Upload folder using huggingface_hub

27_128_e3_3e-5/adapter_config.json

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

27_128_e3_3e-5/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ab0289c1d97e3955fcca8e86230929ad72be0eb7da287917d5f8d495bbc2f78
+size 791751704

27_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
+}

27_128_e3_3e-5/all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.5985427869765468e+18,
+    "train_loss": 0.5499852971898185,
+    "train_runtime": 792.1755,
+    "train_samples": 11517,
+    "train_samples_per_second": 43.615,
+    "train_steps_per_second": 1.363
+}

27_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 %}

27_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
+}

27_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
+  }
+}

27_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
+}

27_128_e3_3e-5/train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.5985427869765468e+18,
+    "train_loss": 0.5499852971898185,
+    "train_runtime": 792.1755,
+    "train_samples": 11517,
+    "train_samples_per_second": 43.615,
+    "train_steps_per_second": 1.363
+}

27_128_e3_3e-5/trainer_state.json

@@ -0,0 +1,1555 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1080,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013888888888888888,
+      "grad_norm": 3.2211008071899414,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 1.4919,
+      "step": 5
+    },
+    {
+      "epoch": 0.027777777777777776,
+      "grad_norm": 2.112604856491089,
+      "learning_rate": 4.9999999999999996e-06,
+      "loss": 1.449,
+      "step": 10
+    },
+    {
+      "epoch": 0.041666666666666664,
+      "grad_norm": 0.774435818195343,
+      "learning_rate": 7.777777777777777e-06,
+      "loss": 1.3416,
+      "step": 15
+    },
+    {
+      "epoch": 0.05555555555555555,
+      "grad_norm": 0.49576497077941895,
+      "learning_rate": 1.0555555555555555e-05,
+      "loss": 1.3337,
+      "step": 20
+    },
+    {
+      "epoch": 0.06944444444444445,
+      "grad_norm": 0.5466096997261047,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 1.3148,
+      "step": 25
+    },
+    {
+      "epoch": 0.08333333333333333,
+      "grad_norm": 0.38828131556510925,
+      "learning_rate": 1.6111111111111115e-05,
+      "loss": 1.2929,
+      "step": 30
+    },
+    {
+      "epoch": 0.09722222222222222,
+      "grad_norm": 0.4057466387748718,
+      "learning_rate": 1.888888888888889e-05,
+      "loss": 1.2491,
+      "step": 35
+    },
+    {
+      "epoch": 0.1111111111111111,
+      "grad_norm": 0.38087013363838196,
+      "learning_rate": 2.1666666666666667e-05,
+      "loss": 1.2524,
+      "step": 40
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 0.3372047245502472,
+      "learning_rate": 2.4444444444444445e-05,
+      "loss": 1.2145,
+      "step": 45
+    },
+    {
+      "epoch": 0.1388888888888889,
+      "grad_norm": 0.37490731477737427,
+      "learning_rate": 2.7222222222222223e-05,
+      "loss": 1.2623,
+      "step": 50
+    },
+    {
+      "epoch": 0.1527777777777778,
+      "grad_norm": 0.3841039836406708,
+      "learning_rate": 3e-05,
+      "loss": 1.2091,
+      "step": 55
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 0.3887983560562134,
+      "learning_rate": 2.999824208523885e-05,
+      "loss": 1.1803,
+      "step": 60
+    },
+    {
+      "epoch": 0.18055555555555555,
+      "grad_norm": 0.3718923330307007,
+      "learning_rate": 2.9992968752990648e-05,
+      "loss": 1.1532,
+      "step": 65
+    },
+    {
+      "epoch": 0.19444444444444445,
+      "grad_norm": 0.47127917408943176,
+      "learning_rate": 2.9984181239264532e-05,
+      "loss": 1.1891,
+      "step": 70
+    },
+    {
+      "epoch": 0.20833333333333334,
+      "grad_norm": 0.4221467077732086,
+      "learning_rate": 2.997188160375385e-05,
+      "loss": 1.1654,
+      "step": 75
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.4136931002140045,
+      "learning_rate": 2.9956072729353382e-05,
+      "loss": 1.0683,
+      "step": 80
+    },
+    {
+      "epoch": 0.2361111111111111,
+      "grad_norm": 0.3720996677875519,
+      "learning_rate": 2.9936758321483616e-05,
+      "loss": 1.0427,
+      "step": 85
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.43978968262672424,
+      "learning_rate": 2.9913942907222238e-05,
+      "loss": 1.0969,
+      "step": 90
+    },
+    {
+      "epoch": 0.2638888888888889,
+      "grad_norm": 0.4235962927341461,
+      "learning_rate": 2.9887631834243058e-05,
+      "loss": 1.0168,
+      "step": 95
+    },
+    {
+      "epoch": 0.2777777777777778,
+      "grad_norm": 0.4260789752006531,
+      "learning_rate": 2.985783126956255e-05,
+      "loss": 1.0679,
+      "step": 100
+    },
+    {
+      "epoch": 0.2916666666666667,
+      "grad_norm": 0.5100179314613342,
+      "learning_rate": 2.9824548198094386e-05,
+      "loss": 1.0315,
+      "step": 105
+    },
+    {
+      "epoch": 0.3055555555555556,
