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": [
+    "down_proj",
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "q_proj",
+    "up_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 sha256:11ece9443f223eeceaa5d94a06cee1ff60b4e10eee1256331abda7a70524337f
+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": 9.985970482718966e+17,
+    "train_loss": 0.40675276741945654,
+    "train_runtime": 475.847,
+    "train_samples": 8488,
+    "train_samples_per_second": 53.513,
+    "train_steps_per_second": 1.677
+}

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": 9.985970482718966e+17,
+    "train_loss": 0.40675276741945654,
+    "train_runtime": 475.847,
+    "train_samples": 8488,
+    "train_samples_per_second": 53.513,
+    "train_steps_per_second": 1.677
+}

128_128_e3_3e-5/trainer_state.json

@@ -0,0 +1,1156 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 798,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.018832391713747645,
+      "grad_norm": 2.4305875301361084,
+      "learning_rate": 3e-06,
+      "loss": 1.6425,
+      "step": 5
+    },
+    {
+      "epoch": 0.03766478342749529,
+      "grad_norm": 1.4296834468841553,
+      "learning_rate": 6.750000000000001e-06,
+      "loss": 1.6105,
+      "step": 10
+    },
+    {
+      "epoch": 0.05649717514124294,
+      "grad_norm": 0.5960512757301331,
+      "learning_rate": 1.05e-05,
+      "loss": 1.5431,
+      "step": 15
+    },
+    {
+      "epoch": 0.07532956685499058,
+      "grad_norm": 0.46189871430397034,
+      "learning_rate": 1.4249999999999999e-05,
+      "loss": 1.544,
+      "step": 20
+    },
+    {
+      "epoch": 0.09416195856873823,
+      "grad_norm": 0.5276208519935608,
+      "learning_rate": 1.8e-05,
+      "loss": 1.5543,
+      "step": 25
+    },
+    {
+      "epoch": 0.11299435028248588,
+      "grad_norm": 0.4129588305950165,
+      "learning_rate": 2.175e-05,
+      "loss": 1.5102,
+      "step": 30
+    },
+    {
+      "epoch": 0.1318267419962335,
+      "grad_norm": 0.4037308096885681,
+      "learning_rate": 2.55e-05,
+      "loss": 1.4363,
+      "step": 35
+    },
+    {
+      "epoch": 0.15065913370998116,
+      "grad_norm": 0.39305582642555237,
+      "learning_rate": 2.925e-05,
+      "loss": 1.3547,
+      "step": 40
+    },
+    {
+      "epoch": 0.1694915254237288,
+      "grad_norm": 0.4476443827152252,
+      "learning_rate": 2.999793874067524e-05,
+      "loss": 1.4103,
+      "step": 45
+    },
+    {
+      "epoch": 0.18832391713747645,
+      "grad_norm": 0.462146133184433,
+      "learning_rate": 2.9989565845573844e-05,
+      "loss": 1.3664,
+      "step": 50
+    },
+    {
+      "epoch": 0.2071563088512241,
+      "grad_norm": 0.4167875647544861,
+      "learning_rate": 2.9974756078739654e-05,
+      "loss": 1.3126,
+      "step": 55
+    },
+    {
+      "epoch": 0.22598870056497175,
+      "grad_norm": 0.5424031019210815,
+      "learning_rate": 2.995351579983447e-05,
+      "loss": 1.2559,
+      "step": 60
+    },
+    {
+      "epoch": 0.2448210922787194,
+      "grad_norm": 0.5395111441612244,
+      "learning_rate": 2.992585412993307e-05,
+      "loss": 1.209,
+      "step": 65
+    },
+    {
+      "epoch": 0.263653483992467,
