Upload folder using huggingface_hub

105_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",
+    "k_proj",
+    "up_proj",
+    "q_proj",
+    "gate_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

105_128_e3_3e-5/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a6855c0d67a6f757dac9a891807f16f6ddd4a4fd8d5cdf69e19ae0b642cdfd8
+size 791751704

105_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
+}

105_128_e3_3e-5/all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.471836593047208e+18,
+    "train_loss": 0.5828557470760777,
+    "train_runtime": 724.5034,
+    "train_samples": 11301,
+    "train_samples_per_second": 46.795,
+    "train_steps_per_second": 1.466
+}

105_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 %}

105_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
+}

105_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
+  }
+}

105_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
+}

105_128_e3_3e-5/train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.471836593047208e+18,
+    "train_loss": 0.5828557470760777,
+    "train_runtime": 724.5034,
+    "train_samples": 11301,
+    "train_samples_per_second": 46.795,
+    "train_steps_per_second": 1.466
+}

105_128_e3_3e-5/trainer_state.json

@@ -0,0 +1,1527 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1062,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.014144271570014143,
+      "grad_norm": 3.55415940284729,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 1.5989,
+      "step": 5
+    },
+    {
+      "epoch": 0.028288543140028287,
+      "grad_norm": 2.2700791358947754,
+      "learning_rate": 4.9999999999999996e-06,
+      "loss": 1.5383,
+      "step": 10
+    },
+    {
+      "epoch": 0.042432814710042434,
+      "grad_norm": 0.8135097026824951,
+      "learning_rate": 7.777777777777777e-06,
+      "loss": 1.4285,
+      "step": 15
+    },
+    {
+      "epoch": 0.056577086280056574,
+      "grad_norm": 0.5212250351905823,
+      "learning_rate": 1.0555555555555555e-05,
+      "loss": 1.4453,
+      "step": 20
+    },
+    {
+      "epoch": 0.07072135785007072,
+      "grad_norm": 0.42810311913490295,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 1.3262,
+      "step": 25
+    },
+    {
+      "epoch": 0.08486562942008487,
+      "grad_norm": 0.4698460102081299,
+      "learning_rate": 1.6111111111111115e-05,
+      "loss": 1.3958,
+      "step": 30
+    },
+    {
+      "epoch": 0.09900990099009901,
+      "grad_norm": 0.3884115517139435,
+      "learning_rate": 1.888888888888889e-05,
+      "loss": 1.2457,
+      "step": 35
+    },
+    {
+      "epoch": 0.11315417256011315,
+      "grad_norm": 0.4552019238471985,
+      "learning_rate": 2.1666666666666667e-05,
+      "loss": 1.2786,
+      "step": 40
+    },
+    {
+      "epoch": 0.1272984441301273,
+      "grad_norm": 0.39111101627349854,
+      "learning_rate": 2.4444444444444445e-05,
+      "loss": 1.3021,
+      "step": 45
+    },
+    {
+      "epoch": 0.14144271570014144,
+      "grad_norm": 0.4224126935005188,
+      "learning_rate": 2.7222222222222223e-05,
+      "loss": 1.2749,
+      "step": 50
+    },
+    {
+      "epoch": 0.15558698727015557,
+      "grad_norm": 0.5608042478561401,
+      "learning_rate": 3e-05,
+      "loss": 1.3023,
+      "step": 55
+    },
+    {
+      "epoch": 0.16973125884016974,
+      "grad_norm": 0.44848519563674927,
+      "learning_rate": 2.9998178743291113e-05,
+      "loss": 1.2352,
+      "step": 60
+    },
+    {
+      "epoch": 0.18387553041018387,
+      "grad_norm": 0.40621453523635864,
+      "learning_rate": 2.9992715415427915e-05,
+      "loss": 1.1894,
+      "step": 65
+    },
+    {
+      "epoch": 0.19801980198019803,
+      "grad_norm": 0.42729634046554565,
+      "learning_rate": 2.998361134309341e-05,
+      "loss": 1.1479,
+      "step": 70
+    },
+    {
+      "epoch": 0.21216407355021216,
+      "grad_norm": 0.5140171647071838,
+      "learning_rate": 2.997086873706798e-05,
+      "loss": 1.1781,
+      "step": 75
+    },
+    {
+      "epoch": 0.2263083451202263,
+      "grad_norm": 0.44377657771110535,
+      "learning_rate": 2.995449069169251e-05,
+      "loss": 1.1674,
+      "step": 80
+    },
+    {
+      "epoch": 0.24045261669024046,
+      "grad_norm": 0.523114800453186,
+      "learning_rate": 2.9934481184117005e-05,
+      "loss": 1.1601,
+      "step": 85
+    },
+    {
+      "epoch": 0.2545968882602546,
+      "grad_norm": 0.520026683807373,
+      "learning_rate": 2.9910845073334793e-05,
+      "loss": 1.1636,
+      "step": 90
+    },
+    {
+      "epoch": 0.26874115983026875,
+      "grad_norm": 0.578159511089325,
+      "learning_rate": 2.9883588099002583e-05,
+      "loss": 1.1211,
+      "step": 95
+    },
+    {
+      "epoch": 0.2828854314002829,
+      "grad_norm": 0.4866771697998047,
+      "learning_rate": 2.9852716880046687e-05,
+      "loss": 1.0682,
+      "step": 100
+    },
+    {
+      "epoch": 0.297029702970297,
+      "grad_norm": 0.5007590651512146,
