Upload folder using huggingface_hub

108_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",
+    "v_proj",
+    "o_proj",
+    "k_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

108_128_e3_3e-5/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a69db227912c878ed5104c4393959b51c5330bd4aceced332f90bab813fc752d
+size 791751704

108_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
+}

108_128_e3_3e-5/all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.2804667426776023e+18,
+    "train_loss": 0.5722190376081967,
+    "train_runtime": 611.7948,
+    "train_samples": 9333,
+    "train_samples_per_second": 45.765,
+    "train_steps_per_second": 1.432
+}

108_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 %}

108_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
+}

108_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
+  }
+}

108_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
+}

108_128_e3_3e-5/train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.2804667426776023e+18,
+    "train_loss": 0.5722190376081967,
+    "train_runtime": 611.7948,
+    "train_samples": 9333,
+    "train_samples_per_second": 45.765,
+    "train_steps_per_second": 1.432
+}

108_128_e3_3e-5/trainer_state.json

@@ -0,0 +1,1268 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 876,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.017123287671232876,
+      "grad_norm": 3.5807762145996094,
+      "learning_rate": 2.7272727272727272e-06,
+      "loss": 1.5291,
+      "step": 5
+    },
+    {
+      "epoch": 0.03424657534246575,
+      "grad_norm": 3.3091728687286377,
+      "learning_rate": 6.136363636363637e-06,
+      "loss": 1.5898,
+      "step": 10
+    },
+    {
+      "epoch": 0.05136986301369863,
+      "grad_norm": 0.7176612615585327,
+      "learning_rate": 9.545454545454545e-06,
+      "loss": 1.3831,
+      "step": 15
+    },
+    {
+      "epoch": 0.0684931506849315,
+      "grad_norm": 0.47251248359680176,
+      "learning_rate": 1.2954545454545455e-05,
+      "loss": 1.347,
+      "step": 20
+    },
+    {
+      "epoch": 0.08561643835616438,
+      "grad_norm": 0.44420522451400757,
+      "learning_rate": 1.6363636363636363e-05,
+      "loss": 1.3318,
+      "step": 25
+    },
+    {
+      "epoch": 0.10273972602739725,
+      "grad_norm": 0.452013224363327,
+      "learning_rate": 1.9772727272727274e-05,
+      "loss": 1.3084,
+      "step": 30
+    },
+    {
+      "epoch": 0.11986301369863013,
+      "grad_norm": 0.4074641168117523,
+      "learning_rate": 2.318181818181818e-05,
+      "loss": 1.25,
+      "step": 35
+    },
+    {
+      "epoch": 0.136986301369863,
+      "grad_norm": 0.3674299716949463,
+      "learning_rate": 2.6590909090909093e-05,
+      "loss": 1.2546,
+      "step": 40
+    },
+    {
+      "epoch": 0.1541095890410959,
+      "grad_norm": 0.46588748693466187,
+      "learning_rate": 3e-05,
+      "loss": 1.2504,
+      "step": 45
+    },
+    {
+      "epoch": 0.17123287671232876,
+      "grad_norm": 0.3781576454639435,
+      "learning_rate": 2.999732673837156e-05,
+      "loss": 1.2171,
+      "step": 50
+    },
+    {
+      "epoch": 0.18835616438356165,
+      "grad_norm": 0.39464396238327026,
+      "learning_rate": 2.9989307906329936e-05,
+      "loss": 1.2329,
+      "step": 55
+    },
+    {
+      "epoch": 0.2054794520547945,
+      "grad_norm": 0.3637083172798157,
+      "learning_rate": 2.9975946362066596e-05,
+      "loss": 1.161,
+      "step": 60
+    },
+    {
+      "epoch": 0.2226027397260274,
+      "grad_norm": 0.34439516067504883,
+      "learning_rate": 2.995724686810202e-05,
+      "loss": 1.1548,
+      "step": 65
+    },
+    {
+      "epoch": 0.23972602739726026,
+      "grad_norm": 0.38400137424468994,
+      "learning_rate": 2.9933216089588158e-05,
+      "loss": 1.14,
+      "step": 70
+    },
+    {
+      "epoch": 0.2568493150684932,
+      "grad_norm": 0.4240066111087799,
+      "learning_rate": 2.9903862591932762e-05,
+      "loss": 1.1434,
+      "step": 75
+    },
+    {
+      "epoch": 0.273972602739726,
+      "grad_norm": 0.43173477053642273,
+      "learning_rate": 2.986919683774636e-05,
