Upload folder using huggingface_hub

128_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": [
+    "q_proj",
+    "down_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

128_128_e3_3e-5/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3182fd17be63ac0179915476cc06ba472cab424e81c49bbaf3378204496d9e02
+size 791751704

128_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
+}

128_128_e3_3e-5/all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.0852008719076557e+18,
+    "train_loss": 0.5684480382048566,
+    "train_runtime": 514.9885,
+    "train_samples": 8826,
+    "train_samples_per_second": 51.415,
+    "train_steps_per_second": 1.608
+}

128_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 %}

128_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
+}

128_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
+  }
+}

128_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
+}

128_128_e3_3e-5/train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.0852008719076557e+18,
+    "train_loss": 0.5684480382048566,
+    "train_runtime": 514.9885,
+    "train_samples": 8826,
+    "train_samples_per_second": 51.415,
+    "train_steps_per_second": 1.608
+}

128_128_e3_3e-5/trainer_state.json

@@ -0,0 +1,1198 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 828,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.018115942028985508,
+      "grad_norm": 3.141718626022339,
+      "learning_rate": 2.8571428571428573e-06,
+      "loss": 1.6009,
+      "step": 5
+    },
+    {
+      "epoch": 0.036231884057971016,
+      "grad_norm": 1.5839765071868896,
+      "learning_rate": 6.428571428571429e-06,
+      "loss": 1.5254,
+      "step": 10
+    },
+    {
+      "epoch": 0.05434782608695652,
+      "grad_norm": 0.7266197800636292,
+      "learning_rate": 9.999999999999999e-06,
+      "loss": 1.4437,
+      "step": 15
+    },
+    {
+      "epoch": 0.07246376811594203,
+      "grad_norm": 0.48363223671913147,
+      "learning_rate": 1.3571428571428572e-05,
+      "loss": 1.3438,
+      "step": 20
+    },
+    {
+      "epoch": 0.09057971014492754,
+      "grad_norm": 0.5483124256134033,
+      "learning_rate": 1.7142857142857142e-05,
+      "loss": 1.3397,
+      "step": 25
+    },
+    {
+      "epoch": 0.10869565217391304,
+      "grad_norm": 0.5151329636573792,
+      "learning_rate": 2.0714285714285715e-05,
+      "loss": 1.3153,
+      "step": 30
+    },
+    {
+      "epoch": 0.12681159420289856,
+      "grad_norm": 0.4350980222225189,
+      "learning_rate": 2.4285714285714288e-05,
+      "loss": 1.3054,
+      "step": 35
+    },
+    {
+      "epoch": 0.14492753623188406,
+      "grad_norm": 0.43142423033714294,
+      "learning_rate": 2.7857142857142858e-05,
+      "loss": 1.2735,
+      "step": 40
+    },
+    {
+      "epoch": 0.16304347826086957,
+      "grad_norm": 0.5295076966285706,
+      "learning_rate": 2.999952073733835e-05,
+      "loss": 1.2771,
+      "step": 45
+    },
+    {
+      "epoch": 0.18115942028985507,
+      "grad_norm": 0.4926711320877075,
+      "learning_rate": 2.9994129384105553e-05,
+      "loss": 1.2463,
+      "step": 50
+    },
+    {
+      "epoch": 0.19927536231884058,
+      "grad_norm": 0.4256545305252075,
+      "learning_rate": 2.9982749759659206e-05,
+      "loss": 1.1874,
+      "step": 55
+    },
+    {
+      "epoch": 0.21739130434782608,
+      "grad_norm": 0.4436766803264618,
+      "learning_rate": 2.996538640872983e-05,
+      "loss": 1.184,
+      "step": 60
+    },
+    {
+      "epoch": 0.23550724637681159,
+      "grad_norm": 0.47416767477989197,
+      "learning_rate": 2.9942046265795044e-05,
+      "loss": 1.1697,
+      "step": 65
+    },
+    {
+      "epoch": 0.2536231884057971,
+      "grad_norm": 0.4657860994338989,
+      "learning_rate": 2.9912738652310094e-05,
+      "loss": 1.1384,
+      "step": 70
+    },
+    {
+      "epoch": 0.2717391304347826,
+      "grad_norm": 0.466838538646698,