+      "learning_rate": 2.981823891305572e-05,
+      "loss": 1.1251,
+      "step": 105
+    },
+    {
+      "epoch": 0.31117397454031115,
+      "grad_norm": 0.6391701102256775,
+      "learning_rate": 2.9780162570460182e-05,
+      "loss": 1.155,
+      "step": 110
+    },
+    {
+      "epoch": 0.32531824611032534,
+      "grad_norm": 0.5852518677711487,
+      "learning_rate": 2.9738497098499325e-05,
+      "loss": 1.0113,
+      "step": 115
+    },
+    {
+      "epoch": 0.33946251768033947,
+      "grad_norm": 0.5627012252807617,
+      "learning_rate": 2.969325261497586e-05,
+      "loss": 1.0718,
+      "step": 120
+    },
+    {
+      "epoch": 0.3536067892503536,
+      "grad_norm": 0.6053456664085388,
+      "learning_rate": 2.9644440106799003e-05,
+      "loss": 1.0109,
+      "step": 125
+    },
+    {
+      "epoch": 0.36775106082036774,
+      "grad_norm": 0.6510122418403625,
+      "learning_rate": 2.9592071427316492e-05,
+      "loss": 1.0384,
+      "step": 130
+    },
+    {
+      "epoch": 0.38189533239038187,
+      "grad_norm": 0.6372938752174377,
+      "learning_rate": 2.9536159293436172e-05,
+      "loss": 1.0219,
+      "step": 135
+    },
+    {
+      "epoch": 0.39603960396039606,
+      "grad_norm": 0.5774106979370117,
+      "learning_rate": 2.9476717282537897e-05,
+      "loss": 0.9973,
+      "step": 140
+    },
+    {
+      "epoch": 0.4101838755304102,
+      "grad_norm": 0.6167390942573547,
+      "learning_rate": 2.9413759829176497e-05,
+      "loss": 0.9633,
+      "step": 145
+    },
+    {
+      "epoch": 0.4243281471004243,
+      "grad_norm": 0.6446376442909241,
+      "learning_rate": 2.934730222157653e-05,
+      "loss": 0.9927,
+      "step": 150
+    },
+    {
+      "epoch": 0.43847241867043846,
+      "grad_norm": 0.74149489402771,
+      "learning_rate": 2.927736059791984e-05,
+      "loss": 0.9881,
+      "step": 155
+    },
+    {
+      "epoch": 0.4526166902404526,
+      "grad_norm": 0.6144387125968933,
+      "learning_rate": 2.9203951942426587e-05,
+      "loss": 0.97,
+      "step": 160
+    },
+    {
+      "epoch": 0.4667609618104668,
+      "grad_norm": 0.6724966168403625,
+      "learning_rate": 2.9127094081230952e-05,
+      "loss": 0.9868,
+      "step": 165
+    },
+    {
+      "epoch": 0.4809052333804809,
+      "grad_norm": 0.742600679397583,
+      "learning_rate": 2.9046805678052312e-05,
+      "loss": 0.9195,
+      "step": 170
+    },
+    {
+      "epoch": 0.49504950495049505,
+      "grad_norm": 0.6673213243484497,
+      "learning_rate": 2.8963106229663064e-05,
+      "loss": 0.9336,
+      "step": 175
+    },
+    {
+      "epoch": 0.5091937765205092,
+      "grad_norm": 0.7014442086219788,
+      "learning_rate": 2.8876016061154125e-05,
+      "loss": 0.9055,
+      "step": 180
+    },
+    {
+      "epoch": 0.5233380480905233,
+      "grad_norm": 0.8006377816200256,
+      "learning_rate": 2.8785556320999308e-05,
+      "loss": 0.9472,
+      "step": 185
+    },
+    {
+      "epoch": 0.5374823196605375,
+      "grad_norm": 0.7469657063484192,
+      "learning_rate": 2.8691748975919784e-05,
+      "loss": 0.8766,
+      "step": 190
+    },
+    {
+      "epoch": 0.5516265912305516,
+      "grad_norm": 0.807214617729187,
+      "learning_rate": 2.8594616805549752e-05,
+      "loss": 0.9498,
+      "step": 195
+    },
+    {
+      "epoch": 0.5657708628005658,
+      "grad_norm": 0.745466411113739,
+      "learning_rate": 2.84941833969048e-05,
+      "loss": 0.8584,
+      "step": 200
+    },
+    {
+      "epoch": 0.57991513437058,
+      "grad_norm": 0.7496269941329956,
+      "learning_rate": 2.8390473138654175e-05,
+      "loss": 0.8742,
+      "step": 205
+    },
+    {
+      "epoch": 0.594059405940594,
+      "grad_norm": 0.8298000693321228,
+      "learning_rate": 2.828351121519835e-05,
+      "loss": 0.8768,
+      "step": 210
+    },
+    {
+      "epoch": 0.6082036775106082,
+      "grad_norm": 0.8184183835983276,
+      "learning_rate": 2.817332360055343e-05,
+      "loss": 0.8726,
+      "step": 215
+    },
+    {
+      "epoch": 0.6223479490806223,
+      "grad_norm": 0.8296445608139038,
+      "learning_rate": 2.8059937052043724e-05,
+      "loss": 0.8425,
+      "step": 220
+    },
+    {
+      "epoch": 0.6364922206506365,
+      "grad_norm": 0.8369902968406677,
+      "learning_rate": 2.7943379103804196e-05,
+      "loss": 0.8768,
+      "step": 225
+    },
+    {
+      "epoch": 0.6506364922206507,
+      "grad_norm": 0.8682529926300049,
+      "learning_rate": 2.7823678060094198e-05,
+      "loss": 0.8235,
+      "step": 230
+    },
+    {
+      "epoch": 0.6647807637906648,
+      "grad_norm": 0.8881997466087341,
+      "learning_rate": 2.770086298842426e-05,
+      "loss": 0.893,
+      "step": 235
+    },
+    {
+      "epoch": 0.6789250353606789,
+      "grad_norm": 0.8963375687599182,
+      "learning_rate": 2.7574963712497486e-05,
+      "loss": 0.8592,
+      "step": 240
+    },
+    {
