Upload folder using huggingface_hub

120_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": [
+    "gate_proj",
+    "k_proj",
+    "down_proj",
+    "q_proj",
+    "up_proj",
+    "v_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

120_128_e3_3e-5/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8d7cc7366411459a8961b2d6204efb79ef677e413c6081909660a74c3548098
+size 791751704

120_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
+}

120_128_e3_3e-5/all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.2257197252212163e+18,
+    "train_loss": 0.3411129695657965,
+    "train_runtime": 581.4416,
+    "train_samples": 10026,
+    "train_samples_per_second": 51.73,
+    "train_steps_per_second": 1.62
+}

120_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 %}

120_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
+}

120_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
+  }
+}

120_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
+}

120_128_e3_3e-5/train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.2257197252212163e+18,
+    "train_loss": 0.3411129695657965,
+    "train_runtime": 581.4416,
+    "train_samples": 10026,
+    "train_samples_per_second": 51.73,
+    "train_steps_per_second": 1.62
+}

120_128_e3_3e-5/trainer_state.json

@@ -0,0 +1,1359 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 942,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01594896331738437,
+      "grad_norm": 2.0442960262298584,
+      "learning_rate": 2.4999999999999998e-06,
+      "loss": 1.4457,
+      "step": 5
+    },
+    {
+      "epoch": 0.03189792663476874,
+      "grad_norm": 1.502213954925537,
+      "learning_rate": 5.625e-06,
+      "loss": 1.4215,
+      "step": 10
+    },
+    {
+      "epoch": 0.04784688995215311,
+      "grad_norm": 0.6694049835205078,
+      "learning_rate": 8.750000000000001e-06,
+      "loss": 1.3638,
+      "step": 15
+    },
+    {
+      "epoch": 0.06379585326953748,
+      "grad_norm": 0.48533234000205994,
+      "learning_rate": 1.1874999999999999e-05,
+      "loss": 1.3819,
+      "step": 20
+    },
+    {
+      "epoch": 0.07974481658692185,
+      "grad_norm": 0.43539226055145264,
+      "learning_rate": 1.5e-05,
+      "loss": 1.2886,
+      "step": 25
+    },
+    {
+      "epoch": 0.09569377990430622,
+      "grad_norm": 0.45699796080589294,
+      "learning_rate": 1.8125e-05,
+      "loss": 1.2483,
+      "step": 30
+    },
+    {
+      "epoch": 0.11164274322169059,
+      "grad_norm": 0.37747955322265625,
+      "learning_rate": 2.125e-05,
+      "loss": 1.2761,
+      "step": 35
+    },
+    {
+      "epoch": 0.12759170653907495,
+      "grad_norm": 0.4444114565849304,
+      "learning_rate": 2.4375e-05,
+      "loss": 1.2338,
+      "step": 40
+    },
+    {
+      "epoch": 0.14354066985645933,
+      "grad_norm": 0.4113112986087799,
+      "learning_rate": 2.75e-05,
+      "loss": 1.1949,
+      "step": 45
+    },
+    {
+      "epoch": 0.1594896331738437,
+      "grad_norm": 0.3915724754333496,
+      "learning_rate": 2.9999907384105782e-05,
+      "loss": 1.2135,
+      "step": 50
+    },
+    {
+      "epoch": 0.17543859649122806,
+      "grad_norm": 0.4047698378562927,
+      "learning_rate": 2.999666594789427e-05,
+      "loss": 1.205,
+      "step": 55
+    },
+    {
+      "epoch": 0.19138755980861244,
+      "grad_norm": 0.4169858694076538,
+      "learning_rate": 2.998879486060202e-05,
+      "loss": 1.1285,
+      "step": 60
+    },
+    {
+      "epoch": 0.20733652312599682,
+      "grad_norm": 0.5057427287101746,
+      "learning_rate": 2.9976296552128305e-05,
+      "loss": 1.1179,
+      "step": 65
+    },
+    {
+      "epoch": 0.22328548644338117,
+      "grad_norm": 0.46866530179977417,
+      "learning_rate": 2.9959174880851214e-05,
+      "loss": 1.091,
+      "step": 70
+    },
+    {
+      "epoch": 0.23923444976076555,
+      "grad_norm": 0.5045714974403381,
+      "learning_rate": 2.9937435132436517e-05,
+      "loss": 1.1005,
+      "step": 75
+    },
+    {
+      "epoch": 0.2551834130781499,
+      "grad_norm": 0.5114366412162781,
+      "learning_rate": 2.9911084018205935e-05,
+      "loss": 1.0615,
+      "step": 80
+    },
+    {
+      "epoch": 0.2711323763955343,
+      "grad_norm": 0.48188868165016174,
+      "learning_rate": 2.988012967306524e-05,
+      "loss": 0.9969,
+      "step": 85
+    },
+    {
+      "epoch": 0.28708133971291866,
+      "grad_norm": 0.5439262986183167,