+      "grad_norm": 0.5591384172439575,
+      "learning_rate": 2.989178294760638e-05,
+      "loss": 1.2509,
+      "step": 70
+    },
+    {
+      "epoch": 0.2824858757062147,
+      "grad_norm": 0.5978198051452637,
+      "learning_rate": 2.985131688382055e-05,
+      "loss": 1.199,
+      "step": 75
+    },
+    {
+      "epoch": 0.3013182674199623,
+      "grad_norm": 0.6741259098052979,
+      "learning_rate": 2.980447331565406e-05,
+      "loss": 1.1526,
+      "step": 80
+    },
+    {
+      "epoch": 0.32015065913371,
+      "grad_norm": 0.6479899883270264,
+      "learning_rate": 2.97512723588356e-05,
+      "loss": 1.0988,
+      "step": 85
+    },
+    {
+      "epoch": 0.3389830508474576,
+      "grad_norm": 0.6289181709289551,
+      "learning_rate": 2.9691736859105915e-05,
+      "loss": 1.1472,
+      "step": 90
+    },
+    {
+      "epoch": 0.3578154425612053,
+      "grad_norm": 0.7421694993972778,
+      "learning_rate": 2.962589238240729e-05,
+      "loss": 1.0785,
+      "step": 95
+    },
+    {
+      "epoch": 0.3766478342749529,
+      "grad_norm": 0.7682233452796936,
+      "learning_rate": 2.9553767203904945e-05,
+      "loss": 1.03,
+      "step": 100
+    },
+    {
+      "epoch": 0.3954802259887006,
+      "grad_norm": 0.7714775204658508,
+      "learning_rate": 2.9475392295845004e-05,
+      "loss": 1.0023,
+      "step": 105
+    },
+    {
+      "epoch": 0.4143126177024482,
+      "grad_norm": 0.8032833337783813,
+      "learning_rate": 2.9390801314254295e-05,
+      "loss": 0.9926,
+      "step": 110
+    },
+    {
+      "epoch": 0.4331450094161959,
+      "grad_norm": 0.89559406042099,
+      "learning_rate": 2.9300030584487665e-05,
+      "loss": 0.8925,
+      "step": 115
+    },
+    {
+      "epoch": 0.4519774011299435,
+      "grad_norm": 0.7680811285972595,
+      "learning_rate": 2.9203119085629e-05,
+      "loss": 0.9337,
+      "step": 120
+    },
+    {
+      "epoch": 0.4708097928436911,
+      "grad_norm": 0.8831218481063843,
+      "learning_rate": 2.910010843375271e-05,
+      "loss": 0.8723,
+      "step": 125
+    },
+    {
+      "epoch": 0.4896421845574388,
+      "grad_norm": 0.9340122938156128,
+      "learning_rate": 2.8991042864052803e-05,
+      "loss": 0.9321,
+      "step": 130
+    },
+    {
+      "epoch": 0.5084745762711864,
+      "grad_norm": 0.9294770956039429,
+      "learning_rate": 2.887596921184725e-05,
+      "loss": 0.8328,
+      "step": 135
+    },
+    {
+      "epoch": 0.527306967984934,
+      "grad_norm": 0.8923389911651611,
+      "learning_rate": 2.87549368924658e-05,
+      "loss": 0.8111,
+      "step": 140
+    },
+    {
+      "epoch": 0.5461393596986818,
+      "grad_norm": 0.9669232368469238,
+      "learning_rate": 2.8627997880029878e-05,
+      "loss": 0.7766,
+      "step": 145
+    },
+    {
+      "epoch": 0.5649717514124294,
+      "grad_norm": 1.111694097518921,
+      "learning_rate": 2.8495206685133676e-05,
+      "loss": 0.7774,
+      "step": 150
+    },
+    {
+      "epoch": 0.583804143126177,
+      "grad_norm": 1.0074784755706787,
+      "learning_rate": 2.8356620331436027e-05,
+      "loss": 0.7715,
+      "step": 155
+    },
+    {