+      "epoch": 0.693069306930693,
+      "grad_norm": 0.8523443937301636,
+      "learning_rate": 2.7446010804967314e-05,
+      "loss": 0.7966,
+      "step": 245
+    },
+    {
+      "epoch": 0.7072135785007072,
+      "grad_norm": 0.9112760424613953,
+      "learning_rate": 2.7314035580013487e-05,
+      "loss": 0.7891,
+      "step": 250
+    },
+    {
+      "epoch": 0.7213578500707214,
+      "grad_norm": 0.9217811822891235,
+      "learning_rate": 2.717907008573785e-05,
+      "loss": 0.8306,
+      "step": 255
+    },
+    {
+      "epoch": 0.7355021216407355,
+      "grad_norm": 0.8450111150741577,
+      "learning_rate": 2.7041147096381988e-05,
+      "loss": 0.8116,
+      "step": 260
+    },
+    {
+      "epoch": 0.7496463932107497,
+      "grad_norm": 0.8215683102607727,
+      "learning_rate": 2.6900300104368527e-05,
+      "loss": 0.7755,
+      "step": 265
+    },
+    {
+      "epoch": 0.7637906647807637,
+      "grad_norm": 0.86981201171875,
+      "learning_rate": 2.6756563312168022e-05,
+      "loss": 0.804,
+      "step": 270
+    },
+    {
+      "epoch": 0.7779349363507779,
+      "grad_norm": 0.9821562170982361,
+      "learning_rate": 2.6609971623993412e-05,
+      "loss": 0.7992,
+      "step": 275
+    },
+    {
+      "epoch": 0.7920792079207921,
+      "grad_norm": 0.8629034161567688,
+      "learning_rate": 2.6460560637324113e-05,
+      "loss": 0.7163,
+      "step": 280
+    },
+    {
+      "epoch": 0.8062234794908062,
+      "grad_norm": 0.9552486538887024,
+      "learning_rate": 2.6308366634261697e-05,
+      "loss": 0.7559,
+      "step": 285
+    },
+    {
+      "epoch": 0.8203677510608204,
+      "grad_norm": 1.0110570192337036,
+      "learning_rate": 2.6153426572719393e-05,
+      "loss": 0.8072,
+      "step": 290
+    },
+    {
+      "epoch": 0.8345120226308345,
+      "grad_norm": 0.9830376505851746,
+      "learning_rate": 2.5995778077447393e-05,
+      "loss": 0.7447,
+      "step": 295
+    },
+    {
+      "epoch": 0.8486562942008486,
+      "grad_norm": 0.9542567729949951,
+      "learning_rate": 2.5835459430896334e-05,
+      "loss": 0.7267,
+      "step": 300
+    },
+    {
+      "epoch": 0.8628005657708628,
+      "grad_norm": 0.942893922328949,
+      "learning_rate": 2.5672509563920953e-05,
+      "loss": 0.7441,
+      "step": 305
+    },
+    {
+      "epoch": 0.8769448373408769,
+      "grad_norm": 1.074002981185913,
+      "learning_rate": 2.5506968046326374e-05,
+      "loss": 0.7111,
+      "step": 310
+    },
+    {
+      "epoch": 0.8910891089108911,
+      "grad_norm": 1.037377119064331,
+      "learning_rate": 2.5338875077259207e-05,
+      "loss": 0.7363,
+      "step": 315
+    },
+    {
+      "epoch": 0.9052333804809052,
+      "grad_norm": 0.9588910937309265,
+      "learning_rate": 2.5168271475445795e-05,
+      "loss": 0.7366,
+      "step": 320
+    },
+    {
+      "epoch": 0.9193776520509194,
+      "grad_norm": 1.0788989067077637,
+      "learning_rate": 2.499519866928006e-05,
+      "loss": 0.6869,
+      "step": 325
+    },
+    {
+      "epoch": 0.9335219236209336,
+      "grad_norm": 0.9878784418106079,
+      "learning_rate": 2.4819698686763245e-05,
+      "loss": 0.6435,
+      "step": 330
+    },
+    {
+      "epoch": 0.9476661951909476,
+      "grad_norm": 0.9808891415596008,
+      "learning_rate": 2.464181414529809e-05,
+      "loss": 0.7304,
+      "step": 335
+    },
+    {
+      "epoch": 0.9618104667609618,
+      "grad_norm": 0.8885067105293274,
+      "learning_rate": 2.4461588241339877e-05,
+      "loss": 0.6975,
+      "step": 340
+    },
+    {
+      "epoch": 0.9759547383309759,
+      "grad_norm": 1.036365270614624,
+      "learning_rate": 2.4279064739906824e-05,
+      "loss": 0.7024,
+      "step": 345
+    },
+    {
+      "epoch": 0.9900990099009901,
+      "grad_norm": 0.9946621060371399,
+      "learning_rate": 2.4094287963952468e-05,
+      "loss": 0.6902,
+      "step": 350
+    },
+    {
+      "epoch": 1.002828854314003,
+      "grad_norm": 0.9998151659965515,
+      "learning_rate": 2.3907302783602522e-05,
+      "loss": 0.6263,
+      "step": 355
+    },
+    {
+      "epoch": 1.016973125884017,
+      "grad_norm": 1.1200729608535767,
+      "learning_rate": 2.3718154605258885e-05,
+      "loss": 0.6127,
+      "step": 360
+    },
+    {
+      "epoch": 1.031117397454031,
+      "grad_norm": 0.9791126847267151,
+      "learning_rate": 2.3526889360573387e-05,
+      "loss": 0.6213,
+      "step": 365
+    },
+    {
+      "epoch": 1.0452616690240453,
+      "grad_norm": 1.0279935598373413,
+      "learning_rate": 2.3333553495294033e-05,
+      "loss": 0.6068,
+      "step": 370
+    },
+    {
+      "epoch": 1.0594059405940595,
+      "grad_norm": 1.035305142402649,
+      "learning_rate": 2.3138193957986392e-05,
+      "loss": 0.5775,
+      "step": 375
+    },
+    {
+      "epoch": 1.0735502121640736,
+      "grad_norm": 1.1097909212112427,
+      "learning_rate": 2.2940858188632853e-05,
+      "loss": 0.6183,