+      "loss": 1.0514,
+      "step": 80
+    },
+    {
+      "epoch": 0.2910958904109589,
+      "grad_norm": 0.4568031132221222,
+      "learning_rate": 2.9829231183113013e-05,
+      "loss": 1.0286,
+      "step": 85
+    },
+    {
+      "epoch": 0.3082191780821918,
+      "grad_norm": 0.45293739438056946,
+      "learning_rate": 2.9783979873186188e-05,
+      "loss": 1.0349,
+      "step": 90
+    },
+    {
+      "epoch": 0.3253424657534247,
+      "grad_norm": 0.4283130466938019,
+      "learning_rate": 2.973345903711128e-05,
+      "loss": 1.0239,
+      "step": 95
+    },
+    {
+      "epoch": 0.3424657534246575,
+      "grad_norm": 0.454668790102005,
+      "learning_rate": 2.9677686682276623e-05,
+      "loss": 1.0439,
+      "step": 100
+    },
+    {
+      "epoch": 0.3595890410958904,
+      "grad_norm": 0.5247825980186462,
+      "learning_rate": 2.9616682687895038e-05,
+      "loss": 1.0893,
+      "step": 105
+    },
+    {
+      "epoch": 0.3767123287671233,
+      "grad_norm": 0.4669569134712219,
+      "learning_rate": 2.9550468797918162e-05,
+      "loss": 1.0283,
+      "step": 110
+    },
+    {
+      "epoch": 0.3938356164383562,
+      "grad_norm": 0.5175986886024475,
+      "learning_rate": 2.947906861328618e-05,
+      "loss": 0.9868,
+      "step": 115
+    },
+    {
+      "epoch": 0.410958904109589,
+      "grad_norm": 0.5429822206497192,
+      "learning_rate": 2.9402507583515604e-05,
+      "loss": 0.9923,
+      "step": 120
+    },
+    {
+      "epoch": 0.4280821917808219,
+      "grad_norm": 0.5113222599029541,
+      "learning_rate": 2.9320812997628184e-05,
+      "loss": 0.9701,
+      "step": 125
+    },
+    {
+      "epoch": 0.4452054794520548,
+      "grad_norm": 0.5228748321533203,
+      "learning_rate": 2.923401397442415e-05,
+      "loss": 0.9191,
+      "step": 130
+    },
+    {
+      "epoch": 0.4623287671232877,
+      "grad_norm": 0.5837630033493042,
+      "learning_rate": 2.914214145210324e-05,
+      "loss": 0.9546,
+      "step": 135
+    },
+    {
+      "epoch": 0.4794520547945205,
+      "grad_norm": 0.5830627679824829,
+      "learning_rate": 2.9045228177237285e-05,
+      "loss": 0.9492,
+      "step": 140
+    },
+    {
+      "epoch": 0.4965753424657534,
+      "grad_norm": 0.6123244166374207,
+      "learning_rate": 2.894330869309814e-05,
+      "loss": 0.9228,
+      "step": 145
+    },
+    {
+      "epoch": 0.5136986301369864,
+      "grad_norm": 0.6550973057746887,
+      "learning_rate": 2.8836419327345297e-05,
+      "loss": 0.9001,
+      "step": 150
+    },
+    {
+      "epoch": 0.5308219178082192,
+      "grad_norm": 0.6780920028686523,
+      "learning_rate": 2.8724598179077413e-05,
+      "loss": 0.9136,
+      "step": 155
+    },
+    {
+      "epoch": 0.547945205479452,
+      "grad_norm": 0.6322837471961975,
+      "learning_rate": 2.8607885105252473e-05,
+      "loss": 0.9194,
+      "step": 160
+    },
+    {
+      "epoch": 0.565068493150685,
+      "grad_norm": 0.6611925959587097,
+      "learning_rate": 2.848632170648139e-05,
+      "loss": 0.9192,
+      "step": 165
+    },
+    {
+      "epoch": 0.5821917808219178,
+      "grad_norm": 0.6739152073860168,
+      "learning_rate": 2.8359951312200077e-05,
+      "loss": 0.8745,
+      "step": 170
+    },
+    {
+      "epoch": 0.5993150684931506,
+      "grad_norm": 0.6996152997016907,
+      "learning_rate": 2.8228818965225325e-05,
+      "loss": 0.8917,
+      "step": 175
+    },
+    {
+      "epoch": 0.6164383561643836,
+      "grad_norm": 0.6731507778167725,
+      "learning_rate": 2.8092971405700004e-05,
+      "loss": 0.8417,
+      "step": 180
+    },
+    {
+      "epoch": 0.6335616438356164,
+      "grad_norm": 0.7309231162071228,
+      "learning_rate": 2.7952457054433193e-05,
+      "loss": 0.8388,
+      "step": 185
+    },
+    {
+      "epoch": 0.6506849315068494,
+      "grad_norm": 0.7271023392677307,
+      "learning_rate": 2.780732599564137e-05,
+      "loss": 0.8218,
+      "step": 190
+    },
+    {
+      "epoch": 0.6678082191780822,
+      "grad_norm": 0.6842921376228333,
+      "learning_rate": 2.76576299590966e-05,
+      "loss": 0.7642,
