Upload folder using huggingface_hub

109_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": [
+    "down_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj",
+    "k_proj",
+    "up_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

109_128_e3_3e-5/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17d5f05838b9408ebc5c57fcf2bdfe8825288cc77d999dae1cb81e79d27951eb
+size 791751704

109_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
+}

109_128_e3_3e-5/all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 2.0902059450816266e+18,
+    "train_loss": 0.5750568343942221,
+    "train_runtime": 964.5713,
+    "train_samples": 15528,
+    "train_samples_per_second": 48.295,
+    "train_steps_per_second": 1.512
+}

109_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 %}

109_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
+}

109_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
+  }
+}

109_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
+}

109_128_e3_3e-5/train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 2.0902059450816266e+18,
+    "train_loss": 0.5750568343942221,
+    "train_runtime": 964.5713,
+    "train_samples": 15528,
+    "train_samples_per_second": 48.295,
+    "train_steps_per_second": 1.512
+}

109_128_e3_3e-5/trainer_state.json

@@ -0,0 +1,2080 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1458,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.010298661174047374,
+      "grad_norm": 3.3823161125183105,
+      "learning_rate": 1.6438356164383561e-06,
+      "loss": 1.5504,
+      "step": 5
+    },
+    {
+      "epoch": 0.02059732234809475,
+      "grad_norm": 2.453728675842285,
+      "learning_rate": 3.6986301369863014e-06,
+      "loss": 1.5633,
+      "step": 10
+    },
+    {
+      "epoch": 0.030895983522142123,
+      "grad_norm": 1.3152430057525635,
+      "learning_rate": 5.753424657534246e-06,
+      "loss": 1.452,
+      "step": 15
+    },
+    {
+      "epoch": 0.0411946446961895,
+      "grad_norm": 0.6186983585357666,
+      "learning_rate": 7.808219178082192e-06,
+      "loss": 1.3814,
+      "step": 20
+    },
+    {
+      "epoch": 0.05149330587023687,
+      "grad_norm": 0.4865432679653168,
+      "learning_rate": 9.863013698630136e-06,
+      "loss": 1.4391,
+      "step": 25
+    },
+    {
+      "epoch": 0.061791967044284246,
+      "grad_norm": 0.427501916885376,
+      "learning_rate": 1.1917808219178083e-05,
+      "loss": 1.366,
+      "step": 30
+    },
+    {
+      "epoch": 0.07209062821833162,
+      "grad_norm": 0.38758790493011475,
+      "learning_rate": 1.3972602739726027e-05,
+      "loss": 1.3349,
+      "step": 35
+    },
+    {
+      "epoch": 0.082389289392379,
+      "grad_norm": 0.4395686089992523,
+      "learning_rate": 1.6027397260273974e-05,
+      "loss": 1.3165,
+      "step": 40
+    },
+    {
+      "epoch": 0.09268795056642637,
+      "grad_norm": 0.47586125135421753,
+      "learning_rate": 1.8082191780821916e-05,
+      "loss": 1.3125,
+      "step": 45
+    },
+    {
+      "epoch": 0.10298661174047374,
+      "grad_norm": 0.377314031124115,
+      "learning_rate": 2.0136986301369863e-05,
+      "loss": 1.2937,
+      "step": 50
+    },
+    {
+      "epoch": 0.11328527291452112,
+      "grad_norm": 0.5234676599502563,
+      "learning_rate": 2.219178082191781e-05,
+      "loss": 1.2764,
+      "step": 55
+    },
+    {
+      "epoch": 0.12358393408856849,
+      "grad_norm": 0.36369845271110535,
+      "learning_rate": 2.4246575342465755e-05,
+      "loss": 1.2344,
+      "step": 60
+    },
+    {
+      "epoch": 0.13388259526261587,
+      "grad_norm": 0.357096403837204,
+      "learning_rate": 2.6301369863013698e-05,
+      "loss": 1.231,
+      "step": 65
+    },
+    {
+      "epoch": 0.14418125643666324,
+      "grad_norm": 0.4017985761165619,
+      "learning_rate": 2.8356164383561644e-05,
+      "loss": 1.2552,
+      "step": 70
+    },
+    {
+      "epoch": 0.15447991761071062,
+      "grad_norm": 0.40629255771636963,
+      "learning_rate": 2.99999614111998e-05,
+      "loss": 1.2622,
+      "step": 75
+    },
+    {
+      "epoch": 0.164778578784758,
+      "grad_norm": 0.37567687034606934,
+      "learning_rate": 2.9998610824039904e-05,
+      "loss": 1.2019,
+      "step": 80
+    },
+    {
+      "epoch": 0.17507723995880536,
+      "grad_norm": 0.4077652096748352,
+      "learning_rate": 2.999533099541131e-05,
+      "loss": 1.1921,
+      "step": 85
+    },
+    {
+      "epoch": 0.18537590113285274,
+      "grad_norm": 0.43803462386131287,
+      "learning_rate": 2.9990122347191856e-05,
+      "loss": 1.195,
+      "step": 90
+    },
+    {
+      "epoch": 0.1956745623069001,
+      "grad_norm": 0.4093933403491974,
+      "learning_rate": 2.99829855493596e-05,
+      "loss": 1.1192,
+      "step": 95
+    },
+    {
+      "epoch": 0.2059732234809475,
+      "grad_norm": 0.4145336449146271,
+      "learning_rate": 2.9973921519906633e-05,
+      "loss": 1.1634,
+      "step": 100
+    },
+    {
+      "epoch": 0.21627188465499486,
+      "grad_norm": 0.43248122930526733,
+      "learning_rate": 2.9962931424721048e-05,
+      "loss": 1.1619,
+      "step": 105
+    },
+    {
+      "epoch": 0.22657054582904224,
+      "grad_norm": 0.47124388813972473,
+      "learning_rate": 2.995001667743691e-05,
+      "loss": 1.1545,
+      "step": 110
+    },
+    {
+      "epoch": 0.2368692070030896,
+      "grad_norm": 0.4486331641674042,
+      "learning_rate": 2.9935178939252478e-05,
+      "loss": 1.1434,
+      "step": 115
+    },
+    {
+      "epoch": 0.24716786817713698,
+      "grad_norm": 0.5017436146736145,
+      "learning_rate": 2.9918420118716478e-05,
+      "loss": 1.1577,
+      "step": 120
+    },
+    {
+      "epoch": 0.25746652935118436,
+      "grad_norm": 0.48066893219947815,
+      "learning_rate": 2.9899742371482663e-05,
+      "loss": 1.0614,
+      "step": 125
+    },
+    {
+      "epoch": 0.26776519052523173,
+      "grad_norm": 0.5081754922866821,
+      "learning_rate": 2.987914810003249e-05,
+      "loss": 1.0888,
+      "step": 130
+    },
+    {
+      "epoch": 0.2780638516992791,
+      "grad_norm": 0.4730719029903412,
+      "learning_rate": 2.9856639953366138e-05,
+      "loss": 1.1391,
+      "step": 135
+    },
+    {
+      "epoch": 0.2883625128733265,
+      "grad_norm": 0.5357269048690796,
+      "learning_rate": 2.9832220826661707e-05,
+      "loss": 1.1453,
+      "step": 140
+    },
+    {
+      "epoch": 0.29866117404737386,
+      "grad_norm": 0.5506560206413269,
+      "learning_rate": 2.980589386090289e-05,
+      "loss": 1.1306,
+      "step": 145
+    },
+    {
+      "epoch": 0.30895983522142123,
+      "grad_norm": 0.5453603267669678,
+      "learning_rate": 2.977766244247492e-05,
+      "loss": 1.1096,