+      "learning_rate": 2.9877475272985114e-05,
+      "loss": 1.0944,
+      "step": 75
+    },
+    {
+      "epoch": 0.2898550724637681,
+      "grad_norm": 0.512215793132782,
+      "learning_rate": 2.9836270211110567e-05,
+      "loss": 1.1878,
+      "step": 80
+    },
+    {
+      "epoch": 0.3079710144927536,
+      "grad_norm": 0.5532276034355164,
+      "learning_rate": 2.978913992293273e-05,
+      "loss": 1.0962,
+      "step": 85
+    },
+    {
+      "epoch": 0.32608695652173914,
+      "grad_norm": 0.5240709781646729,
+      "learning_rate": 2.9736103231081494e-05,
+      "loss": 1.1392,
+      "step": 90
+    },
+    {
+      "epoch": 0.3442028985507246,
+      "grad_norm": 0.4689042568206787,
+      "learning_rate": 2.9677181317053095e-05,
+      "loss": 1.0627,
+      "step": 95
+    },
+    {
+      "epoch": 0.36231884057971014,
+      "grad_norm": 0.5682642459869385,
+      "learning_rate": 2.961239771275076e-05,
+      "loss": 1.0391,
+      "step": 100
+    },
+    {
+      "epoch": 0.3804347826086957,
+      "grad_norm": 0.5367546677589417,
+      "learning_rate": 2.9541778291086666e-05,
+      "loss": 1.0483,
+      "step": 105
+    },
+    {
+      "epoch": 0.39855072463768115,
+      "grad_norm": 0.6141631007194519,
+      "learning_rate": 2.9465351255648967e-05,
+      "loss": 1.058,
+      "step": 110
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 0.5437244772911072,
+      "learning_rate": 2.9383147129438e-05,
+      "loss": 1.0233,
+      "step": 115
+    },
+    {
+      "epoch": 0.43478260869565216,
+      "grad_norm": 0.5839408040046692,
+      "learning_rate": 2.929519874267619e-05,
+      "loss": 1.043,
+      "step": 120
+    },
+    {
+      "epoch": 0.4528985507246377,
+      "grad_norm": 0.6401098966598511,
+      "learning_rate": 2.9201541219696464e-05,
+      "loss": 0.9842,
+      "step": 125
+    },
+    {
+      "epoch": 0.47101449275362317,
+      "grad_norm": 0.5253692865371704,
+      "learning_rate": 2.9102211964914554e-05,
+      "loss": 0.9681,
+      "step": 130
+    },
+    {
+      "epoch": 0.4891304347826087,
+      "grad_norm": 0.7245438694953918,
+      "learning_rate": 2.899725064789058e-05,
+      "loss": 0.9361,
+      "step": 135
+    },
+    {
+      "epoch": 0.5072463768115942,
+      "grad_norm": 0.6089861392974854,
+      "learning_rate": 2.888669918748606e-05,
+      "loss": 0.9595,
+      "step": 140
+    },
+    {
+      "epoch": 0.5253623188405797,
+      "grad_norm": 0.6549133062362671,
+      "learning_rate": 2.8770601735122593e-05,
+      "loss": 0.9773,
+      "step": 145
+    },
+    {
+      "epoch": 0.5434782608695652,
+      "grad_norm": 0.6593577265739441,
+      "learning_rate": 2.864900465714891e-05,
+      "loss": 0.9214,
+      "step": 150
+    },
+    {
+      "epoch": 0.5615942028985508,
+      "grad_norm": 0.7598589658737183,
+      "learning_rate": 2.852195651632334e-05,
+      "loss": 0.9222,
+      "step": 155
+    },
+    {
+      "epoch": 0.5797101449275363,
+      "grad_norm": 0.6366355419158936,
+      "learning_rate": 2.8389508052419107e-05,
+      "loss": 0.9004,
+      "step": 160
+    },
+    {
+      "epoch": 0.5978260869565217,
+      "grad_norm": 0.7453078627586365,
+      "learning_rate": 2.8251712161960118e-05,
+      "loss": 0.9022,
+      "step": 165
+    },
+    {
+      "epoch": 0.6159420289855072,
+      "grad_norm": 0.7428743243217468,
+      "learning_rate": 2.810862387709551e-05,
+      "loss": 0.877,
+      "step": 170
+    },
+    {
+      "epoch": 0.6340579710144928,
+      "grad_norm": 0.7032713890075684,
+      "learning_rate": 2.7960300343621145e-05,
+      "loss": 0.8117,
+      "step": 175
+    },
+    {
+      "epoch": 0.6521739130434783,
+      "grad_norm": 0.8186202049255371,
+      "learning_rate": 2.7806800798157126e-05,
+      "loss": 0.85,
+      "step": 180
+    },
+    {
+      "epoch": 0.6702898550724637,
+      "grad_norm": 0.8010949492454529,