+      "step": 195
+    },
+    {
+      "epoch": 0.684931506849315,
+      "grad_norm": 0.7116798758506775,
+      "learning_rate": 2.7503422301688276e-05,
+      "loss": 0.8356,
+      "step": 200
+    },
+    {
+      "epoch": 0.702054794520548,
+      "grad_norm": 0.7833829522132874,
+      "learning_rate": 2.7344757988404845e-05,
+      "loss": 0.8014,
+      "step": 205
+    },
+    {
+      "epoch": 0.7191780821917808,
+      "grad_norm": 0.7158685922622681,
+      "learning_rate": 2.718169357274238e-05,
+      "loss": 0.7942,
+      "step": 210
+    },
+    {
+      "epoch": 0.7363013698630136,
+      "grad_norm": 0.7951450347900391,
+      "learning_rate": 2.7014287176546922e-05,
+      "loss": 0.8405,
+      "step": 215
+    },
+    {
+      "epoch": 0.7534246575342466,
+      "grad_norm": 0.8001946806907654,
+      "learning_rate": 2.6842598469297846e-05,
+      "loss": 0.7866,
+      "step": 220
+    },
+    {
+      "epoch": 0.7705479452054794,
+      "grad_norm": 0.7733917832374573,
+      "learning_rate": 2.6666688646839574e-05,
+      "loss": 0.7758,
+      "step": 225
+    },
+    {
+      "epoch": 0.7876712328767124,
+      "grad_norm": 1.265261173248291,
+      "learning_rate": 2.6486620409569222e-05,
+      "loss": 0.7632,
+      "step": 230
+    },
+    {
+      "epoch": 0.8047945205479452,
+      "grad_norm": 0.8097914457321167,
+      "learning_rate": 2.6302457940088024e-05,
+      "loss": 0.8139,
+      "step": 235
+    },
+    {
+      "epoch": 0.821917808219178,
+      "grad_norm": 0.8714144229888916,
+      "learning_rate": 2.611426688032439e-05,
+      "loss": 0.7777,
+      "step": 240
+    },
+    {
+      "epoch": 0.839041095890411,
+      "grad_norm": 0.8730566501617432,
+      "learning_rate": 2.5922114308136826e-05,
+      "loss": 0.7323,
+      "step": 245
+    },
+    {
+      "epoch": 0.8561643835616438,
+      "grad_norm": 0.8538572788238525,
+      "learning_rate": 2.5726068713405084e-05,
+      "loss": 0.7418,
+      "step": 250
+    },
+    {
+      "epoch": 0.8732876712328768,
+      "grad_norm": 0.9105691313743591,
+      "learning_rate": 2.5526199973617932e-05,
+      "loss": 0.6692,
+      "step": 255
+    },
+    {
+      "epoch": 0.8904109589041096,
+      "grad_norm": 1.2026197910308838,
+      "learning_rate": 2.532257932896641e-05,
+      "loss": 0.7544,
+      "step": 260
+    },
+    {
+      "epoch": 0.9075342465753424,
+      "grad_norm": 0.8264621496200562,
+      "learning_rate": 2.511527935695133e-05,
+      "loss": 0.7603,
+      "step": 265
+    },
+    {
+      "epoch": 0.9246575342465754,
+      "grad_norm": 0.9663636684417725,
+      "learning_rate": 2.4904373946514136e-05,
+      "loss": 0.6813,
+      "step": 270
+    },
+    {
+      "epoch": 0.9417808219178082,
+      "grad_norm": 1.0044124126434326,
+      "learning_rate": 2.468993827170028e-05,
+      "loss": 0.7415,
+      "step": 275
+    },
+    {
+      "epoch": 0.958904109589041,
+      "grad_norm": 0.8889259696006775,
+      "learning_rate": 2.4472048764864602e-05,
+      "loss": 0.6579,
+      "step": 280
+    },
+    {
+      "epoch": 0.976027397260274,
+      "grad_norm": 0.9680169224739075,
+      "learning_rate": 2.425078308942815e-05,
+      "loss": 0.6719,
+      "step": 285
+    },
+    {
+      "epoch": 0.9931506849315068,
+      "grad_norm": 0.8709210753440857,
+      "learning_rate": 2.402622011219622e-05,
+      "loss": 0.6945,
+      "step": 290
+    },
+    {
+      "epoch": 1.0102739726027397,
+      "grad_norm": 0.9271451234817505,
+      "learning_rate": 2.379843987524753e-05,
+      "loss": 0.5937,
+      "step": 295
+    },
+    {
+      "epoch": 1.0273972602739727,
+      "grad_norm": 0.9400733709335327,
+      "learning_rate": 2.3567523567404346e-05,
+      "loss": 0.5772,
+      "step": 300
+    },
+    {
+      "epoch": 1.0445205479452055,
+      "grad_norm": 0.972431480884552,
+      "learning_rate": 2.3333553495294033e-05,
+      "loss": 0.5882,
+      "step": 305
+    },
+    {
+      "epoch": 1.0616438356164384,
+      "grad_norm": 1.0050362348556519,
+      "learning_rate": 2.309661305401205e-05,
+      "loss": 0.6248,
+      "step": 310
+    },
+    {
