Upload folder using huggingface_hub

130_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",
+    "gate_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

130_128_e3_3e-5/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12b85ffc034d931280cd879ff30dec4158fd94b95c4c4c330539b0458ca4c889
+size 791751704

130_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
+}

130_128_e3_3e-5/all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.3651678818425897e+18,
+    "train_loss": 0.5071639379632179,
+    "train_runtime": 663.9063,
+    "train_samples": 9924,
+    "train_samples_per_second": 44.844,
+    "train_steps_per_second": 1.405
+}

130_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 %}

130_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
+}

130_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
+  }
+}

130_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
+}

130_128_e3_3e-5/train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.3651678818425897e+18,
+    "train_loss": 0.5071639379632179,
+    "train_runtime": 663.9063,
+    "train_samples": 9924,
+    "train_samples_per_second": 44.844,
+    "train_steps_per_second": 1.405
+}

130_128_e3_3e-5/trainer_state.json

@@ -0,0 +1,1345 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 933,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01610305958132045,
+      "grad_norm": 3.3880650997161865,
+      "learning_rate": 2.553191489361702e-06,
+      "loss": 1.4919,
+      "step": 5
+    },
+    {
+      "epoch": 0.0322061191626409,
+      "grad_norm": 1.7943085432052612,
+      "learning_rate": 5.74468085106383e-06,
+      "loss": 1.3642,
+      "step": 10
+    },
+    {
+      "epoch": 0.04830917874396135,
+      "grad_norm": 0.8876295685768127,
+      "learning_rate": 8.936170212765958e-06,
+      "loss": 1.3288,
+      "step": 15
+    },
+    {
+      "epoch": 0.0644122383252818,
+      "grad_norm": 0.47065576910972595,
+      "learning_rate": 1.2127659574468084e-05,
+      "loss": 1.2687,
+      "step": 20
+    },
+    {
+      "epoch": 0.08051529790660225,
+      "grad_norm": 0.5253630876541138,
+      "learning_rate": 1.531914893617021e-05,
+      "loss": 1.218,
+      "step": 25
+    },
+    {
+      "epoch": 0.0966183574879227,
+      "grad_norm": 0.4386317729949951,
+      "learning_rate": 1.8510638297872342e-05,
+      "loss": 1.2261,
+      "step": 30
+    },
+    {
+      "epoch": 0.11272141706924316,
+      "grad_norm": 0.40713176131248474,
+      "learning_rate": 2.170212765957447e-05,
+      "loss": 1.1529,
+      "step": 35
+    },
+    {
+      "epoch": 0.1288244766505636,
+      "grad_norm": 0.37646347284317017,
+      "learning_rate": 2.4893617021276595e-05,
+      "loss": 1.1813,
+      "step": 40
+    },
+    {
+      "epoch": 0.14492753623188406,
+      "grad_norm": 0.4038074016571045,
+      "learning_rate": 2.8085106382978723e-05,
+      "loss": 1.1581,
+      "step": 45
+    },
+    {
+      "epoch": 0.1610305958132045,
+      "grad_norm": 0.38708236813545227,
+      "learning_rate": 2.9999622817324995e-05,
+      "loss": 1.1052,
+      "step": 50
+    },
+    {
+      "epoch": 0.17713365539452497,
+      "grad_norm": 0.32834795117378235,
+      "learning_rate": 2.9995379730074167e-05,
+      "loss": 1.1212,
+      "step": 55
+    },
+    {
+      "epoch": 0.1932367149758454,
+      "grad_norm": 0.4203507602214813,
+      "learning_rate": 2.9986423415327763e-05,
+      "loss": 1.0534,
+      "step": 60
+    },
+    {
+      "epoch": 0.20933977455716588,
+      "grad_norm": 0.3880218267440796,
+      "learning_rate": 2.99727566881628e-05,
+      "loss": 1.1154,
+      "step": 65
+    },
+    {
+      "epoch": 0.22544283413848631,
+      "grad_norm": 0.37999510765075684,
+      "learning_rate": 2.9954383844195356e-05,
+      "loss": 1.0857,
+      "step": 70
+    },
+    {
+      "epoch": 0.24154589371980675,
+      "grad_norm": 0.4368254542350769,
+      "learning_rate": 2.9931310658230394e-05,
+      "loss": 1.0531,
+      "step": 75
+    },
+    {
+      "epoch": 0.2576489533011272,
+      "grad_norm": 0.5098922252655029,
+      "learning_rate": 2.99035443824467e-05,
+      "loss": 1.0383,
+      "step": 80
+    },
+    {
+      "epoch": 0.27375201288244766,
+      "grad_norm": 0.4001052677631378,
+      "learning_rate": 2.9871093744117377e-05,
+      "loss": 1.0994,
+      "step": 85
+    },
+    {
+      "epoch": 0.2898550724637681,