+      "learning_rate": 2.7648186544490135e-05,
+      "loss": 0.8477,
+      "step": 185
+    },
+    {
+      "epoch": 0.6884057971014492,
+      "grad_norm": 0.6747431755065918,
+      "learning_rate": 2.7484520929090313e-05,
+      "loss": 0.7661,
+      "step": 190
+    },
+    {
+      "epoch": 0.7065217391304348,
+      "grad_norm": 0.8960378766059875,
+      "learning_rate": 2.731586931581229e-05,
+      "loss": 0.795,
+      "step": 195
+    },
+    {
+      "epoch": 0.7246376811594203,
+      "grad_norm": 0.7971881628036499,
+      "learning_rate": 2.7142299059790534e-05,
+      "loss": 0.8131,
+      "step": 200
+    },
+    {
+      "epoch": 0.7427536231884058,
+      "grad_norm": 0.947172999382019,
+      "learning_rate": 2.6963879480539437e-05,
+      "loss": 0.7951,
+      "step": 205
+    },
+    {
+      "epoch": 0.7608695652173914,
+      "grad_norm": 0.7786508202552795,
+      "learning_rate": 2.678068183426888e-05,
+      "loss": 0.7512,
+      "step": 210
+    },
+    {
+      "epoch": 0.7789855072463768,
+      "grad_norm": 0.8430163264274597,
+      "learning_rate": 2.6592779285426332e-05,
+      "loss": 0.771,
+      "step": 215
+    },
+    {
+      "epoch": 0.7971014492753623,
+      "grad_norm": 0.9334030747413635,
+      "learning_rate": 2.640024687747682e-05,
+      "loss": 0.7409,
+      "step": 220
+    },
+    {
+      "epoch": 0.8152173913043478,
+      "grad_norm": 0.8622900247573853,
+      "learning_rate": 2.6203161502932514e-05,
+      "loss": 0.7615,
+      "step": 225
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.8947198987007141,
+      "learning_rate": 2.600160187264384e-05,
+      "loss": 0.7351,
+      "step": 230
+    },
+    {
+      "epoch": 0.8514492753623188,
+      "grad_norm": 0.9292824268341064,
+      "learning_rate": 2.579564848436433e-05,
+      "loss": 0.7657,
+      "step": 235
+    },
+    {
+      "epoch": 0.8695652173913043,
+      "grad_norm": 0.8689068555831909,
+      "learning_rate": 2.5585383590601953e-05,
+      "loss": 0.6999,
+      "step": 240
+    },
+    {
+      "epoch": 0.8876811594202898,
+      "grad_norm": 1.1047435998916626,
+      "learning_rate": 2.5370891165769498e-05,
+      "loss": 0.7169,
+      "step": 245
+    },
+    {
+      "epoch": 0.9057971014492754,
+      "grad_norm": 0.9786391854286194,
+      "learning_rate": 2.5152256872647403e-05,
+      "loss": 0.6943,
+      "step": 250
+    },
+    {
+      "epoch": 0.9239130434782609,
+      "grad_norm": 0.8988637328147888,
+      "learning_rate": 2.4929568028172196e-05,
+      "loss": 0.706,
+      "step": 255
+    },
+    {
+      "epoch": 0.9420289855072463,
+      "grad_norm": 1.0526165962219238,
+      "learning_rate": 2.470291356856437e-05,
+      "loss": 0.6858,
+      "step": 260
+    },
+    {
+      "epoch": 0.9601449275362319,
+      "grad_norm": 0.907991349697113,
+      "learning_rate": 2.4472384013809516e-05,
+      "loss": 0.6663,
+      "step": 265
+    },
+    {
+      "epoch": 0.9782608695652174,
+      "grad_norm": 0.8756071925163269,
+      "learning_rate": 2.4238071431506977e-05,
+      "loss": 0.6676,
+      "step": 270
+    },
+    {
+      "epoch": 0.9963768115942029,
+      "grad_norm": 0.9228700399398804,
+      "learning_rate": 2.400006940010041e-05,
+      "loss": 0.6477,
+      "step": 275
+    },
+    {
+      "epoch": 1.0144927536231885,
+      "grad_norm": 0.9365453720092773,
+      "learning_rate": 2.375847297150491e-05,
+      "loss": 0.6013,
+      "step": 280
+    },
+    {
+      "epoch": 1.0326086956521738,
+      "grad_norm": 1.1155225038528442,
+      "learning_rate": 2.351337863314578e-05,
+      "loss": 0.5986,
+      "step": 285
+    },
+    {
+      "epoch": 1.0507246376811594,
+      "grad_norm": 0.9249854683876038,
+      "learning_rate": 2.3264884269423855e-05,
+      "loss": 0.563,
+      "step": 290
+    },
+    {
+      "epoch": 1.068840579710145,