+      "step": 150
+    },
+    {
+      "epoch": 0.3192584963954686,
+      "grad_norm": 0.5690296292304993,
+      "learning_rate": 2.9747530202728965e-05,
+      "loss": 1.0987,
+      "step": 155
+    },
+    {
+      "epoch": 0.329557157569516,
+      "grad_norm": 0.5686823725700378,
+      "learning_rate": 2.9715501017515083e-05,
+      "loss": 1.1112,
+      "step": 160
+    },
+    {
+      "epoch": 0.33985581874356335,
+      "grad_norm": 0.5019310712814331,
+      "learning_rate": 2.9681579006683635e-05,
+      "loss": 1.0609,
+      "step": 165
+    },
+    {
+      "epoch": 0.35015447991761073,
+      "grad_norm": 0.6643099784851074,
+      "learning_rate": 2.9645768533555387e-05,
+      "loss": 1.0873,
+      "step": 170
+    },
+    {
+      "epoch": 0.3604531410916581,
+      "grad_norm": 0.5490696430206299,
+      "learning_rate": 2.960807420436025e-05,
+      "loss": 1.0345,
+      "step": 175
+    },
+    {
+      "epoch": 0.3707518022657055,
+      "grad_norm": 0.6353822350502014,
+      "learning_rate": 2.956850086764478e-05,
+      "loss": 0.9968,
+      "step": 180
+    },
+    {
+      "epoch": 0.38105046343975285,
+      "grad_norm": 0.5472348928451538,
+      "learning_rate": 2.952705361364855e-05,
+      "loss": 1.007,
+      "step": 185
+    },
+    {
+      "epoch": 0.3913491246138002,
+      "grad_norm": 0.5896895527839661,
+      "learning_rate": 2.948373777364938e-05,
+      "loss": 1.0113,
+      "step": 190
+    },
+    {
+      "epoch": 0.4016477857878476,
+      "grad_norm": 0.6380281448364258,
+      "learning_rate": 2.9438558919277575e-05,
+      "loss": 1.0077,
+      "step": 195
+    },
+    {
+      "epoch": 0.411946446961895,
+      "grad_norm": 0.608356237411499,
+      "learning_rate": 2.9391522861799298e-05,
+      "loss": 1.0557,
+      "step": 200
+    },
+    {
+      "epoch": 0.42224510813594235,
+      "grad_norm": 0.604296088218689,
+      "learning_rate": 2.9342635651369033e-05,
+      "loss": 0.943,
+      "step": 205
+    },
+    {
+      "epoch": 0.4325437693099897,
+      "grad_norm": 0.6335668563842773,
+      "learning_rate": 2.9291903576251393e-05,
+      "loss": 0.9771,
+      "step": 210
+    },
+    {
+      "epoch": 0.4428424304840371,
+      "grad_norm": 0.6432603597640991,
+      "learning_rate": 2.9239333162012256e-05,
+      "loss": 0.9511,
+      "step": 215
+    },
+    {
+      "epoch": 0.45314109165808447,
+      "grad_norm": 0.663787305355072,
+      "learning_rate": 2.9184931170679413e-05,
+      "loss": 1.0233,
+      "step": 220
+    },
+    {
+      "epoch": 0.46343975283213185,
+      "grad_norm": 0.682392954826355,
+      "learning_rate": 2.912870459987277e-05,
+      "loss": 0.9927,
+      "step": 225
+    },
+    {
+      "epoch": 0.4737384140061792,
+      "grad_norm": 0.7003035545349121,
+      "learning_rate": 2.907066068190426e-05,
+      "loss": 0.9864,
+      "step": 230
+    },
+    {
+      "epoch": 0.4840370751802266,
+      "grad_norm": 0.7271223068237305,
+      "learning_rate": 2.901080688284757e-05,
+      "loss": 0.9295,
+      "step": 235
+    },
+    {
+      "epoch": 0.49433573635427397,
+      "grad_norm": 0.7064180374145508,
+      "learning_rate": 2.8949150901577783e-05,
+      "loss": 0.9624,
+      "step": 240
+    },
+    {
+      "epoch": 0.5046343975283213,
+      "grad_norm": 0.721971869468689,
+      "learning_rate": 2.888570066878109e-05,
+      "loss": 0.9238,
+      "step": 245
+    },
+    {
+      "epoch": 0.5149330587023687,
+      "grad_norm": 0.7580565810203552,
+      "learning_rate": 2.8820464345934708e-05,
+      "loss": 0.9442,
+      "step": 250
+    },
+    {
+      "epoch": 0.525231719876416,
+      "grad_norm": 0.7572207450866699,
+      "learning_rate": 2.8753450324257035e-05,
+      "loss": 0.9243,
+      "step": 255
+    },
+    {
+      "epoch": 0.5355303810504635,
+      "grad_norm": 0.8332147002220154,
+      "learning_rate": 2.868466722362836e-05,
+      "loss": 0.8602,
+      "step": 260
+    },
+    {
+      "epoch": 0.5458290422245108,
+      "grad_norm": 0.7519991993904114,
+      "learning_rate": 2.861412389148205e-05,
+      "loss": 0.895,
+      "step": 265
+    },
+    {
+      "epoch": 0.5561277033985582,
+      "grad_norm": 0.7677023410797119,
+      "learning_rate": 2.8541829401666575e-05,
+      "loss": 0.8985,
+      "step": 270
+    },
+    {
+      "epoch": 0.5664263645726055,
+      "grad_norm": 0.7989876866340637,
+      "learning_rate": 2.8467793053278318e-05,
+      "loss": 0.9046,
+      "step": 275
+    },
+    {
+      "epoch": 0.576725025746653,
+      "grad_norm": 0.7854174375534058,
+      "learning_rate": 2.8392024369465462e-05,
+      "loss": 0.8768,
+      "step": 280
+    },
+    {
+      "epoch": 0.5870236869207003,
+      "grad_norm": 0.8013259768486023,
+      "learning_rate": 2.8314533096203066e-05,
+      "loss": 0.8911,
+      "step": 285
+    },
+    {
+      "epoch": 0.5973223480947477,
+      "grad_norm": 0.79050213098526,
+      "learning_rate": 2.8235329201039424e-05,
+      "loss": 0.8873,
+      "step": 290
+    },
+    {
+      "epoch": 0.607621009268795,
+      "grad_norm": 0.8942621350288391,
+      "learning_rate": 2.8154422871813987e-05,
+      "loss": 0.8144,
+      "step": 295
+    },
+    {
+      "epoch": 0.6179196704428425,
+      "grad_norm": 0.939459502696991,
+      "learning_rate": 2.8071824515346904e-05,
+      "loss": 0.8547,
+      "step": 300
+    },
+    {
+      "epoch": 0.6282183316168898,
+      "grad_norm": 0.8087759613990784,
+      "learning_rate": 2.798754475610044e-05,
+      "loss": 0.841,
+      "step": 305
+    },
+    {
+      "epoch": 0.6385169927909372,
+      "grad_norm": 0.8379127979278564,
+      "learning_rate": 2.7901594434812326e-05,
+      "loss": 0.8158,
+      "step": 310
+    },
+    {
+      "epoch": 0.6488156539649845,
+      "grad_norm": 0.9374361038208008,
+      "learning_rate": 2.7813984607101396e-05,
+      "loss": 0.8323,
+      "step": 315
+    },
+    {
+      "epoch": 0.659114315139032,
+      "grad_norm": 0.8558433055877686,
+      "learning_rate": 2.7724726542045463e-05,
+      "loss": 0.8212,
+      "step": 320
+    },
+    {
+      "epoch": 0.6694129763130793,
+      "grad_norm": 0.8821544647216797,
+      "learning_rate": 2.7633831720731862e-05,
+      "loss": 0.8379,
+      "step": 325
+    },
+    {
+      "epoch": 0.6797116374871267,
+      "grad_norm": 0.8124337196350098,
+      "learning_rate": 2.75413118347806e-05,
+      "loss": 0.8437,
+      "step": 330
+    },
+    {
+      "epoch": 0.690010298661174,
+      "grad_norm": 0.8305995464324951,
+      "learning_rate": 2.744717878484053e-05,
+      "loss": 0.9127,
+      "step": 335
+    },
+    {
+      "epoch": 0.7003089598352215,
+      "grad_norm": 0.9433283805847168,