+      "grad_norm": 0.4185938537120819,
+      "learning_rate": 2.9833968942866826e-05,
+      "loss": 0.9996,
+      "step": 90
+    },
+    {
+      "epoch": 0.3059581320450886,
+      "grad_norm": 0.4400230944156647,
+      "learning_rate": 2.9792181647464833e-05,
+      "loss": 0.9848,
+      "step": 95
+    },
+    {
+      "epoch": 0.322061191626409,
+      "grad_norm": 0.4907327890396118,
+      "learning_rate": 2.974574499215896e-05,
+      "loss": 0.9808,
+      "step": 100
+    },
+    {
+      "epoch": 0.33816425120772947,
+      "grad_norm": 0.4393748939037323,
+      "learning_rate": 2.9694673572546295e-05,
+      "loss": 0.9658,
+      "step": 105
+    },
+    {
+      "epoch": 0.35426731078904994,
+      "grad_norm": 0.4166032671928406,
+      "learning_rate": 2.963898344098585e-05,
+      "loss": 0.9307,
+      "step": 110
+    },
+    {
+      "epoch": 0.37037037037037035,
+      "grad_norm": 0.4696148633956909,
+      "learning_rate": 2.957869210155316e-05,
+      "loss": 0.9753,
+      "step": 115
+    },
+    {
+      "epoch": 0.3864734299516908,
+      "grad_norm": 0.46172577142715454,
+      "learning_rate": 2.95138185045385e-05,
+      "loss": 0.9342,
+      "step": 120
+    },
+    {
+      "epoch": 0.4025764895330113,
+      "grad_norm": 0.6020083427429199,
+      "learning_rate": 2.9444383040490607e-05,
+      "loss": 0.936,
+      "step": 125
+    },
+    {
+      "epoch": 0.41867954911433175,
+      "grad_norm": 0.5589181184768677,
+      "learning_rate": 2.9370407533807677e-05,
+      "loss": 0.899,
+      "step": 130
+    },
+    {
+      "epoch": 0.43478260869565216,
+      "grad_norm": 0.5189202427864075,
+      "learning_rate": 2.9291915235877694e-05,
+      "loss": 0.9411,
+      "step": 135
+    },
+    {
+      "epoch": 0.45088566827697263,
+      "grad_norm": 0.6038169264793396,
+      "learning_rate": 2.9208930817770242e-05,
+      "loss": 0.8473,
+      "step": 140
+    },
+    {
+      "epoch": 0.4669887278582931,
+      "grad_norm": 0.5672014951705933,
+      "learning_rate": 2.9121480362482106e-05,
+      "loss": 0.8621,
+      "step": 145
+    },
+    {
+      "epoch": 0.4830917874396135,
+      "grad_norm": 0.5854055285453796,
+      "learning_rate": 2.9029591356739038e-05,
+      "loss": 0.863,
+      "step": 150
+    },
+    {
+      "epoch": 0.499194847020934,
+      "grad_norm": 0.5416742563247681,
+      "learning_rate": 2.893329268235639e-05,
+      "loss": 0.889,
+      "step": 155
+    },
+    {
+      "epoch": 0.5152979066022544,
+      "grad_norm": 0.5476135015487671,
+      "learning_rate": 2.8832614607161186e-05,
+      "loss": 0.8077,
+      "step": 160
+    },
+    {
+      "epoch": 0.5314009661835749,
+      "grad_norm": 0.6754342317581177,
+      "learning_rate": 2.8727588775478602e-05,
+      "loss": 0.7904,
+      "step": 165
+    },
+    {
+      "epoch": 0.5475040257648953,
+      "grad_norm": 0.6575109362602234,
+      "learning_rate": 2.861824819818575e-05,
+      "loss": 0.7685,
+      "step": 170
+    },
+    {
+      "epoch": 0.5636070853462157,
+      "grad_norm": 0.6243380904197693,
+      "learning_rate": 2.850462724233599e-05,
+      "loss": 0.8113,
+      "step": 175
+    },
+    {
+      "epoch": 0.5797101449275363,
+      "grad_norm": 0.6122981905937195,
+      "learning_rate": 2.838676162035694e-05,
+      "loss": 0.7709,
+      "step": 180
+    },
+    {
+      "epoch": 0.5958132045088567,
+      "grad_norm": 0.6494635343551636,
+      "learning_rate": 2.8264688378825627e-05,
+      "loss": 0.7685,
+      "step": 185
+    },
+    {
+      "epoch": 0.6119162640901772,
+      "grad_norm": 0.6207959651947021,
+      "learning_rate": 2.8138445886824324e-05,
+      "loss": 0.7482,
+      "step": 190
+    },
+    {
+      "epoch": 0.6280193236714976,
+      "grad_norm": 0.65889972448349,
+      "learning_rate": 2.8008073823880653e-05,
+      "loss": 0.7633,
+      "step": 195
+    },
+    {
+      "epoch": 0.644122383252818,
+      "grad_norm": 0.6659872531890869,
+      "learning_rate": 2.7873613167495882e-05,
+      "loss": 0.7211,
+      "step": 200
+    },
+    {
+      "epoch": 0.6602254428341385,
+      "grad_norm": 0.6806595921516418,
+      "learning_rate": 2.7735106180265163e-05,
+      "loss": 0.7053,
+      "step": 205
+    },
+    {
+      "epoch": 0.6763285024154589,
+      "grad_norm": 0.7452434301376343,
+      "learning_rate": 2.7592596396593917e-05,