+      "grad_norm": 1.0821144580841064,
+      "learning_rate": 2.301308912262303e-05,
+      "loss": 0.5427,
+      "step": 295
+    },
+    {
+      "epoch": 1.0869565217391304,
+      "grad_norm": 0.9385888576507568,
+      "learning_rate": 2.27580937532754e-05,
+      "loss": 0.5815,
+      "step": 300
+    },
+    {
+      "epoch": 1.105072463768116,
+      "grad_norm": 0.9940763711929321,
+      "learning_rate": 2.25e-05,
+      "loss": 0.5385,
+      "step": 305
+    },
+    {
+      "epoch": 1.1231884057971016,
+      "grad_norm": 1.0167127847671509,
+      "learning_rate": 2.2238910938831012e-05,
+      "loss": 0.5201,
+      "step": 310
+    },
+    {
+      "epoch": 1.141304347826087,
+      "grad_norm": 1.006917953491211,
+      "learning_rate": 2.197493084205189e-05,
+      "loss": 0.5538,
+      "step": 315
+    },
+    {
+      "epoch": 1.1594202898550725,
+      "grad_norm": 1.013184666633606,
+      "learning_rate": 2.1708165136551643e-05,
+      "loss": 0.5196,
+      "step": 320
+    },
+    {
+      "epoch": 1.177536231884058,
+      "grad_norm": 0.9539540410041809,
+      "learning_rate": 2.1438720361720074e-05,
+      "loss": 0.5319,
+      "step": 325
+    },
+    {
+      "epoch": 1.1956521739130435,
+      "grad_norm": 1.0721772909164429,
+      "learning_rate": 2.1166704126898627e-05,
+      "loss": 0.5056,
+      "step": 330
+    },
+    {
+      "epoch": 1.213768115942029,
+      "grad_norm": 1.0080801248550415,
+      "learning_rate": 2.089222506840402e-05,
+      "loss": 0.4988,
+      "step": 335
+    },
+    {
+      "epoch": 1.2318840579710144,
+      "grad_norm": 1.0586236715316772,
+      "learning_rate": 2.0615392806141663e-05,
+      "loss": 0.5225,
+      "step": 340
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 1.0020700693130493,
+      "learning_rate": 2.033631789982626e-05,
+      "loss": 0.5245,
+      "step": 345
+    },
+    {
+      "epoch": 1.2681159420289856,
+      "grad_norm": 0.9718517065048218,
+      "learning_rate": 2.005511180482712e-05,
+      "loss": 0.5456,
+      "step": 350
+    },
+    {
+      "epoch": 1.286231884057971,
+      "grad_norm": 1.053589105606079,
+      "learning_rate": 1.9771886827655725e-05,
+      "loss": 0.546,
+      "step": 355
+    },
+    {
+      "epoch": 1.3043478260869565,
+      "grad_norm": 1.0060533285140991,
+      "learning_rate": 1.9486756081113373e-05,
+      "loss": 0.4915,
+      "step": 360
+    },
+    {
+      "epoch": 1.322463768115942,
+      "grad_norm": 0.9878813028335571,
+      "learning_rate": 1.9199833439116844e-05,
+      "loss": 0.4985,
+      "step": 365
+    },
+    {
+      "epoch": 1.3405797101449275,
+      "grad_norm": 1.2007569074630737,
+      "learning_rate": 1.8911233491220054e-05,
+      "loss": 0.5059,
+      "step": 370
+    },
+    {
+      "epoch": 1.358695652173913,
+      "grad_norm": 1.0838305950164795,
+      "learning_rate": 1.8621071496849948e-05,
+      "loss": 0.4775,
+      "step": 375
+    },
+    {
+      "epoch": 1.3768115942028984,
+      "grad_norm": 1.0870875120162964,
+      "learning_rate": 1.8329463339274812e-05,
+      "loss": 0.4963,
+      "step": 380
+    },
+    {
+      "epoch": 1.394927536231884,
+      "grad_norm": 1.0038487911224365,
+      "learning_rate": 1.8036525479323464e-05,
+      "loss": 0.4824,
+      "step": 385
+    },
+    {
+      "epoch": 1.4130434782608696,
+      "grad_norm": 1.0514211654663086,
+      "learning_rate": 1.7742374908873817e-05,
+      "loss": 0.4713,
+      "step": 390
+    },
+    {
+      "epoch": 1.431159420289855,
+      "grad_norm": 1.166392207145691,
+      "learning_rate": 1.744712910412927e-05,
+      "loss": 0.4566,
+      "step": 395
+    },
+    {
+      "epoch": 1.4492753623188406,
+      "grad_norm": 1.1911746263504028,
+      "learning_rate": 1.7150905978701765e-05,
+      "loss": 0.4708,
+      "step": 400
+    },
+    {
+      "epoch": 1.4673913043478262,
+      "grad_norm": 1.0741174221038818,