+      "step": 380
+    },
+    {
+      "epoch": 1.0876944837340876,
+      "grad_norm": 1.1338350772857666,
+      "learning_rate": 2.27415941071126e-05,
+      "loss": 0.5978,
+      "step": 385
+    },
+    {
+      "epoch": 1.1018387553041018,
+      "grad_norm": 1.0650681257247925,
+      "learning_rate": 2.2540450101565002e-05,
+      "loss": 0.577,
+      "step": 390
+    },
+    {
+      "epoch": 1.115983026874116,
+      "grad_norm": 1.0820870399475098,
+      "learning_rate": 2.233747501663934e-05,
+      "loss": 0.5816,
+      "step": 395
+    },
+    {
+      "epoch": 1.1301272984441302,
+      "grad_norm": 1.1441088914871216,
+      "learning_rate": 2.213271814163363e-05,
+      "loss": 0.5796,
+      "step": 400
+    },
+    {
+      "epoch": 1.1442715700141444,
+      "grad_norm": 1.0199620723724365,
+      "learning_rate": 2.192622919852551e-05,
+      "loss": 0.5751,
+      "step": 405
+    },
+    {
+      "epoch": 1.1584158415841583,
+      "grad_norm": 1.0987247228622437,
+      "learning_rate": 2.171805832989804e-05,
+      "loss": 0.51,
+      "step": 410
+    },
+    {
+      "epoch": 1.1725601131541725,
+      "grad_norm": 1.1647366285324097,
+      "learning_rate": 2.1508256086763372e-05,
+      "loss": 0.5321,
+      "step": 415
+    },
+    {
+      "epoch": 1.1867043847241867,
+      "grad_norm": 1.174546718597412,
+      "learning_rate": 2.1296873416287216e-05,
+      "loss": 0.5956,
+      "step": 420
+    },
+    {
+      "epoch": 1.200848656294201,
+      "grad_norm": 1.108580231666565,
+      "learning_rate": 2.108396164941713e-05,
+      "loss": 0.5355,
+      "step": 425
+    },
+    {
+      "epoch": 1.214992927864215,
+      "grad_norm": 1.1179651021957397,
+      "learning_rate": 2.0869572488417626e-05,
+      "loss": 0.5438,
+      "step": 430
+    },
+    {
+      "epoch": 1.229137199434229,
+      "grad_norm": 1.0850542783737183,
+      "learning_rate": 2.0653757994315078e-05,
+      "loss": 0.5525,
+      "step": 435
+    },
+    {
+      "epoch": 1.2432814710042432,
+      "grad_norm": 1.0062577724456787,
+      "learning_rate": 2.0436570574255526e-05,
+      "loss": 0.5538,
+      "step": 440
+    },
+    {
+      "epoch": 1.2574257425742574,
+      "grad_norm": 1.046433448791504,
+      "learning_rate": 2.0218062968778407e-05,
+      "loss": 0.5299,
+      "step": 445
+    },
+    {
+      "epoch": 1.2715700141442716,
+      "grad_norm": 1.1260758638381958,
+      "learning_rate": 1.999828823900939e-05,
+      "loss": 0.5599,
+      "step": 450
+    },
+    {
+      "epoch": 1.2857142857142856,
+      "grad_norm": 1.2644517421722412,
+      "learning_rate": 1.977729975377527e-05,
+      "loss": 0.5122,
+      "step": 455
+    },
+    {
+      "epoch": 1.2998585572842998,
+      "grad_norm": 1.0869758129119873,
+      "learning_rate": 1.9555151176644223e-05,
+      "loss": 0.5064,
+      "step": 460
+    },
+    {
+      "epoch": 1.314002828854314,
+      "grad_norm": 1.292248249053955,
+      "learning_rate": 1.933189645289445e-05,
+      "loss": 0.556,
+      "step": 465
+    },
+    {
+      "epoch": 1.3281471004243282,
+      "grad_norm": 1.0759299993515015,
+      "learning_rate": 1.91075897964144e-05,
+      "loss": 0.5626,
+      "step": 470
+    },
+    {
+      "epoch": 1.3422913719943423,
+      "grad_norm": 1.1467018127441406,
+      "learning_rate": 1.888228567653781e-05,
+      "loss": 0.5246,
+      "step": 475
+    },
+    {
+      "epoch": 1.3564356435643563,
+      "grad_norm": 0.993481457233429,
+      "learning_rate": 1.8656038804816662e-05,
+      "loss": 0.5437,
+      "step": 480
+    },
+    {
+      "epoch": 1.3705799151343705,
+      "grad_norm": 1.1052156686782837,
+      "learning_rate": 1.8428904121735345e-05,
+      "loss": 0.4808,
+      "step": 485
+    },
+    {
+      "epoch": 1.3847241867043847,
+      "grad_norm": 1.1526223421096802,
+      "learning_rate": 1.8200936783369252e-05,
+      "loss": 0.4878,
+      "step": 490
+    },
+    {
+      "epoch": 1.3988684582743989,
+      "grad_norm": 1.2043397426605225,
+      "learning_rate": 1.7972192147990966e-05,
+      "loss": 0.4899,
+      "step": 495
+    },
+    {
+      "epoch": 1.413012729844413,
+      "grad_norm": 1.1565533876419067,
+      "learning_rate": 1.7742725762627395e-05,
+      "loss": 0.5098,
+      "step": 500
+    },
+    {
+      "epoch": 1.427157001414427,
+      "grad_norm": 1.131499171257019,
+      "learning_rate": 1.7512593349571046e-05,
+      "loss": 0.4921,
+      "step": 505
+    },
+    {
+      "epoch": 1.4413012729844414,
+      "grad_norm": 1.2194310426712036,
+      "learning_rate": 1.7281850792848752e-05,
+      "loss": 0.4927,
+      "step": 510
+    },
+    {
+      "epoch": 1.4554455445544554,
+      "grad_norm": 1.2039005756378174,
+      "learning_rate": 1.7050554124651103e-05,
+      "loss": 0.4427,
+      "step": 515
+    },
+    {
+      "epoch": 1.4695898161244696,
+      "grad_norm": 1.0419765710830688,
+      "learning_rate": 1.6818759511725922e-05,