+      "epoch": 1.0787671232876712,
+      "grad_norm": 0.8770918846130371,
+      "learning_rate": 2.285678669739705e-05,
+      "loss": 0.6198,
+      "step": 315
+    },
+    {
+      "epoch": 1.095890410958904,
+      "grad_norm": 1.025366187095642,
+      "learning_rate": 2.2614159907928588e-05,
+      "loss": 0.5653,
+      "step": 320
+    },
+    {
+      "epoch": 1.1130136986301369,
+      "grad_norm": 0.9350120425224304,
+      "learning_rate": 2.236881916625816e-05,
+      "loss": 0.5649,
+      "step": 325
+    },
+    {
+      "epoch": 1.13013698630137,
+      "grad_norm": 0.9606553912162781,
+      "learning_rate": 2.212085192038453e-05,
+      "loss": 0.5369,
+      "step": 330
+    },
+    {
+      "epoch": 1.1472602739726028,
+      "grad_norm": 1.0226980447769165,
+      "learning_rate": 2.1870346554484154e-05,
+      "loss": 0.5471,
+      "step": 335
+    },
+    {
+      "epoch": 1.1643835616438356,
+      "grad_norm": 0.9591693878173828,
+      "learning_rate": 2.161739235740802e-05,
+      "loss": 0.5503,
+      "step": 340
+    },
+    {
+      "epoch": 1.1815068493150684,
+      "grad_norm": 0.9610605835914612,
+      "learning_rate": 2.1362079490855968e-05,
+      "loss": 0.4876,
+      "step": 345
+    },
+    {
+      "epoch": 1.1986301369863013,
+      "grad_norm": 0.991715669631958,
+      "learning_rate": 2.110449895723991e-05,
+      "loss": 0.525,
+      "step": 350
+    },
+    {
+      "epoch": 1.2157534246575343,
+      "grad_norm": 0.9738296270370483,
+      "learning_rate": 2.084474256724743e-05,
+      "loss": 0.5085,
+      "step": 355
+    },
+    {
+      "epoch": 1.2328767123287672,
+      "grad_norm": 1.0474423170089722,
+      "learning_rate": 2.0582902907117193e-05,
+      "loss": 0.5342,
+      "step": 360
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 1.1119288206100464,
+      "learning_rate": 2.0319073305638035e-05,
+      "loss": 0.48,
+      "step": 365
+    },
+    {
+      "epoch": 1.2671232876712328,
+      "grad_norm": 0.9946816563606262,
+      "learning_rate": 2.00533478008833e-05,
+      "loss": 0.5386,
+      "step": 370
+    },
+    {
+      "epoch": 1.2842465753424657,
+      "grad_norm": 0.9403849840164185,
+      "learning_rate": 1.97858211066924e-05,
+      "loss": 0.4838,
+      "step": 375
+    },
+    {
+      "epoch": 1.3013698630136985,
+      "grad_norm": 1.010441780090332,
+      "learning_rate": 1.9516588578911484e-05,
+      "loss": 0.4826,
+      "step": 380
+    },
+    {
+      "epoch": 1.3184931506849316,
+      "grad_norm": 1.0472416877746582,
+      "learning_rate": 1.9245746181405306e-05,
+      "loss": 0.5162,
+      "step": 385
+    },
+    {
+      "epoch": 1.3356164383561644,
+      "grad_norm": 1.007859706878662,
+      "learning_rate": 1.8973390451852348e-05,
+      "loss": 0.4804,
+      "step": 390
+    },
+    {
+      "epoch": 1.3527397260273972,
+      "grad_norm": 1.2064732313156128,
+      "learning_rate": 1.8699618467335428e-05,
+      "loss": 0.539,
+      "step": 395
+    },
+    {
+      "epoch": 1.36986301369863,
+      "grad_norm": 0.9618467092514038,
+      "learning_rate": 1.8424527809740028e-05,
+      "loss": 0.4904,
+      "step": 400
+    },
+    {
+      "epoch": 1.3869863013698631,
+      "grad_norm": 1.0133264064788818,
+      "learning_rate": 1.8148216530972714e-05,
+      "loss": 0.4753,
+      "step": 405
+    },
+    {
+      "epoch": 1.404109589041096,
+      "grad_norm": 0.9880134463310242,
+      "learning_rate": 1.7870783118012034e-05,
+      "loss": 0.4782,
+      "step": 410
+    },
+    {
+      "epoch": 1.4212328767123288,
+      "grad_norm": 1.0568008422851562,
+      "learning_rate": 1.7592326457804295e-05,
+      "loss": 0.4432,
+      "step": 415
+    },
+    {
+      "epoch": 1.4383561643835616,
+      "grad_norm": 1.0978039503097534,
+      "learning_rate": 1.7312945802016817e-05,
+      "loss": 0.4789,
+      "step": 420
+    },
+    {
+      "epoch": 1.4554794520547945,
+      "grad_norm": 1.0475904941558838,
+      "learning_rate": 1.7032740731661178e-05,
+      "loss": 0.5044,
+      "step": 425
+    },
+    {
+      "epoch": 1.4726027397260273,
