479729593088083,
+    "train_runtime": 662.1163,
+    "train_samples": 11038,
+    "train_samples_per_second": 50.012,
+    "train_steps_per_second": 1.563
+}

129_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 %}

129_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
+}

129_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
+  }
+}

129_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
+}

129_128_e3_3e-5/train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.442704717057622e+18,
+    "train_loss": 0.35479729593088083,
+    "train_runtime": 662.1163,
+    "train_samples": 11038,
+    "train_samples_per_second": 50.012,
+    "train_steps_per_second": 1.563
+}

129_128_e3_3e-5/trainer_state.json

@@ -0,0 +1,1492 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1035,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.014492753623188406,
+      "grad_norm": 2.29368257522583,
+      "learning_rate": 2.307692307692308e-06,
+      "loss": 1.487,
+      "step": 5
+    },
+    {
+      "epoch": 0.028985507246376812,
+      "grad_norm": 1.6915779113769531,
+      "learning_rate": 5.192307692307692e-06,
+      "loss": 1.4456,
+      "step": 10
+    },
+    {
+      "epoch": 0.043478260869565216,
+      "grad_norm": 0.784110426902771,
+      "learning_rate": 8.076923076923077e-06,
+      "loss": 1.3661,
+      "step": 15
+    },
+    {
+      "epoch": 0.057971014492753624,
+      "grad_norm": 0.4805578589439392,
+      "learning_rate": 1.0961538461538462e-05,
+      "loss": 1.3531,
+      "step": 20
+    },
+    {
+      "epoch": 0.07246376811594203,
+      "grad_norm": 0.3890978693962097,
+      "learning_rate": 1.3846153846153847e-05,
+      "loss": 1.2926,
+      "step": 25
+    },
+    {
+      "epoch": 0.08695652173913043,
+      "grad_norm": 0.4676070809364319,
+      "learning_rate": 1.673076923076923e-05,
+      "loss": 1.3558,
+      "step": 30
+    },
+    {
+      "epoch": 0.10144927536231885,
+      "grad_norm": 0.37151506543159485,
+      "learning_rate": 1.9615384615384617e-05,
+      "loss": 1.3104,
+      "step": 35
+    },
+    {
+      "epoch": 0.11594202898550725,
+      "grad_norm": 0.37128910422325134,
+      "learning_rate": 2.25e-05,
+      "loss": 1.28,
+      "step": 40
+    },
+    {
+      "epoch": 0.13043478260869565,
+      "grad_norm": 0.45238012075424194,
+      "learning_rate": 2.5384615384615386e-05,
+      "loss": 1.2367,
+      "step": 45
+    },
+    {
+      "epoch": 0.14492753623188406,
+      "grad_norm": 0.3955983519554138,
+      "learning_rate": 2.8269230769230768e-05,
+      "loss": 1.1941,
+      "step": 50
+    },
+    {
+      "epoch": 0.15942028985507245,
+      "grad_norm": 0.39793866872787476,
+      "learning_rate": 2.9999693583261366e-05,
+      "loss": 1.2288,
+      "step": 55
+    },
+    {
+      "epoch": 0.17391304347826086,
+      "grad_norm": 0.40226852893829346,
+      "learning_rate": 2.999624653872102e-05,
+      "loss": 1.1967,
+      "step": 60
+    },
+    {
+      "epoch": 0.18840579710144928,
+      "grad_norm": 0.4234427809715271,
+      "learning_rate": 2.9988970311828866e-05,
+      "loss": 1.1199,
+      "step": 65
+    },
+    {
+      "epoch": 0.2028985507246377,
+      "grad_norm": 0.49113038182258606,
+      "learning_rate": 2.9977866760516453e-05,
+      "loss": 1.1373,
+      "step": 70
+    },
+    {
+      "epoch": 0.21739130434782608,
+      "grad_norm": 0.5057420134544373,
+      "learning_rate": 2.9962938719994754e-05,
+      "loss": 1.1385,
+      "step": 75
+    },
+    {
+      "epoch": 0.2318840579710145,
+      "grad_norm": 0.49440595507621765,
+      "learning_rate": 2.9944190002030212e-05,
+      "loss": 1.0794,
+      "step": 80
+    },
+    {
+      "epoch": 0.2463768115942029,
+      "grad_norm": 0.5614175796508789,
+      "learning_rate": 2.9921625393971432e-05,
+      "loss": 1.0574,
+      "step": 85
+    },
+    {
+      "epoch": 0.2608695652173913,
+      "grad_norm": 0.5597239136695862,
+      "learning_rate": 2.9895250657526762e-05,
+      "loss": 1.0322,
+      "step": 90
+    },
+    {
+      "epoch": 0.2753623188405797,
+      "grad_norm": 0.6083477735519409,
+      "learning_rate": 2.9865072527293107e-05,
+      "loss": 0.9871,
+      "step": 95
+    },
+    {
+      "epoch": 0.2898550724637681,
+      "grad_norm": 0.6516250371932983,
+      "learning_rate": 2.983109870903625e-05,
+      "loss": 0.9918,
+      "step": 100
+    },
+    {
+      "epoch": 0.30434782608695654,
+      "grad_norm": 0.5929535031318665,
+      "learning_rate": 2.97933378777233e-05,
+      "loss": 0.9931,
+      "step": 105
+    },
+    {
+      "epoch": 0.3188405797101449,
+      "grad_norm": 0.6267664432525635,
+      "learning_rate": 2.9751799675307554e-05,
+      "loss": 0.8745,
+      "step": 110