+      "loss": 0.472,
+      "step": 520
+    },
+    {
+      "epoch": 1.4837340876944838,
+      "grad_norm": 1.1437103748321533,
+      "learning_rate": 1.658652324173907e-05,
+      "loss": 0.469,
+      "step": 525
+    },
+    {
+      "epoch": 1.4978783592644977,
+      "grad_norm": 1.3159091472625732,
+      "learning_rate": 1.6353901709605838e-05,
+      "loss": 0.462,
+      "step": 530
+    },
+    {
+      "epoch": 1.5120226308345122,
+      "grad_norm": 1.1723538637161255,
+      "learning_rate": 1.6120951403796367e-05,
+      "loss": 0.4704,
+      "step": 535
+    },
+    {
+      "epoch": 1.5261669024045261,
+      "grad_norm": 1.174741268157959,
+      "learning_rate": 1.5887728892618292e-05,
+      "loss": 0.4689,
+      "step": 540
+    },
+    {
+      "epoch": 1.5403111739745403,
+      "grad_norm": 1.3775728940963745,
+      "learning_rate": 1.5654290810480043e-05,
+      "loss": 0.4779,
+      "step": 545
+    },
+    {
+      "epoch": 1.5544554455445545,
+      "grad_norm": 1.1974047422409058,
+      "learning_rate": 1.5420693844138036e-05,
+      "loss": 0.4801,
+      "step": 550
+    },
+    {
+      "epoch": 1.5685997171145685,
+      "grad_norm": 1.1919121742248535,
+      "learning_rate": 1.5186994718931227e-05,
+      "loss": 0.4434,
+      "step": 555
+    },
+    {
+      "epoch": 1.5827439886845829,
+      "grad_norm": 1.0517688989639282,
+      "learning_rate": 1.4953250185006236e-05,
+      "loss": 0.4347,
+      "step": 560
+    },
+    {
+      "epoch": 1.5968882602545968,
+      "grad_norm": 1.387012243270874,
+      "learning_rate": 1.471951700353647e-05,
+      "loss": 0.4411,
+      "step": 565
+    },
+    {
+      "epoch": 1.611032531824611,
+      "grad_norm": 1.2351195812225342,
+      "learning_rate": 1.4485851932938575e-05,
+      "loss": 0.4722,
+      "step": 570
+    },
+    {
+      "epoch": 1.6251768033946252,
+      "grad_norm": 1.1913583278656006,
+      "learning_rate": 1.4252311715089542e-05,
+      "loss": 0.4502,
+      "step": 575
+    },
+    {
+      "epoch": 1.6393210749646392,
+      "grad_norm": 1.2106176614761353,
+      "learning_rate": 1.4018953061547854e-05,
+      "loss": 0.4569,
+      "step": 580
+    },
+    {
+      "epoch": 1.6534653465346536,
+      "grad_norm": 1.2371139526367188,
+      "learning_rate": 1.3785832639781951e-05,
+      "loss": 0.4153,
+      "step": 585
+    },
+    {
+      "epoch": 1.6676096181046676,
+      "grad_norm": 1.1295750141143799,
+      "learning_rate": 1.355300705940945e-05,
+      "loss": 0.4255,
+      "step": 590
+    },
+    {
+      "epoch": 1.6817538896746818,
+      "grad_norm": 1.276272177696228,
+      "learning_rate": 1.3320532858450382e-05,
+      "loss": 0.4558,
+      "step": 595
+    },
+    {
+      "epoch": 1.695898161244696,
+      "grad_norm": 1.2146130800247192,
+      "learning_rate": 1.3088466489597838e-05,
+      "loss": 0.4178,
+      "step": 600
+    },
+    {
+      "epoch": 1.71004243281471,
+      "grad_norm": 1.1120046377182007,
+      "learning_rate": 1.2856864306509303e-05,
+      "loss": 0.442,
+      "step": 605
+    },
+    {
+      "epoch": 1.7241867043847243,
+      "grad_norm": 1.134915828704834,
+      "learning_rate": 1.2625782550122076e-05,
+      "loss": 0.4185,
+      "step": 610
+    },
+    {
+      "epoch": 1.7383309759547383,
+      "grad_norm": 1.2604330778121948,
+      "learning_rate": 1.2395277334996045e-05,
+      "loss": 0.4049,
+      "step": 615
+    },
+    {
+      "epoch": 1.7524752475247525,
+      "grad_norm": 1.2006709575653076,
+      "learning_rate": 1.2165404635687139e-05,
+      "loss": 0.4622,
+      "step": 620
+    },
+    {
+      "epoch": 1.7666195190947667,
+      "grad_norm": 1.1547012329101562,
+      "learning_rate": 1.1936220273154797e-05,
+      "loss": 0.3753,
+      "step": 625
+    },
+    {
+      "epoch": 1.7807637906647806,
+      "grad_norm": 1.1750926971435547,
+      "learning_rate": 1.1707779901206733e-05,
+      "loss": 0.482,
+      "step": 630
+    },
+    {
+      "epoch": 1.794908062234795,
+      "grad_norm": 1.3690738677978516,
+      "learning_rate": 1.1480138992984276e-05,
+      "loss": 0.371,
+      "step": 635
+    },
+    {
+      "epoch": 1.809052333804809,
+      "grad_norm": 1.3244385719299316,
+      "learning_rate": 1.1253352827491594e-05,
+      "loss": 0.3728,
+      "step": 640
+    },
+    {
+      "epoch": 1.8231966053748232,
+      "grad_norm": 1.1366060972213745,
+      "learning_rate": 1.102747647617209e-05,
+      "loss": 0.4038,
+      "step": 645
+    },
+    {
+      "epoch": 1.8373408769448374,
+      "grad_norm": 1.191258192062378,
+      "learning_rate": 1.080256478953512e-05,
+      "loss": 0.3866,
+      "step": 650
+    },
+    {
+      "epoch": 1.8514851485148514,
+      "grad_norm": 1.1260064840316772,
+      "learning_rate": 1.0578672383836437e-05,
+      "loss": 0.4132,
+      "step": 655
+    },
+    {
+      "epoch": 1.8656294200848658,
+      "grad_norm": 1.1831655502319336,