+      "learning_rate": 1.6853823836520076e-05,
+      "loss": 0.4483,
+      "step": 405
+    },
+    {
+      "epoch": 1.4855072463768115,
+      "grad_norm": 0.9730079174041748,
+      "learning_rate": 1.6556001324582275e-05,
+      "loss": 0.4217,
+      "step": 410
+    },
+    {
+      "epoch": 1.5036231884057971,
+      "grad_norm": 1.1837623119354248,
+      "learning_rate": 1.6257557385571147e-05,
+      "loss": 0.4718,
+      "step": 415
+    },
+    {
+      "epoch": 1.5217391304347827,
+      "grad_norm": 0.9853111505508423,
+      "learning_rate": 1.595861121035154e-05,
+      "loss": 0.4093,
+      "step": 420
+    },
+    {
+      "epoch": 1.539855072463768,
+      "grad_norm": 1.1605192422866821,
+      "learning_rate": 1.565928219036856e-05,
+      "loss": 0.4159,
+      "step": 425
+    },
+    {
+      "epoch": 1.5579710144927537,
+      "grad_norm": 1.1583753824234009,
+      "learning_rate": 1.535968986996573e-05,
+      "loss": 0.4318,
+      "step": 430
+    },
+    {
+      "epoch": 1.5760869565217392,
+      "grad_norm": 1.1273375749588013,
+      "learning_rate": 1.5059953898641993e-05,
+      "loss": 0.4123,
+      "step": 435
+    },
+    {
+      "epoch": 1.5942028985507246,
+      "grad_norm": 0.9596806168556213,
+      "learning_rate": 1.4760193983266813e-05,
+      "loss": 0.4395,
+      "step": 440
+    },
+    {
+      "epoch": 1.6123188405797102,
+      "grad_norm": 1.1581813097000122,
+      "learning_rate": 1.4460529840272285e-05,
+      "loss": 0.4315,
+      "step": 445
+    },
+    {
+      "epoch": 1.6304347826086958,
+      "grad_norm": 1.0041747093200684,
+      "learning_rate": 1.4161081147841456e-05,
+      "loss": 0.4175,
+      "step": 450
+    },
+    {
+      "epoch": 1.6485507246376812,
+      "grad_norm": 0.9771676063537598,
+      "learning_rate": 1.3861967498111952e-05,
+      "loss": 0.374,
+      "step": 455
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 1.1321799755096436,
+      "learning_rate": 1.3563308349413926e-05,
+      "loss": 0.4629,
+      "step": 460
+    },
+    {
+      "epoch": 1.6847826086956523,
+      "grad_norm": 1.18793785572052,
+      "learning_rate": 1.3265222978561453e-05,
+      "loss": 0.4179,
+      "step": 465
+    },
+    {
+      "epoch": 1.7028985507246377,
+      "grad_norm": 1.0415338277816772,
+      "learning_rate": 1.2967830433216436e-05,
+      "loss": 0.4228,
+      "step": 470
+    },
+    {
+      "epoch": 1.721014492753623,
+      "grad_norm": 1.3442658185958862,
+      "learning_rate": 1.2671249484344016e-05,
+      "loss": 0.4126,
+      "step": 475
+    },
+    {
+      "epoch": 1.7391304347826086,
+      "grad_norm": 1.0836507081985474,
+      "learning_rate": 1.2375598578778496e-05,
+      "loss": 0.403,
+      "step": 480
+    },
+    {
+      "epoch": 1.7572463768115942,
+      "grad_norm": 1.2494847774505615,
+      "learning_rate": 1.2080995791918697e-05,
+      "loss": 0.3797,
+      "step": 485
+    },
+    {
+      "epoch": 1.7753623188405796,
+      "grad_norm": 1.0330952405929565,
+      "learning_rate": 1.1787558780571678e-05,
+      "loss": 0.3793,
+      "step": 490
+    },
+    {
+      "epoch": 1.7934782608695652,
+      "grad_norm": 0.9909242987632751,
+      "learning_rate": 1.1495404735963622e-05,
+      "loss": 0.3692,
+      "step": 495
+    },
+    {
+      "epoch": 1.8115942028985508,
+      "grad_norm": 1.134205937385559,
+      "learning_rate": 1.1204650336936665e-05,
+      "loss": 0.3879,
+      "step": 500
+    },
+    {
+      "epoch": 1.8297101449275361,
+      "grad_norm": 1.3966150283813477,
+      "learning_rate": 1.0915411703350326e-05,
+      "loss": 0.4046,
+      "step": 505
+    },
+    {
+      "epoch": 1.8478260869565217,
+      "grad_norm": 1.1596742868423462,
+      "learning_rate": 1.0627804349706252e-05,
+      "loss": 0.3786,
+      "step": 510
+    },
+    {
+      "epoch": 1.8659420289855073,