+      "loss": 0.6914,
+      "step": 210
+    },
+    {
+      "epoch": 0.6924315619967794,
+      "grad_norm": 0.7069318294525146,
+      "learning_rate": 2.7446128609014427e-05,
+      "loss": 0.7597,
+      "step": 215
+    },
+    {
+      "epoch": 0.7085346215780999,
+      "grad_norm": 0.8175865411758423,
+      "learning_rate": 2.729574885410704e-05,
+      "loss": 0.702,
+      "step": 220
+    },
+    {
+      "epoch": 0.7246376811594203,
+      "grad_norm": 0.781525194644928,
+      "learning_rate": 2.7141504398030284e-05,
+      "loss": 0.7173,
+      "step": 225
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 0.7334632277488708,
+      "learning_rate": 2.6983443721664574e-05,
+      "loss": 0.6897,
+      "step": 230
+    },
+    {
+      "epoch": 0.7568438003220612,
+      "grad_norm": 0.7013916969299316,
+      "learning_rate": 2.6821616505374074e-05,
+      "loss": 0.6982,
+      "step": 235
+    },
+    {
+      "epoch": 0.7729468599033816,
+      "grad_norm": 0.9042900800704956,
+      "learning_rate": 2.665607361339158e-05,
+      "loss": 0.6881,
+      "step": 240
+    },
+    {
+      "epoch": 0.789049919484702,
+      "grad_norm": 0.7931616306304932,
+      "learning_rate": 2.6486867077831264e-05,
+      "loss": 0.6705,
+      "step": 245
+    },
+    {
+      "epoch": 0.8051529790660226,
+      "grad_norm": 0.8558270335197449,
+      "learning_rate": 2.6314050082334356e-05,
+      "loss": 0.6543,
+      "step": 250
+    },
+    {
+      "epoch": 0.821256038647343,
+      "grad_norm": 0.807102382183075,
+      "learning_rate": 2.613767694535292e-05,
+      "loss": 0.7003,
+      "step": 255
+    },
+    {
+      "epoch": 0.8373590982286635,
+      "grad_norm": 0.8515969514846802,
+      "learning_rate": 2.5957803103076878e-05,
+      "loss": 0.6658,
+      "step": 260
+    },
+    {
+      "epoch": 0.8534621578099839,
+      "grad_norm": 0.7777636647224426,
+      "learning_rate": 2.5774485092009765e-05,
+      "loss": 0.6752,
+      "step": 265
+    },
+    {
+      "epoch": 0.8695652173913043,
+      "grad_norm": 0.8136283755302429,
+      "learning_rate": 2.5587780531198628e-05,
+      "loss": 0.6661,
+      "step": 270
+    },
+    {
+      "epoch": 0.8856682769726248,
+      "grad_norm": 0.817470371723175,
+      "learning_rate": 2.539774810412368e-05,
+      "loss": 0.6754,
+      "step": 275
+    },
+    {
+      "epoch": 0.9017713365539453,
+      "grad_norm": 0.8445294499397278,
+      "learning_rate": 2.520444754025336e-05,
+      "loss": 0.646,
+      "step": 280
+    },
+    {
+      "epoch": 0.9178743961352657,
+      "grad_norm": 0.8335075378417969,
+      "learning_rate": 2.5007939596270654e-05,
+      "loss": 0.6382,
+      "step": 285
+    },
+    {
+      "epoch": 0.9339774557165862,
+      "grad_norm": 0.7831994295120239,
+      "learning_rate": 2.4808286036976538e-05,
+      "loss": 0.6083,
+      "step": 290
+    },
+    {
+      "epoch": 0.9500805152979066,
+      "grad_norm": 0.8937245011329651,
+      "learning_rate": 2.460554961587658e-05,
+      "loss": 0.6452,
+      "step": 295
+    },
+    {
+      "epoch": 0.966183574879227,
+      "grad_norm": 0.8482663035392761,
+      "learning_rate": 2.4399794055456738e-05,
+      "loss": 0.5947,
+      "step": 300
+    },
+    {
+      "epoch": 0.9822866344605475,
+      "grad_norm": 0.8801554441452026,
+      "learning_rate": 2.4191084027154622e-05,
+      "loss": 0.588,
+      "step": 305
+    },
+    {
+      "epoch": 0.998389694041868,
+      "grad_norm": 0.8394781947135925,
+      "learning_rate": 2.3979485131032502e-05,
+      "loss": 0.5791,
+      "step": 310
+    },
+    {
+      "epoch": 1.0128824476650564,
+      "grad_norm": 1.0175528526306152,
+      "learning_rate": 2.376506387515841e-05,
+      "loss": 0.5418,
+      "step": 315
+    },
+    {
+      "epoch": 1.0289855072463767,
+      "grad_norm": 0.9109962582588196,
+      "learning_rate": 2.3547887654701858e-05,
+      "loss": 0.5394,
+      "step": 320
+    },
+    {
+      "epoch": 1.0450885668276972,
+      "grad_norm": 0.8849002122879028,
+      "learning_rate": 2.3328024730750726e-05,
+      "loss": 0.4829,
+      "step": 325
+    },
+    {
+      "epoch": 1.0611916264090178,
+      "grad_norm": 0.9622481465339661,
+      "learning_rate": 2.3105544208856005e-05,
+      "loss": 0.4916,
+      "step": 330
+    },
+    {
+      "epoch": 1.077294685990338,