+      "grad_norm": 0.4651437997817993,
+      "learning_rate": 2.9787790421012247e-05,
+      "loss": 1.0422,
+      "step": 110
+    },
+    {
+      "epoch": 0.3194444444444444,
+      "grad_norm": 0.5040125846862793,
+      "learning_rate": 2.9747566553921326e-05,
+      "loss": 1.0048,
+      "step": 115
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.4472350478172302,
+      "learning_rate": 2.9703886024838916e-05,
+      "loss": 1.0111,
+      "step": 120
+    },
+    {
+      "epoch": 0.3472222222222222,
+      "grad_norm": 0.5227202773094177,
+      "learning_rate": 2.9656759071984602e-05,
+      "loss": 1.0351,
+      "step": 125
+    },
+    {
+      "epoch": 0.3611111111111111,
+      "grad_norm": 0.5318294763565063,
+      "learning_rate": 2.960619674138052e-05,
+      "loss": 1.0424,
+      "step": 130
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 0.5562703013420105,
+      "learning_rate": 2.955221088426231e-05,
+      "loss": 0.9892,
+      "step": 135
+    },
+    {
+      "epoch": 0.3888888888888889,
+      "grad_norm": 0.5283619165420532,
+      "learning_rate": 2.9494814154301328e-05,
+      "loss": 0.9624,
+      "step": 140
+    },
+    {
+      "epoch": 0.4027777777777778,
+      "grad_norm": 0.600264310836792,
+      "learning_rate": 2.9434020004638757e-05,
+      "loss": 0.9501,
+      "step": 145
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 0.5495845675468445,
+      "learning_rate": 2.9369842684732334e-05,
+      "loss": 0.9355,
+      "step": 150
+    },
+    {
+      "epoch": 0.4305555555555556,
+      "grad_norm": 0.6037551760673523,
+      "learning_rate": 2.9302297237016462e-05,
+      "loss": 0.9779,
+      "step": 155
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.5766875147819519,
+      "learning_rate": 2.9231399493376414e-05,
+      "loss": 0.9252,
+      "step": 160
+    },
+    {
+      "epoch": 0.4583333333333333,
+      "grad_norm": 0.5481635928153992,
+      "learning_rate": 2.9157166071437542e-05,
+      "loss": 0.9503,
+      "step": 165
+    },
+    {
+      "epoch": 0.4722222222222222,
+      "grad_norm": 0.5580893158912659,
+      "learning_rate": 2.9079614370670268e-05,
+      "loss": 0.8964,
+      "step": 170
+    },
+    {
+      "epoch": 0.4861111111111111,
+      "grad_norm": 0.6972624659538269,
+      "learning_rate": 2.8998762568311857e-05,
+      "loss": 0.8597,
+      "step": 175
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.6588099002838135,
+      "learning_rate": 2.89146296151059e-05,
+      "loss": 0.8535,
+      "step": 180
+    },
+    {
+      "epoch": 0.5138888888888888,
+      "grad_norm": 0.7054685950279236,
+      "learning_rate": 2.8827235230860425e-05,
+      "loss": 0.9052,
+      "step": 185
+    },
+    {
+      "epoch": 0.5277777777777778,
+      "grad_norm": 0.602948784828186,
+      "learning_rate": 2.873659989982586e-05,
+      "loss": 0.8759,
+      "step": 190
+    },
+    {
+      "epoch": 0.5416666666666666,
+      "grad_norm": 0.6691058874130249,
+      "learning_rate": 2.864274486589371e-05,
+      "loss": 0.8327,
+      "step": 195
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.6832404136657715,
+      "learning_rate": 2.8545692127617248e-05,
+      "loss": 0.821,
+      "step": 200
+    },
+    {
+      "epoch": 0.5694444444444444,
+      "grad_norm": 0.6601212620735168,
+      "learning_rate": 2.8445464433055303e-05,
+      "loss": 0.9004,
+      "step": 205
+    },
+    {
+      "epoch": 0.5833333333333334,
+      "grad_norm": 0.7965134978294373,
+      "learning_rate": 2.8342085274440372e-05,
+      "loss": 0.8618,
+      "step": 210
+    },
+    {
+      "epoch": 0.5972222222222222,
+      "grad_norm": 0.782162070274353,
+      "learning_rate": 2.823557888267232e-05,
+      "loss": 0.8363,
+      "step": 215
+    },
+    {
+      "epoch": 0.6111111111111112,
+      "grad_norm": 0.6964525580406189,
+      "learning_rate": 2.8125970221638906e-05,
+      "loss": 0.8187,
+      "step": 220
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 0.7283791899681091,
+      "learning_rate": 2.8013284982364558e-05,
+      "loss": 0.8657,
+      "step": 225
+    },
+    {
+      "epoch": 0.6388888888888888,
+      "grad_norm": 0.7080844044685364,
+      "learning_rate": 2.7897549576988668e-05,
+      "loss": 0.8612,
+      "step": 230
+    },
+    {
+      "epoch": 0.6527777777777778,
+      "grad_norm": 0.8012256622314453,
+      "learning_rate": 2.7778791132574908e-05,
+      "loss": 0.8231,
+      "step": 235
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.8633471727371216,
+      "learning_rate": 2.7657037484752935e-05,
+      "loss": 0.7644,
+      "step": 240
+    },
+    {
+      "epoch": 0.6805555555555556,
+      "grad_norm": 0.7956590056419373,
+      "learning_rate": 2.753231717119405e-05,
+      "loss": 0.7997,
+      "step": 245
+    },
+    {
+      "epoch": 0.6944444444444444,
+      "grad_norm": 0.8399053812026978,
+      "learning_rate": 2.7404659424922274e-05,
+      "loss": 0.753,
