Upload folder using huggingface_hub

112_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": [
+    "up_proj",
+    "gate_proj",
+    "q_proj",
+    "o_proj",
+    "k_proj",
+    "v_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

112_128_e3_3e-5/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a153e1df1d0c3f2b57a3ada7ef57a2a866e8cd51a5c55a57fd26913cfd948bc0
+size 791751704

112_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
+}

112_128_e3_3e-5/all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.3183900712456684e+18,
+    "train_loss": 0.5964417562652857,
+    "train_runtime": 624.021,
+    "train_samples": 9981,
+    "train_samples_per_second": 47.984,
+    "train_steps_per_second": 1.5
+}

112_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 %}

112_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
+}

112_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
+  }
+}

112_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
+}

112_128_e3_3e-5/train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.3183900712456684e+18,
+    "train_loss": 0.5964417562652857,
+    "train_runtime": 624.021,
+    "train_samples": 9981,
+    "train_samples_per_second": 47.984,
+    "train_steps_per_second": 1.5
+}

112_128_e3_3e-5/trainer_state.json

@@ -0,0 +1,1352 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 936,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.016025641025641024,
+      "grad_norm": 3.609208583831787,
+      "learning_rate": 2.553191489361702e-06,
+      "loss": 1.5829,
+      "step": 5
+    },
+    {
+      "epoch": 0.03205128205128205,
+      "grad_norm": 2.0544307231903076,
+      "learning_rate": 5.74468085106383e-06,
+      "loss": 1.5878,
+      "step": 10
+    },
+    {
+      "epoch": 0.04807692307692308,
+      "grad_norm": 0.6716304421424866,
+      "learning_rate": 8.936170212765958e-06,
+      "loss": 1.4567,
+      "step": 15
+    },
+    {
+      "epoch": 0.0641025641025641,
+      "grad_norm": 0.4489082992076874,
+      "learning_rate": 1.2127659574468084e-05,
+      "loss": 1.374,
+      "step": 20
+    },
+    {
+      "epoch": 0.08012820512820513,
+      "grad_norm": 0.40922755002975464,
+      "learning_rate": 1.531914893617021e-05,
+      "loss": 1.3624,
+      "step": 25
+    },
+    {
+      "epoch": 0.09615384615384616,
+      "grad_norm": 0.4467664659023285,
+      "learning_rate": 1.8510638297872342e-05,
+      "loss": 1.3395,
+      "step": 30
+    },
+    {
+      "epoch": 0.11217948717948718,
+      "grad_norm": 0.4665050804615021,
+      "learning_rate": 2.170212765957447e-05,
+      "loss": 1.3133,
+      "step": 35
+    },
+    {
+      "epoch": 0.1282051282051282,
+      "grad_norm": 0.3687248229980469,
+      "learning_rate": 2.4893617021276595e-05,
+      "loss": 1.3153,
+      "step": 40
+    },
+    {
+      "epoch": 0.14423076923076922,
+      "grad_norm": 0.34136056900024414,
+      "learning_rate": 2.8085106382978723e-05,
+      "loss": 1.2737,
+      "step": 45
+    },
+    {
+      "epoch": 0.16025641025641027,
+      "grad_norm": 0.3566436469554901,
+      "learning_rate": 2.999962535868399e-05,
+      "loss": 1.2647,
+      "step": 50
+    },
+    {
+      "epoch": 0.1762820512820513,
+      "grad_norm": 0.4001357853412628,
+      "learning_rate": 2.9995410858796248e-05,
+      "loss": 1.2563,
+      "step": 55
+    },
+    {
+      "epoch": 0.19230769230769232,
+      "grad_norm": 0.3485203981399536,
+      "learning_rate": 2.9986514877504622e-05,
+      "loss": 1.2165,
+      "step": 60
+    },
+    {
+      "epoch": 0.20833333333333334,
+      "grad_norm": 0.3852127492427826,
+      "learning_rate": 2.997294019208353e-05,
+      "loss": 1.2189,
+      "step": 65
+    },
+    {
+      "epoch": 0.22435897435897437,
+      "grad_norm": 0.3994678258895874,
+      "learning_rate": 2.995469104047204e-05,
+      "loss": 1.1871,
+      "step": 70
+    },
+    {
+      "epoch": 0.2403846153846154,
+      "grad_norm": 0.41952067613601685,
+      "learning_rate": 2.9931773119950775e-05,
+      "loss": 1.2037,
+      "step": 75
+    },
+    {
+      "epoch": 0.2564102564102564,
+      "grad_norm": 0.4179547131061554,
+      "learning_rate": 2.99041935853633e-05,
+      "loss": 1.131,
+      "step": 80
+    },
+    {
+      "epoch": 0.2724358974358974,
+      "grad_norm": 0.426399827003479,
+      "learning_rate": 2.9871961046882377e-05,
+      "loss": 1.159,
+      "step": 85