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.6780182719230652,
+      "learning_rate": 2.9706494708266526e-05,
+      "loss": 0.9405,
+      "step": 115
+    },
+    {
+      "epoch": 0.34782608695652173,
+      "grad_norm": 0.7127269506454468,
+      "learning_rate": 2.965743454489363e-05,
+      "loss": 0.9091,
+      "step": 120
+    },
+    {
+      "epoch": 0.36231884057971014,
+      "grad_norm": 0.7203830480575562,
+      "learning_rate": 2.9604631712344344e-05,
+      "loss": 0.8655,
+      "step": 125
+    },
+    {
+      "epoch": 0.37681159420289856,
+      "grad_norm": 0.7120890617370605,
+      "learning_rate": 2.9548099693437444e-05,
+      "loss": 0.9081,
+      "step": 130
+    },
+    {
+      "epoch": 0.391304347826087,
+      "grad_norm": 0.8813191652297974,
+      "learning_rate": 2.9487852923212293e-05,
+      "loss": 0.812,
+      "step": 135
+    },
+    {
+      "epoch": 0.4057971014492754,
+      "grad_norm": 0.7968631982803345,
+      "learning_rate": 2.942390678524296e-05,
+      "loss": 0.8208,
+      "step": 140
+    },
+    {
+      "epoch": 0.42028985507246375,
+      "grad_norm": 0.9084857106208801,
+      "learning_rate": 2.935627760771012e-05,
+      "loss": 0.7734,
+      "step": 145
+    },
+    {
+      "epoch": 0.43478260869565216,
+      "grad_norm": 0.7910677790641785,
+      "learning_rate": 2.9284982659231786e-05,
+      "loss": 0.7834,
+      "step": 150
+    },
+    {
+      "epoch": 0.4492753623188406,
+      "grad_norm": 0.8696058392524719,
+      "learning_rate": 2.9210040144453882e-05,
+      "loss": 0.7624,
+      "step": 155
+    },
+    {
+      "epoch": 0.463768115942029,
+      "grad_norm": 0.8860491514205933,
+      "learning_rate": 2.9131469199401834e-05,
+      "loss": 0.7789,
+      "step": 160
+    },
+    {
+      "epoch": 0.4782608695652174,
+      "grad_norm": 0.9893876314163208,
+      "learning_rate": 2.904928988659431e-05,
+      "loss": 0.7261,
+      "step": 165
+    },
+    {
+      "epoch": 0.4927536231884058,
+      "grad_norm": 0.9019428491592407,
+      "learning_rate": 2.896352318992041e-05,
+      "loss": 0.7486,
+      "step": 170
+    },
+    {
+      "epoch": 0.5072463768115942,
+      "grad_norm": 1.0983377695083618,
+      "learning_rate": 2.887419100928158e-05,
+      "loss": 0.7475,
+      "step": 175
+    },
+    {
+      "epoch": 0.5217391304347826,
+      "grad_norm": 0.8559118509292603,
+      "learning_rate": 2.8781316154999635e-05,
+      "loss": 0.6219,
+      "step": 180
+    },
+    {
+      "epoch": 0.5362318840579711,
+      "grad_norm": 0.9794448614120483,
+      "learning_rate": 2.8684922341992308e-05,
+      "loss": 0.6509,
+      "step": 185
+    },
+    {
+      "epoch": 0.5507246376811594,
+      "grad_norm": 0.9140684008598328,
+      "learning_rate": 2.858503418371781e-05,
+      "loss": 0.6742,
+      "step": 190
+    },
+    {
+      "epoch": 0.5652173913043478,
+      "grad_norm": 1.0438441038131714,
+      "learning_rate": 2.8481677185889985e-05,
+      "loss": 0.7169,
+      "step": 195
+    },
+    {
+      "epoch": 0.5797101449275363,
+      "grad_norm": 1.053440809249878,
+      "learning_rate": 2.837487773996558e-05,
+      "loss": 0.6935,
+      "step": 200
+    },
+    {
+      "epoch": 0.5942028985507246,
+      "grad_norm": 0.9789332151412964,
+      "learning_rate": 2.8264663116405413e-05,
+      "loss": 0.6124,
+      "step": 205
+    },
+    {
+      "epoch": 0.6086956521739131,
+      "grad_norm": 1.0646133422851562,
+      "learning_rate": 2.8151061457711023e-05,
+      "loss": 0.6517,
+      "step": 210
+    },
+    {
+      "epoch": 0.6231884057971014,
+      "grad_norm": 1.2079098224639893,
+      "learning_rate": 2.803410177123872e-05,
+      "loss": 0.6123,
+      "step": 215
+    },
+    {
+      "epoch": 0.6376811594202898,
+      "grad_norm": 1.0250849723815918,
+      "learning_rate": 2.7913813921792755e-05,
+      "loss": 0.625,
+      "step": 220
+    },
+    {
+      "epoch": 0.6521739130434783,
+      "grad_norm": 0.9295159578323364,
+      "learning_rate": 2.7790228623999554e-05,
+      "loss": 0.5973,
+      "step": 225
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 1.0242691040039062,
+      "learning_rate": 2.766337743446496e-05,
+      "loss": 0.549,
+      "step": 230
+    },
+    {
+      "epoch": 0.6811594202898551,
+      "grad_norm": 1.1183089017868042,
+      "learning_rate": 2.7533292743716508e-05,
+      "loss": 0.5535,
+      "step": 235
+    },
+    {
+      "epoch": 0.6956521739130435,
+      "grad_norm": 1.0617679357528687,
+      "learning_rate": 2.74000077679327e-05,
+      "loss": 0.5657,
+      "step": 240
+    },
+    {
+      "epoch": 0.7101449275362319,
+      "grad_norm": 1.1382501125335693,
+      "learning_rate": 2.7263556540461533e-05,
+      "loss": 0.5337,
+      "step": 245
+    },