+      "step": 250
+    },
+    {
+      "epoch": 0.7083333333333334,
+      "grad_norm": 0.7861112952232361,
+      "learning_rate": 2.727409416746249e-05,
+      "loss": 0.7989,
+      "step": 255
+    },
+    {
+      "epoch": 0.7222222222222222,
+      "grad_norm": 0.7473494410514832,
+      "learning_rate": 2.714065200182714e-05,
+      "loss": 0.7778,
+      "step": 260
+    },
+    {
+      "epoch": 0.7361111111111112,
+      "grad_norm": 0.7678909301757812,
+      "learning_rate": 2.700436420534326e-05,
+      "loss": 0.791,
+      "step": 265
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.9624865055084229,
+      "learning_rate": 2.686526272232141e-05,
+      "loss": 0.7434,
+      "step": 270
+    },
+    {
+      "epoch": 0.7638888888888888,
+      "grad_norm": 0.7595170736312866,
+      "learning_rate": 2.67233801565683e-05,
+      "loss": 0.7364,
+      "step": 275
+    },
+    {
+      "epoch": 0.7777777777777778,
+      "grad_norm": 0.8897536993026733,
+      "learning_rate": 2.6578749763744815e-05,
+      "loss": 0.7895,
+      "step": 280
+    },
+    {
+      "epoch": 0.7916666666666666,
+      "grad_norm": 0.8211910724639893,
+      "learning_rate": 2.6431405443571282e-05,
+      "loss": 0.7302,
+      "step": 285
+    },
+    {
+      "epoch": 0.8055555555555556,
+      "grad_norm": 0.775287926197052,
+      "learning_rate": 2.6281381731881763e-05,
+      "loss": 0.7526,
+      "step": 290
+    },
+    {
+      "epoch": 0.8194444444444444,
+      "grad_norm": 0.917742133140564,
+      "learning_rate": 2.6128713792529225e-05,
+      "loss": 0.6939,
+      "step": 295
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.822134256362915,
+      "learning_rate": 2.5973437409143557e-05,
+      "loss": 0.7377,
+      "step": 300
+    },
+    {
+      "epoch": 0.8472222222222222,
+      "grad_norm": 0.8758741021156311,
+      "learning_rate": 2.5815588976744274e-05,
+      "loss": 0.7084,
+      "step": 305
+    },
+    {
+      "epoch": 0.8611111111111112,
+      "grad_norm": 0.8832114934921265,
+      "learning_rate": 2.565520549320996e-05,
+      "loss": 0.6638,
+      "step": 310
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 0.8048897981643677,
+      "learning_rate": 2.549232455060637e-05,
+      "loss": 0.7156,
+      "step": 315
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.9665600657463074,
+      "learning_rate": 2.532698432637528e-05,
+      "loss": 0.6762,
+      "step": 320
+    },
+    {
+      "epoch": 0.9027777777777778,
+      "grad_norm": 0.8282063603401184,
+      "learning_rate": 2.5159223574386117e-05,
+      "loss": 0.6406,
+      "step": 325
+    },
+    {
+      "epoch": 0.9166666666666666,
+      "grad_norm": 0.8876408338546753,
+      "learning_rate": 2.498908161585253e-05,
+      "loss": 0.6599,
+      "step": 330
+    },
+    {
+      "epoch": 0.9305555555555556,
+      "grad_norm": 0.8858140707015991,
+      "learning_rate": 2.48165983301159e-05,
+      "loss": 0.6776,
+      "step": 335
+    },
+    {
+      "epoch": 0.9444444444444444,
+      "grad_norm": 0.9803429245948792,
+      "learning_rate": 2.464181414529809e-05,
+      "loss": 0.6476,
+      "step": 340
+    },
+    {
+      "epoch": 0.9583333333333334,
+      "grad_norm": 0.8738537430763245,
+      "learning_rate": 2.4464770028825586e-05,
+      "loss": 0.6321,
+      "step": 345
+    },
+    {
+      "epoch": 0.9722222222222222,
+      "grad_norm": 0.9205712080001831,
+      "learning_rate": 2.4285507477827138e-05,
+      "loss": 0.604,
+      "step": 350
+    },
+    {
+      "epoch": 0.9861111111111112,
+      "grad_norm": 0.8464882969856262,
+      "learning_rate": 2.410406850940735e-05,
+      "loss": 0.6451,
+      "step": 355
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.0285252332687378,
+      "learning_rate": 2.3920495650798343e-05,
+      "loss": 0.6959,
+      "step": 360
+    },
+    {
+      "epoch": 1.0138888888888888,
+      "grad_norm": 0.9646236896514893,
+      "learning_rate": 2.3734831929391824e-05,
+      "loss": 0.5478,
+      "step": 365
+    },
+    {
+      "epoch": 1.0277777777777777,
+      "grad_norm": 0.8589456081390381,
+      "learning_rate": 2.3547120862653995e-05,
+      "loss": 0.565,
+      "step": 370
+    },
+    {
+      "epoch": 1.0416666666666667,
+      "grad_norm": 0.9315431714057922,
+      "learning_rate": 2.3357406447925528e-05,
+      "loss": 0.5559,
+      "step": 375
+    },
+    {
+      "epoch": 1.0555555555555556,
+      "grad_norm": 1.054972529411316,
+      "learning_rate": 2.3165733152109097e-05,
+      "loss": 0.5359,
+      "step": 380
+    },
+    {
+      "epoch": 1.0694444444444444,
+      "grad_norm": 0.9502842426300049,
+      "learning_rate": 2.297214590124684e-05,
+      "loss": 0.5511,
+      "step": 385
+    },
+    {
+      "epoch": 1.0833333333333333,
+      "grad_norm": 0.9008628129959106,
+      "learning_rate": 2.2776690069990208e-05,
+      "loss": 0.482,
+      "step": 390
+    },
+    {