+      "epoch": 0.6026365348399246,
+      "grad_norm": 1.0731223821640015,
+      "learning_rate": 2.8212298331173103e-05,
+      "loss": 0.7161,
+      "step": 160
+    },
+    {
+      "epoch": 0.6214689265536724,
+      "grad_norm": 1.259097695350647,
+      "learning_rate": 2.8062302659602455e-05,
+      "loss": 0.7222,
+      "step": 165
+    },
+    {
+      "epoch": 0.64030131826742,
+      "grad_norm": 1.1057515144348145,
+      "learning_rate": 2.790669772838939e-05,
+      "loss": 0.6559,
+      "step": 170
+    },
+    {
+      "epoch": 0.6591337099811676,
+      "grad_norm": 1.1796486377716064,
+      "learning_rate": 2.774555035794709e-05,
+      "loss": 0.7221,
+      "step": 175
+    },
+    {
+      "epoch": 0.6779661016949152,
+      "grad_norm": 0.9738118648529053,
+      "learning_rate": 2.757892974874236e-05,
+      "loss": 0.6497,
+      "step": 180
+    },
+    {
+      "epoch": 0.696798493408663,
+      "grad_norm": 1.1581305265426636,
+      "learning_rate": 2.7406907451579298e-05,
+      "loss": 0.6385,
+      "step": 185
+    },
+    {
+      "epoch": 0.7156308851224106,
+      "grad_norm": 1.0092982053756714,
+      "learning_rate": 2.7229557336873738e-05,
+      "loss": 0.614,
+      "step": 190
+    },
+    {
+      "epoch": 0.7344632768361582,
+      "grad_norm": 1.0647833347320557,
+      "learning_rate": 2.7046955562931514e-05,
+      "loss": 0.5855,
+      "step": 195
+    },
+    {
+      "epoch": 0.7532956685499058,
+      "grad_norm": 1.1494686603546143,
+      "learning_rate": 2.685918054324434e-05,
+      "loss": 0.5879,
+      "step": 200
+    },
+    {
+      "epoch": 0.7721280602636534,
+      "grad_norm": 1.2322264909744263,
+      "learning_rate": 2.6666312912817174e-05,
+      "loss": 0.5737,
+      "step": 205
+    },
+    {
+      "epoch": 0.7909604519774012,
+      "grad_norm": 1.3123664855957031,
+      "learning_rate": 2.6468435493541664e-05,
+      "loss": 0.5748,
+      "step": 210
+    },
+    {
+      "epoch": 0.8097928436911488,
+      "grad_norm": 1.1682828664779663,
+      "learning_rate": 2.6265633258630514e-05,
+      "loss": 0.6162,
+      "step": 215
+    },
+    {
+      "epoch": 0.8286252354048964,
+      "grad_norm": 1.3484441041946411,
+      "learning_rate": 2.605799329612794e-05,
+      "loss": 0.5229,
+      "step": 220
+    },
+    {
+      "epoch": 0.847457627118644,
+      "grad_norm": 1.2276291847229004,
+      "learning_rate": 2.584560477151205e-05,
+      "loss": 0.4838,
+      "step": 225
+    },
+    {
+      "epoch": 0.8662900188323918,
+      "grad_norm": 1.2339166402816772,
+      "learning_rate": 2.5628558889405085e-05,
+      "loss": 0.5833,
+      "step": 230
+    },
+    {
+      "epoch": 0.8851224105461394,
+      "grad_norm": 1.181424617767334,
+      "learning_rate": 2.5406948854408e-05,
+      "loss": 0.486,
+      "step": 235
+    },
+    {
+      "epoch": 0.903954802259887,
+      "grad_norm": 1.2508269548416138,
+      "learning_rate": 2.5180869831076246e-05,
+      "loss": 0.5182,
+      "step": 240
+    },
+    {
+      "epoch": 0.9227871939736346,
+      "grad_norm": 1.44541597366333,
+      "learning_rate": 2.495041890305385e-05,
+      "loss": 0.4841,
+      "step": 245
+    },
+    {