+      "grad_norm": 1.1703317165374756,
+      "learning_rate": 1.675181112159907e-05,
+      "loss": 0.4944,
+      "step": 430
+    },
+    {
+      "epoch": 1.4897260273972603,
+      "grad_norm": 1.0947250127792358,
+      "learning_rate": 1.6470257104943414e-05,
+      "loss": 0.4517,
+      "step": 435
+    },
+    {
+      "epoch": 1.5068493150684932,
+      "grad_norm": 1.2484368085861206,
+      "learning_rate": 1.618817903736741e-05,
+      "loss": 0.4844,
+      "step": 440
+    },
+    {
+      "epoch": 1.523972602739726,
+      "grad_norm": 1.01430344581604,
+      "learning_rate": 1.5905677461334292e-05,
+      "loss": 0.418,
+      "step": 445
+    },
+    {
+      "epoch": 1.541095890410959,
+      "grad_norm": 1.0765246152877808,
+      "learning_rate": 1.5622853070260492e-05,
+      "loss": 0.474,
+      "step": 450
+    },
+    {
+      "epoch": 1.558219178082192,
+      "grad_norm": 1.195828914642334,
+      "learning_rate": 1.5339806672624982e-05,
+      "loss": 0.4931,
+      "step": 455
+    },
+    {
+      "epoch": 1.5753424657534247,
+      "grad_norm": 1.2522104978561401,
+      "learning_rate": 1.5056639156037597e-05,
+      "loss": 0.4156,
+      "step": 460
+    },
+    {
+      "epoch": 1.5924657534246576,
+      "grad_norm": 1.5915766954421997,
+      "learning_rate": 1.4773451451279213e-05,
+      "loss": 0.404,
+      "step": 465
+    },
+    {
+      "epoch": 1.6095890410958904,
+      "grad_norm": 1.119336485862732,
+      "learning_rate": 1.4490344496326463e-05,
+      "loss": 0.5165,
+      "step": 470
+    },
+    {
+      "epoch": 1.6267123287671232,
+      "grad_norm": 1.0856037139892578,
+      "learning_rate": 1.4207419200373942e-05,
+      "loss": 0.4388,
+      "step": 475
+    },
+    {
+      "epoch": 1.643835616438356,
+      "grad_norm": 1.198949933052063,
+      "learning_rate": 1.3924776407866634e-05,
+      "loss": 0.436,
+      "step": 480
+    },
+    {
+      "epoch": 1.660958904109589,
+      "grad_norm": 1.0617130994796753,
+      "learning_rate": 1.3642516862555433e-05,
+      "loss": 0.4294,
+      "step": 485
+    },
+    {
+      "epoch": 1.678082191780822,
+      "grad_norm": 1.1422547101974487,
+      "learning_rate": 1.3360741171588578e-05,
+      "loss": 0.4385,
+      "step": 490
+    },
+    {
+      "epoch": 1.6952054794520548,
+      "grad_norm": 1.066074252128601,
+      "learning_rate": 1.3079549769651737e-05,
+      "loss": 0.4393,
+      "step": 495
+    },
+    {
+      "epoch": 1.7123287671232876,
+      "grad_norm": 0.9132263660430908,
+      "learning_rate": 1.2799042883169576e-05,
+      "loss": 0.3903,
+      "step": 500
+    },
+    {
+      "epoch": 1.7294520547945207,
+      "grad_norm": 1.1798787117004395,
+      "learning_rate": 1.2519320494581581e-05,
+      "loss": 0.4102,
+      "step": 505
+    },
+    {
+      "epoch": 1.7465753424657535,
+      "grad_norm": 1.1041642427444458,
+      "learning_rate": 1.2240482306704831e-05,
+      "loss": 0.4169,
+      "step": 510
+    },
+    {
+      "epoch": 1.7636986301369864,
+      "grad_norm": 1.080991268157959,
+      "learning_rate": 1.1962627707196407e-05,
+      "loss": 0.4233,
+      "step": 515
+    },
+    {
+      "epoch": 1.7808219178082192,
+      "grad_norm": 0.9368865489959717,
+      "learning_rate": 1.1685855733128203e-05,
+      "loss": 0.3847,
+      "step": 520
+    },
+    {
+      "epoch": 1.797945205479452,
+      "grad_norm": 1.019186019897461,
+      "learning_rate": 1.1410265035686639e-05,
+      "loss": 0.3882,
+      "step": 525
+    },
+    {
+      "epoch": 1.8150684931506849,
+      "grad_norm": 1.120586633682251,
+      "learning_rate": 1.1135953845009914e-05,
+      "loss": 0.4098,
+      "step": 530
+    },
+    {
+      "epoch": 1.8321917808219177,
+      "grad_norm": 1.0819021463394165,
+      "learning_rate": 1.0863019935175415e-05,
+      "loss": 0.3812,
+      "step": 535
+    },
+    {
+      "epoch": 1.8493150684931505,
+      "grad_norm": 1.0242397785186768,
+      "learning_rate": 1.0591560589349568e-05,
+      "loss": 0.3861,
+      "step": 540
+    },
+    {
+      "epoch": 1.8664383561643836,
+      "grad_norm": 1.2031731605529785,