+      "epoch": 1.0972222222222223,
+      "grad_norm": 0.895050048828125,
+      "learning_rate": 2.257941147096465e-05,
+      "loss": 0.5666,
+      "step": 395
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 1.10245680809021,
+      "learning_rate": 2.2380356344031677e-05,
+      "loss": 0.5948,
+      "step": 400
+    },
+    {
+      "epoch": 1.125,
+      "grad_norm": 0.9714730381965637,
+      "learning_rate": 2.217957134545074e-05,
+      "loss": 0.5297,
+      "step": 405
+    },
+    {
+      "epoch": 1.1388888888888888,
+      "grad_norm": 1.0223896503448486,
+      "learning_rate": 2.197710353694355e-05,
+      "loss": 0.5037,
+      "step": 410
+    },
+    {
+      "epoch": 1.1527777777777777,
+      "grad_norm": 0.877342164516449,
+      "learning_rate": 2.177300037466334e-05,
+      "loss": 0.5331,
+      "step": 415
+    },
+    {
+      "epoch": 1.1666666666666667,
+      "grad_norm": 0.9664136171340942,
+      "learning_rate": 2.156730969807168e-05,
+      "loss": 0.512,
+      "step": 420
+    },
+    {
+      "epoch": 1.1805555555555556,
+      "grad_norm": 0.9725602865219116,
+      "learning_rate": 2.1360079718725452e-05,
+      "loss": 0.4956,
+      "step": 425
+    },
+    {
+      "epoch": 1.1944444444444444,
+      "grad_norm": 1.0216833353042603,
+      "learning_rate": 2.1151359008976604e-05,
+      "loss": 0.4865,
+      "step": 430
+    },
+    {
+      "epoch": 1.2083333333333333,
+      "grad_norm": 1.0147571563720703,
+      "learning_rate": 2.0941196490587352e-05,
+      "loss": 0.533,
+      "step": 435
+    },
+    {
+      "epoch": 1.2222222222222223,
+      "grad_norm": 1.0112186670303345,
+      "learning_rate": 2.072964142326348e-05,
+      "loss": 0.4889,
+      "step": 440
+    },
+    {
+      "epoch": 1.2361111111111112,
+      "grad_norm": 0.9771940112113953,
+      "learning_rate": 2.05167433931084e-05,
+      "loss": 0.5168,
+      "step": 445
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 1.0951805114746094,
+      "learning_rate": 2.0302552301000757e-05,
+      "loss": 0.4746,
+      "step": 450
+    },
+    {
+      "epoch": 1.2638888888888888,
+      "grad_norm": 0.9993045926094055,
+      "learning_rate": 2.008711835089822e-05,
+      "loss": 0.4721,
+      "step": 455
+    },
+    {
+      "epoch": 1.2777777777777777,
+      "grad_norm": 1.0383926630020142,
+      "learning_rate": 1.9870492038070255e-05,
+      "loss": 0.5339,
+      "step": 460
+    },
+    {
+      "epoch": 1.2916666666666667,
+      "grad_norm": 1.1353601217269897,
+      "learning_rate": 1.965272413726258e-05,
+      "loss": 0.4655,
+      "step": 465
+    },
+    {
+      "epoch": 1.3055555555555556,
+      "grad_norm": 0.9714365005493164,
+      "learning_rate": 1.943386569079618e-05,
+      "loss": 0.4823,
+      "step": 470
+    },
+    {
+      "epoch": 1.3194444444444444,
+      "grad_norm": 0.9634111523628235,
+      "learning_rate": 1.9213967996603542e-05,
+      "loss": 0.489,
+      "step": 475
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 1.0810520648956299,
+      "learning_rate": 1.8993082596205e-05,
+      "loss": 0.4849,
+      "step": 480
+    },
+    {
+      "epoch": 1.3472222222222223,
+      "grad_norm": 1.058505892753601,
+      "learning_rate": 1.8771261262628018e-05,
+      "loss": 0.4845,
+      "step": 485
+    },
+    {
+      "epoch": 1.3611111111111112,
+      "grad_norm": 0.9834576845169067,
+      "learning_rate": 1.8548555988272138e-05,
+      "loss": 0.4709,
+      "step": 490
+    },
+    {
+      "epoch": 1.375,
+      "grad_norm": 0.9450607299804688,
+      "learning_rate": 1.832501897272258e-05,
+      "loss": 0.5097,
+      "step": 495
+    },
+    {
+      "epoch": 1.3888888888888888,
+      "grad_norm": 1.1241111755371094,
+      "learning_rate": 1.810070261051526e-05,
+      "loss": 0.469,
+      "step": 500
+    },
+    {
+      "epoch": 1.4027777777777777,
+      "grad_norm": 1.060816764831543,
+      "learning_rate": 1.7875659478856077e-05,
+      "loss": 0.5055,
+      "step": 505
+    },
+    {
+      "epoch": 1.4166666666666667,
+      "grad_norm": 0.8707916140556335,
+      "learning_rate": 1.764994232529744e-05,
+      "loss": 0.484,
+      "step": 510
+    },
+    {
+      "epoch": 1.4305555555555556,
+      "grad_norm": 1.0018506050109863,
+      "learning_rate": 1.7423604055374824e-05,
+      "loss": 0.4324,
+      "step": 515
+    },
+    {
+      "epoch": 1.4444444444444444,
+      "grad_norm": 1.1296194791793823,
+      "learning_rate": 1.7196697720206327e-05,
+      "loss": 0.4396,
+      "step": 520
+    },
+    {
+      "epoch": 1.4583333333333333,
+      "grad_norm": 1.1075674295425415,
+      "learning_rate": 1.6969276504058073e-05,
+      "loss": 0.4283,
+      "step": 525
+    },
+    {
+      "epoch": 1.4722222222222223,
+      "grad_norm": 1.078908920288086,
+      "learning_rate": 1.6741393711878455e-05,
+      "loss": 0.4565,
+      "step": 530
+    },
+    {
+      "epoch": 1.4861111111111112,
+      "grad_norm": 0.8687962293624878,