+    {
+      "epoch": 0.7246376811594203,
+      "grad_norm": 1.015152096748352,
+      "learning_rate": 2.7123973903130312e-05,
+      "loss": 0.5501,
+      "step": 250
+    },
+    {
+      "epoch": 0.7391304347826086,
+      "grad_norm": 1.1674869060516357,
+      "learning_rate": 2.6981295497349044e-05,
+      "loss": 0.5538,
+      "step": 255
+    },
+    {
+      "epoch": 0.7536231884057971,
+      "grad_norm": 0.9769027233123779,
+      "learning_rate": 2.6835557755009675e-05,
+      "loss": 0.4918,
+      "step": 260
+    },
+    {
+      "epoch": 0.7681159420289855,
+      "grad_norm": 1.2402764558792114,
+      "learning_rate": 2.668679788918345e-05,
+      "loss": 0.4701,
+      "step": 265
+    },
+    {
+      "epoch": 0.782608695652174,
+      "grad_norm": 1.1118128299713135,
+      "learning_rate": 2.653505388461885e-05,
+      "loss": 0.4813,
+      "step": 270
+    },
+    {
+      "epoch": 0.7971014492753623,
+      "grad_norm": 1.1061789989471436,
+      "learning_rate": 2.6380364488042448e-05,
+      "loss": 0.4986,
+      "step": 275
+    },
+    {
+      "epoch": 0.8115942028985508,
+      "grad_norm": 1.131933569908142,
+      "learning_rate": 2.622276919826522e-05,
+      "loss": 0.5132,
+      "step": 280
+    },
+    {
+      "epoch": 0.8260869565217391,
+      "grad_norm": 0.9779942035675049,
+      "learning_rate": 2.6062308256096808e-05,
+      "loss": 0.4648,
+      "step": 285
+    },
+    {
+      "epoch": 0.8405797101449275,
+      "grad_norm": 1.0667296648025513,
+      "learning_rate": 2.589902263407034e-05,
+      "loss": 0.4638,
+      "step": 290
+    },
+    {
+      "epoch": 0.855072463768116,
+      "grad_norm": 1.106985092163086,
+      "learning_rate": 2.573295402598034e-05,
+      "loss": 0.484,
+      "step": 295
+    },
+    {
+      "epoch": 0.8695652173913043,
+      "grad_norm": 1.3256334066390991,
+      "learning_rate": 2.55641448362366e-05,
+      "loss": 0.4971,
+      "step": 300
+    },
+    {
+      "epoch": 0.8840579710144928,
+      "grad_norm": 1.0940841436386108,
+      "learning_rate": 2.5392638169036455e-05,
+      "loss": 0.4242,
+      "step": 305
+    },
+    {
+      "epoch": 0.8985507246376812,
+      "grad_norm": 1.042338490486145,
+      "learning_rate": 2.5218477817358476e-05,
+      "loss": 0.4759,
+      "step": 310
+    },
+    {
+      "epoch": 0.9130434782608695,
+      "grad_norm": 1.2884581089019775,
+      "learning_rate": 2.5041708251780228e-05,
+      "loss": 0.4169,
+      "step": 315
+    },
+    {
+      "epoch": 0.927536231884058,
+      "grad_norm": 1.2630621194839478,
+      "learning_rate": 2.4862374609123066e-05,
+      "loss": 0.4263,
+      "step": 320
+    },
+    {
+      "epoch": 0.9420289855072463,
+      "grad_norm": 1.2954730987548828,
+      "learning_rate": 2.468052268092674e-05,
+      "loss": 0.3979,
+      "step": 325
+    },
+    {
+      "epoch": 0.9565217391304348,
+      "grad_norm": 1.2494120597839355,
+      "learning_rate": 2.449619890175688e-05,
+      "loss": 0.3904,
+      "step": 330
+    },
+    {
+      "epoch": 0.9710144927536232,
+      "grad_norm": 1.0689351558685303,
+      "learning_rate": 2.430945033734826e-05,
+      "loss": 0.3937,
+      "step": 335
+    },
+    {
+      "epoch": 0.9855072463768116,
+      "grad_norm": 1.2330207824707031,
+      "learning_rate": 2.412032467258691e-05,
+      "loss": 0.3403,
+      "step": 340
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.176853895187378,
+      "learning_rate": 2.3928870199334122e-05,
+      "loss": 0.4216,
+      "step": 345
+    },
+    {
+      "epoch": 1.0144927536231885,
+      "grad_norm": 1.2628767490386963,
+      "learning_rate": 2.373513580409548e-05,
+      "loss": 0.35,
+      "step": 350
+    },
+    {
+      "epoch": 1.0289855072463767,
+      "grad_norm": 1.271819829940796,
+      "learning_rate": 2.3539170955538052e-05,
+      "loss": 0.3091,
+      "step": 355
+    },
+    {
+      "epoch": 1.0434782608695652,
+      "grad_norm": 1.049347996711731,
+      "learning_rate": 2.33410256918589e-05,
+      "loss": 0.3421,
+      "step": 360
+    },
+    {
+      "epoch": 1.0579710144927537,
+      "grad_norm": 1.1845500469207764,
+      "learning_rate": 2.3140750608008236e-05,
+      "loss": 0.3106,
+      "step": 365
+    },
+    {
+      "epoch": 1.0724637681159421,
+      "grad_norm": 1.2562522888183594,
+      "learning_rate": 2.2938396842770318e-05,
+      "loss": 0.2991,
+      "step": 370
+    },
+    {
+      "epoch": 1.0869565217391304,
+      "grad_norm": 1.3001786470413208,
+      "learning_rate": 2.2734016065705572e-05,
+      "loss": 0.3021,
+      "step": 375
+    },
+    {
+      "epoch": 1.1014492753623188,
+      "grad_norm": 1.1793432235717773,
+      "learning_rate": 2.252766046395713e-05,
+      "loss": 0.3073,