+    },
+    {
+      "epoch": 0.28846153846153844,
+      "grad_norm": 0.47932013869285583,
+      "learning_rate": 2.983508556732196e-05,
+      "loss": 1.1381,
+      "step": 90
+    },
+    {
+      "epoch": 0.30448717948717946,
+      "grad_norm": 0.4751587212085724,
+      "learning_rate": 2.979357865899561e-05,
+      "loss": 1.1266,
+      "step": 95
+    },
+    {
+      "epoch": 0.32051282051282054,
+      "grad_norm": 0.4897017776966095,
+      "learning_rate": 2.9747453280122436e-05,
+      "loss": 1.1427,
+      "step": 100
+    },
+    {
+      "epoch": 0.33653846153846156,
+      "grad_norm": 0.45273348689079285,
+      "learning_rate": 2.969672383078159e-05,
+      "loss": 1.1369,
+      "step": 105
+    },
+    {
+      "epoch": 0.3525641025641026,
+      "grad_norm": 0.45712795853614807,
+      "learning_rate": 2.964140614841668e-05,
+      "loss": 1.0883,
+      "step": 110
+    },
+    {
+      "epoch": 0.3685897435897436,
+      "grad_norm": 0.49390172958374023,
+      "learning_rate": 2.9581517502891373e-05,
+      "loss": 1.1141,
+      "step": 115
+    },
+    {
+      "epoch": 0.38461538461538464,
+      "grad_norm": 0.47936689853668213,
+      "learning_rate": 2.9517076591097877e-05,
+      "loss": 1.0641,
+      "step": 120
+    },
+    {
+      "epoch": 0.40064102564102566,
+      "grad_norm": 0.5411584973335266,
+      "learning_rate": 2.9448103531119858e-05,
+      "loss": 1.0101,
+      "step": 125
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 0.5501630902290344,
+      "learning_rate": 2.9374619855951676e-05,
+      "loss": 1.0342,
+      "step": 130
+    },
+    {
+      "epoch": 0.4326923076923077,
+      "grad_norm": 0.5636549592018127,
+      "learning_rate": 2.929664850677595e-05,
+      "loss": 1.0389,
+      "step": 135
+    },
+    {
+      "epoch": 0.44871794871794873,
+      "grad_norm": 0.5519638061523438,
+      "learning_rate": 2.921421382580142e-05,
+      "loss": 1.0133,
+      "step": 140
+    },
+    {
+      "epoch": 0.46474358974358976,
+      "grad_norm": 0.5617138743400574,
+      "learning_rate": 2.9127341548663437e-05,
+      "loss": 1.0532,
+      "step": 145
+    },
+    {
+      "epoch": 0.4807692307692308,
+      "grad_norm": 0.6172569990158081,
+      "learning_rate": 2.9036058796389484e-05,
+      "loss": 1.0175,
+      "step": 150
+    },
+    {
+      "epoch": 0.4967948717948718,
+      "grad_norm": 0.6247866749763489,
+      "learning_rate": 2.8940394066932122e-05,
+      "loss": 0.9961,
+      "step": 155
+    },
+    {
+      "epoch": 0.5128205128205128,
+      "grad_norm": 0.6410828232765198,
+      "learning_rate": 2.8840377226272102e-05,
+      "loss": 0.9782,
+      "step": 160
+    },
+    {
+      "epoch": 0.5288461538461539,
+      "grad_norm": 0.5969492793083191,
+      "learning_rate": 2.873603949909435e-05,
+      "loss": 0.9276,
+      "step": 165
+    },
+    {
+      "epoch": 0.5448717948717948,
+      "grad_norm": 0.6620483994483948,
+      "learning_rate": 2.862741345903985e-05,
+      "loss": 0.9186,
+      "step": 170
+    },
+    {
+      "epoch": 0.5608974358974359,
+      "grad_norm": 0.7593024373054504,
+      "learning_rate": 2.8514533018536286e-05,
+      "loss": 0.9674,
+      "step": 175
+    },
+    {
+      "epoch": 0.5769230769230769,
+      "grad_norm": 0.6714551448822021,
+      "learning_rate": 2.839743341821082e-05,
+      "loss": 0.9039,
+      "step": 180
+    },
+    {
+      "epoch": 0.592948717948718,
+      "grad_norm": 0.6707265377044678,
+      "learning_rate": 2.8276151215888127e-05,
+      "loss": 0.9058,
+      "step": 185
+    },
+    {
+      "epoch": 0.6089743589743589,
+      "grad_norm": 0.6786128282546997,
+      "learning_rate": 2.8150724275177312e-05,
+      "loss": 0.9086,
+      "step": 190
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 0.7407107353210449,
+      "learning_rate": 2.8021191753651025e-05,
+      "loss": 0.8393,
+      "step": 195
+    },
+    {
+      "epoch": 0.6410256410256411,
+      "grad_norm": 0.7203366756439209,
+      "learning_rate": 2.788759409062078e-05,
+      "loss": 0.8802,
+      "step": 200
+    },
+    {
+      "epoch": 0.657051282051282,
+      "grad_norm": 0.7305294275283813,
+      "learning_rate": 2.774997299451196e-05,
+      "loss": 0.8253,
+      "step": 205
+    },
+    {
+      "epoch": 0.6730769230769231,
+      "grad_norm": 0.8393168449401855,
+      "learning_rate": 2.760837142984274e-05,