+      "learning_rate": 1.6513102756804025e-05,
+      "loss": 0.4449,
+      "step": 535
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 1.022986888885498,
+      "learning_rate": 1.6284457147640084e-05,
+      "loss": 0.4173,
+      "step": 540
+    },
+    {
+      "epoch": 1.5138888888888888,
+      "grad_norm": 0.9766154885292053,
+      "learning_rate": 1.6055510476318827e-05,
+      "loss": 0.4417,
+      "step": 545
+    },
+    {
+      "epoch": 1.5277777777777777,
+      "grad_norm": 1.0998139381408691,
+      "learning_rate": 1.5826316405337983e-05,
+      "loss": 0.4366,
+      "step": 550
+    },
+    {
+      "epoch": 1.5416666666666665,
+      "grad_norm": 1.0709365606307983,
+      "learning_rate": 1.5596928655182962e-05,
+      "loss": 0.4119,
+      "step": 555
+    },
+    {
+      "epoch": 1.5555555555555556,
+      "grad_norm": 1.0134344100952148,
+      "learning_rate": 1.536740099173537e-05,
+      "loss": 0.4144,
+      "step": 560
+    },
+    {
+      "epoch": 1.5694444444444444,
+      "grad_norm": 1.1979199647903442,
+      "learning_rate": 1.5137787213670899e-05,
+      "loss": 0.4942,
+      "step": 565
+    },
+    {
+      "epoch": 1.5833333333333335,
+      "grad_norm": 1.0069036483764648,
+      "learning_rate": 1.490814113984951e-05,
+      "loss": 0.3919,
+      "step": 570
+    },
+    {
+      "epoch": 1.5972222222222223,
+      "grad_norm": 1.0106252431869507,
+      "learning_rate": 1.4678516596700956e-05,
+      "loss": 0.4103,
+      "step": 575
+    },
+    {
+      "epoch": 1.6111111111111112,
+      "grad_norm": 1.2134196758270264,
+      "learning_rate": 1.4448967405608415e-05,
+      "loss": 0.4135,
+      "step": 580
+    },
+    {
+      "epoch": 1.625,
+      "grad_norm": 1.0365575551986694,
+      "learning_rate": 1.4219547370293414e-05,
+      "loss": 0.4455,
+      "step": 585
+    },
+    {
+      "epoch": 1.6388888888888888,
+      "grad_norm": 1.132775068283081,
+      "learning_rate": 1.399031026420483e-05,
+      "loss": 0.4093,
+      "step": 590
+    },
+    {
+      "epoch": 1.6527777777777777,
+      "grad_norm": 1.1647281646728516,
+      "learning_rate": 1.3761309817915017e-05,
+      "loss": 0.4561,
+      "step": 595
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 1.1083650588989258,
+      "learning_rate": 1.3532599706525943e-05,
+      "loss": 0.3914,
+      "step": 600
+    },
+    {
+      "epoch": 1.6805555555555556,
+      "grad_norm": 1.0493947267532349,
+      "learning_rate": 1.3304233537088392e-05,
+      "loss": 0.4207,
+      "step": 605
+    },
+    {
+      "epoch": 1.6944444444444444,
+      "grad_norm": 1.030792474746704,
+      "learning_rate": 1.307626483603705e-05,
+      "loss": 0.3568,
+      "step": 610
+    },
+    {
+      "epoch": 1.7083333333333335,
+      "grad_norm": 1.0136348009109497,
+      "learning_rate": 1.2848747036644558e-05,
+      "loss": 0.4144,
+      "step": 615
+    },
+    {
+      "epoch": 1.7222222222222223,
+      "grad_norm": 1.188499093055725,
+      "learning_rate": 1.2621733466497287e-05,
+      "loss": 0.3628,
+      "step": 620
+    },
+    {
+      "epoch": 1.7361111111111112,
+      "grad_norm": 1.1271867752075195,
+      "learning_rate": 1.2395277334996045e-05,
+      "loss": 0.4152,
+      "step": 625
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 1.1080422401428223,
+      "learning_rate": 1.2169431720884336e-05,
+      "loss": 0.4124,
+      "step": 630
+    },
+    {
+      "epoch": 1.7638888888888888,
+      "grad_norm": 1.0047310590744019,
+      "learning_rate": 1.1944249559807342e-05,
+      "loss": 0.4124,
+      "step": 635
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 1.1300867795944214,
+      "learning_rate": 1.1719783631904364e-05,
+      "loss": 0.408,
+      "step": 640
+    },
+    {
+      "epoch": 1.7916666666666665,
+      "grad_norm": 1.1100444793701172,
+      "learning_rate": 1.1496086549437821e-05,
+      "loss": 0.3588,
+      "step": 645
+    },
+    {
+      "epoch": 1.8055555555555556,
+      "grad_norm": 1.1678626537322998,
+      "learning_rate": 1.127321074446148e-05,
+      "loss": 0.3867,
+      "step": 650
+    },
+    {
+      "epoch": 1.8194444444444444,
+      "grad_norm": 1.0988038778305054,
+      "learning_rate": 1.1051208456531016e-05,
+      "loss": 0.4278,
+      "step": 655
+    },
+    {
+      "epoch": 1.8333333333333335,
+      "grad_norm": 1.2045801877975464,
+      "learning_rate": 1.0830131720459602e-05,
+      "loss": 0.3993,
+      "step": 660
+    },
+    {
+      "epoch": 1.8472222222222223,
+      "grad_norm": 1.0833828449249268,
+      "learning_rate": 1.0610032354121613e-05,
+      "loss": 0.3421,
+      "step": 665
+    },
+    {
+      "epoch": 1.8611111111111112,
+      "grad_norm": 1.2317794561386108,
+      "learning_rate": 1.0390961946307041e-05,
+      "loss": 0.3798,
+      "step": 670
+    },
+    {
+      "epoch": 1.875,
+      "grad_norm": 1.0517349243164062,
+      "learning_rate": 1.0172971844629716e-05,