+      "step": 380
+    },
+    {
+      "epoch": 1.1159420289855073,
+      "grad_norm": 1.284938931465149,
+      "learning_rate": 2.2319382728925234e-05,
+      "loss": 0.2755,
+      "step": 385
+    },
+    {
+      "epoch": 1.1304347826086956,
+      "grad_norm": 1.0531214475631714,
+      "learning_rate": 2.2109236042812854e-05,
+      "loss": 0.2696,
+      "step": 390
+    },
+    {
+      "epoch": 1.144927536231884,
+      "grad_norm": 1.151487946510315,
+      "learning_rate": 2.1897274065046008e-05,
+      "loss": 0.2851,
+      "step": 395
+    },
+    {
+      "epoch": 1.1594202898550725,
+      "grad_norm": 1.0929127931594849,
+      "learning_rate": 2.1683550918572232e-05,
+      "loss": 0.2741,
+      "step": 400
+    },
+    {
+      "epoch": 1.1739130434782608,
+      "grad_norm": 1.2057164907455444,
+      "learning_rate": 2.1468121176040653e-05,
+      "loss": 0.2576,
+      "step": 405
+    },
+    {
+      "epoch": 1.1884057971014492,
+      "grad_norm": 1.3144835233688354,
+      "learning_rate": 2.1251039845867278e-05,
+      "loss": 0.2526,
+      "step": 410
+    },
+    {
+      "epoch": 1.2028985507246377,
+      "grad_norm": 1.3060120344161987,
+      "learning_rate": 2.1032362358188998e-05,
+      "loss": 0.2661,
+      "step": 415
+    },
+    {
+      "epoch": 1.2173913043478262,
+      "grad_norm": 1.0789402723312378,
+      "learning_rate": 2.0812144550709882e-05,
+      "loss": 0.248,
+      "step": 420
+    },
+    {
+      "epoch": 1.2318840579710144,
+      "grad_norm": 1.1521925926208496,
+      "learning_rate": 2.0590442654443466e-05,
+      "loss": 0.2701,
+      "step": 425
+    },
+    {
+      "epoch": 1.2463768115942029,
+      "grad_norm": 1.4659336805343628,
+      "learning_rate": 2.036731327935454e-05,
+      "loss": 0.2274,
+      "step": 430
+    },
+    {
+      "epoch": 1.2608695652173914,
+      "grad_norm": 1.3186372518539429,
+      "learning_rate": 2.0142813399904212e-05,
+      "loss": 0.2472,
+      "step": 435
+    },
+    {
+      "epoch": 1.2753623188405796,
+      "grad_norm": 1.1641013622283936,
+      "learning_rate": 1.9917000340501904e-05,
+      "loss": 0.2251,
+      "step": 440
+    },
+    {
+      "epoch": 1.289855072463768,
+      "grad_norm": 1.0886751413345337,
+      "learning_rate": 1.968993176086798e-05,
+      "loss": 0.2599,
+      "step": 445
+    },
+    {
+      "epoch": 1.3043478260869565,
+      "grad_norm": 1.2953417301177979,
+      "learning_rate": 1.946166564131075e-05,
+      "loss": 0.2385,
+      "step": 450
+    },
+    {
+      "epoch": 1.318840579710145,
+      "grad_norm": 1.2262042760849,
+      "learning_rate": 1.9232260267921616e-05,
+      "loss": 0.2271,
+      "step": 455
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 1.3017724752426147,
+      "learning_rate": 1.9001774217692157e-05,
+      "loss": 0.2407,
+      "step": 460
+    },
+    {
+      "epoch": 1.3478260869565217,
+      "grad_norm": 1.23837411403656,
+      "learning_rate": 1.877026634355691e-05,
+      "loss": 0.2125,
+      "step": 465
+    },
+    {
+      "epoch": 1.3623188405797102,
+      "grad_norm": 1.076448678970337,
+      "learning_rate": 1.8537795759365712e-05,
+      "loss": 0.2039,
+      "step": 470
+    },
+    {
+      "epoch": 1.3768115942028984,
+      "grad_norm": 1.4278571605682373,
+      "learning_rate": 1.83044218247894e-05,
+      "loss": 0.2476,
+      "step": 475
+    },
+    {
+      "epoch": 1.391304347826087,
+      "grad_norm": 1.1833091974258423,
+      "learning_rate": 1.8070204130162743e-05,
+      "loss": 0.2286,
+      "step": 480
+    },
+    {
+      "epoch": 1.4057971014492754,
+      "grad_norm": 1.1611639261245728,
+      "learning_rate": 1.7835202481268512e-05,
+      "loss": 0.2192,
+      "step": 485
+    },
+    {
+      "epoch": 1.4202898550724639,
+      "grad_norm": 1.2656430006027222,
+      "learning_rate": 1.759947688406648e-05,
+      "loss": 0.242,
+      "step": 490
+    },
+    {
+      "epoch": 1.434782608695652,
+      "grad_norm": 1.2327630519866943,
+      "learning_rate": 1.7363087529371348e-05,
+      "loss": 0.1956,
+      "step": 495
+    },
+    {
+      "epoch": 1.4492753623188406,
+      "grad_norm": 1.2998470067977905,
+      "learning_rate": 1.7126094777483467e-05,
+      "loss": 0.197,
+      "step": 500
+    },
+    {
+      "epoch": 1.463768115942029,
+      "grad_norm": 1.221003770828247,
+      "learning_rate": 1.6888559142776264e-05,
+      "loss": 0.2047,
+      "step": 505
+    },
+    {
+      "epoch": 1.4782608695652173,
+      "grad_norm": 1.2196900844573975,
+      "learning_rate": 1.6650541278244334e-05,
+      "loss": 0.2252,
+      "step": 510
+    },
+    {
+      "epoch": 1.4927536231884058,
+      "grad_norm": 1.2826776504516602,
+      "learning_rate": 1.6412101960016163e-05,