+      "grad_norm": 0.8995106220245361,
+      "learning_rate": 2.2880516017311066e-05,
+      "loss": 0.4836,
+      "step": 335
+    },
+    {
+      "epoch": 1.0933977455716586,
+      "grad_norm": 1.0017765760421753,
+      "learning_rate": 2.2653010885172373e-05,
+      "loss": 0.4732,
+      "step": 340
+    },
+    {
+      "epoch": 1.109500805152979,
+      "grad_norm": 0.9236481189727783,
+      "learning_rate": 2.24231003200285e-05,
+      "loss": 0.4921,
+      "step": 345
+    },
+    {
+      "epoch": 1.1256038647342996,
+      "grad_norm": 0.939917802810669,
+      "learning_rate": 2.2190856585524428e-05,
+      "loss": 0.4972,
+      "step": 350
+    },
+    {
+      "epoch": 1.14170692431562,
+      "grad_norm": 0.8781351447105408,
+      "learning_rate": 2.1956352678648206e-05,
+      "loss": 0.5319,
+      "step": 355
+    },
+    {
+      "epoch": 1.1578099838969405,
+      "grad_norm": 1.0297682285308838,
+      "learning_rate": 2.171966230678717e-05,
+      "loss": 0.4979,
+      "step": 360
+    },
+    {
+      "epoch": 1.1739130434782608,
+      "grad_norm": 1.009824514389038,
+      "learning_rate": 2.1480859864560757e-05,
+      "loss": 0.4651,
+      "step": 365
+    },
+    {
+      "epoch": 1.1900161030595813,
+      "grad_norm": 0.9090453386306763,
+      "learning_rate": 2.1240020410437453e-05,
+      "loss": 0.4519,
+      "step": 370
+    },
+    {
+      "epoch": 1.2061191626409018,
+      "grad_norm": 0.9835789203643799,
+      "learning_rate": 2.0997219643142967e-05,
+      "loss": 0.4354,
+      "step": 375
+    },
+    {
+      "epoch": 1.2222222222222223,
+      "grad_norm": 0.9404028058052063,
+      "learning_rate": 2.0752533877867242e-05,
+      "loss": 0.4574,
+      "step": 380
+    },
+    {
+      "epoch": 1.2383252818035426,
+      "grad_norm": 0.9458686113357544,
+      "learning_rate": 2.0506040022277667e-05,
+      "loss": 0.4343,
+      "step": 385
+    },
+    {
+      "epoch": 1.2544283413848631,
+      "grad_norm": 0.7967801690101624,
+      "learning_rate": 2.0257815552346084e-05,
+      "loss": 0.4463,
+      "step": 390
+    },
+    {
+      "epoch": 1.2705314009661834,
+      "grad_norm": 0.9472321271896362,
+      "learning_rate": 2.0007938487997147e-05,
+      "loss": 0.4626,
+      "step": 395
+    },
+    {
+      "epoch": 1.286634460547504,
+      "grad_norm": 0.8866984844207764,
+      "learning_rate": 1.975648736858574e-05,
+      "loss": 0.4468,
+      "step": 400
+    },
+    {
+      "epoch": 1.3027375201288245,
+      "grad_norm": 0.9366528391838074,
+      "learning_rate": 1.950354122821111e-05,
+      "loss": 0.4033,
+      "step": 405
+    },
+    {
+      "epoch": 1.318840579710145,
+      "grad_norm": 0.8973490595817566,
+      "learning_rate": 1.9249179570875495e-05,
+      "loss": 0.4222,
+      "step": 410
+    },
+    {
+      "epoch": 1.3349436392914653,
+      "grad_norm": 0.8840349316596985,
+      "learning_rate": 1.8993482345495077e-05,
+      "loss": 0.4189,
+      "step": 415
+    },
+    {
+      "epoch": 1.3510466988727858,
+      "grad_norm": 1.1151107549667358,
+      "learning_rate": 1.873652992077109e-05,
+      "loss": 0.4175,
+      "step": 420
+    },
+    {
+      "epoch": 1.3671497584541064,
+      "grad_norm": 0.957012951374054,
+      "learning_rate": 1.8478403059928934e-05,
+      "loss": 0.4494,
+      "step": 425
+    },
+    {
+      "epoch": 1.3832528180354267,
+      "grad_norm": 1.0091239213943481,
+      "learning_rate": 1.8219182895333362e-05,
+      "loss": 0.4326,
+      "step": 430
+    },
+    {
+      "epoch": 1.3993558776167472,
+      "grad_norm": 1.074291467666626,
+      "learning_rate": 1.7958950902987597e-05,
+      "loss": 0.4137,
+      "step": 435
+    },
+    {
+      "epoch": 1.4154589371980677,
+      "grad_norm": 1.104121446609497,
+      "learning_rate": 1.7697788876924437e-05,
+      "loss": 0.4342,
+      "step": 440
+    },
+    {
+      "epoch": 1.431561996779388,
+      "grad_norm": 1.0362356901168823,
+      "learning_rate": 1.7435778903497437e-05,
+      "loss": 0.399,
+      "step": 445
+    },
+    {
+      "epoch": 1.4476650563607085,
+      "grad_norm": 1.0427170991897583,
+      "learning_rate": 1.7173003335580147e-05,
+      "loss": 0.4399,
+      "step": 450
+    },
+    {
+      "epoch": 1.463768115942029,
+      "grad_norm": 0.9759876132011414,
+      "learning_rate": 1.690954476668165e-05,
+      "loss": 0.4154,