+      "loss": 0.3828,
+      "step": 675
+    },
+    {
+      "epoch": 1.8888888888888888,
+      "grad_norm": 0.9857127070426941,
+      "learning_rate": 9.956113143491959e-06,
+      "loss": 0.3568,
+      "step": 680
+    },
+    {
+      "epoch": 1.9027777777777777,
+      "grad_norm": 1.0072497129440308,
+      "learning_rate": 9.740436672108686e-06,
+      "loss": 0.3513,
+      "step": 685
+    },
+    {
+      "epoch": 1.9166666666666665,
+      "grad_norm": 1.079379916191101,
+      "learning_rate": 9.525992982593584e-06,
+      "loss": 0.3963,
+      "step": 690
+    },
+    {
+      "epoch": 1.9305555555555556,
+      "grad_norm": 1.128957748413086,
+      "learning_rate": 9.312832338110292e-06,
+      "loss": 0.3973,
+      "step": 695
+    },
+    {
+      "epoch": 1.9444444444444444,
+      "grad_norm": 1.1786658763885498,
+      "learning_rate": 9.101004701091253e-06,
+      "loss": 0.3662,
+      "step": 700
+    },
+    {
+      "epoch": 1.9583333333333335,
+      "grad_norm": 1.18641996383667,
+      "learning_rate": 8.890559721527139e-06,
+      "loss": 0.354,
+      "step": 705
+    },
+    {
+      "epoch": 1.9722222222222223,
+      "grad_norm": 1.2030516862869263,
+      "learning_rate": 8.68154672532941e-06,
+      "loss": 0.395,
+      "step": 710
+    },
+    {
+      "epoch": 1.9861111111111112,
+      "grad_norm": 1.213351845741272,
+      "learning_rate": 8.474014702768905e-06,
+      "loss": 0.3542,
+      "step": 715
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.160871148109436,
+      "learning_rate": 8.268012296993067e-06,
+      "loss": 0.3575,
+      "step": 720
+    },
+    {
+      "epoch": 2.013888888888889,
+      "grad_norm": 1.0242027044296265,
+      "learning_rate": 8.063587792624568e-06,
+      "loss": 0.2924,
+      "step": 725
+    },
+    {
+      "epoch": 2.0277777777777777,
+      "grad_norm": 1.2001488208770752,
+      "learning_rate": 7.860789104443897e-06,
+      "loss": 0.3014,
+      "step": 730
+    },
+    {
+      "epoch": 2.0416666666666665,
+      "grad_norm": 1.0160436630249023,
+      "learning_rate": 7.659663766158734e-06,
+      "loss": 0.2964,
+      "step": 735
+    },
+    {
+      "epoch": 2.0555555555555554,
+      "grad_norm": 0.9895650744438171,
+      "learning_rate": 7.4602589192625295e-06,
+      "loss": 0.2746,
+      "step": 740
+    },
+    {
+      "epoch": 2.0694444444444446,
+      "grad_norm": 1.0355356931686401,
+      "learning_rate": 7.262621301985145e-06,
+      "loss": 0.2711,
+      "step": 745
+    },
+    {
+      "epoch": 2.0833333333333335,
+      "grad_norm": 1.052233338356018,
+      "learning_rate": 7.066797238337863e-06,
+      "loss": 0.3509,
+      "step": 750
+    },
+    {
+      "epoch": 2.0972222222222223,
+      "grad_norm": 1.0358434915542603,
+      "learning_rate": 6.872832627255643e-06,
+      "loss": 0.2925,
+      "step": 755
+    },
+    {
+      "epoch": 2.111111111111111,
+      "grad_norm": 1.1014931201934814,
+      "learning_rate": 6.680772931838868e-06,
+      "loss": 0.2599,
+      "step": 760
+    },
+    {
+      "epoch": 2.125,
+      "grad_norm": 1.1987323760986328,
+      "learning_rate": 6.49066316869736e-06,
+      "loss": 0.2816,
+      "step": 765
+    },
+    {
+      "epoch": 2.138888888888889,
+      "grad_norm": 1.1125656366348267,
+      "learning_rate": 6.302547897398959e-06,
+      "loss": 0.2794,
+      "step": 770
+    },
+    {
+      "epoch": 2.1527777777777777,
+      "grad_norm": 1.1091867685317993,
+      "learning_rate": 6.116471210025302e-06,
+      "loss": 0.3008,
+      "step": 775
+    },
+    {
+      "epoch": 2.1666666666666665,
+      "grad_norm": 1.089145541191101,
+      "learning_rate": 5.9324767208371055e-06,
+      "loss": 0.2663,
+      "step": 780
+    },
+    {
+      "epoch": 2.1805555555555554,
+      "grad_norm": 1.0546962022781372,
+      "learning_rate": 5.750607556051515e-06,
+      "loss": 0.3325,
+      "step": 785
+    },
+    {
+      "epoch": 2.1944444444444446,
+      "grad_norm": 1.2454535961151123,
+      "learning_rate": 5.570906343733769e-06,
+      "loss": 0.2676,
+      "step": 790
+    },
+    {
+      "epoch": 2.2083333333333335,
+      "grad_norm": 1.0933462381362915,
+      "learning_rate": 5.393415203805708e-06,
+      "loss": 0.2559,
+      "step": 795
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 1.2037767171859741,
+      "learning_rate": 5.218175738173304e-06,
+      "loss": 0.2752,
+      "step": 800
+    },
+    {
+      "epoch": 2.236111111111111,
+      "grad_norm": 1.166928768157959,
+      "learning_rate": 5.045229020975681e-06,
+      "loss": 0.2722,
+      "step": 805
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 1.1887221336364746,
+      "learning_rate": 4.874615588957773e-06,
+      "loss": 0.296,
+      "step": 810
+    },
+    {
+      "epoch": 2.263888888888889,
+      "grad_norm": 1.0863522291183472,
+      "learning_rate": 4.706375431968998e-06,
+      "loss": 0.298,
+      "step": 815