+      "grad_norm": 1.2314115762710571,
+      "learning_rate": 1.034194313901466e-05,
+      "loss": 0.3797,
+      "step": 515
+    },
+    {
+      "epoch": 1.8840579710144927,
+      "grad_norm": 1.2033650875091553,
+      "learning_rate": 1.0057942236921005e-05,
+      "loss": 0.3941,
+      "step": 520
+    },
+    {
+      "epoch": 1.9021739130434783,
+      "grad_norm": 1.1681276559829712,
+      "learning_rate": 9.775915066111116e-06,
+      "loss": 0.3961,
+      "step": 525
+    },
+    {
+      "epoch": 1.9202898550724639,
+      "grad_norm": 1.1927913427352905,
+      "learning_rate": 9.495974261013126e-06,
+      "loss": 0.3435,
+      "step": 530
+    },
+    {
+      "epoch": 1.9384057971014492,
+      "grad_norm": 1.2595330476760864,
+      "learning_rate": 9.21823162281413e-06,
+      "loss": 0.3321,
+      "step": 535
+    },
+    {
+      "epoch": 1.9565217391304348,
+      "grad_norm": 1.076352596282959,
+      "learning_rate": 8.94279807480968e-06,
+      "loss": 0.3558,
+      "step": 540
+    },
+    {
+      "epoch": 1.9746376811594204,
+      "grad_norm": 1.2065880298614502,
+      "learning_rate": 8.669783618103834e-06,
+      "loss": 0.3454,
+      "step": 545
+    },
+    {
+      "epoch": 1.9927536231884058,
+      "grad_norm": 1.1726124286651611,
+      "learning_rate": 8.39929728767756e-06,
+      "loss": 0.3701,
+      "step": 550
+    },
+    {
+      "epoch": 2.010869565217391,
+      "grad_norm": 1.1098450422286987,
+      "learning_rate": 8.13144710884294e-06,
+      "loss": 0.3205,
+      "step": 555
+    },
+    {
+      "epoch": 2.028985507246377,
+      "grad_norm": 1.2119437456130981,
+      "learning_rate": 7.866340054100642e-06,
+      "loss": 0.274,
+      "step": 560
+    },
+    {
+      "epoch": 2.0471014492753623,
+      "grad_norm": 0.9838385581970215,
+      "learning_rate": 7.604082000417818e-06,
+      "loss": 0.2839,
+      "step": 565
+    },
+    {
+      "epoch": 2.0652173913043477,
+      "grad_norm": 1.1750751733779907,
+      "learning_rate": 7.344777686943588e-06,
+      "loss": 0.2846,
+      "step": 570
+    },
+    {
+      "epoch": 2.0833333333333335,
+      "grad_norm": 1.1088839769363403,
+      "learning_rate": 7.088530673178884e-06,
+      "loss": 0.2909,
+      "step": 575
+    },
+    {
+      "epoch": 2.101449275362319,
+      "grad_norm": 1.2768173217773438,
+      "learning_rate": 6.835443297617446e-06,
+      "loss": 0.2733,
+      "step": 580
+    },
+    {
+      "epoch": 2.119565217391304,
+      "grad_norm": 1.0808906555175781,
+      "learning_rate": 6.585616636874438e-06,
+      "loss": 0.3018,
+      "step": 585
+    },
+    {
+      "epoch": 2.13768115942029,
+      "grad_norm": 1.2789727449417114,
+      "learning_rate": 6.339150465319057e-06,
+      "loss": 0.2597,
+      "step": 590
+    },
+    {
+      "epoch": 2.1557971014492754,
+      "grad_norm": 1.0952117443084717,
+      "learning_rate": 6.096143215227199e-06,
+      "loss": 0.2933,
+      "step": 595
+    },
+    {
+      "epoch": 2.1739130434782608,
+      "grad_norm": 1.1481599807739258,
+      "learning_rate": 5.856691937470104e-06,
+      "loss": 0.2835,
+      "step": 600
+    },
+    {
+      "epoch": 2.1920289855072466,
+      "grad_norm": 1.0424528121948242,
+      "learning_rate": 5.620892262754764e-06,
+      "loss": 0.2735,
+      "step": 605
+    },
+    {
+      "epoch": 2.210144927536232,
+      "grad_norm": 1.0625262260437012,
+      "learning_rate": 5.388838363431443e-06,
+      "loss": 0.2642,
+      "step": 610
+    },
+    {
+      "epoch": 2.2282608695652173,
+      "grad_norm": 1.1052013635635376,
+      "learning_rate": 5.1606229158836625e-06,
+      "loss": 0.2714,
+      "step": 615
+    },
+    {
+      "epoch": 2.246376811594203,
+      "grad_norm": 1.2426427602767944,
+      "learning_rate": 4.936337063515611e-06,
+      "loss": 0.2845,
+      "step": 620
+    },
+    {
+      "epoch": 2.2644927536231885,