+      "loss": 0.8447,
+      "step": 210
+    },
+    {
+      "epoch": 0.6891025641025641,
+      "grad_norm": 0.7442613244056702,
+      "learning_rate": 2.7462833603810768e-05,
+      "loss": 0.8864,
+      "step": 215
+    },
+    {
+      "epoch": 0.7051282051282052,
+      "grad_norm": 0.7570145726203918,
+      "learning_rate": 2.731340495249196e-05,
+      "loss": 0.8231,
+      "step": 220
+    },
+    {
+      "epoch": 0.7211538461538461,
+      "grad_norm": 0.7445229887962341,
+      "learning_rate": 2.7160132126655602e-05,
+      "loss": 0.8656,
+      "step": 225
+    },
+    {
+      "epoch": 0.7371794871794872,
+      "grad_norm": 0.8494444489479065,
+      "learning_rate": 2.700306297720026e-05,
+      "loss": 0.8239,
+      "step": 230
+    },
+    {
+      "epoch": 0.7532051282051282,
+      "grad_norm": 0.7834222912788391,
+      "learning_rate": 2.684224654021498e-05,
+      "loss": 0.83,
+      "step": 235
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 0.764818549156189,
+      "learning_rate": 2.667773302167053e-05,
+      "loss": 0.7838,
+      "step": 240
+    },
+    {
+      "epoch": 0.7852564102564102,
+      "grad_norm": 0.8579456806182861,
+      "learning_rate": 2.6509573781745376e-05,
+      "loss": 0.7771,
+      "step": 245
+    },
+    {
+      "epoch": 0.8012820512820513,
+      "grad_norm": 0.8856070637702942,
+      "learning_rate": 2.6337821318791303e-05,
+      "loss": 0.7701,
+      "step": 250
+    },
+    {
+      "epoch": 0.8173076923076923,
+      "grad_norm": 0.8341820240020752,
+      "learning_rate": 2.6162529252943772e-05,
+      "loss": 0.7709,
+      "step": 255
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.9213716983795166,
+      "learning_rate": 2.598375230938198e-05,
+      "loss": 0.7479,
+      "step": 260
+    },
+    {
+      "epoch": 0.8493589743589743,
+      "grad_norm": 0.8392142653465271,
+      "learning_rate": 2.5801546301244004e-05,
+      "loss": 0.8218,
+      "step": 265
+    },
+    {
+      "epoch": 0.8653846153846154,
+      "grad_norm": 0.8672253489494324,
+      "learning_rate": 2.561596811220225e-05,
+      "loss": 0.7455,
+      "step": 270
+    },
+    {
+      "epoch": 0.8814102564102564,
+      "grad_norm": 0.8946928381919861,
+      "learning_rate": 2.5427075678704676e-05,
+      "loss": 0.7391,
+      "step": 275
+    },
+    {
+      "epoch": 0.8974358974358975,
+      "grad_norm": 0.9163057804107666,
+      "learning_rate": 2.5234927971887388e-05,
+      "loss": 0.7352,
+      "step": 280
+    },
+    {
+      "epoch": 0.9134615384615384,
+      "grad_norm": 0.8829193115234375,
+      "learning_rate": 2.503958497916419e-05,
+      "loss": 0.6906,
+      "step": 285
+    },
+    {
+      "epoch": 0.9294871794871795,
+      "grad_norm": 0.9966152310371399,
+      "learning_rate": 2.484110768549885e-05,
+      "loss": 0.7109,
+      "step": 290
+    },
+    {
+      "epoch": 0.9455128205128205,
+      "grad_norm": 0.9102237820625305,
+      "learning_rate": 2.4639558054365917e-05,
+      "loss": 0.6811,
+      "step": 295
+    },
+    {
+      "epoch": 0.9615384615384616,
+      "grad_norm": 0.8688910603523254,
+      "learning_rate": 2.443499900840614e-05,
+      "loss": 0.6548,
+      "step": 300
+    },
+    {
+      "epoch": 0.9775641025641025,
+      "grad_norm": 0.8749269843101501,
+      "learning_rate": 2.422749440978232e-05,
+      "loss": 0.7052,
+      "step": 305
+    },
+    {
+      "epoch": 0.9935897435897436,
+      "grad_norm": 0.8675684332847595,
+      "learning_rate": 2.4017109040241948e-05,
+      "loss": 0.7035,
+      "step": 310
+    },
+    {
+      "epoch": 1.0096153846153846,
+      "grad_norm": 1.0981121063232422,
+      "learning_rate": 2.3803908580892694e-05,
+      "loss": 0.6495,
+      "step": 315
+    },
+    {
+      "epoch": 1.0256410256410255,
+      "grad_norm": 0.9418532848358154,
+      "learning_rate": 2.358795959169713e-05,
+      "loss": 0.601,
+      "step": 320
+    },
+    {
+      "epoch": 1.0416666666666667,
+      "grad_norm": 0.9367761015892029,
+      "learning_rate": 2.336932949069314e-05,
+      "loss": 0.6193,
+      "step": 325
+    },
+    {
+      "epoch": 1.0576923076923077,
+      "grad_norm": 0.9836122393608093,
+      "learning_rate": 2.314808653294634e-05,
+      "loss": 0.6624,
+      "step": 330
+    },
+    {
+      "epoch": 1.0737179487179487,
+      "grad_norm": 1.0578281879425049,