+      "learning_rate": 2.7351444679058573e-05,
+      "loss": 0.7848,
+      "step": 340
+    },
+    {
+      "epoch": 0.7106076210092688,
+      "grad_norm": 0.8368889093399048,
+      "learning_rate": 2.7254121831522288e-05,
+      "loss": 0.8419,
+      "step": 345
+    },
+    {
+      "epoch": 0.7209062821833162,
+      "grad_norm": 0.8212844729423523,
+      "learning_rate": 2.715522276067591e-05,
+      "loss": 0.8471,
+      "step": 350
+    },
+    {
+      "epoch": 0.7312049433573635,
+      "grad_norm": 0.8189219832420349,
+      "learning_rate": 2.7054760187710156e-05,
+      "loss": 0.8241,
+      "step": 355
+    },
+    {
+      "epoch": 0.741503604531411,
+      "grad_norm": 0.8989495038986206,
+      "learning_rate": 2.69527470349259e-05,
+      "loss": 0.8446,
+      "step": 360
+    },
+    {
+      "epoch": 0.7518022657054583,
+      "grad_norm": 0.8802312016487122,
+      "learning_rate": 2.684919642407202e-05,
+      "loss": 0.7928,
+      "step": 365
+    },
+    {
+      "epoch": 0.7621009268795057,
+      "grad_norm": 0.9473286271095276,
+      "learning_rate": 2.6744121674657563e-05,
+      "loss": 0.8258,
+      "step": 370
+    },
+    {
+      "epoch": 0.772399588053553,
+      "grad_norm": 0.8868286609649658,
+      "learning_rate": 2.6637536302238485e-05,
+      "loss": 0.7897,
+      "step": 375
+    },
+    {
+      "epoch": 0.7826982492276005,
+      "grad_norm": 0.8699805736541748,
+      "learning_rate": 2.6529454016679175e-05,
+      "loss": 0.777,
+      "step": 380
+    },
+    {
+      "epoch": 0.7929969104016478,
+      "grad_norm": 1.0012321472167969,
+      "learning_rate": 2.6419888720388984e-05,
+      "loss": 0.8186,
+      "step": 385
+    },
+    {
+      "epoch": 0.8032955715756952,
+      "grad_norm": 0.8919087052345276,
+      "learning_rate": 2.6308854506533975e-05,
+      "loss": 0.7626,
+      "step": 390
+    },
+    {
+      "epoch": 0.8135942327497425,
+      "grad_norm": 0.8587056398391724,
+      "learning_rate": 2.6196365657224166e-05,
+      "loss": 0.8127,
+      "step": 395
+    },
+    {
+      "epoch": 0.82389289392379,
+      "grad_norm": 0.8773703575134277,
+      "learning_rate": 2.6082436641676428e-05,
+      "loss": 0.7261,
+      "step": 400
+    },
+    {
+      "epoch": 0.8341915550978373,
+      "grad_norm": 0.9173433780670166,
+      "learning_rate": 2.5967082114353363e-05,
+      "loss": 0.7267,
+      "step": 405
+    },
+    {
+      "epoch": 0.8444902162718847,
+      "grad_norm": 1.0326611995697021,
+      "learning_rate": 2.5850316913078298e-05,
+      "loss": 0.7604,
+      "step": 410
+    },
+    {
+      "epoch": 0.854788877445932,
+      "grad_norm": 0.8668928742408752,
+      "learning_rate": 2.573215605712676e-05,
+      "loss": 0.7376,
+      "step": 415
+    },
+    {
+      "epoch": 0.8650875386199794,
+      "grad_norm": 0.9582007527351379,
+      "learning_rate": 2.561261474529455e-05,
+      "loss": 0.7902,
+      "step": 420
+    },
+    {
+      "epoch": 0.8753861997940268,
+      "grad_norm": 0.8808298110961914,
+      "learning_rate": 2.5491708353942773e-05,
+      "loss": 0.717,
+      "step": 425
+    },
+    {
+      "epoch": 0.8856848609680742,
+      "grad_norm": 1.0085995197296143,
+      "learning_rate": 2.5369452435019988e-05,
+      "loss": 0.7247,
+      "step": 430
+    },
+    {
+      "epoch": 0.8959835221421215,
+      "grad_norm": 0.8899257183074951,
+      "learning_rate": 2.52458627140618e-05,
+      "loss": 0.6582,
+      "step": 435
+    },
+    {
+      "epoch": 0.9062821833161689,
+      "grad_norm": 0.9038539528846741,
+      "learning_rate": 2.512095508816812e-05,
+      "loss": 0.7288,
+      "step": 440
+    },
+    {
+      "epoch": 0.9165808444902163,
+      "grad_norm": 0.9046438336372375,
+      "learning_rate": 2.499474562395835e-05,
+      "loss": 0.6563,
+      "step": 445
+    },
+    {
+      "epoch": 0.9268795056642637,
+      "grad_norm": 0.9700610041618347,
+      "learning_rate": 2.4867250555504757e-05,
+      "loss": 0.7074,
+      "step": 450
+    },
+    {
+      "epoch": 0.937178166838311,
+      "grad_norm": 0.9176031947135925,
+      "learning_rate": 2.4738486282244333e-05,
+      "loss": 0.719,
+      "step": 455
+    },
+    {
+      "epoch": 0.9474768280123584,
+      "grad_norm": 0.8907363414764404,
+      "learning_rate": 2.460846936686935e-05,
+      "loss": 0.6478,
+      "step": 460
+    },
+    {
+      "epoch": 0.9577754891864058,
+      "grad_norm": 0.9568797945976257,
+      "learning_rate": 2.4477216533196954e-05,
+      "loss": 0.7165,
+      "step": 465
+    },
+    {
+      "epoch": 0.9680741503604532,
+      "grad_norm": 0.9160274267196655,
+      "learning_rate": 2.4344744664018e-05,
+      "loss": 0.7126,
+      "step": 470
+    },
+    {
+      "epoch": 0.9783728115345005,
+      "grad_norm": 0.9830437898635864,
+      "learning_rate": 2.421107079892544e-05,
+      "loss": 0.7068,
+      "step": 475
+    },
+    {
+      "epoch": 0.9886714727085479,
+      "grad_norm": 1.0129786729812622,
+      "learning_rate": 2.4076212132122586e-05,
+      "loss": 0.6614,
+      "step": 480
+    },
+    {
+      "epoch": 0.9989701338825953,
+      "grad_norm": 0.9700234532356262,
+      "learning_rate": 2.394018601021143e-05,
+      "loss": 0.6966,
+      "step": 485
+    },
+    {
+      "epoch": 1.008238928939238,
+      "grad_norm": 1.289340853691101,
+      "learning_rate": 2.3803009929961393e-05,
+      "loss": 0.5697,
+      "step": 490
+    },
+    {
+      "epoch": 1.0185375901132854,
+      "grad_norm": 0.9230129718780518,
+      "learning_rate": 2.3664701536058746e-05,
+      "loss": 0.6115,
+      "step": 495
+    },
+    {
+      "epoch": 1.0288362512873326,
+      "grad_norm": 1.0552504062652588,
+      "learning_rate": 2.352527861883702e-05,
+      "loss": 0.5883,
+      "step": 500
+    },
+    {
+      "epoch": 1.03913491246138,
+      "grad_norm": 1.0811355113983154,
+      "learning_rate": 2.3384759111988657e-05,
+      "loss": 0.5755,
+      "step": 505
+    },
+    {
+      "epoch": 1.0494335736354274,
+      "grad_norm": 1.1151247024536133,
+      "learning_rate": 2.3243161090258236e-05,
+      "loss": 0.5683,
+      "step": 510
+    },
+    {
+      "epoch": 1.0597322348094749,
+      "grad_norm": 0.9552525877952576,
+      "learning_rate": 2.3100502767117566e-05,
+      "loss": 0.5772,
+      "step": 515
+    },
+    {
+      "epoch": 1.070030895983522,
+      "grad_norm": 1.019511342048645,
+      "learning_rate": 2.2956802492422925e-05,
+      "loss": 0.613,
+      "step": 520
+    },
+    {
+      "epoch": 1.0803295571575695,
+      "grad_norm": 1.0493453741073608,
+      "learning_rate": 2.281207875005473e-05,
+      "loss": 0.5645,
+      "step": 525
+    },
+    {
+      "epoch": 1.090628218331617,