+      "epoch": 0.9416195856873822,
+      "grad_norm": 1.239762306213379,
+      "learning_rate": 2.4715695031383415e-05,
+      "loss": 0.495,
+      "step": 250
+    },
+    {
+      "epoch": 0.96045197740113,
+      "grad_norm": 1.2438496351242065,
+      "learning_rate": 2.4476799012009958e-05,
+      "loss": 0.3907,
+      "step": 255
+    },
+    {
+      "epoch": 0.9792843691148776,
+      "grad_norm": 1.314880609512329,
+      "learning_rate": 2.4233833432496712e-05,
+      "loss": 0.5291,
+      "step": 260
+    },
+    {
+      "epoch": 0.9981167608286252,
+      "grad_norm": 1.753326416015625,
+      "learning_rate": 2.3986902627971658e-05,
+      "loss": 0.4342,
+      "step": 265
+    },
+    {
+      "epoch": 1.015065913370998,
+      "grad_norm": 1.0976529121398926,
+      "learning_rate": 2.3736112636323545e-05,
+      "loss": 0.3609,
+      "step": 270
+    },
+    {
+      "epoch": 1.0338983050847457,
+      "grad_norm": 1.3320940732955933,
+      "learning_rate": 2.3481571152666748e-05,
+      "loss": 0.3541,
+      "step": 275
+    },
+    {
+      "epoch": 1.0527306967984935,
+      "grad_norm": 1.5409212112426758,
+      "learning_rate": 2.322338748309444e-05,
+      "loss": 0.3352,
+      "step": 280
+    },
+    {
+      "epoch": 1.0715630885122411,
+      "grad_norm": 1.2464486360549927,
+      "learning_rate": 2.2961672497740006e-05,
+      "loss": 0.3351,
+      "step": 285
+    },
+    {
+      "epoch": 1.0903954802259888,
+      "grad_norm": 1.2821121215820312,
+      "learning_rate": 2.2696538583166764e-05,
+      "loss": 0.3527,
+      "step": 290
+    },
+    {
+      "epoch": 1.1092278719397364,
+      "grad_norm": 1.2982563972473145,
+      "learning_rate": 2.2428099594106592e-05,
+      "loss": 0.2853,
+      "step": 295
+    },
+    {
+      "epoch": 1.128060263653484,
+      "grad_norm": 1.2914270162582397,
+      "learning_rate": 2.215647080456799e-05,
+      "loss": 0.3367,
+      "step": 300
+    },
+    {
+      "epoch": 1.1468926553672316,
+      "grad_norm": 1.07498300075531,
+      "learning_rate": 2.1881768858334715e-05,
+      "loss": 0.3232,
+      "step": 305
+    },
+    {
+      "epoch": 1.1657250470809792,
+      "grad_norm": 1.2604783773422241,
+      "learning_rate": 2.1604111718876214e-05,
+      "loss": 0.3241,
+      "step": 310
+    },
+    {
+      "epoch": 1.1845574387947269,
+      "grad_norm": 1.2573599815368652,
+      "learning_rate": 2.1323618618691336e-05,
+      "loss": 0.2953,
+      "step": 315
+    },
+    {
+      "epoch": 1.2033898305084745,
+      "grad_norm": 1.2548270225524902,
+      "learning_rate": 2.1040410008107088e-05,
+      "loss": 0.2897,
+      "step": 320
+    },
+    {
+      "epoch": 1.2222222222222223,
+      "grad_norm": 1.396133542060852,
+      "learning_rate": 2.0754607503554445e-05,
+      "loss": 0.2511,
+      "step": 325
+    },
+    {
+      "epoch": 1.24105461393597,
+      "grad_norm": 1.294316291809082,
+      "learning_rate": 2.0466333835343386e-05,
+      "loss": 0.2903,
+      "step": 330
+    },
+    {
+      "epoch": 1.2598870056497176,
+      "grad_norm": 1.4475504159927368,
+      "learning_rate": 2.017571279495963e-05,
+      "loss": 0.2878,
+      "step": 335