+      "learning_rate": 2.2924299789241255e-05,
+      "loss": 0.5822,
+      "step": 335
+    },
+    {
+      "epoch": 1.0897435897435896,
+      "grad_norm": 0.9923457503318787,
+      "learning_rate": 2.2698039124517843e-05,
+      "loss": 0.5778,
+      "step": 340
+    },
+    {
+      "epoch": 1.1057692307692308,
+      "grad_norm": 1.0091066360473633,
+      "learning_rate": 2.2469375176060017e-05,
+      "loss": 0.5569,
+      "step": 345
+    },
+    {
+      "epoch": 1.1217948717948718,
+      "grad_norm": 1.0267237424850464,
+      "learning_rate": 2.2238379331443118e-05,
+      "loss": 0.5858,
+      "step": 350
+    },
+    {
+      "epoch": 1.1378205128205128,
+      "grad_norm": 0.9796570539474487,
+      "learning_rate": 2.2005123706247113e-05,
+      "loss": 0.5575,
+      "step": 355
+    },
+    {
+      "epoch": 1.1538461538461537,
+      "grad_norm": 1.1447466611862183,
+      "learning_rate": 2.1769681121542527e-05,
+      "loss": 0.5793,
+      "step": 360
+    },
+    {
+      "epoch": 1.169871794871795,
+      "grad_norm": 0.991858959197998,
+      "learning_rate": 2.153212508115613e-05,
+      "loss": 0.5667,
+      "step": 365
+    },
+    {
+      "epoch": 1.185897435897436,
+      "grad_norm": 1.0337620973587036,
+      "learning_rate": 2.1292529748723436e-05,
+      "loss": 0.5945,
+      "step": 370
+    },
+    {
+      "epoch": 1.2019230769230769,
+      "grad_norm": 1.0859087705612183,
+      "learning_rate": 2.1050969924535267e-05,
+      "loss": 0.5264,
+      "step": 375
+    },
+    {
+      "epoch": 1.217948717948718,
+      "grad_norm": 1.0909671783447266,
+      "learning_rate": 2.080752102218553e-05,
+      "loss": 0.5654,
+      "step": 380
+    },
+    {
+      "epoch": 1.233974358974359,
+      "grad_norm": 1.1950091123580933,
+      "learning_rate": 2.05622590450275e-05,
+      "loss": 0.5281,
+      "step": 385
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.9471327066421509,
+      "learning_rate": 2.0315260562446048e-05,
+      "loss": 0.5661,
+      "step": 390
+    },
+    {
+      "epoch": 1.266025641025641,
+      "grad_norm": 1.0066086053848267,
+      "learning_rate": 2.0066602685953065e-05,
+      "loss": 0.5771,
+      "step": 395
+    },
+    {
+      "epoch": 1.282051282051282,
+      "grad_norm": 1.0472204685211182,
+      "learning_rate": 1.9816363045113748e-05,
+      "loss": 0.4999,
+      "step": 400
+    },
+    {
+      "epoch": 1.2980769230769231,
+      "grad_norm": 0.9724038243293762,
+      "learning_rate": 1.9564619763311043e-05,
+      "loss": 0.557,
+      "step": 405
+    },
+    {
+      "epoch": 1.314102564102564,
+      "grad_norm": 1.0106151103973389,
+      "learning_rate": 1.931145143335601e-05,
+      "loss": 0.5512,
+      "step": 410
+    },
+    {
+      "epoch": 1.330128205128205,
+      "grad_norm": 1.1549545526504517,
+      "learning_rate": 1.905693709295158e-05,
+      "loss": 0.5186,
+      "step": 415
+    },
+    {
+      "epoch": 1.3461538461538463,
+      "grad_norm": 0.9872467517852783,
+      "learning_rate": 1.880115620001743e-05,
+      "loss": 0.5484,
+      "step": 420
+    },
+    {
+      "epoch": 1.3621794871794872,
+      "grad_norm": 1.084097981452942,
+      "learning_rate": 1.854418860788369e-05,
+      "loss": 0.4849,
+      "step": 425
+    },
+    {
+      "epoch": 1.3782051282051282,
+      "grad_norm": 1.0635563135147095,
+      "learning_rate": 1.8286114540361192e-05,
+      "loss": 0.5089,
+      "step": 430
+    },
+    {
+      "epoch": 1.3942307692307692,
+      "grad_norm": 0.9852320551872253,
+      "learning_rate": 1.802701456669603e-05,
+      "loss": 0.511,
+      "step": 435
+    },
+    {
+      "epoch": 1.4102564102564101,
+      "grad_norm": 1.0456236600875854,
+      "learning_rate": 1.776696957641634e-05,
+      "loss": 0.5214,
+      "step": 440
+    },
+    {
+      "epoch": 1.4262820512820513,
+      "grad_norm": 1.1276960372924805,
+      "learning_rate": 1.7506060754079025e-05,
+      "loss": 0.5036,
+      "step": 445
+    },
+    {
+      "epoch": 1.4423076923076923,
+      "grad_norm": 1.050790548324585,
+      "learning_rate": 1.7244369553924408e-05,
+      "loss": 0.5092,
+      "step": 450
+    },
+    {
+      "epoch": 1.4583333333333333,
+      "grad_norm": 1.1323204040527344,
+      "learning_rate": 1.6981977674446692e-05,
+      "loss": 0.4922,
+      "step": 455
+    },
+    {
+      "epoch": 1.4743589743589745,