+      "grad_norm": 0.9346718788146973,
+      "learning_rate": 2.266635015554002e-05,
+      "loss": 0.5323,
+      "step": 530
+    },
+    {
+      "epoch": 1.1009268795056641,
+      "grad_norm": 1.0112980604171753,
+      "learning_rate": 2.2519635453657958e-05,
+      "loss": 0.5505,
+      "step": 535
+    },
+    {
+      "epoch": 1.1112255406797116,
+      "grad_norm": 1.0268110036849976,
+      "learning_rate": 2.237195351602874e-05,
+      "loss": 0.6064,
+      "step": 540
+    },
+    {
+      "epoch": 1.121524201853759,
+      "grad_norm": 1.1547778844833374,
+      "learning_rate": 2.222332333868618e-05,
+      "loss": 0.5805,
+      "step": 545
+    },
+    {
+      "epoch": 1.1318228630278064,
+      "grad_norm": 1.0207399129867554,
+      "learning_rate": 2.207376403963426e-05,
+      "loss": 0.575,
+      "step": 550
+    },
+    {
+      "epoch": 1.1421215242018539,
+      "grad_norm": 1.0759607553482056,
+      "learning_rate": 2.1923294856388058e-05,
+      "loss": 0.5932,
+      "step": 555
+    },
+    {
+      "epoch": 1.152420185375901,
+      "grad_norm": 1.0854506492614746,
+      "learning_rate": 2.1771935143499233e-05,
+      "loss": 0.5666,
+      "step": 560
+    },
+    {
+      "epoch": 1.1627188465499485,
+      "grad_norm": 0.9875121116638184,
+      "learning_rate": 2.161970437006651e-05,
+      "loss": 0.5669,
+      "step": 565
+    },
+    {
+      "epoch": 1.173017507723996,
+      "grad_norm": 1.0967878103256226,
+      "learning_rate": 2.146662211723139e-05,
+      "loss": 0.5305,
+      "step": 570
+    },
+    {
+      "epoch": 1.1833161688980431,
+      "grad_norm": 1.1200672388076782,
+      "learning_rate": 2.131270807565948e-05,
+      "loss": 0.5249,
+      "step": 575
+    },
+    {
+      "epoch": 1.1936148300720906,
+      "grad_norm": 1.0108928680419922,
+      "learning_rate": 2.115798204300771e-05,
+      "loss": 0.5805,
+      "step": 580
+    },
+    {
+      "epoch": 1.203913491246138,
+      "grad_norm": 1.158383846282959,
+      "learning_rate": 2.1002463921377818e-05,
+      "loss": 0.5276,
+      "step": 585
+    },
+    {
+      "epoch": 1.2142121524201854,
+      "grad_norm": 1.0787115097045898,
+      "learning_rate": 2.0846173714756372e-05,
+      "loss": 0.5785,
+      "step": 590
+    },
+    {
+      "epoch": 1.2245108135942329,
+      "grad_norm": 0.9920424222946167,
+      "learning_rate": 2.068913152644169e-05,
+      "loss": 0.5383,
+      "step": 595
+    },
+    {
+      "epoch": 1.23480947476828,
+      "grad_norm": 0.9930887222290039,
+      "learning_rate": 2.0531357556457994e-05,
+      "loss": 0.5072,
+      "step": 600
+    },
+    {
+      "epoch": 1.2451081359423275,
+      "grad_norm": 1.0695741176605225,
+      "learning_rate": 2.037287209895713e-05,
+      "loss": 0.4986,
+      "step": 605
+    },
+    {
+      "epoch": 1.255406797116375,
+      "grad_norm": 1.159101128578186,
+      "learning_rate": 2.0213695539608182e-05,
+      "loss": 0.5523,
+      "step": 610
+    },
+    {
+      "epoch": 1.2657054582904221,
+      "grad_norm": 1.1912457942962646,
+      "learning_rate": 2.005384835297527e-05,
+      "loss": 0.5469,
+      "step": 615
+    },
+    {
+      "epoch": 1.2760041194644696,
+      "grad_norm": 1.1158777475357056,
+      "learning_rate": 1.989335109988397e-05,
+      "loss": 0.5356,
+      "step": 620
+    },
+    {
+      "epoch": 1.286302780638517,
+      "grad_norm": 1.0937846899032593,
+      "learning_rate": 1.973222442477662e-05,
+      "loss": 0.4849,
+      "step": 625
+    },
+    {
+      "epoch": 1.2966014418125644,
+      "grad_norm": 1.1300711631774902,
+      "learning_rate": 1.9570489053056868e-05,
+      "loss": 0.508,
+      "step": 630
+    },
+    {
+      "epoch": 1.3069001029866119,
+      "grad_norm": 1.091271996498108,
+      "learning_rate": 1.9408165788423776e-05,
+      "loss": 0.5272,
+      "step": 635
+    },
+    {
+      "epoch": 1.317198764160659,
+      "grad_norm": 1.1383930444717407,
+      "learning_rate": 1.9245275510195908e-05,
+      "loss": 0.5032,
+      "step": 640
+    },
+    {
+      "epoch": 1.3274974253347065,
+      "grad_norm": 1.0633445978164673,
+      "learning_rate": 1.908183917062567e-05,
+      "loss": 0.4966,
+      "step": 645
+    },
+    {
+      "epoch": 1.337796086508754,
+      "grad_norm": 1.1198703050613403,
+      "learning_rate": 1.8917877792204238e-05,
+      "loss": 0.4877,
+      "step": 650
+    },
+    {
+      "epoch": 1.3480947476828011,
+      "grad_norm": 1.00174081325531,
+      "learning_rate": 1.8753412464957505e-05,
+      "loss": 0.4709,
+      "step": 655
+    },
+    {
+      "epoch": 1.3583934088568486,
+      "grad_norm": 1.314014196395874,
+      "learning_rate": 1.8588464343733287e-05,
+      "loss": 0.4688,
+      "step": 660
+    },
+    {
+      "epoch": 1.368692070030896,
+      "grad_norm": 1.0839755535125732,
+      "learning_rate": 1.8423054645480228e-05,
+      "loss": 0.5234,
+      "step": 665
+    },
+    {
+      "epoch": 1.3789907312049434,
+      "grad_norm": 1.1334782838821411,
+      "learning_rate": 1.825720464651871e-05,
+      "loss": 0.4832,
+      "step": 670
+    },
+    {
+      "epoch": 1.3892893923789909,
+      "grad_norm": 1.0330963134765625,
+      "learning_rate": 1.8090935679804126e-05,
+      "loss": 0.5063,
+      "step": 675
+    },
+    {
+      "epoch": 1.399588053553038,
+      "grad_norm": 1.0906732082366943,
+      "learning_rate": 1.7924269132182855e-05,
+      "loss": 0.4959,
+      "step": 680
+    },
+    {
+      "epoch": 1.4098867147270855,
+      "grad_norm": 1.056031584739685,
+      "learning_rate": 1.7757226441641303e-05,
+      "loss": 0.4889,
+      "step": 685
+    },
+    {
+      "epoch": 1.420185375901133,
+      "grad_norm": 1.073580026626587,
+      "learning_rate": 1.758982909454841e-05,
+      "loss": 0.4748,
+      "step": 690
+    },
+    {
+      "epoch": 1.4304840370751801,
+      "grad_norm": 1.1307774782180786,
+      "learning_rate": 1.7422098622891873e-05,
+      "loss": 0.4671,
+      "step": 695
+    },
+    {
+      "epoch": 1.4407826982492276,
+      "grad_norm": 1.1314843893051147,
+      "learning_rate": 1.725405660150854e-05,
+      "loss": 0.4769,
+      "step": 700
+    },
+    {
+      "epoch": 1.451081359423275,
+      "grad_norm": 1.0799882411956787,
+      "learning_rate": 1.7085724645309276e-05,
+      "loss": 0.4654,
+      "step": 705
+    },
+    {
+      "epoch": 1.4613800205973224,
+      "grad_norm": 1.1364656686782837,
+      "learning_rate": 1.6917124406498697e-05,
+      "loss": 0.4473,
+      "step": 710
+    },
+    {
+      "epoch": 1.4716786817713698,
+      "grad_norm": 1.1196246147155762,
+      "learning_rate": 1.6748277571790066e-05,
+      "loss": 0.4791,
+      "step": 715
+    },
+    {
+      "epoch": 1.481977342945417,