+      "learning_rate": 1.0355853627815506e-05,
+      "loss": 0.3882,
+      "step": 660
+    },
+    {
+      "epoch": 1.8797736916548797,
+      "grad_norm": 1.2979127168655396,
+      "learning_rate": 1.0134162629492895e-05,
+      "loss": 0.3725,
+      "step": 665
+    },
+    {
+      "epoch": 1.893917963224894,
+      "grad_norm": 1.2173168659210205,
+      "learning_rate": 9.913653223031e-06,
+      "loss": 0.427,
+      "step": 670
+    },
+    {
+      "epoch": 1.908062234794908,
+      "grad_norm": 1.1884539127349854,
+      "learning_rate": 9.69437895566128e-06,
+      "loss": 0.4261,
+      "step": 675
+    },
+    {
+      "epoch": 1.922206506364922,
+      "grad_norm": 1.128859519958496,
+      "learning_rate": 9.476393074681134e-06,
+      "loss": 0.3658,
+      "step": 680
+    },
+    {
+      "epoch": 1.9363507779349365,
+      "grad_norm": 1.505871057510376,
+      "learning_rate": 9.259748514523654e-06,
+      "loss": 0.42,
+      "step": 685
+    },
+    {
+      "epoch": 1.9504950495049505,
+      "grad_norm": 1.2792670726776123,
+      "learning_rate": 9.044497883903326e-06,
+      "loss": 0.3988,
+      "step": 690
+    },
+    {
+      "epoch": 1.9646393210749646,
+      "grad_norm": 1.3008604049682617,
+      "learning_rate": 8.83069345304083e-06,
+      "loss": 0.3943,
+      "step": 695
+    },
+    {
+      "epoch": 1.9787835926449788,
+      "grad_norm": 1.1482751369476318,
+      "learning_rate": 8.618387140970047e-06,
+      "loss": 0.3975,
+      "step": 700
+    },
+    {
+      "epoch": 1.9929278642149928,
+      "grad_norm": 1.222287654876709,
+      "learning_rate": 8.407630502930325e-06,
+      "loss": 0.3626,
+      "step": 705
+    },
+    {
+      "epoch": 2.005657708628006,
+      "grad_norm": 1.1567516326904297,
+      "learning_rate": 8.198474717847146e-06,
+      "loss": 0.3215,
+      "step": 710
+    },
+    {
+      "epoch": 2.01980198019802,
+      "grad_norm": 1.2434115409851074,
+      "learning_rate": 7.99097057590407e-06,
+      "loss": 0.2903,
+      "step": 715
+    },
+    {
+      "epoch": 2.033946251768034,
+      "grad_norm": 1.2865327596664429,
+      "learning_rate": 7.785168466209188e-06,
+      "loss": 0.3595,
+      "step": 720
+    },
+    {
+      "epoch": 2.048090523338048,
+      "grad_norm": 1.0991758108139038,
+      "learning_rate": 7.581118364558889e-06,
+      "loss": 0.3165,
+      "step": 725
+    },
+    {
+      "epoch": 2.062234794908062,
+      "grad_norm": 1.2618017196655273,
+      "learning_rate": 7.378869821302062e-06,
+      "loss": 0.2762,
+      "step": 730
+    },
+    {
+      "epoch": 2.0763790664780766,
+      "grad_norm": 1.2464656829833984,
+      "learning_rate": 7.17847194930753e-06,
+      "loss": 0.3139,
+      "step": 735
+    },
+    {
+      "epoch": 2.0905233380480905,
+      "grad_norm": 1.1940979957580566,
+      "learning_rate": 6.9799734120378105e-06,
+      "loss": 0.2943,
+      "step": 740
+    },
+    {
+      "epoch": 2.1046676096181045,
+      "grad_norm": 1.2410266399383545,
+      "learning_rate": 6.783422411731932e-06,
+      "loss": 0.3193,
+      "step": 745
+    },
+    {
+      "epoch": 2.118811881188119,
+      "grad_norm": 1.3134958744049072,
+      "learning_rate": 6.58886667770028e-06,
+      "loss": 0.3011,
+      "step": 750
+    },
+    {
+      "epoch": 2.132956152758133,
+      "grad_norm": 1.3728560209274292,
+      "learning_rate": 6.3963534547343126e-06,
+      "loss": 0.3477,
+      "step": 755
+    },
+    {
+      "epoch": 2.1471004243281473,
+      "grad_norm": 1.2219020128250122,
+      "learning_rate": 6.205929491633869e-06,
+      "loss": 0.2951,
+      "step": 760
+    },
+    {
+      "epoch": 2.1612446958981613,
+      "grad_norm": 1.2190998792648315,
+      "learning_rate": 6.017641029854996e-06,
+      "loss": 0.295,
+      "step": 765
+    },
+    {
+      "epoch": 2.1753889674681752,
+      "grad_norm": 1.2725532054901123,
+      "learning_rate": 5.831533792280926e-06,
+      "loss": 0.2933,
+      "step": 770
+    },
+    {
+      "epoch": 2.1895332390381896,
+      "grad_norm": 1.221935510635376,
+      "learning_rate": 5.647652972118998e-06,
+      "loss": 0.3125,
+      "step": 775
+    },
+    {
+      "epoch": 2.2036775106082036,
+      "grad_norm": 1.2480595111846924,
+      "learning_rate": 5.46604322192618e-06,
+      "loss": 0.3019,
+      "step": 780
+    },
+    {
+      "epoch": 2.217821782178218,
+      "grad_norm": 1.4406380653381348,
+      "learning_rate": 5.286748642765945e-06,
+      "loss": 0.3,
+      "step": 785
+    },
+    {
+      "epoch": 2.231966053748232,
+      "grad_norm": 1.231207251548767,
+      "learning_rate": 5.109812773498968e-06,
+      "loss": 0.318,
+      "step": 790
+    },
+    {
+      "epoch": 2.246110325318246,
+      "grad_norm": 1.198382019996643,
+      "learning_rate": 4.935278580210451e-06,
+      "loss": 0.307,
+      "step": 795
+    },
+    {
+      "epoch": 2.2602545968882604,
+      "grad_norm": 1.2243497371673584,