+      "grad_norm": 1.0770153999328613,
+      "learning_rate": 1.671896703288815e-05,
+      "loss": 0.4957,
+      "step": 460
+    },
+    {
+      "epoch": 1.4903846153846154,
+      "grad_norm": 1.0927847623825073,
+      "learning_rate": 1.6455419739665037e-05,
+      "loss": 0.4948,
+      "step": 465
+    },
+    {
+      "epoch": 1.5064102564102564,
+      "grad_norm": 1.1074756383895874,
+      "learning_rate": 1.6191418072733176e-05,
+      "loss": 0.4594,
+      "step": 470
+    },
+    {
+      "epoch": 1.5224358974358974,
+      "grad_norm": 1.1282039880752563,
+      "learning_rate": 1.5927044451901265e-05,
+      "loss": 0.4451,
+      "step": 475
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 1.1057143211364746,
+      "learning_rate": 1.5662381413099885e-05,
+      "loss": 0.4699,
+      "step": 480
+    },
+    {
+      "epoch": 1.5544871794871795,
+      "grad_norm": 1.0162197351455688,
+      "learning_rate": 1.5397511582614238e-05,
+      "loss": 0.4658,
+      "step": 485
+    },
+    {
+      "epoch": 1.5705128205128205,
+      "grad_norm": 1.1802141666412354,
+      "learning_rate": 1.5132517651288716e-05,
+      "loss": 0.4526,
+      "step": 490
+    },
+    {
+      "epoch": 1.5865384615384617,
+      "grad_norm": 1.1582833528518677,
+      "learning_rate": 1.4867482348711284e-05,
+      "loss": 0.5254,
+      "step": 495
+    },
+    {
+      "epoch": 1.6025641025641026,
+      "grad_norm": 1.0994395017623901,
+      "learning_rate": 1.4602488417385766e-05,
+      "loss": 0.4594,
+      "step": 500
+    },
+    {
+      "epoch": 1.6185897435897436,
+      "grad_norm": 1.1028861999511719,
+      "learning_rate": 1.4337618586900119e-05,
+      "loss": 0.4699,
+      "step": 505
+    },
+    {
+      "epoch": 1.6346153846153846,
+      "grad_norm": 1.2392289638519287,
+      "learning_rate": 1.4072955548098741e-05,
+      "loss": 0.4281,
+      "step": 510
+    },
+    {
+      "epoch": 1.6506410256410255,
+      "grad_norm": 1.2069967985153198,
+      "learning_rate": 1.3808581927266827e-05,
+      "loss": 0.4708,
+      "step": 515
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 1.2590070962905884,
+      "learning_rate": 1.354458026033497e-05,
+      "loss": 0.4482,
+      "step": 520
+    },
+    {
+      "epoch": 1.6826923076923077,
+      "grad_norm": 1.069236159324646,
+      "learning_rate": 1.3281032967111851e-05,
+      "loss": 0.3877,
+      "step": 525
+    },
+    {
+      "epoch": 1.6987179487179487,
+      "grad_norm": 1.1420222520828247,
+      "learning_rate": 1.3018022325553313e-05,
+      "loss": 0.4697,
+      "step": 530
+    },
+    {
+      "epoch": 1.7147435897435899,
+      "grad_norm": 1.1403447389602661,
+      "learning_rate": 1.2755630446075594e-05,
+      "loss": 0.4158,
+      "step": 535
+    },
+    {
+      "epoch": 1.7307692307692308,
+      "grad_norm": 1.1803133487701416,
+      "learning_rate": 1.2493939245920982e-05,
+      "loss": 0.435,
+      "step": 540
+    },
+    {
+      "epoch": 1.7467948717948718,
+      "grad_norm": 1.127475380897522,
+      "learning_rate": 1.2233030423583662e-05,
+      "loss": 0.4445,
+      "step": 545
+    },
+    {
+      "epoch": 1.7628205128205128,
+      "grad_norm": 1.141200065612793,
+      "learning_rate": 1.1972985433303976e-05,
+      "loss": 0.4063,
+      "step": 550
+    },
+    {
+      "epoch": 1.7788461538461537,
+      "grad_norm": 1.1613876819610596,
+      "learning_rate": 1.1713885459638814e-05,
+      "loss": 0.4352,
+      "step": 555
+    },
+    {
+      "epoch": 1.7948717948717947,
+      "grad_norm": 1.2905280590057373,
+      "learning_rate": 1.1455811392116308e-05,
+      "loss": 0.421,
+      "step": 560
+    },
+    {
+      "epoch": 1.810897435897436,
+      "grad_norm": 1.1915687322616577,
+      "learning_rate": 1.1198843799982572e-05,
+      "loss": 0.4298,
+      "step": 565
+    },
+    {
+      "epoch": 1.8269230769230769,
+      "grad_norm": 1.2459077835083008,
+      "learning_rate": 1.0943062907048421e-05,
+      "loss": 0.3987,
+      "step": 570
+    },
+    {
+      "epoch": 1.842948717948718,
+      "grad_norm": 1.1660549640655518,
+      "learning_rate": 1.0688548566643992e-05,
+      "loss": 0.4044,
+      "step": 575
+    },
+    {
+      "epoch": 1.858974358974359,
+      "grad_norm": 1.1100025177001953,
+      "learning_rate": 1.0435380236688958e-05,
+      "loss": 0.3785,
+      "step": 580