+      "step": 455
+    },
+    {
+      "epoch": 1.4798711755233493,
+      "grad_norm": 0.9761471748352051,
+      "learning_rate": 1.6645486004986412e-05,
+      "loss": 0.4158,
+      "step": 460
+    },
+    {
+      "epoch": 1.4959742351046699,
+      "grad_norm": 0.8958402276039124,
+      "learning_rate": 1.6380910047326687e-05,
+      "loss": 0.3963,
+      "step": 465
+    },
+    {
+      "epoch": 1.5120772946859904,
+      "grad_norm": 1.0740455389022827,
+      "learning_rate": 1.6115900053095626e-05,
+      "loss": 0.4025,
+      "step": 470
+    },
+    {
+      "epoch": 1.528180354267311,
+      "grad_norm": 1.0623130798339844,
+      "learning_rate": 1.585053931810926e-05,
+      "loss": 0.3865,
+      "step": 475
+    },
+    {
+      "epoch": 1.5442834138486312,
+      "grad_norm": 1.0220630168914795,
+      "learning_rate": 1.5584911248425657e-05,
+      "loss": 0.386,
+      "step": 480
+    },
+    {
+      "epoch": 1.5603864734299517,
+      "grad_norm": 0.9684439301490784,
+      "learning_rate": 1.5319099334129366e-05,
+      "loss": 0.4162,
+      "step": 485
+    },
+    {
+      "epoch": 1.576489533011272,
+      "grad_norm": 0.9672483205795288,
+      "learning_rate": 1.5053187123089508e-05,
+      "loss": 0.3219,
+      "step": 490
+    },
+    {
+      "epoch": 1.5925925925925926,
+      "grad_norm": 1.0233534574508667,
+      "learning_rate": 1.4787258194699673e-05,
+      "loss": 0.3887,
+      "step": 495
+    },
+    {
+      "epoch": 1.608695652173913,
+      "grad_norm": 1.0141592025756836,
+      "learning_rate": 1.4521396133607923e-05,
+      "loss": 0.3621,
+      "step": 500
+    },
+    {
+      "epoch": 1.6247987117552336,
+      "grad_norm": 0.9790269732475281,
+      "learning_rate": 1.4255684503445102e-05,
+      "loss": 0.3404,
+      "step": 505
+    },
+    {
+      "epoch": 1.640901771336554,
+      "grad_norm": 1.1322671175003052,
+      "learning_rate": 1.3990206820559842e-05,
+      "loss": 0.4131,
+      "step": 510
+    },
+    {
+      "epoch": 1.6570048309178744,
+      "grad_norm": 1.0798503160476685,
+      "learning_rate": 1.3725046527768315e-05,
+      "loss": 0.4035,
+      "step": 515
+    },
+    {
+      "epoch": 1.6731078904991947,
+      "grad_norm": 0.9912155270576477,
+      "learning_rate": 1.3460286968127212e-05,
+      "loss": 0.3564,
+      "step": 520
+    },
+    {
+      "epoch": 1.6892109500805152,
+      "grad_norm": 1.0493098497390747,
+      "learning_rate": 1.3196011358737966e-05,
+      "loss": 0.337,
+      "step": 525
+    },
+    {
+      "epoch": 1.7053140096618358,
+      "grad_norm": 0.9467443227767944,
+      "learning_rate": 1.2932302764590663e-05,
+      "loss": 0.3262,
+      "step": 530
+    },
+    {
+      "epoch": 1.7214170692431563,
+      "grad_norm": 0.9496434926986694,
+      "learning_rate": 1.266924407245571e-05,
+      "loss": 0.3766,
+      "step": 535
+    },
+    {
+      "epoch": 1.7375201288244766,
+      "grad_norm": 0.9676245450973511,
+      "learning_rate": 1.2406917964831516e-05,
+      "loss": 0.3544,
+      "step": 540
+    },
+    {
+      "epoch": 1.7536231884057971,
+      "grad_norm": 1.144945502281189,
+      "learning_rate": 1.2145406893956396e-05,
+      "loss": 0.3635,
+      "step": 545
+    },
+    {
+      "epoch": 1.7697262479871174,
+      "grad_norm": 0.9748466610908508,
+      "learning_rate": 1.1884793055892874e-05,
+      "loss": 0.3135,
+      "step": 550
+    },
+    {
+      "epoch": 1.785829307568438,
+      "grad_norm": 1.0328468084335327,
+      "learning_rate": 1.1625158364692428e-05,
+      "loss": 0.3579,
+      "step": 555
+    },
+    {
+      "epoch": 1.8019323671497585,
+      "grad_norm": 0.9047795534133911,
+      "learning_rate": 1.1366584426648964e-05,
+      "loss": 0.3535,
+      "step": 560
+    },
+    {
+      "epoch": 1.818035426731079,
+      "grad_norm": 0.9178308844566345,
+      "learning_rate": 1.1109152514648946e-05,
+      "loss": 0.3361,
+      "step": 565
+    },
+    {
+      "epoch": 1.8341384863123995,
+      "grad_norm": 1.0122443437576294,
+      "learning_rate": 1.0852943542626387e-05,
+      "loss": 0.3546,
+      "step": 570
+    },
+    {
+      "epoch": 1.8502415458937198,
+      "grad_norm": 1.0439883470535278,
+      "learning_rate": 1.0598038040130605e-05,
+      "loss": 0.3672,
+      "step": 575
+    },
+    {
+      "epoch": 1.86634460547504,
+      "grad_norm": 1.1405988931655884,