+    },
+    {
+      "epoch": 2.2777777777777777,
+      "grad_norm": 0.9994515776634216,
+      "learning_rate": 4.5405479835900695e-06,
+      "loss": 0.2448,
+      "step": 820
+    },
+    {
+      "epoch": 2.2916666666666665,
+      "grad_norm": 1.2771220207214355,
+      "learning_rate": 4.3771721118902345e-06,
+      "loss": 0.2528,
+      "step": 825
+    },
+    {
+      "epoch": 2.3055555555555554,
+      "grad_norm": 1.2188071012496948,
+      "learning_rate": 4.2162861103170135e-06,
+      "loss": 0.3031,
+      "step": 830
+    },
+    {
+      "epoch": 2.3194444444444446,
+      "grad_norm": 1.2380175590515137,
+      "learning_rate": 4.05792768872069e-06,
+      "loss": 0.3106,
+      "step": 835
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 1.0944781303405762,
+      "learning_rate": 3.902133964515503e-06,
+      "loss": 0.3063,
+      "step": 840
+    },
+    {
+      "epoch": 2.3472222222222223,
+      "grad_norm": 1.0908677577972412,
+      "learning_rate": 3.7489414539797903e-06,
+      "loss": 0.2835,
+      "step": 845
+    },
+    {
+      "epoch": 2.361111111111111,
+      "grad_norm": 1.041326880455017,
+      "learning_rate": 3.5983860636969528e-06,
+      "loss": 0.2332,
+      "step": 850
+    },
+    {
+      "epoch": 2.375,
+      "grad_norm": 1.3400294780731201,
+      "learning_rate": 3.4505030821393935e-06,
+      "loss": 0.2695,
+      "step": 855
+    },
+    {
+      "epoch": 2.388888888888889,
+      "grad_norm": 1.3053709268569946,
+      "learning_rate": 3.3053271713972635e-06,
+      "loss": 0.2832,
+      "step": 860
+    },
+    {
+      "epoch": 2.4027777777777777,
+      "grad_norm": 1.0280226469039917,
+      "learning_rate": 3.162892359054098e-06,
+      "loss": 0.2612,
+      "step": 865
+    },
+    {
+      "epoch": 2.4166666666666665,
+      "grad_norm": 1.1506812572479248,
+      "learning_rate": 3.023232030211105e-06,
+      "loss": 0.2533,
+      "step": 870
+    },
+    {
+      "epoch": 2.4305555555555554,
+      "grad_norm": 1.2825955152511597,
+      "learning_rate": 2.8863789196621094e-06,
+      "loss": 0.2594,
+      "step": 875
+    },
+    {
+      "epoch": 2.4444444444444446,
+      "grad_norm": 1.1212204694747925,
+      "learning_rate": 2.7523651042208564e-06,
+      "loss": 0.2711,
+      "step": 880
+    },
+    {
+      "epoch": 2.4583333333333335,
+      "grad_norm": 1.4847643375396729,
+      "learning_rate": 2.6212219952026e-06,
+      "loss": 0.2818,
+      "step": 885
+    },
+    {
+      "epoch": 2.4722222222222223,
+      "grad_norm": 1.0873907804489136,
+      "learning_rate": 2.492980331061622e-06,
+      "loss": 0.2661,
+      "step": 890
+    },
+    {
+      "epoch": 2.486111111111111,
+      "grad_norm": 1.050211787223816,
+      "learning_rate": 2.367670170186516e-06,
+      "loss": 0.2483,
+      "step": 895
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 1.0944018363952637,
+      "learning_rate": 2.24532088385481e-06,
+      "loss": 0.2535,
+      "step": 900
+    },
+    {
+      "epoch": 2.513888888888889,
+      "grad_norm": 1.0953317880630493,
+      "learning_rate": 2.125961149348706e-06,
+      "loss": 0.2898,
+      "step": 905
+    },
+    {
+      "epoch": 2.5277777777777777,
+      "grad_norm": 1.0513213872909546,
+      "learning_rate": 2.0096189432334194e-06,
+      "loss": 0.2394,
+      "step": 910
+    },
+    {
+      "epoch": 2.5416666666666665,
+      "grad_norm": 1.1305993795394897,
+      "learning_rate": 1.896321534799823e-06,
+      "loss": 0.2864,
+      "step": 915
+    },
+    {
+      "epoch": 2.5555555555555554,
+      "grad_norm": 1.0719528198242188,
+      "learning_rate": 1.7860954796727997e-06,
+      "loss": 0.2893,
+      "step": 920
+    },
+    {
+      "epoch": 2.5694444444444446,
+      "grad_norm": 1.2391268014907837,
+      "learning_rate": 1.6789666135869376e-06,
+      "loss": 0.2536,
+      "step": 925
+    },
+    {
+      "epoch": 2.5833333333333335,
+      "grad_norm": 1.0820634365081787,
+      "learning_rate": 1.574960046330905e-06,
+      "loss": 0.238,
+      "step": 930
+    },
+    {
+      "epoch": 2.5972222222222223,
+      "grad_norm": 1.1792165040969849,
+      "learning_rate": 1.4741001558620166e-06,
+      "loss": 0.2482,
+      "step": 935
+    },
+    {
+      "epoch": 2.611111111111111,
+      "grad_norm": 1.0961277484893799,
+      "learning_rate": 1.3764105825923068e-06,
+      "loss": 0.2614,
+      "step": 940
+    },
+    {
+      "epoch": 2.625,
+      "grad_norm": 1.0383102893829346,
+      "learning_rate": 1.2819142238474863e-06,
+      "loss": 0.2766,
+      "step": 945
+    },
+    {
+      "epoch": 2.638888888888889,
+      "grad_norm": 1.2211796045303345,
+      "learning_rate": 1.1906332285000793e-06,
+      "loss": 0.2826,
+      "step": 950
+    },
+    {
+      "epoch": 2.6527777777777777,
+      "grad_norm": 1.1081433296203613,
+      "learning_rate": 1.1025889917779735e-06,
+      "loss": 0.2822,
+      "step": 955