+      "learning_rate": 1.0321672565112767e-05,
+      "loss": 0.3772,
+      "step": 545
+    },
+    {
+      "epoch": 1.8835616438356164,
+      "grad_norm": 1.1985048055648804,
+      "learning_rate": 1.0053452059971555e-05,
+      "loss": 0.4125,
+      "step": 550
+    },
+    {
+      "epoch": 1.9006849315068495,
+      "grad_norm": 1.119626522064209,
+      "learning_rate": 9.786994677070523e-06,
+      "loss": 0.3984,
+      "step": 555
+    },
+    {
+      "epoch": 1.9178082191780823,
+      "grad_norm": 1.401971697807312,
+      "learning_rate": 9.52239539111598e-06,
+      "loss": 0.3851,
+      "step": 560
+    },
+    {
+      "epoch": 1.9349315068493151,
+      "grad_norm": 1.1090917587280273,
+      "learning_rate": 9.259748514523654e-06,
+      "loss": 0.3773,
+      "step": 565
+    },
+    {
+      "epoch": 1.952054794520548,
+      "grad_norm": 0.9235194325447083,
+      "learning_rate": 8.999147663802494e-06,
+      "loss": 0.356,
+      "step": 570
+    },
+    {
+      "epoch": 1.9691780821917808,
+      "grad_norm": 1.1582798957824707,
+      "learning_rate": 8.740685726186445e-06,
+      "loss": 0.4134,
+      "step": 575
+    },
+    {
+      "epoch": 1.9863013698630136,
+      "grad_norm": 1.1277037858963013,
+      "learning_rate": 8.484454826526199e-06,
+      "loss": 0.3499,
+      "step": 580
+    },
+    {
+      "epoch": 2.0034246575342465,
+      "grad_norm": 1.036704182624817,
+      "learning_rate": 8.2305462944527e-06,
+      "loss": 0.3822,
+      "step": 585
+    },
+    {
+      "epoch": 2.0205479452054793,
+      "grad_norm": 1.3104430437088013,
+      "learning_rate": 7.979050631824074e-06,
+      "loss": 0.3038,
+      "step": 590
+    },
+    {
+      "epoch": 2.037671232876712,
+      "grad_norm": 1.0896505117416382,
+      "learning_rate": 7.730057480467604e-06,
+      "loss": 0.2917,
+      "step": 595
+    },
+    {
+      "epoch": 2.0547945205479454,
+      "grad_norm": 1.1111066341400146,
+      "learning_rate": 7.4836555902282534e-06,
+      "loss": 0.2935,
+      "step": 600
+    },
+    {
+      "epoch": 2.0719178082191783,
+      "grad_norm": 1.0536811351776123,
+      "learning_rate": 7.239932787335147e-06,
+      "loss": 0.2996,
+      "step": 605
+    },
+    {
+      "epoch": 2.089041095890411,
+      "grad_norm": 1.0928549766540527,
+      "learning_rate": 6.9989759430972105e-06,
+      "loss": 0.2864,
+      "step": 610
+    },
+    {
+      "epoch": 2.106164383561644,
+      "grad_norm": 1.093943476676941,
+      "learning_rate": 6.760870942939202e-06,
+      "loss": 0.3072,
+      "step": 615
+    },
+    {
+      "epoch": 2.1232876712328768,
+      "grad_norm": 1.1354261636734009,
+      "learning_rate": 6.525702655789201e-06,
+      "loss": 0.3115,
+      "step": 620
+    },
+    {
+      "epoch": 2.1404109589041096,
+      "grad_norm": 1.266814947128296,
+      "learning_rate": 6.293554903828302e-06,
+      "loss": 0.3171,
+      "step": 625
+    },
+    {
+      "epoch": 2.1575342465753424,
+      "grad_norm": 1.0408298969268799,
+      "learning_rate": 6.0645104326135e-06,
+      "loss": 0.2856,
+      "step": 630
+    },
+    {
+      "epoch": 2.1746575342465753,
+      "grad_norm": 1.0795354843139648,
+      "learning_rate": 5.8386508815842746e-06,
+      "loss": 0.3023,
+      "step": 635
+    },
+    {
+      "epoch": 2.191780821917808,
+      "grad_norm": 1.1301606893539429,
+      "learning_rate": 5.61605675496345e-06,
+      "loss": 0.2984,
+      "step": 640
+    },
+    {
+      "epoch": 2.208904109589041,
+      "grad_norm": 1.1565942764282227,
+      "learning_rate": 5.396807393062681e-06,
+      "loss": 0.2965,
+      "step": 645
+    },
+    {
+      "epoch": 2.2260273972602738,
+      "grad_norm": 1.2035876512527466,
+      "learning_rate": 5.180980944002799e-06,
+      "loss": 0.285,
+      "step": 650
+    },
+    {
+      "epoch": 2.243150684931507,
+      "grad_norm": 1.1199487447738647,
+      "learning_rate": 4.9686543358590934e-06,
+      "loss": 0.3081,
+      "step": 655
+    },
+    {
+      "epoch": 2.26027397260274,
+      "grad_norm": 1.2621663808822632,
+      "learning_rate": 4.759903249241464e-06,