+      "grad_norm": 1.0974736213684082,
+      "learning_rate": 1.6579205859615797e-05,
+      "loss": 0.502,
+      "step": 720
+    },
+    {
+      "epoch": 1.4922760041194645,
+      "grad_norm": 1.1675491333007812,
+      "learning_rate": 1.640993101733383e-05,
+      "loss": 0.4476,
+      "step": 725
+    },
+    {
+      "epoch": 1.502574665293512,
+      "grad_norm": 1.196878433227539,
+      "learning_rate": 1.624047481843034e-05,
+      "loss": 0.4397,
+      "step": 730
+    },
+    {
+      "epoch": 1.5128733264675591,
+      "grad_norm": 1.3178632259368896,
+      "learning_rate": 1.6070859059719028e-05,
+      "loss": 0.459,
+      "step": 735
+    },
+    {
+      "epoch": 1.5231719876416066,
+      "grad_norm": 1.1056122779846191,
+      "learning_rate": 1.5901105558537472e-05,
+      "loss": 0.4252,
+      "step": 740
+    },
+    {
+      "epoch": 1.533470648815654,
+      "grad_norm": 1.1540517807006836,
+      "learning_rate": 1.573123614994078e-05,
+      "loss": 0.496,
+      "step": 745
+    },
+    {
+      "epoch": 1.5437693099897012,
+      "grad_norm": 1.0923795700073242,
+      "learning_rate": 1.5561272683893016e-05,
+      "loss": 0.4283,
+      "step": 750
+    },
+    {
+      "epoch": 1.5540679711637488,
+      "grad_norm": 1.1902728080749512,
+      "learning_rate": 1.5391237022456636e-05,
+      "loss": 0.4605,
+      "step": 755
+    },
+    {
+      "epoch": 1.564366632337796,
+      "grad_norm": 1.1004552841186523,
+      "learning_rate": 1.5221151036980478e-05,
+      "loss": 0.4535,
+      "step": 760
+    },
+    {
+      "epoch": 1.5746652935118435,
+      "grad_norm": 1.1242482662200928,
+      "learning_rate": 1.5051036605286436e-05,
+      "loss": 0.4424,
+      "step": 765
+    },
+    {
+      "epoch": 1.584963954685891,
+      "grad_norm": 1.0503530502319336,
+      "learning_rate": 1.4880915608855402e-05,
+      "loss": 0.4138,
+      "step": 770
+    },
+    {
+      "epoch": 1.5952626158599381,
+      "grad_norm": 1.2440671920776367,
+      "learning_rate": 1.4710809930012672e-05,
+      "loss": 0.4639,
+      "step": 775
+    },
+    {
+      "epoch": 1.6055612770339855,
+      "grad_norm": 1.1396325826644897,
+      "learning_rate": 1.4540741449113255e-05,
+      "loss": 0.4726,
+      "step": 780
+    },
+    {
+      "epoch": 1.615859938208033,
+      "grad_norm": 1.0694893598556519,
+      "learning_rate": 1.4370732041727495e-05,
+      "loss": 0.4092,
+      "step": 785
+    },
+    {
+      "epoch": 1.6261585993820802,
+      "grad_norm": 1.331519365310669,
+      "learning_rate": 1.4200803575827193e-05,
+      "loss": 0.4554,
+      "step": 790
+    },
+    {
+      "epoch": 1.6364572605561278,
+      "grad_norm": 1.1854562759399414,
+      "learning_rate": 1.4030977908972842e-05,
+      "loss": 0.4412,
+      "step": 795
+    },
+    {
+      "epoch": 1.646755921730175,
+      "grad_norm": 1.1538197994232178,
+      "learning_rate": 1.386127688550206e-05,
+      "loss": 0.4241,
+      "step": 800
+    },
+    {
+      "epoch": 1.6570545829042225,
+      "grad_norm": 1.1079086065292358,
+      "learning_rate": 1.3691722333719873e-05,
+      "loss": 0.463,
+      "step": 805
+    },
+    {
+      "epoch": 1.66735324407827,
+      "grad_norm": 1.124470829963684,
+      "learning_rate": 1.3522336063090911e-05,
+      "loss": 0.4311,
+      "step": 810
+    },
+    {
+      "epoch": 1.677651905252317,
+      "grad_norm": 1.2267584800720215,
+      "learning_rate": 1.335313986143416e-05,
+      "loss": 0.4228,
+      "step": 815
+    },
+    {
+      "epoch": 1.6879505664263645,
+      "grad_norm": 1.1515077352523804,
+      "learning_rate": 1.3184155492120403e-05,
+      "loss": 0.3892,
+      "step": 820
+    },
+    {
+      "epoch": 1.698249227600412,
+      "grad_norm": 1.1764094829559326,
+      "learning_rate": 1.301540469127284e-05,
+      "loss": 0.3948,
+      "step": 825
+    },
+    {
+      "epoch": 1.7085478887744592,
+      "grad_norm": 1.231463074684143,
+      "learning_rate": 1.2846909164971244e-05,
+      "loss": 0.4073,
+      "step": 830
+    },
+    {
+      "epoch": 1.7188465499485068,
+      "grad_norm": 1.1313854455947876,
+      "learning_rate": 1.2678690586459912e-05,
+      "loss": 0.4431,
+      "step": 835
+    },
+    {
+      "epoch": 1.729145211122554,
+      "grad_norm": 1.1482270956039429,
+      "learning_rate": 1.2510770593359917e-05,
+      "loss": 0.4288,
+      "step": 840
+    },
+    {
+      "epoch": 1.7394438722966015,
+      "grad_norm": 1.1811319589614868,
+      "learning_rate": 1.2343170784885859e-05,
+      "loss": 0.432,
+      "step": 845
+    },
+    {
+      "epoch": 1.749742533470649,
+      "grad_norm": 1.1519742012023926,
+      "learning_rate": 1.2175912719067656e-05,
+      "loss": 0.4127,
+      "step": 850
+    },
+    {
+      "epoch": 1.760041194644696,
+      "grad_norm": 1.262083888053894,
+      "learning_rate": 1.2009017909977519e-05,
+      "loss": 0.3925,
+      "step": 855
+    },
+    {
+      "epoch": 1.7703398558187435,
+      "grad_norm": 1.0992200374603271,
+      "learning_rate": 1.1842507824962694e-05,
+      "loss": 0.4088,
+      "step": 860
+    },
+    {
+      "epoch": 1.780638516992791,
+      "grad_norm": 1.2741643190383911,
+      "learning_rate": 1.1676403881884118e-05,
+      "loss": 0.4437,
+      "step": 865
+    },
+    {
+      "epoch": 1.7909371781668382,
+      "grad_norm": 1.194522500038147,
+      "learning_rate": 1.1510727446361515e-05,
+      "loss": 0.4217,
+      "step": 870
+    },
+    {
+      "epoch": 1.8012358393408858,
+      "grad_norm": 1.1314176321029663,
+      "learning_rate": 1.1345499829025136e-05,
+      "loss": 0.4275,
+      "step": 875
+    },
+    {
+      "epoch": 1.811534500514933,
+      "grad_norm": 1.2185325622558594,
+      "learning_rate": 1.1180742282774668e-05,
+      "loss": 0.3821,
+      "step": 880
+    },
+    {
+      "epoch": 1.8218331616889805,
+      "grad_norm": 1.0925527811050415,
+      "learning_rate": 1.1016476000045485e-05,
+      "loss": 0.3907,
+      "step": 885
+    },
+    {
+      "epoch": 1.832131822863028,
+      "grad_norm": 1.174952745437622,
+      "learning_rate": 1.0852722110082693e-05,
+      "loss": 0.3726,
+      "step": 890
+    },
+    {
+      "epoch": 1.842430484037075,
+      "grad_norm": 1.1238709688186646,
+      "learning_rate": 1.0689501676223362e-05,
+      "loss": 0.3677,
+      "step": 895
+    },
+    {
+      "epoch": 1.8527291452111225,
+      "grad_norm": 1.2410848140716553,
+      "learning_rate": 1.052683569318714e-05,
+      "loss": 0.4227,
+      "step": 900
+    },
+    {
+      "epoch": 1.86302780638517,
+      "grad_norm": 1.063857078552246,
+      "learning_rate": 1.036474508437579e-05,
+      "loss": 0.4146,
+      "step": 905