+      "learning_rate": 4.763188445776447e-06,
+      "loss": 0.2766,
+      "step": 800
+    },
+    {
+      "epoch": 2.2743988684582743,
+      "grad_norm": 1.0849330425262451,
+      "learning_rate": 4.593584159571875e-06,
+      "loss": 0.301,
+      "step": 805
+    },
+    {
+      "epoch": 2.2885431400282887,
+      "grad_norm": 1.242175579071045,
+      "learning_rate": 4.426506907322624e-06,
+      "loss": 0.2811,
+      "step": 810
+    },
+    {
+      "epoch": 2.3026874115983027,
+      "grad_norm": 1.4007819890975952,
+      "learning_rate": 4.261997261104223e-06,
+      "loss": 0.2956,
+      "step": 815
+    },
+    {
+      "epoch": 2.3168316831683167,
+      "grad_norm": 1.3087992668151855,
+      "learning_rate": 4.100095169489597e-06,
+      "loss": 0.3003,
+      "step": 820
+    },
+    {
+      "epoch": 2.330975954738331,
+      "grad_norm": 1.1632558107376099,
+      "learning_rate": 3.940839947848141e-06,
+      "loss": 0.2822,
+      "step": 825
+    },
+    {
+      "epoch": 2.345120226308345,
+      "grad_norm": 1.1044288873672485,
+      "learning_rate": 3.7842702687986374e-06,
+      "loss": 0.2973,
+      "step": 830
+    },
+    {
+      "epoch": 2.3592644978783595,
+      "grad_norm": 1.27266526222229,
+      "learning_rate": 3.630424152818203e-06,
+      "loss": 0.2812,
+      "step": 835
+    },
+    {
+      "epoch": 2.3734087694483734,
+      "grad_norm": 1.2727618217468262,
+      "learning_rate": 3.479338959009625e-06,
+      "loss": 0.2798,
+      "step": 840
+    },
+    {
+      "epoch": 2.3875530410183874,
+      "grad_norm": 1.1531083583831787,
+      "learning_rate": 3.331051376029279e-06,
+      "loss": 0.2904,
+      "step": 845
+    },
+    {
+      "epoch": 2.401697312588402,
+      "grad_norm": 1.2054781913757324,
+      "learning_rate": 3.1855974131778696e-06,
+      "loss": 0.2997,
+      "step": 850
+    },
+    {
+      "epoch": 2.4158415841584158,
+      "grad_norm": 1.1705334186553955,
+      "learning_rate": 3.0430123916561677e-06,
+      "loss": 0.2886,
+      "step": 855
+    },
+    {
+      "epoch": 2.42998585572843,
+      "grad_norm": 1.23530912399292,
+      "learning_rate": 2.90333093598776e-06,
+      "loss": 0.2826,
+      "step": 860
+    },
+    {
+      "epoch": 2.444130127298444,
+      "grad_norm": 1.1815848350524902,
+      "learning_rate": 2.7665869656110974e-06,
+      "loss": 0.2894,
+      "step": 865
+    },
+    {
+      "epoch": 2.458274398868458,
+      "grad_norm": 1.0981158018112183,
+      "learning_rate": 2.6328136866426294e-06,
+      "loss": 0.2946,
+      "step": 870
+    },
+    {
+      "epoch": 2.4724186704384725,
+      "grad_norm": 1.103598713874817,
+      "learning_rate": 2.502043583813268e-06,
+      "loss": 0.3192,
+      "step": 875
+    },
+    {
+      "epoch": 2.4865629420084865,
+      "grad_norm": 1.165908932685852,
+      "learning_rate": 2.3743084125799515e-06,
+      "loss": 0.2812,
+      "step": 880
+    },
+    {
+      "epoch": 2.500707213578501,
+      "grad_norm": 1.1292260885238647,
+      "learning_rate": 2.2496391914143634e-06,
+      "loss": 0.2756,
+      "step": 885
+    },
+    {
+      "epoch": 2.514851485148515,
+      "grad_norm": 1.1673662662506104,
+      "learning_rate": 2.1280661942705554e-06,
+      "loss": 0.2847,
+      "step": 890
+    },
+    {
+      "epoch": 2.528995756718529,
+      "grad_norm": 1.28085196018219,
+      "learning_rate": 2.0096189432334194e-06,
+      "loss": 0.2928,
+      "step": 895
+    },
+    {
+      "epoch": 2.5431400282885432,
+      "grad_norm": 1.392196774482727,
+      "learning_rate": 1.8943262013497082e-06,
+      "loss": 0.2912,
+      "step": 900
+    },
+    {
+      "epoch": 2.557284299858557,
+      "grad_norm": 1.1114780902862549,
+      "learning_rate": 1.782215965643364e-06,
+      "loss": 0.2891,
+      "step": 905
+    },
+    {
+      "epoch": 2.571428571428571,
+      "grad_norm": 1.3842506408691406,
+      "learning_rate": 1.6733154603169177e-06,
+      "loss": 0.2716,
+      "step": 910
+    },
+    {
+      "epoch": 2.5855728429985856,
+      "grad_norm": 1.1169549226760864,
+      "learning_rate": 1.5676511301404861e-06,
+      "loss": 0.2955,
+      "step": 915
+    },
+    {
+      "epoch": 2.5997171145685996,
+      "grad_norm": 1.1807849407196045,
+      "learning_rate": 1.465248634030103e-06,
+      "loss": 0.269,
+      "step": 920
+    },
+    {
+      "epoch": 2.613861386138614,
+      "grad_norm": 1.2528729438781738,
+      "learning_rate": 1.3661328388168358e-06,
+      "loss": 0.3127,
+      "step": 925
+    },
+    {
+      "epoch": 2.628005657708628,
+      "grad_norm": 1.1673890352249146,
+      "learning_rate": 1.2703278132082936e-06,
+      "loss": 0.2826,
+      "step": 930
+    },
+    {
+      "epoch": 2.6421499292786423,
+      "grad_norm": 1.3932900428771973,
+      "learning_rate": 1.177856821943884e-06,
+      "loss": 0.2929,
+      "step": 935
+    },
+    {
+      "epoch": 2.6562942008486563,
+      "grad_norm": 1.2356282472610474,