+      "loss": 0.1925,
+      "step": 515
+    },
+    {
+      "epoch": 1.5072463768115942,
+      "grad_norm": 1.1805167198181152,
+      "learning_rate": 1.6173302071835345e-05,
+      "loss": 0.182,
+      "step": 520
+    },
+    {
+      "epoch": 1.5217391304347827,
+      "grad_norm": 1.113867163658142,
+      "learning_rate": 1.593420258951441e-05,
+      "loss": 0.2017,
+      "step": 525
+    },
+    {
+      "epoch": 1.5362318840579712,
+      "grad_norm": 1.1226778030395508,
+      "learning_rate": 1.5694864565365052e-05,
+      "loss": 0.1801,
+      "step": 530
+    },
+    {
+      "epoch": 1.5507246376811594,
+      "grad_norm": 1.2150529623031616,
+      "learning_rate": 1.54553491126089e-05,
+      "loss": 0.1594,
+      "step": 535
+    },
+    {
+      "epoch": 1.5652173913043477,
+      "grad_norm": 1.070756196975708,
+      "learning_rate": 1.5215717389772667e-05,
+      "loss": 0.1646,
+      "step": 540
+    },
+    {
+      "epoch": 1.5797101449275361,
+      "grad_norm": 1.3430756330490112,
+      "learning_rate": 1.4976030585071798e-05,
+      "loss": 0.1919,
+      "step": 545
+    },
+    {
+      "epoch": 1.5942028985507246,
+      "grad_norm": 1.1809768676757812,
+      "learning_rate": 1.4736349900786485e-05,
+      "loss": 0.1821,
+      "step": 550
+    },
+    {
+      "epoch": 1.608695652173913,
+      "grad_norm": 1.1754435300827026,
+      "learning_rate": 1.4496736537634117e-05,
+      "loss": 0.1867,
+      "step": 555
+    },
+    {
+      "epoch": 1.6231884057971016,
+      "grad_norm": 0.9939794540405273,
+      "learning_rate": 1.4257251679142138e-05,
+      "loss": 0.1709,
+      "step": 560
+    },
+    {
+      "epoch": 1.6376811594202898,
+      "grad_norm": 1.0102311372756958,
+      "learning_rate": 1.401795647602523e-05,
+      "loss": 0.1576,
+      "step": 565
+    },
+    {
+      "epoch": 1.6521739130434783,
+      "grad_norm": 1.0596693754196167,
+      "learning_rate": 1.377891203057098e-05,
+      "loss": 0.1687,
+      "step": 570
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.9647271037101746,
+      "learning_rate": 1.3540179381037828e-05,
+      "loss": 0.1469,
+      "step": 575
+    },
+    {
+      "epoch": 1.681159420289855,
+      "grad_norm": 0.9522281289100647,
+      "learning_rate": 1.3301819486069398e-05,
+      "loss": 0.1486,
+      "step": 580
+    },
+    {
+      "epoch": 1.6956521739130435,
+      "grad_norm": 1.176292061805725,
+      "learning_rate": 1.3063893209129138e-05,
+      "loss": 0.1732,
+      "step": 585
+    },
+    {
+      "epoch": 1.710144927536232,
+      "grad_norm": 1.1907657384872437,
+      "learning_rate": 1.2826461302959302e-05,
+      "loss": 0.1556,
+      "step": 590
+    },
+    {
+      "epoch": 1.7246376811594204,
+      "grad_norm": 1.2872556447982788,
+      "learning_rate": 1.2589584394068174e-05,
+      "loss": 0.152,
+      "step": 595
+    },
+    {
+      "epoch": 1.7391304347826086,
+      "grad_norm": 0.9509644508361816,
+      "learning_rate": 1.2353322967249495e-05,
+      "loss": 0.1484,
+      "step": 600
+    },
+    {
+      "epoch": 1.7536231884057971,
+      "grad_norm": 1.0537123680114746,
+      "learning_rate": 1.2117737350138172e-05,
+      "loss": 0.1454,
+      "step": 605
+    },
+    {
+      "epoch": 1.7681159420289854,
+      "grad_norm": 1.2225844860076904,
+      "learning_rate": 1.188288769780601e-05,
+      "loss": 0.1418,
+      "step": 610
+    },
+    {
+      "epoch": 1.7826086956521738,
+      "grad_norm": 1.3232041597366333,
+      "learning_rate": 1.1648833977401575e-05,
+      "loss": 0.1386,
+      "step": 615
+    },
+    {
+      "epoch": 1.7971014492753623,
+      "grad_norm": 1.0928504467010498,
+      "learning_rate": 1.1415635952838e-05,
+      "loss": 0.1341,
+      "step": 620
+    },
+    {
+      "epoch": 1.8115942028985508,
+      "grad_norm": 1.0872105360031128,
+      "learning_rate": 1.1183353169532721e-05,
+      "loss": 0.1364,
+      "step": 625
+    },
+    {
+      "epoch": 1.8260869565217392,
+      "grad_norm": 1.0524715185165405,
+      "learning_rate": 1.0952044939202995e-05,
+      "loss": 0.1099,
+      "step": 630
+    },
+    {
+      "epoch": 1.8405797101449275,
+      "grad_norm": 0.9809101819992065,
+      "learning_rate": 1.0721770324721043e-05,
+      "loss": 0.1517,
+      "step": 635
+    },
+    {
+      "epoch": 1.855072463768116,
+      "grad_norm": 0.9006941914558411,
+      "learning_rate": 1.0492588125032843e-05,
+      "loss": 0.1411,
+      "step": 640
+    },
+    {
+      "epoch": 1.8695652173913042,
+      "grad_norm": 1.0190712213516235,
+      "learning_rate": 1.0264556860144187e-05,
+      "loss": 0.1262,
+      "step": 645
+    },
+    {
+      "epoch": 1.8840579710144927,
+      "grad_norm": 1.0811265707015991,