+    },
+    {
+      "epoch": 1.2787193973634652,
+      "grad_norm": 1.2430810928344727,
+      "learning_rate": 1.9882869181905642e-05,
+      "loss": 0.2675,
+      "step": 340
+    },
+    {
+      "epoch": 1.2975517890772128,
+      "grad_norm": 1.2076201438903809,
+      "learning_rate": 1.9587928750108816e-05,
+      "loss": 0.2662,
+      "step": 345
+    },
+    {
+      "epoch": 1.3163841807909604,
+      "grad_norm": 1.259722113609314,
+      "learning_rate": 1.9291018153919783e-05,
+      "loss": 0.2376,
+      "step": 350
+    },
+    {
+      "epoch": 1.335216572504708,
+      "grad_norm": 1.2036066055297852,
+      "learning_rate": 1.8992264893724025e-05,
+      "loss": 0.2442,
+      "step": 355
+    },
+    {
+      "epoch": 1.3540489642184557,
+      "grad_norm": 1.1890456676483154,
+      "learning_rate": 1.8691797261190278e-05,
+      "loss": 0.2589,
+      "step": 360
+    },
+    {
+      "epoch": 1.3728813559322033,
+      "grad_norm": 1.4369051456451416,
+      "learning_rate": 1.8389744284179003e-05,
+      "loss": 0.2731,
+      "step": 365
+    },
+    {
+      "epoch": 1.3917137476459511,
+      "grad_norm": 1.1260286569595337,
+      "learning_rate": 1.8086235671334833e-05,
+      "loss": 0.2463,
+      "step": 370
+    },
+    {
+      "epoch": 1.4105461393596987,
+      "grad_norm": 1.2831964492797852,
+      "learning_rate": 1.7781401756386644e-05,
+      "loss": 0.2684,
+      "step": 375
+    },
+    {
+      "epoch": 1.4293785310734464,
+      "grad_norm": 1.137484073638916,
+      "learning_rate": 1.747537344217915e-05,
+      "loss": 0.1875,
+      "step": 380
+    },
+    {
+      "epoch": 1.448210922787194,
+      "grad_norm": 1.2280571460723877,
+      "learning_rate": 1.716828214446017e-05,
+      "loss": 0.2084,
+      "step": 385
+    },
+    {
+      "epoch": 1.4670433145009416,
+      "grad_norm": 1.14994215965271,
+      "learning_rate": 1.6860259735447632e-05,
+      "loss": 0.2048,
+      "step": 390
+    },
+    {
+      "epoch": 1.4858757062146892,
+      "grad_norm": 1.3526432514190674,
+      "learning_rate": 1.6551438487200513e-05,
+      "loss": 0.1952,
+      "step": 395
+    },
+    {
+      "epoch": 1.5047080979284368,
+      "grad_norm": 1.2877998352050781,
+      "learning_rate": 1.624195101481813e-05,
+      "loss": 0.1852,
+      "step": 400
+    },
+    {
+      "epoch": 1.5235404896421847,
+      "grad_norm": 1.1887202262878418,
+      "learning_rate": 1.59319302194921e-05,
+      "loss": 0.1934,
+      "step": 405
+    },
+    {
+      "epoch": 1.542372881355932,
+      "grad_norm": 1.2497541904449463,
+      "learning_rate": 1.562150923143543e-05,
+      "loss": 0.2188,
+      "step": 410
+    },
+    {
+      "epoch": 1.56120527306968,
+      "grad_norm": 1.455832839012146,
+      "learning_rate": 1.5310821352713294e-05,
+      "loss": 0.225,
+      "step": 415
+    },
+    {
+      "epoch": 1.5800376647834273,
+      "grad_norm": 1.1287732124328613,
+      "learning_rate": 1.5e-05,
+      "loss": 0.2014,
+      "step": 420
+    },
+    {
+      "epoch": 1.5988700564971752,
+      "grad_norm": 1.225393533706665,
+      "learning_rate": 1.4689178647286703e-05,
+      "loss": 0.19,
+      "step": 425