+      "loss": 0.2812,
+      "step": 660
+    },
+    {
+      "epoch": 2.2773972602739727,
+      "grad_norm": 1.1657969951629639,
+      "learning_rate": 4.554802090319209e-06,
+      "loss": 0.2966,
+      "step": 665
+    },
+    {
+      "epoch": 2.2945205479452055,
+      "grad_norm": 1.1780309677124023,
+      "learning_rate": 4.353423964300074e-06,
+      "loss": 0.3006,
+      "step": 670
+    },
+    {
+      "epoch": 2.3116438356164384,
+      "grad_norm": 1.0802596807479858,
+      "learning_rate": 4.155840649373015e-06,
+      "loss": 0.2774,
+      "step": 675
+    },
+    {
+      "epoch": 2.328767123287671,
+      "grad_norm": 1.1796915531158447,
+      "learning_rate": 3.96212257112391e-06,
+      "loss": 0.3042,
+      "step": 680
+    },
+    {
+      "epoch": 2.345890410958904,
+      "grad_norm": 1.1817134618759155,
+      "learning_rate": 3.772338777433482e-06,
+      "loss": 0.2585,
+      "step": 685
+    },
+    {
+      "epoch": 2.363013698630137,
+      "grad_norm": 1.1262065172195435,
+      "learning_rate": 3.5865569138661814e-06,
+      "loss": 0.2945,
+      "step": 690
+    },
+    {
+      "epoch": 2.3801369863013697,
+      "grad_norm": 1.2013483047485352,
+      "learning_rate": 3.4048431995589453e-06,
+      "loss": 0.3163,
+      "step": 695
+    },
+    {
+      "epoch": 2.3972602739726026,
+      "grad_norm": 1.316292643547058,
+      "learning_rate": 3.22726240361843e-06,
+      "loss": 0.3051,
+      "step": 700
+    },
+    {
+      "epoch": 2.4143835616438354,
+      "grad_norm": 1.1813979148864746,
+      "learning_rate": 3.053877822034995e-06,
+      "loss": 0.3077,
+      "step": 705
+    },
+    {
+      "epoch": 2.4315068493150687,
+      "grad_norm": 1.1264219284057617,
+      "learning_rate": 2.884751255121827e-06,
+      "loss": 0.2396,
+      "step": 710
+    },
+    {
+      "epoch": 2.4486301369863015,
+      "grad_norm": 1.0954492092132568,
+      "learning_rate": 2.7199429854871544e-06,
+      "loss": 0.2857,
+      "step": 715
+    },
+    {
+      "epoch": 2.4657534246575343,
+      "grad_norm": 1.169098138809204,
+      "learning_rate": 2.559511756547407e-06,
+      "loss": 0.2917,
+      "step": 720
+    },
+    {
+      "epoch": 2.482876712328767,
+      "grad_norm": 1.130307912826538,
+      "learning_rate": 2.403514751589032e-06,
+      "loss": 0.2565,
+      "step": 725
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 1.0802239179611206,
+      "learning_rate": 2.252007573386365e-06,
+      "loss": 0.253,
+      "step": 730
+    },
+    {
+      "epoch": 2.517123287671233,
+      "grad_norm": 1.1628029346466064,
+      "learning_rate": 2.105044224382854e-06,
+      "loss": 0.284,
+      "step": 735
+    },
+    {
+      "epoch": 2.5342465753424657,
+      "grad_norm": 1.0958950519561768,
+      "learning_rate": 1.9626770874427368e-06,
+      "loss": 0.2655,
+      "step": 740
+    },
+    {
+      "epoch": 2.5513698630136985,
+      "grad_norm": 1.1811082363128662,
+      "learning_rate": 1.8249569071799134e-06,
+      "loss": 0.2809,
+      "step": 745
+    },
+    {
+      "epoch": 2.5684931506849313,
+      "grad_norm": 1.0996111631393433,
+      "learning_rate": 1.69193277187083e-06,
+      "loss": 0.2413,
+      "step": 750
+    },
+    {
+      "epoch": 2.5856164383561646,
+      "grad_norm": 1.231388807296753,
+      "learning_rate": 1.5636520959577094e-06,
+      "loss": 0.2644,
+      "step": 755
+    },
+    {
+      "epoch": 2.602739726027397,
+      "grad_norm": 1.0639979839324951,
+      "learning_rate": 1.44016060314835e-06,
+      "loss": 0.245,
+      "step": 760
+    },
+    {
+      "epoch": 2.6198630136986303,
+      "grad_norm": 1.119203805923462,
+      "learning_rate": 1.321502310118649e-06,
+      "loss": 0.2712,
+      "step": 765
+    },
+    {
+      "epoch": 2.636986301369863,
+      "grad_norm": 1.1058067083358765,
+      "learning_rate": 1.2077195108234934e-06,
+      "loss": 0.3131,
+      "step": 770
+    },
+    {
+      "epoch": 2.654109589041096,
+      "grad_norm": 1.2589203119277954,
+      "learning_rate": 1.098852761421719e-06,
+      "loss": 0.258,
+      "step": 775
+    },
+    {