+      "grad_norm": 0.9883778095245361,
+      "learning_rate": 4.7160703803518306e-06,
+      "loss": 0.2679,
+      "step": 625
+    },
+    {
+      "epoch": 2.282608695652174,
+      "grad_norm": 1.2373675107955933,
+      "learning_rate": 4.499910835263625e-06,
+      "loss": 0.3157,
+      "step": 630
+    },
+    {
+      "epoch": 2.300724637681159,
+      "grad_norm": 1.1451621055603027,
+      "learning_rate": 4.2879447568365435e-06,
+      "loss": 0.2677,
+      "step": 635
+    },
+    {
+      "epoch": 2.318840579710145,
+      "grad_norm": 1.0993037223815918,
+      "learning_rate": 4.080256798892981e-06,
+      "loss": 0.2707,
+      "step": 640
+    },
+    {
+      "epoch": 2.3369565217391304,
+      "grad_norm": 1.3176124095916748,
+      "learning_rate": 3.87692990668357e-06,
+      "loss": 0.2927,
+      "step": 645
+    },
+    {
+      "epoch": 2.355072463768116,
+      "grad_norm": 0.9844982028007507,
+      "learning_rate": 3.6780452837610123e-06,
+      "loss": 0.2426,
+      "step": 650
+    },
+    {
+      "epoch": 2.3731884057971016,
+      "grad_norm": 1.1397931575775146,
+      "learning_rate": 3.4836823595494388e-06,
+      "loss": 0.2993,
+      "step": 655
+    },
+    {
+      "epoch": 2.391304347826087,
+      "grad_norm": 1.0888879299163818,
+      "learning_rate": 3.2939187576223232e-06,
+      "loss": 0.2518,
+      "step": 660
+    },
+    {
+      "epoch": 2.4094202898550723,
+      "grad_norm": 1.2873591184616089,
+      "learning_rate": 3.108830264701636e-06,
+      "loss": 0.2756,
+      "step": 665
+    },
+    {
+      "epoch": 2.427536231884058,
+      "grad_norm": 0.9957096576690674,
+      "learning_rate": 2.9284908003905615e-06,
+      "loss": 0.2846,
+      "step": 670
+    },
+    {
+      "epoch": 2.4456521739130435,
+      "grad_norm": 1.0697777271270752,
+      "learning_rate": 2.752972387651897e-06,
+      "loss": 0.253,
+      "step": 675
+    },
+    {
+      "epoch": 2.463768115942029,
+      "grad_norm": 1.1475001573562622,
+      "learning_rate": 2.5823451240439238e-06,
+      "loss": 0.2309,
+      "step": 680
+    },
+    {
+      "epoch": 2.4818840579710146,
+      "grad_norm": 1.146727204322815,
+      "learning_rate": 2.4166771537252496e-06,
+      "loss": 0.2892,
+      "step": 685
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 1.1267262697219849,
+      "learning_rate": 2.2560346402397747e-06,
+      "loss": 0.2871,
+      "step": 690
+    },
+    {
+      "epoch": 2.5181159420289854,
+      "grad_norm": 1.2654765844345093,
+      "learning_rate": 2.1004817400926475e-06,
+      "loss": 0.259,
+      "step": 695
+    },
+    {
+      "epoch": 2.536231884057971,
+      "grad_norm": 1.1569652557373047,
+      "learning_rate": 1.950080577127832e-06,
+      "loss": 0.2675,
+      "step": 700
+    },
+    {
+      "epoch": 2.5543478260869565,
+      "grad_norm": 1.1681987047195435,
+      "learning_rate": 1.8048912177174093e-06,
+      "loss": 0.2551,
+      "step": 705
+    },
+    {
+      "epoch": 2.572463768115942,
+      "grad_norm": 1.1985141038894653,
+      "learning_rate": 1.6649716467726272e-06,
+      "loss": 0.2675,
+      "step": 710
+    },
+    {
+      "epoch": 2.5905797101449277,
+      "grad_norm": 1.1720751523971558,
+      "learning_rate": 1.5303777445861855e-06,
+      "loss": 0.2639,
+      "step": 715
+    },
+    {
+      "epoch": 2.608695652173913,
+      "grad_norm": 1.1878292560577393,
+      "learning_rate": 1.4011632645151078e-06,
+      "loss": 0.2883,
+      "step": 720
+    },
+    {
+      "epoch": 2.6268115942028984,
+      "grad_norm": 1.1438288688659668,
+      "learning_rate": 1.2773798115130114e-06,
+      "loss": 0.2542,
+      "step": 725
+    },
+    {
+      "epoch": 2.644927536231884,
+      "grad_norm": 1.1158024072647095,
+      "learning_rate": 1.159076821520414e-06,
+      "loss": 0.26,
+      "step": 730
+    },
+    {
+      "epoch": 2.6630434782608696,