+    },
+    {
+      "epoch": 1.875,
+      "grad_norm": 1.1751682758331299,
+      "learning_rate": 1.0183636954886256e-05,
+      "loss": 0.38,
+      "step": 585
+    },
+    {
+      "epoch": 1.891025641025641,
+      "grad_norm": 1.3949114084243774,
+      "learning_rate": 9.933397314046936e-06,
+      "loss": 0.3911,
+      "step": 590
+    },
+    {
+      "epoch": 1.907051282051282,
+      "grad_norm": 1.1450115442276,
+      "learning_rate": 9.684739437553957e-06,
+      "loss": 0.3898,
+      "step": 595
+    },
+    {
+      "epoch": 1.9230769230769231,
+      "grad_norm": 1.113592267036438,
+      "learning_rate": 9.437740954972494e-06,
+      "loss": 0.446,
+      "step": 600
+    },
+    {
+      "epoch": 1.939102564102564,
+      "grad_norm": 1.133300542831421,
+      "learning_rate": 9.192478977814472e-06,
+      "loss": 0.3762,
+      "step": 605
+    },
+    {
+      "epoch": 1.9551282051282053,
+      "grad_norm": 1.2030713558197021,
+      "learning_rate": 8.949030075464729e-06,
+      "loss": 0.3695,
+      "step": 610
+    },
+    {
+      "epoch": 1.9711538461538463,
+      "grad_norm": 1.0890647172927856,
+      "learning_rate": 8.707470251276568e-06,
+      "loss": 0.4017,
+      "step": 615
+    },
+    {
+      "epoch": 1.9871794871794872,
+      "grad_norm": 1.2765699625015259,
+      "learning_rate": 8.467874918843875e-06,
+      "loss": 0.4257,
+      "step": 620
+    },
+    {
+      "epoch": 2.003205128205128,
+      "grad_norm": 1.0656068325042725,
+      "learning_rate": 8.230318878457474e-06,
+      "loss": 0.3691,
+      "step": 625
+    },
+    {
+      "epoch": 2.019230769230769,
+      "grad_norm": 1.3077999353408813,
+      "learning_rate": 7.994876293752893e-06,
+      "loss": 0.3018,
+      "step": 630
+    },
+    {
+      "epoch": 2.03525641025641,
+      "grad_norm": 1.1498775482177734,
+      "learning_rate": 7.761620668556888e-06,
+      "loss": 0.3319,
+      "step": 635
+    },
+    {
+      "epoch": 2.051282051282051,
+      "grad_norm": 1.1031510829925537,
+      "learning_rate": 7.530624823939984e-06,
+      "loss": 0.3082,
+      "step": 640
+    },
+    {
+      "epoch": 2.0673076923076925,
+      "grad_norm": 1.1444376707077026,
+      "learning_rate": 7.3019608754821635e-06,
+      "loss": 0.3435,
+      "step": 645
+    },
+    {
+      "epoch": 2.0833333333333335,
+      "grad_norm": 1.2205744981765747,
+      "learning_rate": 7.075700210758744e-06,
+      "loss": 0.3073,
+      "step": 650
+    },
+    {
+      "epoch": 2.0993589743589745,
+      "grad_norm": 1.155632495880127,
+      "learning_rate": 6.851913467053668e-06,
+      "loss": 0.3489,
+      "step": 655
+    },
+    {
+      "epoch": 2.1153846153846154,
+      "grad_norm": 1.2732203006744385,
+      "learning_rate": 6.63067050930686e-06,
+      "loss": 0.3606,
+      "step": 660
+    },
+    {
+      "epoch": 2.1314102564102564,
+      "grad_norm": 1.2430070638656616,
+      "learning_rate": 6.412040408302874e-06,
+      "loss": 0.3275,
+      "step": 665
+    },
+    {
+      "epoch": 2.1474358974358974,
+      "grad_norm": 1.1104846000671387,
+      "learning_rate": 6.19609141910731e-06,
+      "loss": 0.3179,
+      "step": 670
+    },
+    {
+      "epoch": 2.1634615384615383,
+      "grad_norm": 1.1903375387191772,
+      "learning_rate": 5.982890959758057e-06,
+      "loss": 0.3581,
+      "step": 675
+    },
+    {
+      "epoch": 2.1794871794871793,
+      "grad_norm": 1.1907094717025757,
+      "learning_rate": 5.772505590217679e-06,
+      "loss": 0.3271,
+      "step": 680
+    },
+    {
+      "epoch": 2.1955128205128207,
+      "grad_norm": 1.1349706649780273,
+      "learning_rate": 5.5650009915938675e-06,
+      "loss": 0.3107,
+      "step": 685
+    },
+    {
+      "epoch": 2.2115384615384617,
+      "grad_norm": 1.0588167905807495,
+      "learning_rate": 5.360441945634085e-06,
+      "loss": 0.2955,
+      "step": 690
+    },
+    {
+      "epoch": 2.2275641025641026,
+      "grad_norm": 1.1246256828308105,
+      "learning_rate": 5.158892314501157e-06,
+      "loss": 0.2791,
+      "step": 695
+    },
+    {
+      "epoch": 2.2435897435897436,
+      "grad_norm": 1.2544538974761963,
+      "learning_rate": 4.960415020835811e-06,
+      "loss": 0.3232,
+      "step": 700
+    },
+    {
+      "epoch": 2.2596153846153846,
+      "grad_norm": 1.260972499847412,
+      "learning_rate": 4.765072028112614e-06,