+      "learning_rate": 1.0037734756178059e-05,
+      "loss": 0.129,
+      "step": 650
+    },
+    {
+      "epoch": 1.8985507246376812,
+      "grad_norm": 1.0682003498077393,
+      "learning_rate": 9.812179730506989e-06,
+      "loss": 0.1142,
+      "step": 655
+    },
+    {
+      "epoch": 1.9130434782608696,
+      "grad_norm": 1.0650442838668823,
+      "learning_rate": 9.58794937696431e-06,
+      "loss": 0.124,
+      "step": 660
+    },
+    {
+      "epoch": 1.927536231884058,
+      "grad_norm": 0.965182900428772,
+      "learning_rate": 9.365100951137967e-06,
+      "loss": 0.1493,
+      "step": 665
+    },
+    {
+      "epoch": 1.9420289855072463,
+      "grad_norm": 1.055545687675476,
+      "learning_rate": 9.143691355750718e-06,
+      "loss": 0.1239,
+      "step": 670
+    },
+    {
+      "epoch": 1.9565217391304348,
+      "grad_norm": 1.0349035263061523,
+      "learning_rate": 8.923777126130456e-06,
+      "loss": 0.1078,
+      "step": 675
+    },
+    {
+      "epoch": 1.971014492753623,
+      "grad_norm": 0.9817209243774414,
+      "learning_rate": 8.705414415774314e-06,
+      "loss": 0.113,
+      "step": 680
+    },
+    {
+      "epoch": 1.9855072463768115,
+      "grad_norm": 0.9549577832221985,
+      "learning_rate": 8.488658982010277e-06,
+      "loss": 0.1199,
+      "step": 685
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.0334455966949463,
+      "learning_rate": 8.273566171759952e-06,
+      "loss": 0.1226,
+      "step": 690
+    },
+    {
+      "epoch": 2.0144927536231885,
+      "grad_norm": 1.029839277267456,
+      "learning_rate": 8.060190907406136e-06,
+      "loss": 0.1,
+      "step": 695
+    },
+    {
+      "epoch": 2.028985507246377,
+      "grad_norm": 0.816461980342865,
+      "learning_rate": 7.848587672768811e-06,
+      "loss": 0.0888,
+      "step": 700
+    },
+    {
+      "epoch": 2.0434782608695654,
+      "grad_norm": 0.8377205729484558,
+      "learning_rate": 7.63881049919304e-06,
+      "loss": 0.0882,
+      "step": 705
+    },
+    {
+      "epoch": 2.0579710144927534,
+      "grad_norm": 0.7664375305175781,
+      "learning_rate": 7.430912951752516e-06,
+      "loss": 0.0896,
+      "step": 710
+    },
+    {
+      "epoch": 2.072463768115942,
+      "grad_norm": 0.9445498585700989,
+      "learning_rate": 7.224948115572088e-06,
+      "loss": 0.0936,
+      "step": 715
+    },
+    {
+      "epoch": 2.0869565217391304,
+      "grad_norm": 0.8188366293907166,
+      "learning_rate": 7.020968582272843e-06,
+      "loss": 0.0839,
+      "step": 720
+    },
+    {
+      "epoch": 2.101449275362319,
+      "grad_norm": 1.0204064846038818,
+      "learning_rate": 6.819026436543241e-06,
+      "loss": 0.1002,
+      "step": 725
+    },
+    {
+      "epoch": 2.1159420289855073,
+      "grad_norm": 0.7157048583030701,
+      "learning_rate": 6.619173242839658e-06,
+      "loss": 0.0943,
+      "step": 730
+    },
+    {
+      "epoch": 2.130434782608696,
+      "grad_norm": 0.8263306021690369,
+      "learning_rate": 6.421460032219795e-06,
+      "loss": 0.0805,
+      "step": 735
+    },
+    {
+      "epoch": 2.1449275362318843,
+      "grad_norm": 0.8836856484413147,
+      "learning_rate": 6.225937289312244e-06,
+      "loss": 0.0706,
+      "step": 740
+    },
+    {
+      "epoch": 2.1594202898550723,
+      "grad_norm": 0.849089503288269,
+      "learning_rate": 6.032654939425613e-06,
+      "loss": 0.0849,
+      "step": 745
+    },
+    {
+      "epoch": 2.1739130434782608,
+      "grad_norm": 0.7844255566596985,
+      "learning_rate": 5.8416623358004865e-06,
+      "loss": 0.0897,
+      "step": 750
+    },
+    {
+      "epoch": 2.1884057971014492,
+      "grad_norm": 0.8318759202957153,
+      "learning_rate": 5.653008247007395e-06,
+      "loss": 0.0732,
+      "step": 755
+    },
+    {
+      "epoch": 2.2028985507246377,
+      "grad_norm": 0.8238269090652466,
+      "learning_rate": 5.4667408444941455e-06,
+      "loss": 0.0805,
+      "step": 760
+    },
+    {
+      "epoch": 2.217391304347826,
+      "grad_norm": 0.9683007001876831,
+      "learning_rate": 5.2829076902855725e-06,
+      "loss": 0.0776,
+      "step": 765
+    },
+    {
+      "epoch": 2.2318840579710146,
+      "grad_norm": 0.8392951488494873,
+      "learning_rate": 5.1015557248389526e-06,
+      "loss": 0.0892,
+      "step": 770
+    },
+    {
+      "epoch": 2.246376811594203,
+      "grad_norm": 0.7985356450080872,
+      "learning_rate": 4.922731255058062e-06,
+      "loss": 0.0778,
+      "step": 775
+    },
+    {
+      "epoch": 2.260869565217391,
+      "grad_norm": 0.7892628908157349,
+      "learning_rate": 4.7464799424690645e-06,
+      "loss": 0.074,
+      "step": 780
+    },
+    {
+      "epoch": 2.2753623188405796,
+      "grad_norm": 0.8737486004829407,