+      "grad_norm": 1.1707649230957031,
+      "learning_rate": 1.046301541721279e-06,
+      "loss": 0.2599,
+      "step": 735
+    },
+    {
+      "epoch": 2.681159420289855,
+      "grad_norm": 1.2275639772415161,
+      "learning_rate": 9.39099011673713e-07,
+      "loss": 0.2648,
+      "step": 740
+    },
+    {
+      "epoch": 2.699275362318841,
+      "grad_norm": 1.1057640314102173,
+      "learning_rate": 8.375120453223123e-07,
+      "loss": 0.2512,
+      "step": 745
+    },
+    {
+      "epoch": 2.717391304347826,
+      "grad_norm": 1.067372441291809,
+      "learning_rate": 7.415812138993688e-07,
+      "loss": 0.2544,
+      "step": 750
+    },
+    {
+      "epoch": 2.7355072463768115,
+      "grad_norm": 1.063515067100525,
+      "learning_rate": 6.513448297217616e-07,
+      "loss": 0.2336,
+      "step": 755
+    },
+    {
+      "epoch": 2.753623188405797,
+      "grad_norm": 1.2793192863464355,
+      "learning_rate": 5.668389308900012e-07,
+      "loss": 0.2573,
+      "step": 760
+    },
+    {
+      "epoch": 2.7717391304347827,
+      "grad_norm": 1.0330173969268799,
+      "learning_rate": 4.880972668955291e-07,
+      "loss": 0.264,
+      "step": 765
+    },
+    {
+      "epoch": 2.789855072463768,
+      "grad_norm": 1.1933742761611938,
+      "learning_rate": 4.151512851420447e-07,
+      "loss": 0.2834,
+      "step": 770
+    },
+    {
+      "epoch": 2.807971014492754,
+      "grad_norm": 1.201213002204895,
+      "learning_rate": 3.480301183862017e-07,
+      "loss": 0.2308,
+      "step": 775
+    },
+    {
+      "epoch": 2.8260869565217392,
+      "grad_norm": 1.0752284526824951,
+      "learning_rate": 2.867605731027534e-07,
+      "loss": 0.2682,
+      "step": 780
+    },
+    {
+      "epoch": 2.8442028985507246,
+      "grad_norm": 1.1263558864593506,
+      "learning_rate": 2.3136711877871308e-07,
+      "loss": 0.2424,
+      "step": 785
+    },
+    {
+      "epoch": 2.86231884057971,
+      "grad_norm": 0.9950832724571228,
+      "learning_rate": 1.8187187814088456e-07,
+      "loss": 0.2331,
+      "step": 790
+    },
+    {
+      "epoch": 2.880434782608696,
+      "grad_norm": 1.148727297782898,
+      "learning_rate": 1.382946183205913e-07,
+      "loss": 0.2578,
+      "step": 795
+    },
+    {
+      "epoch": 2.898550724637681,
+      "grad_norm": 1.1592689752578735,
+      "learning_rate": 1.0065274295921301e-07,
+      "loss": 0.2534,
+      "step": 800
+    },
+    {
+      "epoch": 2.9166666666666665,
+      "grad_norm": 1.1900664567947388,
+      "learning_rate": 6.896128525760381e-08,
+      "loss": 0.2771,
+      "step": 805
+    },
+    {
+      "epoch": 2.9347826086956523,
+      "grad_norm": 1.0583255290985107,
+      "learning_rate": 4.3232901972216634e-08,
+      "loss": 0.2651,
+      "step": 810
+    },
+    {
+      "epoch": 2.9528985507246377,
+      "grad_norm": 1.090453028678894,
+      "learning_rate": 2.347786836032484e-08,
+      "loss": 0.2416,
+      "step": 815
+    },
+    {
+      "epoch": 2.971014492753623,
+      "grad_norm": 1.0817853212356567,
+      "learning_rate": 9.704074076344882e-09,
+      "loss": 0.2415,
+      "step": 820
+    },
+    {
+      "epoch": 2.9891304347826084,
+      "grad_norm": 1.076716423034668,
+      "learning_rate": 1.917020020906768e-09,
+      "loss": 0.2446,
+      "step": 825
+    },
+    {
+      "epoch": 3.0,
+      "step": 828,
+      "total_flos": 1.0852008719076557e+18,
+      "train_loss": 0.5684480382048566,
+      "train_runtime": 514.9885,
+      "train_samples_per_second": 51.415,
+      "train_steps_per_second": 1.608
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 828,
+  "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": 1.0852008719076557e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

128_128_e3_3e-5/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:106b7090aee4053c335b600efb9d23a6c9b934073087d89974f067e8dca5d23b
+size 8273