+      "loss": 0.2658,
+      "step": 705
+    },
+    {
+      "epoch": 2.2756410256410255,
+      "grad_norm": 1.1222094297409058,
+      "learning_rate": 4.5729243212953285e-06,
+      "loss": 0.2675,
+      "step": 710
+    },
+    {
+      "epoch": 2.2916666666666665,
+      "grad_norm": 1.1967344284057617,
+      "learning_rate": 4.384031887797753e-06,
+      "loss": 0.2945,
+      "step": 715
+    },
+    {
+      "epoch": 2.3076923076923075,
+      "grad_norm": 1.1902748346328735,
+      "learning_rate": 4.198453698755995e-06,
+      "loss": 0.2951,
+      "step": 720
+    },
+    {
+      "epoch": 2.323717948717949,
+      "grad_norm": 1.1482462882995605,
+      "learning_rate": 4.016247690618017e-06,
+      "loss": 0.3096,
+      "step": 725
+    },
+    {
+      "epoch": 2.33974358974359,
+      "grad_norm": 1.2069209814071655,
+      "learning_rate": 3.837470747056231e-06,
+      "loss": 0.2585,
+      "step": 730
+    },
+    {
+      "epoch": 2.355769230769231,
+      "grad_norm": 1.1015130281448364,
+      "learning_rate": 3.6621786812086953e-06,
+      "loss": 0.3171,
+      "step": 735
+    },
+    {
+      "epoch": 2.371794871794872,
+      "grad_norm": 1.2537384033203125,
+      "learning_rate": 3.490426218254629e-06,
+      "loss": 0.2667,
+      "step": 740
+    },
+    {
+      "epoch": 2.3878205128205128,
+      "grad_norm": 1.258795976638794,
+      "learning_rate": 3.322266978329468e-06,
+      "loss": 0.3154,
+      "step": 745
+    },
+    {
+      "epoch": 2.4038461538461537,
+      "grad_norm": 1.1808042526245117,
+      "learning_rate": 3.1577534597850254e-06,
+      "loss": 0.3144,
+      "step": 750
+    },
+    {
+      "epoch": 2.4198717948717947,
+      "grad_norm": 1.1231664419174194,
+      "learning_rate": 2.9969370227997434e-06,
+      "loss": 0.315,
+      "step": 755
+    },
+    {
+      "epoch": 2.435897435897436,
+      "grad_norm": 1.201605200767517,
+      "learning_rate": 2.8398678733444006e-06,
+      "loss": 0.262,
+      "step": 760
+    },
+    {
+      "epoch": 2.451923076923077,
+      "grad_norm": 1.2059309482574463,
+      "learning_rate": 2.68659504750804e-06,
+      "loss": 0.282,
+      "step": 765
+    },
+    {
+      "epoch": 2.467948717948718,
+      "grad_norm": 1.1277828216552734,
+      "learning_rate": 2.5371663961892345e-06,
+      "loss": 0.2945,
+      "step": 770
+    },
+    {
+      "epoch": 2.483974358974359,
+      "grad_norm": 1.327737808227539,
+      "learning_rate": 2.3916285701572586e-06,
+      "loss": 0.3232,
+      "step": 775
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 1.0484308004379272,
+      "learning_rate": 2.250027005488041e-06,
+      "loss": 0.2964,
+      "step": 780
+    },
+    {
+      "epoch": 2.516025641025641,
+      "grad_norm": 1.1470649242401123,
+      "learning_rate": 2.112405909379221e-06,
+      "loss": 0.3139,
+      "step": 785
+    },
+    {
+      "epoch": 2.532051282051282,
+      "grad_norm": 1.1853711605072021,
+      "learning_rate": 1.9788082463489743e-06,
+      "loss": 0.2839,
+      "step": 790
+    },
+    {
+      "epoch": 2.5480769230769234,
+      "grad_norm": 1.1611367464065552,
+      "learning_rate": 1.8492757248226933e-06,
+      "loss": 0.2719,
+      "step": 795
+    },
+    {
+      "epoch": 2.564102564102564,
+      "grad_norm": 1.2011940479278564,
+      "learning_rate": 1.7238487841118705e-06,
+      "loss": 0.2752,
+      "step": 800
+    },
+    {
+      "epoch": 2.5801282051282053,
+      "grad_norm": 1.1791577339172363,
+      "learning_rate": 1.602566581789184e-06,
+      "loss": 0.289,
+      "step": 805
+    },
+    {
+      "epoch": 2.5961538461538463,
+      "grad_norm": 1.1556838750839233,
+      "learning_rate": 1.4854669814637145e-06,
+      "loss": 0.2853,
+      "step": 810
+    },
+    {
+      "epoch": 2.6121794871794872,
+      "grad_norm": 1.1248109340667725,
+      "learning_rate": 1.3725865409601517e-06,
+      "loss": 0.2838,
+      "step": 815
+    },
+    {
+      "epoch": 2.628205128205128,
+      "grad_norm": 1.3234386444091797,
+      "learning_rate": 1.2639605009056486e-06,
+      "loss": 0.2742,
+      "step": 820
+    },
+    {
+      "epoch": 2.644230769230769,
+      "grad_norm": 1.0756906270980835,
+      "learning_rate": 1.1596227737279014e-06,
+      "loss": 0.2848,
+      "step": 825
+    },
+    {
+      "epoch": 2.66025641025641,
+      "grad_norm": 1.1553674936294556,