+      "epoch": 2.671232876712329,
+      "grad_norm": 1.1050349473953247,
+      "learning_rate": 9.949408658205072e-07,
+      "loss": 0.2727,
+      "step": 780
+    },
+    {
+      "epoch": 2.6883561643835616,
+      "grad_norm": 1.0997480154037476,
+      "learning_rate": 8.960208618442883e-07,
+      "loss": 0.2772,
+      "step": 785
+    },
+    {
+      "epoch": 2.7054794520547945,
+      "grad_norm": 1.1793811321258545,
+      "learning_rate": 8.021280080331816e-07,
+      "loss": 0.2813,
+      "step": 790
+    },
+    {
+      "epoch": 2.7226027397260273,
+      "grad_norm": 1.0853631496429443,
+      "learning_rate": 7.132957710756277e-07,
+      "loss": 0.2754,
+      "step": 795
+    },
+    {
+      "epoch": 2.73972602739726,
+      "grad_norm": 1.0766814947128296,
+      "learning_rate": 6.295558138796803e-07,
+      "loss": 0.2788,
+      "step": 800
+    },
+    {
+      "epoch": 2.756849315068493,
+      "grad_norm": 1.2465026378631592,
+      "learning_rate": 5.509379842872558e-07,
+      "loss": 0.2711,
+      "step": 805
+    },
+    {
+      "epoch": 2.7739726027397262,
+      "grad_norm": 1.1534792184829712,
+      "learning_rate": 4.774703044353051e-07,
+      "loss": 0.2554,
+      "step": 810
+    },
+    {
+      "epoch": 2.791095890410959,
+      "grad_norm": 1.0267202854156494,
+      "learning_rate": 4.091789607677582e-07,
+      "loss": 0.2526,
+      "step": 815
+    },
+    {
+      "epoch": 2.808219178082192,
+      "grad_norm": 1.115756869316101,
+      "learning_rate": 3.460882947017635e-07,
+      "loss": 0.2666,
+      "step": 820
+    },
+    {
+      "epoch": 2.8253424657534247,
+      "grad_norm": 1.1267921924591064,
+      "learning_rate": 2.8822079395154357e-07,
+      "loss": 0.2621,
+      "step": 825
+    },
+    {
+      "epoch": 2.8424657534246576,
+      "grad_norm": 1.113959550857544,
+      "learning_rate": 2.3559708451300622e-07,
+      "loss": 0.2774,
+      "step": 830
+    },
+    {
+      "epoch": 2.8595890410958904,
+      "grad_norm": 1.1377060413360596,
+      "learning_rate": 1.8823592331191242e-07,
+      "loss": 0.2757,
+      "step": 835
+    },
+    {
+      "epoch": 2.8767123287671232,
+      "grad_norm": 1.044373869895935,
+      "learning_rate": 1.4615419151824406e-07,
+      "loss": 0.2735,
+      "step": 840
+    },
+    {
+      "epoch": 2.893835616438356,
+      "grad_norm": 1.0506336688995361,
+      "learning_rate": 1.0936688852919042e-07,
+      "loss": 0.2847,
+      "step": 845
+    },
+    {
+      "epoch": 2.910958904109589,
+      "grad_norm": 1.1747305393218994,
+      "learning_rate": 7.788712662281317e-08,
+      "loss": 0.2553,
+      "step": 850
+    },
+    {
+      "epoch": 2.928082191780822,
+      "grad_norm": 1.16020667552948,
+      "learning_rate": 5.1726126284389886e-08,
+      "loss": 0.2604,
+      "step": 855
+    },
+    {
+      "epoch": 2.9452054794520546,
+      "grad_norm": 1.483211874961853,
+      "learning_rate": 3.0893212207036556e-08,
+      "loss": 0.262,
+      "step": 860
+    },
+    {
+      "epoch": 2.962328767123288,
+      "grad_norm": 1.1319483518600464,
+      "learning_rate": 1.5395809968061226e-08,
+      "loss": 0.2774,
+      "step": 865
+    },
+    {
+      "epoch": 2.9794520547945207,
+      "grad_norm": 1.1830449104309082,
+      "learning_rate": 5.239443382229481e-09,
+      "loss": 0.2794,
+      "step": 870
+    },
+    {
+      "epoch": 2.9965753424657535,
+      "grad_norm": 1.1832125186920166,
+      "learning_rate": 4.277325328860826e-10,
+      "loss": 0.2957,
+      "step": 875
+    },
+    {
+      "epoch": 3.0,
+      "step": 876,
+      "total_flos": 1.2804667426776023e+18,
+      "train_loss": 0.5722190376081967,
+      "train_runtime": 611.7948,
+      "train_samples_per_second": 45.765,
+      "train_steps_per_second": 1.432
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 876,
+  "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": 1.2804667426776023e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

108_128_e3_3e-5/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:641ae215a50ac643b53765911da1e13d7c584739744ba94bc4593627b7d0e310
+size 8273