+      "learning_rate": 2.9844581652992936e-05,
+      "loss": 0.9594,
+      "step": 90
+    },
+    {
+      "epoch": 0.30303030303030304,
+      "grad_norm": 0.5824853777885437,
+      "learning_rate": 2.980445093209021e-05,
+      "loss": 0.969,
+      "step": 95
+    },
+    {
+      "epoch": 0.3189792663476874,
+      "grad_norm": 0.636252224445343,
+      "learning_rate": 2.9759749899193087e-05,
+      "loss": 0.941,
+      "step": 100
+    },
+    {
+      "epoch": 0.3349282296650718,
+      "grad_norm": 0.5880025029182434,
+      "learning_rate": 2.9710492354047857e-05,
+      "loss": 0.9127,
+      "step": 105
+    },
+    {
+      "epoch": 0.3508771929824561,
+      "grad_norm": 0.6317743062973022,
+      "learning_rate": 2.9656693503050924e-05,
+      "loss": 0.8841,
+      "step": 110
+    },
+    {
+      "epoch": 0.3668261562998405,
+      "grad_norm": 0.754127562046051,
+      "learning_rate": 2.9598369954554405e-05,
+      "loss": 0.829,
+      "step": 115
+    },
+    {
+      "epoch": 0.3827751196172249,
+      "grad_norm": 0.6557132601737976,
+      "learning_rate": 2.953553971373894e-05,
+      "loss": 0.8479,
+      "step": 120
+    },
+    {
+      "epoch": 0.39872408293460926,
+      "grad_norm": 0.7659090161323547,
+      "learning_rate": 2.946822217705526e-05,
+      "loss": 0.8278,
+      "step": 125
+    },
+    {
+      "epoch": 0.41467304625199364,
+      "grad_norm": 0.8409238457679749,
+      "learning_rate": 2.939643812623629e-05,
+      "loss": 0.8039,
+      "step": 130
+    },
+    {
+      "epoch": 0.430622009569378,
+      "grad_norm": 0.7361692786216736,
+      "learning_rate": 2.932020972188157e-05,
+      "loss": 0.7898,
+      "step": 135
+    },
+    {
+      "epoch": 0.44657097288676234,
+      "grad_norm": 0.8028347492218018,
+      "learning_rate": 2.9239560496616004e-05,
+      "loss": 0.8123,
+      "step": 140
+    },
+    {
+      "epoch": 0.4625199362041467,
+      "grad_norm": 0.7872179746627808,
+      "learning_rate": 2.9154515347825065e-05,
+      "loss": 0.7716,
+      "step": 145
+    },
+    {
+      "epoch": 0.4784688995215311,
+      "grad_norm": 0.788037896156311,
+      "learning_rate": 2.9065100529968675e-05,
+      "loss": 0.7812,
+      "step": 150
+    },
+    {
+      "epoch": 0.4944178628389155,
+      "grad_norm": 0.9818453192710876,
+      "learning_rate": 2.8971343646476114e-05,
+      "loss": 0.7597,
+      "step": 155
+    },
+    {
+      "epoch": 0.5103668261562998,
+      "grad_norm": 0.8850536942481995,
+      "learning_rate": 2.887327364122455e-05,
+      "loss": 0.7044,
+      "step": 160
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 1.0682122707366943,
+      "learning_rate": 2.8770920789603687e-05,
+      "loss": 0.6995,
+      "step": 165
+    },
+    {
+      "epoch": 0.5422647527910686,
+      "grad_norm": 0.879180371761322,
+      "learning_rate": 2.866431668916939e-05,
+      "loss": 0.6556,
+      "step": 170
+    },
+    {
+      "epoch": 0.5582137161084529,
+      "grad_norm": 0.9156366586685181,
+      "learning_rate": 2.855349424988915e-05,
+      "loss": 0.6852,
+      "step": 175
+    },
+    {
+      "epoch": 0.5741626794258373,
+      "grad_norm": 0.9159861207008362,
+      "learning_rate": 2.8438487683982364e-05,
+      "loss": 0.6162,
+      "step": 180
+    },
+    {
+      "epoch": 0.5901116427432217,
+      "grad_norm": 0.9887858629226685,
+      "learning_rate": 2.831933249535865e-05,
+      "loss": 0.6231,
+      "step": 185
+    },
+    {
+      "epoch": 0.6060606060606061,
+      "grad_norm": 0.8562687635421753,
+      "learning_rate": 2.819606546865731e-05,
+      "loss": 0.6078,
+      "step": 190
+    },
+    {
+      "epoch": 0.6220095693779905,
+      "grad_norm": 0.9360181093215942,
+      "learning_rate": 2.8068724657891507e-05,
+      "loss": 0.5846,
+      "step": 195
+    },
+    {
+      "epoch": 0.6379585326953748,
+      "grad_norm": 1.0566349029541016,
+      "learning_rate": 2.7937349374700527e-05,
+      "loss": 0.5493,
+      "step": 200
+    },
+    {
+      "epoch": 0.6539074960127592,
+      "grad_norm": 0.9491254091262817,
+      "learning_rate": 2.7801980176213798e-05,
+      "loss": 0.5897,
+      "step": 205
+    },
+    {
+      "epoch": 0.6698564593301436,
+      "grad_norm": 1.0197408199310303,
+      "learning_rate": 2.7662658852530412e-05,
+      "loss": 0.5867,
+      "step": 210
+    },
+    {
+      "epoch": 0.6858054226475279,