+      "learning_rate": 1.0344516127014838e-05,
+      "loss": 0.3434,
+      "step": 580
+    },
+    {
+      "epoch": 1.8824476650563606,
+      "grad_norm": 0.9288351535797119,
+      "learning_rate": 1.0092457488253595e-05,
+      "loss": 0.3428,
+      "step": 585
+    },
+    {
+      "epoch": 1.8985507246376812,
+      "grad_norm": 0.9271903038024902,
+      "learning_rate": 9.841941348896725e-06,
+      "loss": 0.348,
+      "step": 590
+    },
+    {
+      "epoch": 1.9146537842190017,
+      "grad_norm": 1.0033196210861206,
+      "learning_rate": 9.593046449168054e-06,
+      "loss": 0.332,
+      "step": 595
+    },
+    {
+      "epoch": 1.9307568438003222,
+      "grad_norm": 1.3156334161758423,
+      "learning_rate": 9.345851019716351e-06,
+      "loss": 0.3648,
+      "step": 600
+    },
+    {
+      "epoch": 1.9468599033816425,
+      "grad_norm": 1.1618995666503906,
+      "learning_rate": 9.100432757026517e-06,
+      "loss": 0.299,
+      "step": 605
+    },
+    {
+      "epoch": 1.9629629629629628,
+      "grad_norm": 0.9836344122886658,
+      "learning_rate": 8.856868798998663e-06,
+      "loss": 0.3361,
+      "step": 610
+    },
+    {
+      "epoch": 1.9790660225442833,
+      "grad_norm": 1.0316345691680908,
+      "learning_rate": 8.615235700702718e-06,
+      "loss": 0.2978,
+      "step": 615
+    },
+    {
+      "epoch": 1.9951690821256038,
+      "grad_norm": 1.154642939567566,
+      "learning_rate": 8.375609410316274e-06,
+      "loss": 0.3279,
+      "step": 620
+    },
+    {
+      "epoch": 2.0096618357487923,
+      "grad_norm": 0.9890927672386169,
+      "learning_rate": 8.138065245253147e-06,
+      "loss": 0.2654,
+      "step": 625
+    },
+    {
+      "epoch": 2.025764895330113,
+      "grad_norm": 1.259535312652588,
+      "learning_rate": 7.902677868490222e-06,
+      "loss": 0.2474,
+      "step": 630
+    },
+    {
+      "epoch": 2.0418679549114334,
+      "grad_norm": 1.0284183025360107,
+      "learning_rate": 7.669521265099988e-06,
+      "loss": 0.2864,
+      "step": 635
+    },
+    {
+      "epoch": 2.0579710144927534,
+      "grad_norm": 0.9185959100723267,
+      "learning_rate": 7.438668718996129e-06,
+      "loss": 0.278,
+      "step": 640
+    },
+    {
+      "epoch": 2.074074074074074,
+      "grad_norm": 0.9040402770042419,
+      "learning_rate": 7.2101927898995405e-06,
+      "loss": 0.2461,
+      "step": 645
+    },
+    {
+      "epoch": 2.0901771336553945,
+      "grad_norm": 1.0661463737487793,
+      "learning_rate": 6.984165290531887e-06,
+      "loss": 0.2837,
+      "step": 650
+    },
+    {
+      "epoch": 2.106280193236715,
+      "grad_norm": 1.0359954833984375,
+      "learning_rate": 6.7606572640440604e-06,
+      "loss": 0.2644,
+      "step": 655
+    },
+    {
+      "epoch": 2.1223832528180355,
+      "grad_norm": 1.0452792644500732,
+      "learning_rate": 6.539738961686448e-06,
+      "loss": 0.2371,
+      "step": 660
+    },
+    {
+      "epoch": 2.138486312399356,
+      "grad_norm": 1.0253435373306274,
+      "learning_rate": 6.3214798207281066e-06,
+      "loss": 0.2213,
+      "step": 665
+    },
+    {
+      "epoch": 2.154589371980676,
+      "grad_norm": 1.0696303844451904,
+      "learning_rate": 6.105948442631794e-06,
+      "loss": 0.2654,
+      "step": 670
+    },
+    {
+      "epoch": 2.1706924315619966,
+      "grad_norm": 1.1096014976501465,
+      "learning_rate": 5.893212571491755e-06,
+      "loss": 0.2459,
+      "step": 675
+    },
+    {
+      "epoch": 2.186795491143317,
+      "grad_norm": 1.1183967590332031,
+      "learning_rate": 5.683339072740882e-06,
+      "loss": 0.2254,
+      "step": 680
+    },
+    {
+      "epoch": 2.2028985507246377,
+      "grad_norm": 1.0131981372833252,
+      "learning_rate": 5.476393912134141e-06,
+      "loss": 0.2491,
+      "step": 685
+    },
+    {
+      "epoch": 2.219001610305958,
+      "grad_norm": 1.0315091609954834,
+      "learning_rate": 5.272442135014742e-06,
+      "loss": 0.2397,
+      "step": 690
+    },
+    {
+      "epoch": 2.2351046698872787,
+      "grad_norm": 1.131447672843933,
+      "learning_rate": 5.071547845869597e-06,
+      "loss": 0.2304,
+      "step": 695
+    },
+    {
+      "epoch": 2.2512077294685993,
+      "grad_norm": 1.0741468667984009,
+      "learning_rate": 4.873774188180518e-06,
+      "loss": 0.2507,
+      "step": 700
+    },
+    {