+    },
+    {
+      "epoch": 1.8733264675592172,
+      "grad_norm": 1.2665809392929077,
+      "learning_rate": 1.0203250699181816e-05,
+      "loss": 0.3931,
+      "step": 910
+    },
+    {
+      "epoch": 1.8836251287332648,
+      "grad_norm": 1.2078760862350464,
+      "learning_rate": 1.0042373310306683e-05,
+      "loss": 0.3815,
+      "step": 915
+    },
+    {
+      "epoch": 1.893923789907312,
+      "grad_norm": 1.245889663696289,
+      "learning_rate": 9.882133611088827e-06,
+      "loss": 0.4002,
+      "step": 920
+    },
+    {
+      "epoch": 1.9042224510813595,
+      "grad_norm": 1.1145470142364502,
+      "learning_rate": 9.722552212841949e-06,
+      "loss": 0.3686,
+      "step": 925
+    },
+    {
+      "epoch": 1.9145211122554069,
+      "grad_norm": 1.2170394659042358,
+      "learning_rate": 9.563649642203787e-06,
+      "loss": 0.3901,
+      "step": 930
+    },
+    {
+      "epoch": 1.924819773429454,
+      "grad_norm": 1.289502739906311,
+      "learning_rate": 9.40544633849586e-06,
+      "loss": 0.3736,
+      "step": 935
+    },
+    {
+      "epoch": 1.9351184346035015,
+      "grad_norm": 1.1821953058242798,
+      "learning_rate": 9.24796265109435e-06,
+      "loss": 0.3601,
+      "step": 940
+    },
+    {
+      "epoch": 1.945417095777549,
+      "grad_norm": 1.1379320621490479,
+      "learning_rate": 9.091218836812632e-06,
+      "loss": 0.3654,
+      "step": 945
+    },
+    {
+      "epoch": 1.9557157569515962,
+      "grad_norm": 1.2809494733810425,
+      "learning_rate": 8.935235057295683e-06,
+      "loss": 0.3991,
+      "step": 950
+    },
+    {
+      "epoch": 1.9660144181256438,
+      "grad_norm": 1.3044058084487915,
+      "learning_rate": 8.780031376426706e-06,
+      "loss": 0.401,
+      "step": 955
+    },
+    {
+      "epoch": 1.976313079299691,
+      "grad_norm": 1.183264970779419,
+      "learning_rate": 8.625627757746384e-06,
+      "loss": 0.361,
+      "step": 960
+    },
+    {
+      "epoch": 1.9866117404737385,
+      "grad_norm": 1.2557350397109985,
+      "learning_rate": 8.472044061884977e-06,
+      "loss": 0.3516,
+      "step": 965
+    },
+    {
+      "epoch": 1.9969104016477859,
+      "grad_norm": 1.3537737131118774,
+      "learning_rate": 8.319300044007705e-06,
+      "loss": 0.3504,
+      "step": 970
+    },
+    {
+      "epoch": 2.0061791967044282,
+      "grad_norm": 1.2312425374984741,
+      "learning_rate": 8.167415351273688e-06,
+      "loss": 0.3242,
+      "step": 975
+    },
+    {
+      "epoch": 2.016477857878476,
+      "grad_norm": 1.260758638381958,
+      "learning_rate": 8.016409520308768e-06,
+      "loss": 0.2976,
+      "step": 980
+    },
+    {
+      "epoch": 2.026776519052523,
+      "grad_norm": 1.1900808811187744,
+      "learning_rate": 7.866301974692517e-06,
+      "loss": 0.321,
+      "step": 985
+    },
+    {
+      "epoch": 2.0370751802265707,
+      "grad_norm": 1.0744178295135498,
+      "learning_rate": 7.717112022459894e-06,
+      "loss": 0.3037,
+      "step": 990
+    },
+    {
+      "epoch": 2.047373841400618,
+      "grad_norm": 1.2815207242965698,
+      "learning_rate": 7.568858853617599e-06,
+      "loss": 0.2794,
+      "step": 995
+    },
+    {
+      "epoch": 2.057672502574665,
+      "grad_norm": 1.1860491037368774,
+      "learning_rate": 7.421561537675789e-06,
+      "loss": 0.3019,
+      "step": 1000
+    },
+    {
+      "epoch": 2.067971163748713,
+      "grad_norm": 1.1459763050079346,
+      "learning_rate": 7.275239021195143e-06,
+      "loss": 0.2875,
+      "step": 1005
+    },
+    {
+      "epoch": 2.07826982492276,
+      "grad_norm": 1.2066428661346436,
+      "learning_rate": 7.129910125349826e-06,
+      "loss": 0.3074,
+      "step": 1010
+    },
+    {
+      "epoch": 2.0885684860968072,
+      "grad_norm": 1.1209933757781982,
+      "learning_rate": 6.985593543506564e-06,
+      "loss": 0.3032,
+      "step": 1015
+    },
+    {
+      "epoch": 2.098867147270855,
+      "grad_norm": 1.0854389667510986,
+      "learning_rate": 6.842307838820136e-06,
+      "loss": 0.3091,
+      "step": 1020
+    },
+    {
+      "epoch": 2.109165808444902,
+      "grad_norm": 1.081048607826233,
+      "learning_rate": 6.70007144184567e-06,
+      "loss": 0.2917,
+      "step": 1025
+    },
+    {
+      "epoch": 2.1194644696189497,
+      "grad_norm": 1.1880099773406982,
+      "learning_rate": 6.558902648167885e-06,
+      "loss": 0.2941,
+      "step": 1030
+    },
+    {
+      "epoch": 2.129763130792997,
+      "grad_norm": 1.2570151090621948,
+      "learning_rate": 6.418819616047866e-06,
+      "loss": 0.2951,
+      "step": 1035
+    },
+    {
+      "epoch": 2.140061791967044,
+      "grad_norm": 1.1913825273513794,
+      "learning_rate": 6.279840364087298e-06,
+      "loss": 0.3107,
+      "step": 1040
+    },
+    {
+      "epoch": 2.150360453141092,
+      "grad_norm": 1.1225835084915161,
+      "learning_rate": 6.141982768910861e-06,
+      "loss": 0.298,
+      "step": 1045
+    },
+    {
+      "epoch": 2.160659114315139,
+      "grad_norm": 1.1800163984298706,
+      "learning_rate": 6.005264562866731e-06,
+      "loss": 0.3099,
+      "step": 1050
+    },
+    {
+      "epoch": 2.1709577754891862,
+      "grad_norm": 1.1595478057861328,
+      "learning_rate": 5.869703331745736e-06,
+      "loss": 0.2873,
+      "step": 1055
+    },
+    {
+      "epoch": 2.181256436663234,
+      "grad_norm": 1.2419568300247192,
+      "learning_rate": 5.7353165125193165e-06,
+      "loss": 0.3016,
+      "step": 1060
+    },
+    {
+      "epoch": 2.191555097837281,
+      "grad_norm": 1.138638973236084,
+      "learning_rate": 5.602121391096651e-06,
+      "loss": 0.2717,
+      "step": 1065
+    },
+    {
+      "epoch": 2.2018537590113283,
+      "grad_norm": 1.1681976318359375,
+      "learning_rate": 5.470135100101202e-06,
+      "loss": 0.2874,
+      "step": 1070
+    },
+    {
+      "epoch": 2.212152420185376,
+      "grad_norm": 1.1736184358596802,
+      "learning_rate": 5.3393746166669735e-06,
+      "loss": 0.2925,
+      "step": 1075
+    },
+    {
+      "epoch": 2.222451081359423,
+      "grad_norm": 1.258540391921997,
+      "learning_rate": 5.209856760254784e-06,
+      "loss": 0.3237,
+      "step": 1080
+    },
+    {
+      "epoch": 2.232749742533471,
+      "grad_norm": 1.1958656311035156,
+      "learning_rate": 5.0815981904888195e-06,
+      "loss": 0.3135,
+      "step": 1085
+    },
+    {
+      "epoch": 2.243048403707518,
+      "grad_norm": 1.2103713750839233,
+      "learning_rate": 4.9546154050137175e-06,
+      "loss": 0.2718,
+      "step": 1090
+    },
+    {
+      "epoch": 2.253347064881565,
+      "grad_norm": 1.0489109754562378,
+      "learning_rate": 4.8289247373725275e-06,
+      "loss": 0.2813,