+      "learning_rate": 4.572846791561185e-06,
+      "loss": 0.0878,
+      "step": 785
+    },
+    {
+      "epoch": 2.289855072463768,
+      "grad_norm": 0.7430487871170044,
+      "learning_rate": 4.401876138295117e-06,
+      "loss": 0.0719,
+      "step": 790
+    },
+    {
+      "epoch": 2.3043478260869565,
+      "grad_norm": 0.718325674533844,
+      "learning_rate": 4.23361163878217e-06,
+      "loss": 0.0724,
+      "step": 795
+    },
+    {
+      "epoch": 2.318840579710145,
+      "grad_norm": 0.6282200813293457,
+      "learning_rate": 4.06809625813701e-06,
+      "loss": 0.0773,
+      "step": 800
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 0.7274117469787598,
+      "learning_rate": 3.9053722595067995e-06,
+      "loss": 0.0799,
+      "step": 805
+    },
+    {
+      "epoch": 2.3478260869565215,
+      "grad_norm": 0.9844738841056824,
+      "learning_rate": 3.7454811932796562e-06,
+      "loss": 0.0766,
+      "step": 810
+    },
+    {
+      "epoch": 2.36231884057971,
+      "grad_norm": 0.7808008790016174,
+      "learning_rate": 3.5884638864750073e-06,
+      "loss": 0.0676,
+      "step": 815
+    },
+    {
+      "epoch": 2.3768115942028984,
+      "grad_norm": 0.8801343441009521,
+      "learning_rate": 3.4343604323187645e-06,
+      "loss": 0.0805,
+      "step": 820
+    },
+    {
+      "epoch": 2.391304347826087,
+      "grad_norm": 0.8881303668022156,
+      "learning_rate": 3.2832101800057694e-06,
+      "loss": 0.0759,
+      "step": 825
+    },
+    {
+      "epoch": 2.4057971014492754,
+      "grad_norm": 0.8214950561523438,
+      "learning_rate": 3.1350517246522807e-06,
+      "loss": 0.0707,
+      "step": 830
+    },
+    {
+      "epoch": 2.420289855072464,
+      "grad_norm": 0.6971524357795715,
+      "learning_rate": 2.9899228974409966e-06,
+      "loss": 0.0616,
+      "step": 835
+    },
+    {
+      "epoch": 2.4347826086956523,
+      "grad_norm": 0.7410798072814941,
+      "learning_rate": 2.8478607559611185e-06,
+      "loss": 0.0768,
+      "step": 840
+    },
+    {
+      "epoch": 2.449275362318841,
+      "grad_norm": 0.8154103755950928,
+      "learning_rate": 2.7089015747459946e-06,
+      "loss": 0.0734,
+      "step": 845
+    },
+    {
+      "epoch": 2.463768115942029,
+      "grad_norm": 0.6762921810150146,
+      "learning_rate": 2.5730808360106416e-06,
+      "loss": 0.0652,
+      "step": 850
+    },
+    {
+      "epoch": 2.4782608695652173,
+      "grad_norm": 0.5677682161331177,
+      "learning_rate": 2.4404332205916663e-06,
+      "loss": 0.0725,
+      "step": 855
+    },
+    {
+      "epoch": 2.4927536231884058,
+      "grad_norm": 0.6338042616844177,
+      "learning_rate": 2.3109925990917306e-06,
+      "loss": 0.0579,
+      "step": 860
+    },
+    {
+      "epoch": 2.5072463768115942,
+      "grad_norm": 0.5832827687263489,
+      "learning_rate": 2.184792023230951e-06,
+      "loss": 0.0678,
+      "step": 865
+    },
+    {
+      "epoch": 2.5217391304347827,
+      "grad_norm": 0.6395509243011475,
+      "learning_rate": 2.061863717407395e-06,
+      "loss": 0.0676,
+      "step": 870
+    },
+    {
+      "epoch": 2.536231884057971,
+      "grad_norm": 0.8154150247573853,
+      "learning_rate": 1.9422390704687894e-06,
+      "loss": 0.0729,
+      "step": 875
+    },
+    {
+      "epoch": 2.550724637681159,
+      "grad_norm": 0.6983283758163452,
+      "learning_rate": 1.8259486276976367e-06,
+      "loss": 0.0619,
+      "step": 880
+    },
+    {
+      "epoch": 2.5652173913043477,
+      "grad_norm": 0.6199825406074524,
+      "learning_rate": 1.713022083011677e-06,
+      "loss": 0.069,
+      "step": 885
+    },
+    {
+      "epoch": 2.579710144927536,
+      "grad_norm": 0.6500135660171509,
+      "learning_rate": 1.603488271381765e-06,
+      "loss": 0.0656,
+      "step": 890
+    },
+    {
+      "epoch": 2.5942028985507246,
+      "grad_norm": 0.7450733780860901,
+      "learning_rate": 1.4973751614690905e-06,
+      "loss": 0.0709,
+      "step": 895
+    },
+    {
+      "epoch": 2.608695652173913,
+      "grad_norm": 0.7423087954521179,
+      "learning_rate": 1.3947098484835496e-06,
+      "loss": 0.0674,
+      "step": 900
+    },
+    {
+      "epoch": 2.6231884057971016,
+      "grad_norm": 0.7187048196792603,
+      "learning_rate": 1.2955185472652176e-06,
+      "loss": 0.0673,
+      "step": 905
+    },
+    {
+      "epoch": 2.63768115942029,
+      "grad_norm": 0.7221335172653198,
+      "learning_rate": 1.1998265855905487e-06,
+      "loss": 0.0712,
+      "step": 910
+    },
+    {
+      "epoch": 2.6521739130434785,
+      "grad_norm": 0.6639856696128845,
+      "learning_rate": 1.1076583977051386e-06,
+      "loss": 0.0645,
+      "step": 915
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.7440511584281921,