+      "epoch": 2.2673107890499193,
+      "grad_norm": 1.0906713008880615,
+      "learning_rate": 4.679183324577483e-06,
+      "loss": 0.2407,
+      "step": 705
+    },
+    {
+      "epoch": 2.28341384863124,
+      "grad_norm": 0.9737504124641418,
+      "learning_rate": 4.487836417300128e-06,
+      "loss": 0.2623,
+      "step": 710
+    },
+    {
+      "epoch": 2.2995169082125604,
+      "grad_norm": 1.125701904296875,
+      "learning_rate": 4.2997936089737715e-06,
+      "loss": 0.243,
+      "step": 715
+    },
+    {
+      "epoch": 2.315619967793881,
+      "grad_norm": 1.127188801765442,
+      "learning_rate": 4.11511400370585e-06,
+      "loss": 0.2268,
+      "step": 720
+    },
+    {
+      "epoch": 2.3317230273752014,
+      "grad_norm": 1.093748688697815,
+      "learning_rate": 3.933855648508788e-06,
+      "loss": 0.2266,
+      "step": 725
+    },
+    {
+      "epoch": 2.3478260869565215,
+      "grad_norm": 1.0176098346710205,
+      "learning_rate": 3.756075515055105e-06,
+      "loss": 0.2551,
+      "step": 730
+    },
+    {
+      "epoch": 2.363929146537842,
+      "grad_norm": 1.0171095132827759,
+      "learning_rate": 3.581829481770584e-06,
+      "loss": 0.2108,
+      "step": 735
+    },
+    {
+      "epoch": 2.3800322061191626,
+      "grad_norm": 1.1229734420776367,
+      "learning_rate": 3.4111723162709713e-06,
+      "loss": 0.2375,
+      "step": 740
+    },
+    {
+      "epoch": 2.396135265700483,
+      "grad_norm": 1.1092017889022827,
+      "learning_rate": 3.2441576581478777e-06,
+      "loss": 0.2351,
+      "step": 745
+    },
+    {
+      "epoch": 2.4122383252818036,
+      "grad_norm": 1.0351029634475708,
+      "learning_rate": 3.0808380021092035e-06,
+      "loss": 0.2621,
+      "step": 750
+    },
+    {
+      "epoch": 2.428341384863124,
+      "grad_norm": 1.2042315006256104,
+      "learning_rate": 2.9212646814794338e-06,
+      "loss": 0.2229,
+      "step": 755
+    },
+    {
+      "epoch": 2.4444444444444446,
+      "grad_norm": 0.9367467761039734,
+      "learning_rate": 2.7654878520649425e-06,
+      "loss": 0.2347,
+      "step": 760
+    },
+    {
+      "epoch": 2.4605475040257647,
+      "grad_norm": 1.179587960243225,
+      "learning_rate": 2.613556476389454e-06,
+      "loss": 0.2146,
+      "step": 765
+    },
+    {
+      "epoch": 2.4766505636070852,
+      "grad_norm": 1.1558105945587158,
+      "learning_rate": 2.4655183083044858e-06,
+      "loss": 0.2127,
+      "step": 770
+    },
+    {
+      "epoch": 2.4927536231884058,
+      "grad_norm": 0.975750744342804,
+      "learning_rate": 2.3214198779797807e-06,
+      "loss": 0.2143,
+      "step": 775
+    },
+    {
+      "epoch": 2.5088566827697263,
+      "grad_norm": 0.9153541922569275,
+      "learning_rate": 2.181306477278317e-06,
+      "loss": 0.2437,
+      "step": 780
+    },
+    {
+      "epoch": 2.524959742351047,
+      "grad_norm": 1.1135258674621582,
+      "learning_rate": 2.045222145520505e-06,
+      "loss": 0.2667,
+      "step": 785
+    },
+    {
+      "epoch": 2.541062801932367,
+      "grad_norm": 1.0112967491149902,
+      "learning_rate": 1.913209655642118e-06,
+      "loss": 0.2126,
+      "step": 790
+    },
+    {
+      "epoch": 2.5571658615136874,
+      "grad_norm": 0.9722472429275513,
+      "learning_rate": 1.7853105007502546e-06,
+      "loss": 0.3049,
+      "step": 795
+    },
+    {
+      "epoch": 2.573268921095008,
+      "grad_norm": 1.1213710308074951,
+      "learning_rate": 1.6615648810815442e-06,
+      "loss": 0.2428,
+      "step": 800
+    },
+    {
+      "epoch": 2.5893719806763285,
+      "grad_norm": 1.0378894805908203,
+      "learning_rate": 1.5420116913667347e-06,
+      "loss": 0.2228,
+      "step": 805
+    },
+    {
+      "epoch": 2.605475040257649,
+      "grad_norm": 1.078855037689209,
+      "learning_rate": 1.4266885086056163e-06,
+      "loss": 0.2499,
+      "step": 810
+    },
+    {
+      "epoch": 2.6215780998389695,
+      "grad_norm": 1.1062284708023071,
+      "learning_rate": 1.3156315802561124e-06,
+      "loss": 0.2094,
+      "step": 815
+    },
+    {
+      "epoch": 2.63768115942029,
+      "grad_norm": 1.072355031967163,
+      "learning_rate": 1.2088758128412802e-06,
+      "loss": 0.2255,
+      "step": 820
+    },
+    {
+      "epoch": 2.6537842190016105,
+      "grad_norm": 1.0223000049591064,
+      "learning_rate": 1.1064547609777682e-06,