+      "grad_norm": 1.0253812074661255,
+      "learning_rate": 2.7519428413818034e-05,
+      "loss": 0.5435,
+      "step": 215
+    },
+    {
+      "epoch": 0.7017543859649122,
+      "grad_norm": 1.0823724269866943,
+      "learning_rate": 2.7372333077035128e-05,
+      "loss": 0.5483,
+      "step": 220
+    },
+    {
+      "epoch": 0.7177033492822966,
+      "grad_norm": 1.0201082229614258,
+      "learning_rate": 2.722141825228066e-05,
+      "loss": 0.4958,
+      "step": 225
+    },
+    {
+      "epoch": 0.733652312599681,
+      "grad_norm": 1.18533194065094,
+      "learning_rate": 2.706673052877547e-05,
+      "loss": 0.5073,
+      "step": 230
+    },
+    {
+      "epoch": 0.7496012759170654,
+      "grad_norm": 1.0104401111602783,
+      "learning_rate": 2.6908317660479583e-05,
+      "loss": 0.507,
+      "step": 235
+    },
+    {
+      "epoch": 0.7655502392344498,
+      "grad_norm": 1.1793594360351562,
+      "learning_rate": 2.6746228551350013e-05,
+      "loss": 0.4975,
+      "step": 240
+    },
+    {
+      "epoch": 0.7814992025518341,
+      "grad_norm": 1.0399819612503052,
+      "learning_rate": 2.6580513240243524e-05,
+      "loss": 0.4617,
+      "step": 245
+    },
+    {
+      "epoch": 0.7974481658692185,
+      "grad_norm": 1.1018468141555786,
+      "learning_rate": 2.6411222885469025e-05,
+      "loss": 0.4228,
+      "step": 250
+    },
+    {
+      "epoch": 0.8133971291866029,
+      "grad_norm": 1.0843634605407715,
+      "learning_rate": 2.623840974899439e-05,
+      "loss": 0.4657,
+      "step": 255
+    },
+    {
+      "epoch": 0.8293460925039873,
+      "grad_norm": 1.1001250743865967,
+      "learning_rate": 2.6062127180312545e-05,
+      "loss": 0.3838,
+      "step": 260
+    },
+    {
+      "epoch": 0.8452950558213717,
+      "grad_norm": 1.0429110527038574,
+      "learning_rate": 2.5882429599971872e-05,
+      "loss": 0.4428,
+      "step": 265
+    },
+    {
+      "epoch": 0.861244019138756,
+      "grad_norm": 1.2471680641174316,
+      "learning_rate": 2.569937248277589e-05,
+      "loss": 0.4109,
+      "step": 270
+    },
+    {
+      "epoch": 0.8771929824561403,
+      "grad_norm": 1.0565444231033325,
+      "learning_rate": 2.5513012340657557e-05,
+      "loss": 0.3756,
+      "step": 275
+    },
+    {
+      "epoch": 0.8931419457735247,
+      "grad_norm": 1.1230541467666626,
+      "learning_rate": 2.5323406705233308e-05,
+      "loss": 0.4393,
+      "step": 280
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 1.0404366254806519,
+      "learning_rate": 2.5130614110042415e-05,
+      "loss": 0.3777,
+      "step": 285
+    },
+    {
+      "epoch": 0.9250398724082934,
+      "grad_norm": 1.0032368898391724,
+      "learning_rate": 2.4934694072476913e-05,
+      "loss": 0.4511,
+      "step": 290
+    },
+    {
+      "epoch": 0.9409888357256778,
+      "grad_norm": 1.2259116172790527,
+      "learning_rate": 2.473570707540793e-05,
+      "loss": 0.3922,
+      "step": 295
+    },
+    {
+      "epoch": 0.9569377990430622,
+      "grad_norm": 1.3363443613052368,
+      "learning_rate": 2.453371454851384e-05,
+      "loss": 0.4126,
+      "step": 300
+    },
+    {
+      "epoch": 0.9728867623604466,
+      "grad_norm": 1.1064257621765137,
+      "learning_rate": 2.432877884931623e-05,
+      "loss": 0.3646,
+      "step": 305
+    },
+    {
+      "epoch": 0.988835725677831,
+      "grad_norm": 1.1875357627868652,
+      "learning_rate": 2.4120963243929348e-05,
+      "loss": 0.3572,
+      "step": 310
+    },
+    {
+      "epoch": 1.003189792663477,
+      "grad_norm": 1.3052610158920288,
+      "learning_rate": 2.391033188752911e-05,
+      "loss": 0.3856,
+      "step": 315
+    },
+    {
+      "epoch": 1.0191387559808613,
+      "grad_norm": 1.050253987312317,
+      "learning_rate": 2.3696949804547632e-05,
+      "loss": 0.2933,
+      "step": 320
+    },
+    {
+      "epoch": 1.0350877192982457,
+      "grad_norm": 1.0432811975479126,
+      "learning_rate": 2.3480882868599383e-05,
+      "loss": 0.2831,
+      "step": 325
+    },
+    {
+      "epoch": 1.0510366826156299,
+      "grad_norm": 1.3027548789978027,
+      "learning_rate": 2.3262197782145237e-05,
+      "loss": 0.3219,
+      "step": 330
+    },
+    {
+      "epoch": 1.0669856459330143,
+      "grad_norm": 1.017551302909851,
+      "learning_rate": 2.3040962055900598e-05,
+      "loss": 0.2669,
+      "step": 335
+    },
+    {