+      "step": 1095
+    },
+    {
+      "epoch": 2.263645726055613,
+      "grad_norm": 1.2313042879104614,
+      "learning_rate": 4.704542354905751e-06,
+      "loss": 0.2865,
+      "step": 1100
+    },
+    {
+      "epoch": 2.27394438722966,
+      "grad_norm": 1.1651129722595215,
+      "learning_rate": 4.581484256671767e-06,
+      "loss": 0.2993,
+      "step": 1105
+    },
+    {
+      "epoch": 2.2842430484037077,
+      "grad_norm": 1.1578460931777954,
+      "learning_rate": 4.459766271388916e-06,
+      "loss": 0.2952,
+      "step": 1110
+    },
+    {
+      "epoch": 2.294541709577755,
+      "grad_norm": 1.1344382762908936,
+      "learning_rate": 4.339404055399469e-06,
+      "loss": 0.3014,
+      "step": 1115
+    },
+    {
+      "epoch": 2.304840370751802,
+      "grad_norm": 1.2620543241500854,
+      "learning_rate": 4.220413090655795e-06,
+      "loss": 0.296,
+      "step": 1120
+    },
+    {
+      "epoch": 2.31513903192585,
+      "grad_norm": 1.152414083480835,
+      "learning_rate": 4.102808682728938e-06,
+      "loss": 0.288,
+      "step": 1125
+    },
+    {
+      "epoch": 2.325437693099897,
+      "grad_norm": 1.2424604892730713,
+      "learning_rate": 3.986605958839911e-06,
+      "loss": 0.2758,
+      "step": 1130
+    },
+    {
+      "epoch": 2.335736354273944,
+      "grad_norm": 1.2598347663879395,
+      "learning_rate": 3.871819865913873e-06,
+      "loss": 0.2851,
+      "step": 1135
+    },
+    {
+      "epoch": 2.346035015447992,
+      "grad_norm": 1.174824595451355,
+      "learning_rate": 3.7584651686575923e-06,
+      "loss": 0.2766,
+      "step": 1140
+    },
+    {
+      "epoch": 2.356333676622039,
+      "grad_norm": 1.1790934801101685,
+      "learning_rate": 3.6465564476602275e-06,
+      "loss": 0.2889,
+      "step": 1145
+    },
+    {
+      "epoch": 2.3666323377960863,
+      "grad_norm": 1.0987571477890015,
+      "learning_rate": 3.5361080975179157e-06,
+      "loss": 0.263,
+      "step": 1150
+    },
+    {
+      "epoch": 2.376930998970134,
+      "grad_norm": 1.2476327419281006,
+      "learning_rate": 3.4271343249821815e-06,
+      "loss": 0.2665,
+      "step": 1155
+    },
+    {
+      "epoch": 2.387229660144181,
+      "grad_norm": 1.2057719230651855,
+      "learning_rate": 3.31964914713257e-06,
+      "loss": 0.2709,
+      "step": 1160
+    },
+    {
+      "epoch": 2.397528321318229,
+      "grad_norm": 1.227776050567627,
+      "learning_rate": 3.2136663895736503e-06,
+      "loss": 0.2723,
+      "step": 1165
+    },
+    {
+      "epoch": 2.407826982492276,
+      "grad_norm": 1.166344404220581,
+      "learning_rate": 3.1091996846566605e-06,
+      "loss": 0.2856,
+      "step": 1170
+    },
+    {
+      "epoch": 2.418125643666323,
+      "grad_norm": 1.1600207090377808,
+      "learning_rate": 3.006262469726014e-06,
+      "loss": 0.2866,
+      "step": 1175
+    },
+    {
+      "epoch": 2.428424304840371,
+      "grad_norm": 1.1660932302474976,
+      "learning_rate": 2.904867985390847e-06,
+      "loss": 0.2465,
+      "step": 1180
+    },
+    {
+      "epoch": 2.438722966014418,
+      "grad_norm": 1.1711407899856567,
+      "learning_rate": 2.8050292738219574e-06,
+      "loss": 0.2749,
+      "step": 1185
+    },
+    {
+      "epoch": 2.4490216271884657,
+      "grad_norm": 1.287010908126831,
+      "learning_rate": 2.7067591770741557e-06,
+      "loss": 0.2856,
+      "step": 1190
+    },
+    {
+      "epoch": 2.459320288362513,
+      "grad_norm": 1.226939082145691,
+      "learning_rate": 2.6100703354344808e-06,
+      "loss": 0.306,
+      "step": 1195
+    },
+    {
+      "epoch": 2.46961894953656,
+      "grad_norm": 1.127946138381958,
+      "learning_rate": 2.5149751857962526e-06,
+      "loss": 0.2772,
+      "step": 1200
+    },
+    {
+      "epoch": 2.479917610710608,
+      "grad_norm": 1.1659767627716064,
+      "learning_rate": 2.4214859600593646e-06,
+      "loss": 0.2748,
+      "step": 1205
+    },
+    {
+      "epoch": 2.490216271884655,
+      "grad_norm": 1.2046109437942505,
+      "learning_rate": 2.3296146835569175e-06,
+      "loss": 0.2787,
+      "step": 1210
+    },
+    {
+      "epoch": 2.500514933058702,
+      "grad_norm": 1.2293471097946167,
+      "learning_rate": 2.2393731735084126e-06,
+      "loss": 0.2481,
+      "step": 1215
+    },
+    {
+      "epoch": 2.51081359423275,
+      "grad_norm": 1.1489880084991455,
+      "learning_rate": 2.1507730374997525e-06,
+      "loss": 0.2882,
+      "step": 1220
+    },
+    {
+      "epoch": 2.521112255406797,
+      "grad_norm": 1.1941146850585938,
+      "learning_rate": 2.063825671990135e-06,
+      "loss": 0.304,
+      "step": 1225
+    },
+    {
+      "epoch": 2.5314109165808443,
+      "grad_norm": 1.2482354640960693,
+      "learning_rate": 1.9785422608462094e-06,
+      "loss": 0.2809,
+      "step": 1230
+    },
+    {
+      "epoch": 2.541709577754892,
+      "grad_norm": 1.1503864526748657,
+      "learning_rate": 1.8949337739034562e-06,
+      "loss": 0.2653,
+      "step": 1235
+    },
+    {
+      "epoch": 2.552008238928939,
+      "grad_norm": 1.1565074920654297,
+      "learning_rate": 1.8130109655552073e-06,
+      "loss": 0.2555,
+      "step": 1240
+    },
+    {
+      "epoch": 2.5623069001029863,
+      "grad_norm": 1.1367086172103882,
+      "learning_rate": 1.732784373369305e-06,
+      "loss": 0.2871,
+      "step": 1245
+    },
+    {
+      "epoch": 2.572605561277034,
+      "grad_norm": 1.2132548093795776,
+      "learning_rate": 1.6542643167326822e-06,
+      "loss": 0.2698,
+      "step": 1250
+    },
+    {
+      "epoch": 2.582904222451081,
+      "grad_norm": 1.3223958015441895,
+      "learning_rate": 1.5774608955239956e-06,
+      "loss": 0.2378,
+      "step": 1255
+    },
+    {
+      "epoch": 2.593202883625129,
+      "grad_norm": 1.2861623764038086,
+      "learning_rate": 1.5023839888145064e-06,
+      "loss": 0.299,
+      "step": 1260
+    },
+    {
+      "epoch": 2.603501544799176,
+      "grad_norm": 1.158660888671875,
+      "learning_rate": 1.4290432535973497e-06,
+      "loss": 0.2767,
+      "step": 1265
+    },
+    {
+      "epoch": 2.6138002059732237,
+      "grad_norm": 1.2246760129928589,
+      "learning_rate": 1.3574481235453767e-06,
+      "loss": 0.2823,
+      "step": 1270
+    },
+    {
+      "epoch": 2.624098867147271,
+      "grad_norm": 1.2212415933609009,
+      "learning_rate": 1.2876078077977187e-06,
+      "loss": 0.2703,
+      "step": 1275
+    },
+    {
+      "epoch": 2.634397528321318,
+      "grad_norm": 1.2260514497756958,
+      "learning_rate": 1.2195312897752315e-06,
+      "loss": 0.2739,
+      "step": 1280
+    },
+    {
+      "epoch": 2.644696189495366,
+      "grad_norm": 1.4936864376068115,