+      "loss": 0.1933,
+      "step": 825
+    },
+    {
+      "epoch": 2.6698872785829306,
+      "grad_norm": 1.11282479763031,
+      "learning_rate": 1.0084006168291926e-06,
+      "loss": 0.2508,
+      "step": 830
+    },
+    {
+      "epoch": 2.685990338164251,
+      "grad_norm": 1.1130576133728027,
+      "learning_rate": 9.14744199987752e-07,
+      "loss": 0.2429,
+      "step": 835
+    },
+    {
+      "epoch": 2.7020933977455717,
+      "grad_norm": 1.0845133066177368,
+      "learning_rate": 8.255149477872837e-07,
+      "loss": 0.246,
+      "step": 840
+    },
+    {
+      "epoch": 2.718196457326892,
+      "grad_norm": 0.9437175989151001,
+      "learning_rate": 7.407409060507264e-07,
+      "loss": 0.2304,
+      "step": 845
+    },
+    {
+      "epoch": 2.7342995169082127,
+      "grad_norm": 0.986255407333374,
+      "learning_rate": 6.604487202750026e-07,
+      "loss": 0.2578,
+      "step": 850
+    },
+    {
+      "epoch": 2.750402576489533,
+      "grad_norm": 0.9439171552658081,
+      "learning_rate": 5.846636272560119e-07,
+      "loss": 0.2326,
+      "step": 855
+    },
+    {
+      "epoch": 2.7665056360708533,
+      "grad_norm": 0.9531322121620178,
+      "learning_rate": 5.134094471564033e-07,
+      "loss": 0.2277,
+      "step": 860
+    },
+    {
+      "epoch": 2.782608695652174,
+      "grad_norm": 1.1307721138000488,
+      "learning_rate": 4.4670857601861406e-07,
+      "loss": 0.2458,
+      "step": 865
+    },
+    {
+      "epoch": 2.7987117552334944,
+      "grad_norm": 1.030348300933838,
+      "learning_rate": 3.8458197872553226e-07,
+      "loss": 0.2564,
+      "step": 870
+    },
+    {
+      "epoch": 2.814814814814815,
+      "grad_norm": 1.1418156623840332,
+      "learning_rate": 3.2704918241096615e-07,
+      "loss": 0.1976,
+      "step": 875
+    },
+    {
+      "epoch": 2.8309178743961354,
+      "grad_norm": 1.0169031620025635,
+      "learning_rate": 2.741282703220471e-07,
+      "loss": 0.2227,
+      "step": 880
+    },
+    {
+      "epoch": 2.847020933977456,
+      "grad_norm": 1.0400892496109009,
+      "learning_rate": 2.2583587613544622e-07,
+      "loss": 0.2462,
+      "step": 885
+    },
+    {
+      "epoch": 2.863123993558776,
+      "grad_norm": 1.0656051635742188,
+      "learning_rate": 1.8218717872920622e-07,
+      "loss": 0.2104,
+      "step": 890
+    },
+    {
+      "epoch": 2.8792270531400965,
+      "grad_norm": 1.0390520095825195,
+      "learning_rate": 1.4319589741183303e-07,
+      "loss": 0.2305,
+      "step": 895
+    },
+    {
+      "epoch": 2.895330112721417,
+      "grad_norm": 0.9960174560546875,
+      "learning_rate": 1.0887428761016837e-07,
+      "loss": 0.1931,
+      "step": 900
+    },
+    {
+      "epoch": 2.9114331723027376,
+      "grad_norm": 1.2972259521484375,
+      "learning_rate": 7.923313701735102e-08,
+      "loss": 0.2338,
+      "step": 905
+    },
+    {
+      "epoch": 2.927536231884058,
+      "grad_norm": 0.979471743106842,
+      "learning_rate": 5.428176220211245e-08,
+      "loss": 0.2069,
+      "step": 910
+    },
+    {
+      "epoch": 2.943639291465378,
+      "grad_norm": 1.0244625806808472,
+      "learning_rate": 3.402800568048259e-08,
+      "loss": 0.2116,
+      "step": 915
+    },
+    {
+      "epoch": 2.9597423510466987,
+      "grad_norm": 1.1115559339523315,
+      "learning_rate": 1.8478233450774927e-08,
+      "loss": 0.23,
+      "step": 920
+    },
+    {
+      "epoch": 2.975845410628019,
+      "grad_norm": 1.0240631103515625,
+      "learning_rate": 7.637332992688762e-09,
+      "loss": 0.2306,
+      "step": 925
+    },
+    {
+      "epoch": 2.9919484702093397,
+      "grad_norm": 0.9473810195922852,
+      "learning_rate": 1.5087117311179955e-09,
+      "loss": 0.2302,
+      "step": 930
+    },
+    {
+      "epoch": 3.0,
+      "step": 933,
+      "total_flos": 1.3651678818425897e+18,
+      "train_loss": 0.5071639379632179,
+      "train_runtime": 663.9063,
+      "train_samples_per_second": 44.844,
+      "train_steps_per_second": 1.405
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 933,
+  "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": 1.3651678818425897e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

130_128_e3_3e-5/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cc17211949cc6b9b15122d44e4c2af6a7b49f262dcfa7729cb3c44d0a18fe10
+size 8273