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.9788774847984314,
+      "learning_rate": 1.0178021502496166e-06,
+      "loss": 0.268,
+      "step": 960
+    },
+    {
+      "epoch": 2.6805555555555554,
+      "grad_norm": 1.018909215927124,
+      "learning_rate": 9.362925769870396e-07,
+      "loss": 0.2696,
+      "step": 965
+    },
+    {
+      "epoch": 2.6944444444444446,
+      "grad_norm": 1.1516112089157104,
+      "learning_rate": 8.580793769078488e-07,
+      "loss": 0.2815,
+      "step": 970
+    },
+    {
+      "epoch": 2.7083333333333335,
+      "grad_norm": 0.987594485282898,
+      "learning_rate": 7.831808822972392e-07,
+      "loss": 0.2472,
+      "step": 975
+    },
+    {
+      "epoch": 2.7222222222222223,
+      "grad_norm": 1.1561530828475952,
+      "learning_rate": 7.116146485111063e-07,
+      "loss": 0.2745,
+      "step": 980
+    },
+    {
+      "epoch": 2.736111111111111,
+      "grad_norm": 1.1640846729278564,
+      "learning_rate": 6.433974498612882e-07,
+      "loss": 0.2522,
+      "step": 985
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 1.0885223150253296,
+      "learning_rate": 5.785452756838483e-07,
+      "loss": 0.2419,
+      "step": 990
+    },
+    {
+      "epoch": 2.763888888888889,
+      "grad_norm": 1.0816514492034912,
+      "learning_rate": 5.170733265913585e-07,
+      "loss": 0.2743,
+      "step": 995
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 1.1799240112304688,
+      "learning_rate": 4.589960109100444e-07,
+      "loss": 0.2388,
+      "step": 1000
+    },
+    {
+      "epoch": 2.7916666666666665,
+      "grad_norm": 1.2002804279327393,
+      "learning_rate": 4.043269413026429e-07,
+      "loss": 0.2703,
+      "step": 1005
+    },
+    {
+      "epoch": 2.8055555555555554,
+      "grad_norm": 1.1375762224197388,
+      "learning_rate": 3.5307893157774664e-07,
+      "loss": 0.2598,
+      "step": 1010
+    },
+    {
+      "epoch": 2.8194444444444446,
+      "grad_norm": 1.1245205402374268,
+      "learning_rate": 3.0526399368639103e-07,
+      "loss": 0.2471,
+      "step": 1015
+    },
+    {
+      "epoch": 2.8333333333333335,
+      "grad_norm": 1.103769302368164,
+      "learning_rate": 2.6089333490659506e-07,
+      "loss": 0.2425,
+      "step": 1020
+    },
+    {
+      "epoch": 2.8472222222222223,
+      "grad_norm": 1.021943211555481,
+      "learning_rate": 2.1997735521649408e-07,
+      "loss": 0.2504,
+      "step": 1025
+    },
+    {
+      "epoch": 2.861111111111111,
+      "grad_norm": 1.1182405948638916,
+      "learning_rate": 1.8252564485670975e-07,
+      "loss": 0.2583,
+      "step": 1030
+    },
+    {
+      "epoch": 2.875,
+      "grad_norm": 1.1222693920135498,
+      "learning_rate": 1.4854698208250638e-07,
+      "loss": 0.2629,
+      "step": 1035
+    },
+    {
+      "epoch": 2.888888888888889,
+      "grad_norm": 1.1009235382080078,
+      "learning_rate": 1.1804933110626359e-07,
+      "loss": 0.235,
+      "step": 1040
+    },
+    {
+      "epoch": 2.9027777777777777,
+      "grad_norm": 1.1490674018859863,
+      "learning_rate": 9.103984023075773e-08,
+      "loss": 0.2667,
+      "step": 1045
+    },
+    {
+      "epoch": 2.9166666666666665,
+      "grad_norm": 1.192660927772522,
+      "learning_rate": 6.752484017368554e-08,
+      "loss": 0.2848,
+      "step": 1050
+    },
+    {
+      "epoch": 2.9305555555555554,
+      "grad_norm": 1.0776135921478271,
+      "learning_rate": 4.7509842583806086e-08,
+      "loss": 0.2471,
+      "step": 1055
+    },
+    {
+      "epoch": 2.9444444444444446,
+      "grad_norm": 1.0938776731491089,
+      "learning_rate": 3.099953874908079e-08,
+      "loss": 0.2478,
+      "step": 1060
+    },
+    {
+      "epoch": 2.9583333333333335,
+      "grad_norm": 1.159061312675476,
+      "learning_rate": 1.7997798497084718e-08,
+      "loss": 0.2697,
+      "step": 1065
+    },
+    {
+      "epoch": 2.9722222222222223,
+      "grad_norm": 1.0631920099258423,
+      "learning_rate": 8.507669287967091e-09,
+      "loss": 0.2484,
+      "step": 1070
+    },
+    {
+      "epoch": 2.986111111111111,
+      "grad_norm": 1.1377451419830322,
+      "learning_rate": 2.5313755001593607e-09,
+      "loss": 0.2464,
+      "step": 1075
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.2484397888183594,
+      "learning_rate": 7.03179089989181e-11,
+      "loss": 0.2523,
+      "step": 1080
+    },
+    {
+      "epoch": 3.0,
+      "step": 1080,
+      "total_flos": 1.5985427869765468e+18,
+      "train_loss": 0.5499852971898185,
+      "train_runtime": 792.1755,
+      "train_samples_per_second": 43.615,
+      "train_steps_per_second": 1.363
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1080,
+  "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": 1.5985427869765468e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

27_128_e3_3e-5/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58230b551fccb8c07bc37e00d7344000cc26e0d320b8fbb71062fa93f5e61949
+size 8209