+      "epoch": 1.0829346092503986,
+      "grad_norm": 1.1759579181671143,
+      "learning_rate": 2.2817243987994043e-05,
+      "loss": 0.2886,
+      "step": 340
+    },
+    {
+      "epoch": 1.098883572567783,
+      "grad_norm": 1.0713731050491333,
+      "learning_rate": 2.2591112642882853e-05,
+      "loss": 0.261,
+      "step": 345
+    },
+    {
+      "epoch": 1.1148325358851674,
+      "grad_norm": 1.1142313480377197,
+      "learning_rate": 2.2362637830032016e-05,
+      "loss": 0.2432,
+      "step": 350
+    },
+    {
+      "epoch": 1.1307814992025518,
+      "grad_norm": 1.2089124917984009,
+      "learning_rate": 2.2131890082363176e-05,
+      "loss": 0.2339,
+      "step": 355
+    },
+    {
+      "epoch": 1.1467304625199362,
+      "grad_norm": 1.0987941026687622,
+      "learning_rate": 2.1898940634480282e-05,
+      "loss": 0.2598,
+      "step": 360
+    },
+    {
+      "epoch": 1.1626794258373205,
+      "grad_norm": 1.2270328998565674,
+      "learning_rate": 2.166386140067861e-05,
+      "loss": 0.2345,
+      "step": 365
+    },
+    {
+      "epoch": 1.178628389154705,
+      "grad_norm": 1.1635388135910034,
+      "learning_rate": 2.1426724952743962e-05,
+      "loss": 0.2311,
+      "step": 370
+    },
+    {
+      "epoch": 1.1945773524720893,
+      "grad_norm": 1.0832668542861938,
+      "learning_rate": 2.1187604497548862e-05,
+      "loss": 0.239,
+      "step": 375
+    },
+    {
+      "epoch": 1.2105263157894737,
+      "grad_norm": 1.0326707363128662,
+      "learning_rate": 2.0946573854452746e-05,
+      "loss": 0.2652,
+      "step": 380
+    },
+    {
+      "epoch": 1.226475279106858,
+      "grad_norm": 1.0561308860778809,
+      "learning_rate": 2.0703707432513006e-05,
+      "loss": 0.2149,
+      "step": 385
+    },
+    {
+      "epoch": 1.2424242424242424,
+      "grad_norm": 1.0303958654403687,
+      "learning_rate": 2.0459080207514043e-05,
+      "loss": 0.2378,
+      "step": 390
+    },
+    {
+      "epoch": 1.2583732057416268,
+      "grad_norm": 1.0214531421661377,
+      "learning_rate": 2.021276769882133e-05,
+      "loss": 0.2113,
+      "step": 395
+    },
+    {
+      "epoch": 1.2743221690590112,
+      "grad_norm": 1.1471946239471436,
+      "learning_rate": 1.9964845946067682e-05,
+      "loss": 0.2272,
+      "step": 400
+    },
+    {
+      "epoch": 1.2902711323763956,
+      "grad_norm": 1.2897123098373413,
+      "learning_rate": 1.9715391485678893e-05,
+      "loss": 0.2122,
+      "step": 405
+    },
+    {
+      "epoch": 1.30622009569378,
+      "grad_norm": 1.2593072652816772,
+      "learning_rate": 1.9464481327246044e-05,
+      "loss": 0.2426,
+      "step": 410
+    },
+    {
+      "epoch": 1.3221690590111643,
+      "grad_norm": 1.0327588319778442,
+      "learning_rate": 1.921219292975169e-05,
+      "loss": 0.2003,
+      "step": 415
+    },
+    {
+      "epoch": 1.3381180223285487,
+      "grad_norm": 1.0776326656341553,
+      "learning_rate": 1.8958604177657374e-05,
+      "loss": 0.1978,
+      "step": 420
+    },
+    {
+      "epoch": 1.354066985645933,
+      "grad_norm": 1.0561981201171875,
+      "learning_rate": 1.8703793356859717e-05,
+      "loss": 0.2115,
+      "step": 425
+    },
+    {
+      "epoch": 1.3700159489633175,
+      "grad_norm": 1.2881872653961182,
+      "learning_rate": 1.8447839130522654e-05,
+      "loss": 0.215,
+      "step": 430
+    },
+    {
+      "epoch": 1.3859649122807016,
+      "grad_norm": 1.1043871641159058,
+      "learning_rate": 1.819082051479315e-05,
+      "loss": 0.1794,
+      "step": 435
+    },
+    {
+      "epoch": 1.401913875598086,
+      "grad_norm": 1.1314457654953003,
+      "learning_rate": 1.7932816854407988e-05,
+      "loss": 0.1876,
+      "step": 440
+    },
+    {
+      "epoch": 1.4178628389154704,
+      "grad_norm": 1.0103955268859863,
+      "learning_rate": 1.7673907798199054e-05,
+      "loss": 0.1973,
+      "step": 445
+    },
+    {
+      "epoch": 1.4338118022328548,
+      "grad_norm": 1.2097939252853394,
+      "learning_rate": 1.741417327450483e-05,
+      "loss": 0.1962,
+      "step": 450
+    },
+    {
+      "epoch": 1.4497607655502391,
+      "grad_norm": 1.2071138620376587,
+      "learning_rate": 1.7153693466495538e-05,
+      "loss": 0.1722,
+      "step": 455
+    },
+    {
+      "epoch": 1.4657097288676235,
+      "grad_norm": 1.1498464345932007,
+      "learning_rate": 1.6892548787419598e-05,
+      "loss": 0.1774,