+      "learning_rate": 1.0596059330678742e-06,
+      "loss": 0.3109,
+      "step": 830
+    },
+    {
+      "epoch": 2.676282051282051,
+      "grad_norm": 1.1039059162139893,
+      "learning_rate": 9.639412036105166e-07,
+      "loss": 0.3418,
+      "step": 835
+    },
+    {
+      "epoch": 2.6923076923076925,
+      "grad_norm": 1.167670488357544,
+      "learning_rate": 8.726584513365638e-07,
+      "loss": 0.2877,
+      "step": 840
+    },
+    {
+      "epoch": 2.7083333333333335,
+      "grad_norm": 1.1737393140792847,
+      "learning_rate": 7.85786174198585e-07,
+      "loss": 0.2998,
+      "step": 845
+    },
+    {
+      "epoch": 2.7243589743589745,
+      "grad_norm": 1.201192855834961,
+      "learning_rate": 7.03351493224046e-07,
+      "loss": 0.2669,
+      "step": 850
+    },
+    {
+      "epoch": 2.7403846153846154,
+      "grad_norm": 1.1230095624923706,
+      "learning_rate": 6.253801440483225e-07,
+      "loss": 0.2708,
+      "step": 855
+    },
+    {
+      "epoch": 2.7564102564102564,
+      "grad_norm": 1.2249581813812256,
+      "learning_rate": 5.518964688801436e-07,
+      "loss": 0.2867,
+      "step": 860
+    },
+    {
+      "epoch": 2.7724358974358974,
+      "grad_norm": 1.1629477739334106,
+      "learning_rate": 4.829234089021229e-07,
+      "loss": 0.2491,
+      "step": 865
+    },
+    {
+      "epoch": 2.7884615384615383,
+      "grad_norm": 1.0632390975952148,
+      "learning_rate": 4.1848249710862597e-07,
+      "loss": 0.2784,
+      "step": 870
+    },
+    {
+      "epoch": 2.8044871794871797,
+      "grad_norm": 1.155190110206604,
+      "learning_rate": 3.585938515833237e-07,
+      "loss": 0.3098,
+      "step": 875
+    },
+    {
+      "epoch": 2.8205128205128203,
+      "grad_norm": 1.156097650527954,
+      "learning_rate": 3.032761692184105e-07,
+      "loss": 0.3094,
+      "step": 880
+    },
+    {
+      "epoch": 2.8365384615384617,
+      "grad_norm": 1.0742539167404175,
+      "learning_rate": 2.525467198775655e-07,
+      "loss": 0.2726,
+      "step": 885
+    },
+    {
+      "epoch": 2.8525641025641026,
+      "grad_norm": 1.2130104303359985,
+      "learning_rate": 2.064213410043886e-07,
+      "loss": 0.2475,
+      "step": 890
+    },
+    {
+      "epoch": 2.8685897435897436,
+      "grad_norm": 1.147454857826233,
+      "learning_rate": 1.6491443267803886e-07,
+      "loss": 0.2836,
+      "step": 895
+    },
+    {
+      "epoch": 2.8846153846153846,
+      "grad_norm": 1.095720887184143,
+      "learning_rate": 1.2803895311762404e-07,
+      "loss": 0.2899,
+      "step": 900
+    },
+    {
+      "epoch": 2.9006410256410255,
+      "grad_norm": 1.163079023361206,
+      "learning_rate": 9.580641463670326e-08,
+      "loss": 0.3307,
+      "step": 905
+    },
+    {
+      "epoch": 2.9166666666666665,
+      "grad_norm": 1.1863731145858765,
+      "learning_rate": 6.822688004922529e-08,
+      "loss": 0.273,
+      "step": 910
+    },
+    {
+      "epoch": 2.9326923076923075,
+      "grad_norm": 1.1555631160736084,
+      "learning_rate": 4.530895952796321e-08,
+      "loss": 0.2916,
+      "step": 915
+    },
+    {
+      "epoch": 2.948717948717949,
+      "grad_norm": 1.0983599424362183,
+      "learning_rate": 2.7059807916468003e-08,
+      "loss": 0.2929,
+      "step": 920
+    },
+    {
+      "epoch": 2.96474358974359,
+      "grad_norm": 1.0668097734451294,
+      "learning_rate": 1.3485122495380253e-08,
+      "loss": 0.2955,
+      "step": 925
+    },
+    {
+      "epoch": 2.980769230769231,
+      "grad_norm": 1.1247258186340332,
+      "learning_rate": 4.589141203752978e-09,
+      "loss": 0.2923,
+      "step": 930
+    },
+    {
+      "epoch": 2.996794871794872,
+      "grad_norm": 1.1967164278030396,
+      "learning_rate": 3.74641316008284e-10,
+      "loss": 0.2651,
+      "step": 935
+    },
+    {
+      "epoch": 3.0,
+      "step": 936,
+      "total_flos": 1.3183900712456684e+18,
+      "train_loss": 0.5964417562652857,
+      "train_runtime": 624.021,
+      "train_samples_per_second": 47.984,
+      "train_steps_per_second": 1.5
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 936,
+  "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": 1.3183900712456684e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

112_128_e3_3e-5/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fa8c55c3d5e618a551bf040d33d7f612c2f50d3629c171ff7dfe814c305b82c
+size 8273