+      "learning_rate": 1.0190375180845985e-06,
+      "loss": 0.0639,
+      "step": 920
+    },
+    {
+      "epoch": 2.681159420289855,
+      "grad_norm": 0.6252512335777283,
+      "learning_rate": 9.339865754252036e-07,
+      "loss": 0.0809,
+      "step": 925
+    },
+    {
+      "epoch": 2.6956521739130435,
+      "grad_norm": 0.8585799336433411,
+      "learning_rate": 8.525272868658346e-07,
+      "loss": 0.0694,
+      "step": 930
+    },
+    {
+      "epoch": 2.710144927536232,
+      "grad_norm": 0.566343367099762,
+      "learning_rate": 7.746804524426299e-07,
+      "loss": 0.0597,
+      "step": 935
+    },
+    {
+      "epoch": 2.7246376811594204,
+      "grad_norm": 0.7024088501930237,
+      "learning_rate": 7.004659497778942e-07,
+      "loss": 0.0666,
+      "step": 940
+    },
+    {
+      "epoch": 2.7391304347826084,
+      "grad_norm": 0.651700496673584,
+      "learning_rate": 6.29902729004449e-07,
+      "loss": 0.0661,
+      "step": 945
+    },
+    {
+      "epoch": 2.753623188405797,
+      "grad_norm": 0.7848781943321228,
+      "learning_rate": 5.630088079268874e-07,
+      "loss": 0.0716,
+      "step": 950
+    },
+    {
+      "epoch": 2.7681159420289854,
+      "grad_norm": 0.7099800705909729,
+      "learning_rate": 4.998012674208369e-07,
+      "loss": 0.0727,
+      "step": 955
+    },
+    {
+      "epoch": 2.782608695652174,
+      "grad_norm": 0.5142015814781189,
+      "learning_rate": 4.402962470714889e-07,
+      "loss": 0.0582,
+      "step": 960
+    },
+    {
+      "epoch": 2.7971014492753623,
+      "grad_norm": 0.6297610998153687,
+      "learning_rate": 3.84508941052481e-07,
+      "loss": 0.0681,
+      "step": 965
+    },
+    {
+      "epoch": 2.8115942028985508,
+      "grad_norm": 0.5114739537239075,
+      "learning_rate": 3.324535942461637e-07,
+      "loss": 0.066,
+      "step": 970
+    },
+    {
+      "epoch": 2.8260869565217392,
+      "grad_norm": 0.6796772480010986,
+      "learning_rate": 2.8414349860627965e-07,
+      "loss": 0.0647,
+      "step": 975
+    },
+    {
+      "epoch": 2.8405797101449277,
+      "grad_norm": 0.6610229015350342,
+      "learning_rate": 2.3959098976395863e-07,
+      "loss": 0.0707,
+      "step": 980
+    },
+    {
+      "epoch": 2.855072463768116,
+      "grad_norm": 0.6537678837776184,
+      "learning_rate": 1.9880744387790585e-07,
+      "loss": 0.058,
+      "step": 985
+    },
+    {
+      "epoch": 2.869565217391304,
+      "grad_norm": 0.5400543808937073,
+      "learning_rate": 1.6180327472957835e-07,
+      "loss": 0.0708,
+      "step": 990
+    },
+    {
+      "epoch": 2.8840579710144927,
+      "grad_norm": 0.5322905778884888,
+      "learning_rate": 1.2858793106410584e-07,
+      "loss": 0.0648,
+      "step": 995
+    },
+    {
+      "epoch": 2.898550724637681,
+      "grad_norm": 0.5769522190093994,
+      "learning_rate": 9.916989417762201e-08,
+      "loss": 0.0632,
+      "step": 1000
+    },
+    {
+      "epoch": 2.9130434782608696,
+      "grad_norm": 0.6417686939239502,
+      "learning_rate": 7.355667575162373e-08,
+      "loss": 0.0657,
+      "step": 1005
+    },
+    {
+      "epoch": 2.927536231884058,
+      "grad_norm": 0.6182323098182678,
+      "learning_rate": 5.175481593492348e-08,
+      "loss": 0.0652,
+      "step": 1010
+    },
+    {
+      "epoch": 2.942028985507246,
+      "grad_norm": 0.6050879955291748,
+      "learning_rate": 3.376988167366535e-08,
+      "loss": 0.0615,
+      "step": 1015
+    },
+    {
+      "epoch": 2.9565217391304346,
+      "grad_norm": 0.6025091409683228,
+      "learning_rate": 1.9606465289848662e-08,
+      "loss": 0.0659,
+      "step": 1020
+    },
+    {
+      "epoch": 2.971014492753623,
+      "grad_norm": 0.6500664353370667,
+      "learning_rate": 9.268183308706046e-09,
+      "loss": 0.0684,
+      "step": 1025
+    },
+    {
+      "epoch": 2.9855072463768115,
+      "grad_norm": 0.7180124521255493,
+      "learning_rate": 2.757675535262072e-09,
+      "loss": 0.0591,
+      "step": 1030
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.6207404136657715,
+      "learning_rate": 7.66043802674643e-11,
+      "loss": 0.0696,
+      "step": 1035
+    },
+    {
+      "epoch": 3.0,
+      "step": 1035,
+      "total_flos": 1.442704717057622e+18,
+      "train_loss": 0.35479729593088083,
+      "train_runtime": 662.1163,
+      "train_samples_per_second": 50.012,
+      "train_steps_per_second": 1.563
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1035,
+  "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": 1.442704717057622e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

129_128_e3_3e-5/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dca116278cdde4ee480ce806e75f75fe9128319eb2e9d5362226c0224c14bdf3
+size 8273