+      "step": 460
+    },
+    {
+      "epoch": 1.481658692185008,
+      "grad_norm": 1.0394760370254517,
+      "learning_rate": 1.663081985577916e-05,
+      "loss": 0.1916,
+      "step": 465
+    },
+    {
+      "epoch": 1.4976076555023923,
+      "grad_norm": 0.8752685785293579,
+      "learning_rate": 1.6368587470442145e-05,
+      "loss": 0.1746,
+      "step": 470
+    },
+    {
+      "epoch": 1.5135566188197767,
+      "grad_norm": 1.2297375202178955,
+      "learning_rate": 1.6105932585698687e-05,
+      "loss": 0.1641,
+      "step": 475
+    },
+    {
+      "epoch": 1.529505582137161,
+      "grad_norm": 0.9057098031044006,
+      "learning_rate": 1.5842936286269562e-05,
+      "loss": 0.164,
+      "step": 480
+    },
+    {
+      "epoch": 1.5454545454545454,
+      "grad_norm": 2.1333580017089844,
+      "learning_rate": 1.5579679762274377e-05,
+      "loss": 0.2028,
+      "step": 485
+    },
+    {
+      "epoch": 1.5614035087719298,
+      "grad_norm": 0.9735280275344849,
+      "learning_rate": 1.5316244284167168e-05,
+      "loss": 0.1558,
+      "step": 490
+    },
+    {
+      "epoch": 1.5773524720893142,
+      "grad_norm": 1.0723003149032593,
+      "learning_rate": 1.505271117764728e-05,
+      "loss": 0.1632,
+      "step": 495
+    },
+    {
+      "epoch": 1.5933014354066986,
+      "grad_norm": 1.1319630146026611,
+      "learning_rate": 1.4789161798553122e-05,
+      "loss": 0.1571,
+      "step": 500
+    },
+    {
+      "epoch": 1.609250398724083,
+      "grad_norm": 0.8555175065994263,
+      "learning_rate": 1.4525677507746615e-05,
+      "loss": 0.1351,
+      "step": 505
+    },
+    {
+      "epoch": 1.6251993620414673,
+      "grad_norm": 0.9291567802429199,
+      "learning_rate": 1.4262339645996185e-05,
+      "loss": 0.1781,
+      "step": 510
+    },
+    {
+      "epoch": 1.6411483253588517,
+      "grad_norm": 1.0024137496948242,
+      "learning_rate": 1.399922950886581e-05,
+      "loss": 0.1365,
+      "step": 515
+    },
+    {
+      "epoch": 1.657097288676236,
+      "grad_norm": 1.286751627922058,
+      "learning_rate": 1.3736428321618159e-05,
+      "loss": 0.127,
+      "step": 520
+    },
+    {
+      "epoch": 1.6730462519936204,
+      "grad_norm": 0.9548271298408508,
+      "learning_rate": 1.347401721413935e-05,
+      "loss": 0.1535,
+      "step": 525
+    },
+    {
+      "epoch": 1.6889952153110048,
+      "grad_norm": 1.1810355186462402,
+      "learning_rate": 1.3212077195893198e-05,
+      "loss": 0.1291,
+      "step": 530
+    },
+    {
+      "epoch": 1.7049441786283892,
+      "grad_norm": 1.0680640935897827,
+      "learning_rate": 1.2950689130912599e-05,
+      "loss": 0.1345,
+      "step": 535
+    },
+    {
+      "epoch": 1.7208931419457736,
+      "grad_norm": 0.9276396632194519,
+      "learning_rate": 1.2689933712835843e-05,
+      "loss": 0.1362,
+      "step": 540
+    },
+    {
+      "epoch": 1.736842105263158,
+      "grad_norm": 1.1457185745239258,
+      "learning_rate": 1.24298914399955e-05,
+      "loss": 0.1448,
+      "step": 545
+    },
+    {
+      "epoch": 1.7527910685805423,
+      "grad_norm": 1.0140496492385864,
+      "learning_rate": 1.2170642590567659e-05,
+      "loss": 0.1509,
+      "step": 550
+    },
+    {
+      "epoch": 1.7687400318979267,
+      "grad_norm": 0.9551206231117249,
+      "learning_rate": 1.1912267197789047e-05,
+      "loss": 0.1234,
+      "step": 555
+    },
+    {
+      "epoch": 1.784688995215311,
+      "grad_norm": 1.0022433996200562,
+      "learning_rate": 1.1654845025249815e-05,
+      "loss": 0.1394,
+      "step": 560
+    },
+    {
+      "epoch": 1.8006379585326955,
+      "grad_norm": 1.0830254554748535,
+      "learning_rate": 1.1398455542269578e-05,
+      "loss": 0.1318,
+      "step": 565
+    },
+    {
+      "epoch": 1.8165869218500799,
+      "grad_norm": 1.0094120502471924,
+      "learning_rate": 1.1143177899364261e-05,
+      "loss": 0.1222,
+      "step": 570
+    },
+    {
+      "epoch": 1.8325358851674642,
+      "grad_norm": 0.9436090588569641,
+      "learning_rate": 1.0889090903811397e-05,
+      "loss": 0.1219,
+      "step": 575
+    },
+    {
+      "epoch": 1.8484848484848486,
+      "grad_norm": 0.9213132858276367,
+      "learning_rate": 1.063627299532136e-05,
+      "loss": 0.1177,
+      "step": 580
+    },
+    {
+      "epoch": 1.864433811802233,
+      "grad_norm": 0.9192546010017395,
+      "learning_rate": 1.0384802221822098e-05,