+      "learning_rate": 1.0887423201453778e-06,
+      "loss": 0.2978,
+      "step": 940
+    },
+    {
+      "epoch": 2.6704384724186703,
+      "grad_norm": 1.195061445236206,
+      "learning_rate": 1.0030059478640025e-06,
+      "loss": 0.2791,
+      "step": 945
+    },
+    {
+      "epoch": 2.6845827439886847,
+      "grad_norm": 1.1517679691314697,
+      "learning_rate": 9.206685248255248e-07,
+      "loss": 0.2981,
+      "step": 950
+    },
+    {
+      "epoch": 2.6987270155586986,
+      "grad_norm": 1.511000633239746,
+      "learning_rate": 8.417500453744864e-07,
+      "loss": 0.2845,
+      "step": 955
+    },
+    {
+      "epoch": 2.7128712871287126,
+      "grad_norm": 1.2736140489578247,
+      "learning_rate": 7.662696736189129e-07,
+      "loss": 0.2622,
+      "step": 960
+    },
+    {
+      "epoch": 2.727015558698727,
+      "grad_norm": 1.238701343536377,
+      "learning_rate": 6.942457387765977e-07,
+      "loss": 0.291,
+      "step": 965
+    },
+    {
+      "epoch": 2.741159830268741,
+      "grad_norm": 1.2383997440338135,
+      "learning_rate": 6.256957307241396e-07,
+      "loss": 0.2886,
+      "step": 970
+    },
+    {
+      "epoch": 2.7553041018387554,
+      "grad_norm": 1.3801984786987305,
+      "learning_rate": 5.606362957498195e-07,
+      "loss": 0.2857,
+      "step": 975
+    },
+    {
+      "epoch": 2.7694483734087694,
+      "grad_norm": 1.1792446374893188,
+      "learning_rate": 4.990832325112898e-07,
+      "loss": 0.3085,
+      "step": 980
+    },
+    {
+      "epoch": 2.783592644978784,
+      "grad_norm": 1.165016770362854,
+      "learning_rate": 4.4105148819913564e-07,
+      "loss": 0.2632,
+      "step": 985
+    },
+    {
+      "epoch": 2.7977369165487977,
+      "grad_norm": 1.3806471824645996,
+      "learning_rate": 3.865551549071772e-07,
+      "loss": 0.2901,
+      "step": 990
+    },
+    {
+      "epoch": 2.8118811881188117,
+      "grad_norm": 1.137433409690857,
+      "learning_rate": 3.3560746621043193e-07,
+      "loss": 0.2865,
+      "step": 995
+    },
+    {
+      "epoch": 2.826025459688826,
+      "grad_norm": 1.2954826354980469,
+      "learning_rate": 2.8822079395154357e-07,
+      "loss": 0.2695,
+      "step": 1000
+    },
+    {
+      "epoch": 2.84016973125884,
+      "grad_norm": 1.2354345321655273,
+      "learning_rate": 2.4440664523648017e-07,
+      "loss": 0.2595,
+      "step": 1005
+    },
+    {
+      "epoch": 2.854314002828854,
+      "grad_norm": 1.1583670377731323,
+      "learning_rate": 2.041756596402161e-07,
+      "loss": 0.3137,
+      "step": 1010
+    },
+    {
+      "epoch": 2.8684582743988685,
+      "grad_norm": 1.259700059890747,
+      "learning_rate": 1.6753760662307217e-07,
+      "loss": 0.2716,
+      "step": 1015
+    },
+    {
+      "epoch": 2.882602545968883,
+      "grad_norm": 1.1810754537582397,
+      "learning_rate": 1.3450138315836303e-07,
+      "loss": 0.3062,
+      "step": 1020
+    },
+    {
+      "epoch": 2.896746817538897,
+      "grad_norm": 1.1928808689117432,
+      "learning_rate": 1.050750115719057e-07,
+      "loss": 0.2748,
+      "step": 1025
+    },
+    {
+      "epoch": 2.910891089108911,
+      "grad_norm": 1.2469139099121094,
+      "learning_rate": 7.926563759392436e-08,
+      "loss": 0.3078,
+      "step": 1030
+    },
+    {
+      "epoch": 2.9250353606789252,
+      "grad_norm": 1.2281895875930786,
+      "learning_rate": 5.7079528623816824e-08,
+      "loss": 0.2918,
+      "step": 1035
+    },
+    {
+      "epoch": 2.939179632248939,
+      "grad_norm": 1.167947769165039,
+      "learning_rate": 3.85220722082269e-08,
+      "loss": 0.2869,
+      "step": 1040
+    },
+    {
+      "epoch": 2.953323903818953,
+      "grad_norm": 1.1115106344223022,
+      "learning_rate": 2.3597774732750932e-08,
+      "loss": 0.2985,
+      "step": 1045
+    },
+    {
+      "epoch": 2.9674681753889676,
+      "grad_norm": 1.154123067855835,
+      "learning_rate": 1.2310260327646483e-08,
+      "loss": 0.2803,
+      "step": 1050
+    },
+    {
+      "epoch": 2.9816124469589815,
+      "grad_norm": 1.2140358686447144,
+      "learning_rate": 4.662269987756318e-09,
+      "loss": 0.2669,
+      "step": 1055
+    },
+    {
+      "epoch": 2.9957567185289955,
+      "grad_norm": 1.2427642345428467,
+      "learning_rate": 6.556609069091613e-10,
+      "loss": 0.2609,
+      "step": 1060
+    },
+    {
+      "epoch": 3.0,
+      "step": 1062,
+      "total_flos": 1.471836593047208e+18,
+      "train_loss": 0.5828557470760777,
+      "train_runtime": 724.5034,
+      "train_samples_per_second": 46.795,
+      "train_steps_per_second": 1.466
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1062,
+  "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": 1.471836593047208e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

105_128_e3_3e-5/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c466680476bfd1de368f031490f8c09e94ef7dee74ef1a0fe1f2f3b5e136125
+size 8273