+      "learning_rate": 1.1532273260249854e-06,
+      "loss": 0.2874,
+      "step": 1285
+    },
+    {
+      "epoch": 2.654994850669413,
+      "grad_norm": 1.1349952220916748,
+      "learning_rate": 1.0887044450939177e-06,
+      "loss": 0.2842,
+      "step": 1290
+    },
+    {
+      "epoch": 2.66529351184346,
+      "grad_norm": 1.1385561227798462,
+      "learning_rate": 1.025970946431824e-06,
+      "loss": 0.2771,
+      "step": 1295
+    },
+    {
+      "epoch": 2.675592173017508,
+      "grad_norm": 1.170721173286438,
+      "learning_rate": 9.650348993238213e-07,
+      "loss": 0.2911,
+      "step": 1300
+    },
+    {
+      "epoch": 2.685890834191555,
+      "grad_norm": 1.2789045572280884,
+      "learning_rate": 9.059041418524105e-07,
+      "loss": 0.2611,
+      "step": 1305
+    },
+    {
+      "epoch": 2.6961894953656023,
+      "grad_norm": 1.115492820739746,
+      "learning_rate": 8.485862798892763e-07,
+      "loss": 0.2615,
+      "step": 1310
+    },
+    {
+      "epoch": 2.70648815653965,
+      "grad_norm": 1.0761568546295166,
+      "learning_rate": 7.930886861169612e-07,
+      "loss": 0.2701,
+      "step": 1315
+    },
+    {
+      "epoch": 2.716786817713697,
+      "grad_norm": 1.1549662351608276,
+      "learning_rate": 7.394184990805336e-07,
+      "loss": 0.289,
+      "step": 1320
+    },
+    {
+      "epoch": 2.7270854788877443,
+      "grad_norm": 1.154183268547058,
+      "learning_rate": 6.875826222693704e-07,
+      "loss": 0.2865,
+      "step": 1325
+    },
+    {
+      "epoch": 2.737384140061792,
+      "grad_norm": 1.1828193664550781,
+      "learning_rate": 6.375877232291688e-07,
+      "loss": 0.2574,
+      "step": 1330
+    },
+    {
+      "epoch": 2.747682801235839,
+      "grad_norm": 1.2014567852020264,
+      "learning_rate": 5.894402327043242e-07,
+      "loss": 0.2703,
+      "step": 1335
+    },
+    {
+      "epoch": 2.757981462409887,
+      "grad_norm": 1.1897326707839966,
+      "learning_rate": 5.431463438107431e-07,
+      "loss": 0.2673,
+      "step": 1340
+    },
+    {
+      "epoch": 2.768280123583934,
+      "grad_norm": 1.3078969717025757,
+      "learning_rate": 4.987120112392513e-07,
+      "loss": 0.2842,
+      "step": 1345
+    },
+    {
+      "epoch": 2.7785787847579817,
+      "grad_norm": 1.0676493644714355,
+      "learning_rate": 4.5614295048963694e-07,
+      "loss": 0.2561,
+      "step": 1350
+    },
+    {
+      "epoch": 2.788877445932029,
+      "grad_norm": 1.1583354473114014,
+      "learning_rate": 4.1544463713548806e-07,
+      "loss": 0.2687,
+      "step": 1355
+    },
+    {
+      "epoch": 2.799176107106076,
+      "grad_norm": 1.2171998023986816,
+      "learning_rate": 3.766223061198787e-07,
+      "loss": 0.2689,
+      "step": 1360
+    },
+    {
+      "epoch": 2.8094747682801238,
+      "grad_norm": 1.1008455753326416,
+      "learning_rate": 3.396809510820026e-07,
+      "loss": 0.2376,
+      "step": 1365
+    },
+    {
+      "epoch": 2.819773429454171,
+      "grad_norm": 1.0786809921264648,
+      "learning_rate": 3.0462532371486216e-07,
+      "loss": 0.2932,
+      "step": 1370
+    },
+    {
+      "epoch": 2.830072090628218,
+      "grad_norm": 1.1290796995162964,
+      "learning_rate": 2.714599331540557e-07,
+      "loss": 0.2715,
+      "step": 1375
+    },
+    {
+      "epoch": 2.840370751802266,
+      "grad_norm": 1.2383511066436768,
+      "learning_rate": 2.4018904539778617e-07,
+      "loss": 0.2462,
+      "step": 1380
+    },
+    {
+      "epoch": 2.850669412976313,
+      "grad_norm": 1.0900682210922241,
+      "learning_rate": 2.108166827581254e-07,
+      "loss": 0.2647,
+      "step": 1385
+    },
+    {
+      "epoch": 2.8609680741503603,
+      "grad_norm": 1.1337480545043945,
+      "learning_rate": 1.8334662334364427e-07,
+      "loss": 0.2892,
+      "step": 1390
+    },
+    {
+      "epoch": 2.871266735324408,
+      "grad_norm": 1.2129875421524048,
+      "learning_rate": 1.5778240057342518e-07,
+      "loss": 0.2402,
+      "step": 1395
+    },
+    {
+      "epoch": 2.881565396498455,
+      "grad_norm": 1.246243953704834,
+      "learning_rate": 1.3412730272258367e-07,
+      "loss": 0.2493,
+      "step": 1400
+    },
+    {
+      "epoch": 2.8918640576725023,
+      "grad_norm": 1.134068250656128,
+      "learning_rate": 1.1238437249929012e-07,
+      "loss": 0.2814,
+      "step": 1405
+    },
+    {
+      "epoch": 2.90216271884655,
+      "grad_norm": 1.1378494501113892,
+      "learning_rate": 9.255640665339794e-08,
+      "loss": 0.2826,
+      "step": 1410
+    },
+    {
+      "epoch": 2.912461380020597,
+      "grad_norm": 1.2398602962493896,
+      "learning_rate": 7.464595561670784e-08,
+      "loss": 0.2615,
+      "step": 1415
+    },
+    {
+      "epoch": 2.922760041194645,
+      "grad_norm": 1.1347421407699585,
+      "learning_rate": 5.8655323174895414e-08,
+      "loss": 0.2534,
+      "step": 1420
+    },
+    {
+      "epoch": 2.933058702368692,
+      "grad_norm": 1.2459594011306763,
+      "learning_rate": 4.4586566171199713e-08,
+      "loss": 0.2577,
+      "step": 1425
+    },
+    {
+      "epoch": 2.9433573635427397,
+      "grad_norm": 1.2137491703033447,
+      "learning_rate": 3.244149424184328e-08,
+      "loss": 0.2627,
+      "step": 1430
+    },
+    {
+      "epoch": 2.953656024716787,
+      "grad_norm": 1.218840479850769,
+      "learning_rate": 2.2221669583261662e-08,
+      "loss": 0.27,
+      "step": 1435
+    },
+    {
+      "epoch": 2.963954685890834,
+      "grad_norm": 1.1140334606170654,
+      "learning_rate": 1.3928406751170797e-08,
+      "loss": 0.2733,
+      "step": 1440
+    },
+    {
+      "epoch": 2.9742533470648818,
+      "grad_norm": 1.155864953994751,
+      "learning_rate": 7.562772491463976e-09,
+      "loss": 0.2564,
+      "step": 1445
+    },
+    {
+      "epoch": 2.984552008238929,
+      "grad_norm": 1.056074619293213,
+      "learning_rate": 3.125585603014902e-09,
+      "loss": 0.2613,
+      "step": 1450
+    },
+    {
+      "epoch": 2.994850669412976,
+      "grad_norm": 1.1137224435806274,
+      "learning_rate": 6.174168323402895e-10,
+      "loss": 0.2519,
+      "step": 1455
+    },
+    {
+      "epoch": 3.0,
+      "step": 1458,
+      "total_flos": 2.0902059450816266e+18,
+      "train_loss": 0.5750568343942221,
+      "train_runtime": 964.5713,
+      "train_samples_per_second": 48.295,
+      "train_steps_per_second": 1.512
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1458,
+  "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": 2.0902059450816266e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

109_128_e3_3e-5/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92b5fea3ee7b117a4feca6de110b367f70db0f2a6ceb211f7b9831471168a35c
+size 8273