+      "loss": 0.123,
+      "step": 585
+    },
+    {
+      "epoch": 1.8803827751196174,
+      "grad_norm": 0.8093781471252441,
+      "learning_rate": 1.0134756215364765e-05,
+      "loss": 0.1009,
+      "step": 590
+    },
+    {
+      "epoch": 1.8963317384370018,
+      "grad_norm": 1.001365303993225,
+      "learning_rate": 9.886212168157848e-06,
+      "loss": 0.1216,
+      "step": 595
+    },
+    {
+      "epoch": 1.912280701754386,
+      "grad_norm": 0.9107691645622253,
+      "learning_rate": 9.639246808736909e-06,
+      "loss": 0.1118,
+      "step": 600
+    },
+    {
+      "epoch": 1.9282296650717703,
+      "grad_norm": 1.0843939781188965,
+      "learning_rate": 9.393936378277632e-06,
+      "loss": 0.1155,
+      "step": 605
+    },
+    {
+      "epoch": 1.9441786283891547,
+      "grad_norm": 0.7620788216590881,
+      "learning_rate": 9.150356607059226e-06,
+      "loss": 0.117,
+      "step": 610
+    },
+    {
+      "epoch": 1.960127591706539,
+      "grad_norm": 0.8137391805648804,
+      "learning_rate": 8.908582691085593e-06,
+      "loss": 0.1013,
+      "step": 615
+    },
+    {
+      "epoch": 1.9760765550239234,
+      "grad_norm": 0.8294237852096558,
+      "learning_rate": 8.66868926887141e-06,
+      "loss": 0.0867,
+      "step": 620
+    },
+    {
+      "epoch": 1.9920255183413078,
+      "grad_norm": 0.7948359251022339,
+      "learning_rate": 8.430750398400309e-06,
+      "loss": 0.1015,
+      "step": 625
+    },
+    {
+      "epoch": 2.006379585326954,
+      "grad_norm": 0.7853657603263855,
+      "learning_rate": 8.194839534262308e-06,
+      "loss": 0.0951,
+      "step": 630
+    },
+    {
+      "epoch": 2.0223285486443383,
+      "grad_norm": 0.8146317601203918,
+      "learning_rate": 7.961029504977487e-06,
+      "loss": 0.0828,
+      "step": 635
+    },
+    {
+      "epoch": 2.0382775119617227,
+      "grad_norm": 0.7882279753684998,
+      "learning_rate": 7.729392490512952e-06,
+      "loss": 0.0786,
+      "step": 640
+    },
+    {
+      "epoch": 2.054226475279107,
+      "grad_norm": 0.9720128774642944,
+      "learning_rate": 7.500000000000004e-06,
+      "loss": 0.0743,
+      "step": 645
+    },
+    {
+      "epoch": 2.0701754385964914,
+      "grad_norm": 0.9139857888221741,
+      "learning_rate": 7.272922849658405e-06,
+      "loss": 0.0785,
+      "step": 650
+    },
+    {
+      "epoch": 2.0861244019138754,
+      "grad_norm": 0.8107704520225525,
+      "learning_rate": 7.048231140934595e-06,
+      "loss": 0.081,
+      "step": 655
+    },
+    {
+      "epoch": 2.1020733652312598,
+      "grad_norm": 0.8537112474441528,
+      "learning_rate": 6.825994238860491e-06,
+      "loss": 0.0881,
+      "step": 660
+    },
+    {
+      "epoch": 2.118022328548644,
+      "grad_norm": 0.8931276798248291,
+      "learning_rate": 6.6062807506396696e-06,
+      "loss": 0.0728,
+      "step": 665
+    },
+    {
+      "epoch": 2.1339712918660285,
+      "grad_norm": 0.76899254322052,
+      "learning_rate": 6.389158504467531e-06,
+      "loss": 0.0722,
+      "step": 670
+    },
+    {
+      "epoch": 2.149920255183413,
+      "grad_norm": 0.6385933756828308,
+      "learning_rate": 6.174694528591902e-06,
+      "loss": 0.0687,
+      "step": 675
+    },
+    {
+      "epoch": 2.1658692185007973,
+      "grad_norm": 0.7460750341415405,
+      "learning_rate": 5.9629550306206025e-06,
+      "loss": 0.0668,
+      "step": 680
+    },
+    {
+      "epoch": 2.1818181818181817,
+      "grad_norm": 1.067893147468567,
+      "learning_rate": 5.754005377082365e-06,
+      "loss": 0.0836,
+      "step": 685
+    },
+    {
+      "epoch": 2.197767145135566,
+      "grad_norm": 0.692867636680603,
+      "learning_rate": 5.547910073247408e-06,
+      "loss": 0.0728,
+      "step": 690
+    },
+    {
+      "epoch": 2.2137161084529504,
+      "grad_norm": 0.7390987277030945,
+      "learning_rate": 5.3447327432138755e-06,
+      "loss": 0.0681,
+      "step": 695
+    },
+    {
+      "epoch": 2.229665071770335,
+      "grad_norm": 0.6601431369781494,
+      "learning_rate": 5.144536110266324e-06,
+      "loss": 0.0808,
+      "step": 700
+    },
+    {
+      "epoch": 2.245614035087719,
+      "grad_norm": 0.710657000541687,
+      "learning_rate": 4.9473819775122716e-06,
+      "loss": 0.0677,
+      "step": 705
+    },
+    {
+      "epoch": 2.2615629984051036,
+      "grad_norm": 0.6292862296104431,
+      "learning_rate": 4.753331208802857e-06,
+      "loss": 0.0654,
+      "step": 710
+    },
+    {
+      "epoch": 2.277511961722488,
+      "grad_norm": 0.6595669388771057,
+      "learning_rate": 4.562443709943424e-06,
+      "loss": 0.0683,
+      "step": 715
+    },
+    {
+      "epoch": 2.2934609250398723,
+      "grad_norm": 0.6610637903213501,
+      "learning_rate": 4.374778410199882e-06,
+      "loss": 0.0577,
+      "step": 720
+    },
+    {
+      "epoch": 2.3094098883572567,
+      "grad_norm": 0.6245145201683044,
+      "learning_rate": 4.1903932441065315e-06,
+      "loss": 0.0678,
+      "step": 725
+    },
+    {
+      "epoch": 2.325358851674641,
+      "grad_norm": 0.6146581768989563,
+      "learning_rate": 4.009345133580981e-06,
+      "loss": 0.0581,
+      "step": 730
+    },
+    {
+      "epoch": 2.3413078149920254,
+      "grad_norm": 0.6645172238349915,
+      "learning_rate": 3.831689970351659e-06,
+      "loss": 0.0652,
+      "step": 735
+    },
+    {
+      "epoch": 2.35725677830941,
+      "grad_norm": 0.62697434425354,
+      "learning_rate": 3.657482598703385e-06,
+      "loss": 0.0805,
+      "step": 740
+    },
+    {
+      "epoch": 2.373205741626794,
+      "grad_norm": 0.5246645212173462,
+      "learning_rate": 3.4867767985462513e-06,
+      "loss": 0.0668,
+      "step": 745
+    },
+    {
+      "epoch": 2.3891547049441786,
+      "grad_norm": 0.6100196838378906,
+      "learning_rate": 3.3196252688131386e-06,
+      "loss": 0.0654,
+      "step": 750
+    },
+    {
+      "epoch": 2.405103668261563,
+      "grad_norm": 0.6529216766357422,
+      "learning_rate": 3.1560796111909017e-06,
+      "loss": 0.0676,
+      "step": 755
+    },
+    {
+      "epoch": 2.4210526315789473,
+      "grad_norm": 0.5777611136436462,
+      "learning_rate": 2.9961903141903453e-06,
+      "loss": 0.062,
+      "step": 760
+    },
+    {
+      "epoch": 2.4370015948963317,
+      "grad_norm": 0.6660313010215759,
+      "learning_rate": 2.8400067375597737e-06,
+      "loss": 0.0662,
+      "step": 765
+    },
+    {
+      "epoch": 2.452950558213716,
+      "grad_norm": 0.5226062536239624,
+      "learning_rate": 2.6875770970470655e-06,
+      "loss": 0.0609,
+      "step": 770
+    },
+    {
+      "epoch": 2.4688995215311005,
+      "grad_norm": 0.7577630281448364,
+      "learning_rate": 2.5389484495148845e-06,
+      "loss": 0.0686,
+      "step": 775
+    },
+    {
+      "epoch": 2.484848484848485,
+      "grad_norm": 0.606472373008728,
+      "learning_rate": 2.3941666784136624e-06,
+      "loss": 0.0709,
+      "step": 780
+    },
+    {
+      "epoch": 2.5007974481658692,
+      "grad_norm": 0.6386182308197021,
+      "learning_rate": 2.2532764796168293e-06,
+      "loss": 0.0663,
+      "step": 785
+    },
+    {
+      "epoch": 2.5167464114832536,
+      "grad_norm": 0.6524743437767029,
+      "learning_rate": 2.1163213476226535e-06,
+      "loss": 0.0645,
+      "step": 790
+    },
+    {
+      "epoch": 2.532695374800638,
+      "grad_norm": 0.659660279750824,
+      "learning_rate": 1.983343562126969e-06,
+      "loss": 0.0642,
+      "step": 795
+    },
+    {
+      "epoch": 2.5486443381180224,
+      "grad_norm": 0.5216109752655029,
+      "learning_rate": 1.8543841749709377e-06,
+      "loss": 0.0594,
+      "step": 800
+    },
+    {
+      "epoch": 2.5645933014354068,
+      "grad_norm": 0.9283502697944641,
+      "learning_rate": 1.7294829974678338e-06,
+      "loss": 0.0609,
+      "step": 805
+    },
+    {
+      "epoch": 2.580542264752791,
+      "grad_norm": 0.6254350543022156,
+      "learning_rate": 1.6086785881128125e-06,
+      "loss": 0.0641,
+      "step": 810
+    },
+    {
+      "epoch": 2.5964912280701755,
+      "grad_norm": 0.6436562538146973,
+      "learning_rate": 1.4920082406794577e-06,
+      "loss": 0.072,
+      "step": 815
+    },
+    {
+      "epoch": 2.61244019138756,
+      "grad_norm": 0.6282499432563782,
+      "learning_rate": 1.3795079727067327e-06,
+      "loss": 0.065,
+      "step": 820
+    },
+    {
+      "epoch": 2.6283891547049443,
+      "grad_norm": 0.6177212595939636,
+      "learning_rate": 1.2712125143799352e-06,
+      "loss": 0.0686,
+      "step": 825
+    },
+    {
+      "epoch": 2.6443381180223287,
+      "grad_norm": 0.5962855219841003,
+      "learning_rate": 1.1671552978090706e-06,
+      "loss": 0.0642,
+      "step": 830
+    },
+    {
+      "epoch": 2.660287081339713,
+      "grad_norm": 0.556856632232666,
+      "learning_rate": 1.0673684467079593e-06,
+      "loss": 0.0572,
+      "step": 835
+    },
+    {
+      "epoch": 2.6762360446570974,
+      "grad_norm": 0.6239065527915955,
+      "learning_rate": 9.718827664772534e-07,
+      "loss": 0.0623,
+      "step": 840
+    },
+    {
+      "epoch": 2.692185007974482,
+      "grad_norm": 0.6061838269233704,
+      "learning_rate": 8.807277346944536e-07,
+      "loss": 0.0643,
+      "step": 845
+    },
+    {
+      "epoch": 2.708133971291866,
+      "grad_norm": 0.5178799629211426,
+      "learning_rate": 7.939314920138152e-07,
+      "loss": 0.0547,
+      "step": 850
+    },
+    {
+      "epoch": 2.7240829346092506,
+      "grad_norm": 0.45348069071769714,
+      "learning_rate": 7.115208334789902e-07,
+      "loss": 0.0633,
+      "step": 855
+    },
+    {
+      "epoch": 2.740031897926635,
+      "grad_norm": 0.608941376209259,
+      "learning_rate": 6.335212002510782e-07,
+      "loss": 0.0554,
+      "step": 860
+    },
+    {
+      "epoch": 2.7559808612440193,
+      "grad_norm": 0.48068109154701233,
+      "learning_rate": 5.599566717546351e-07,
+      "loss": 0.0543,
+      "step": 865
+    },
+    {
+      "epoch": 2.7719298245614032,
+      "grad_norm": 0.6023107171058655,
+      "learning_rate": 4.908499582440645e-07,
+      "loss": 0.0592,
+      "step": 870
+    },
+    {
+      "epoch": 2.787878787878788,
+      "grad_norm": 0.6455354690551758,
+      "learning_rate": 4.2622239379268457e-07,
+      "loss": 0.0718,
+      "step": 875
+    },
+    {
+      "epoch": 2.803827751196172,
+      "grad_norm": 0.4805963337421417,
+      "learning_rate": 3.66093929706649e-07,
+      "loss": 0.0624,
+      "step": 880
+    },
+    {
+      "epoch": 2.819776714513557,
+      "grad_norm": 0.6599013805389404,
+      "learning_rate": 3.104831283657378e-07,
+      "loss": 0.064,
+      "step": 885
+    },
+    {
+      "epoch": 2.8357256778309408,
+      "grad_norm": 0.5970677733421326,
+      "learning_rate": 2.594071574929241e-07,
+      "loss": 0.0624,
+      "step": 890
+    },
+    {
+      "epoch": 2.8516746411483256,
+      "grad_norm": 0.554695188999176,
+      "learning_rate": 2.128817848544956e-07,
+      "loss": 0.063,
+      "step": 895
+    },
+    {
+      "epoch": 2.8676236044657095,
+      "grad_norm": 0.49463924765586853,
+      "learning_rate": 1.7092137339235149e-07,
+      "loss": 0.058,
+      "step": 900
+    },
+    {
+      "epoch": 2.8835725677830943,
+      "grad_norm": 0.5855778455734253,
+      "learning_rate": 1.3353887678999588e-07,
+      "loss": 0.055,
+      "step": 905
+    },
+    {
+      "epoch": 2.8995215311004783,
+      "grad_norm": 0.5649394989013672,
+      "learning_rate": 1.0074583547357352e-07,
+      "loss": 0.0622,
+      "step": 910
+    },
+    {
+      "epoch": 2.915470494417863,
+      "grad_norm": 0.5132880806922913,
+      "learning_rate": 7.255237304920448e-08,
+      "loss": 0.0628,
+      "step": 915
+    },
+    {
+      "epoch": 2.931419457735247,
+      "grad_norm": 0.5147338509559631,
+      "learning_rate": 4.8967193177704154e-08,
+      "loss": 0.0501,
+      "step": 920
+    },
+    {
+      "epoch": 2.9473684210526314,
+      "grad_norm": 0.5239826440811157,
+      "learning_rate": 2.9997576887660915e-08,
+      "loss": 0.0624,
+      "step": 925
+    },
+    {
+      "epoch": 2.963317384370016,
+      "grad_norm": 0.5162458419799805,
+      "learning_rate": 1.5649380327692475e-08,
+      "loss": 0.0568,
+      "step": 930
+    },
+    {
+      "epoch": 2.9792663476874,
+      "grad_norm": 0.6286619305610657,
+      "learning_rate": 5.927032958580325e-09,
+      "loss": 0.0574,
+      "step": 935
+    },
+    {
+      "epoch": 2.9952153110047846,
+      "grad_norm": 0.46798762679100037,
+      "learning_rate": 8.335361858519131e-10,
+      "loss": 0.0531,
+      "step": 940
+    },
+    {
+      "epoch": 3.0,
+      "step": 942,
+      "total_flos": 1.2257197252212163e+18,
+      "train_loss": 0.3411129695657965,
+      "train_runtime": 581.4416,
+      "train_samples_per_second": 51.73,
+      "train_steps_per_second": 1.62
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 942,
+  "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": 1.2257197252212163e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

120_128_e3_3e-5/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32748d92ed97fa54b7716ec0baf2bce48cf35fdabe9a1b46ffd2005a7ae14e83
+size 8273