+    },
+    {
+      "epoch": 1.6177024482109228,
+      "grad_norm": 1.2005695104599,
+      "learning_rate": 1.4378490768564576e-05,
+      "loss": 0.1774,
+      "step": 430
+    },
+    {
+      "epoch": 1.6365348399246704,
+      "grad_norm": 1.0853995084762573,
+      "learning_rate": 1.4068069780507905e-05,
+      "loss": 0.1783,
+      "step": 435
+    },
+    {
+      "epoch": 1.655367231638418,
+      "grad_norm": 1.1311185359954834,
+      "learning_rate": 1.3758048985181869e-05,
+      "loss": 0.1865,
+      "step": 440
+    },
+    {
+      "epoch": 1.6741996233521657,
+      "grad_norm": 0.906913161277771,
+      "learning_rate": 1.3448561512799491e-05,
+      "loss": 0.191,
+      "step": 445
+    },
+    {
+      "epoch": 1.6930320150659135,
+      "grad_norm": 1.2072381973266602,
+      "learning_rate": 1.3139740264552372e-05,
+      "loss": 0.1861,
+      "step": 450
+    },
+    {
+      "epoch": 1.711864406779661,
+      "grad_norm": 1.2415664196014404,
+      "learning_rate": 1.283171785553983e-05,
+      "loss": 0.1693,
+      "step": 455
+    },
+    {
+      "epoch": 1.7306967984934087,
+      "grad_norm": 1.2823901176452637,
+      "learning_rate": 1.2524626557820859e-05,
+      "loss": 0.1711,
+      "step": 460
+    },
+    {
+      "epoch": 1.7495291902071564,
+      "grad_norm": 1.1943491697311401,
+      "learning_rate": 1.221859824361336e-05,
+      "loss": 0.1823,
+      "step": 465
+    },
+    {
+      "epoch": 1.768361581920904,
+      "grad_norm": 1.2898815870285034,
+      "learning_rate": 1.1913764328665166e-05,
+      "loss": 0.143,
+      "step": 470
+    },
+    {
+      "epoch": 1.7871939736346516,
+      "grad_norm": 0.9217419028282166,
+      "learning_rate": 1.1610255715821006e-05,
+      "loss": 0.1603,
+      "step": 475
+    },
+    {
+      "epoch": 1.8060263653483992,
+      "grad_norm": 1.1817373037338257,
+      "learning_rate": 1.1308202738809726e-05,
+      "loss": 0.1559,
+      "step": 480
+    },
+    {
+      "epoch": 1.8248587570621468,
+      "grad_norm": 1.1629239320755005,
+      "learning_rate": 1.1007735106275972e-05,
+      "loss": 0.1584,
+      "step": 485
+    },
+    {
+      "epoch": 1.8436911487758945,
+      "grad_norm": 1.3654931783676147,
+      "learning_rate": 1.0708981846080227e-05,
+      "loss": 0.1527,
+      "step": 490
+    },
+    {
+      "epoch": 1.8625235404896423,
+      "grad_norm": 0.8815438747406006,
+      "learning_rate": 1.0412071249891185e-05,
+      "loss": 0.1453,
+      "step": 495
+    },
+    {
+      "epoch": 1.8813559322033897,
+      "grad_norm": 1.059798240661621,
+      "learning_rate": 1.011713081809436e-05,
+      "loss": 0.1365,
+      "step": 500
+    },
+    {
+      "epoch": 1.9001883239171375,
+      "grad_norm": 1.058200716972351,
+      "learning_rate": 9.824287205040372e-06,
+      "loss": 0.1224,
+      "step": 505
+    },
+    {
+      "epoch": 1.9190207156308852,
+      "grad_norm": 1.0297751426696777,
+      "learning_rate": 9.533666164656614e-06,
+      "loss": 0.1341,
+      "step": 510
+    },
+    {
+      "epoch": 1.9378531073446328,
+      "grad_norm": 1.1890089511871338,
+      "learning_rate": 9.245392496445554e-06,
+      "loss": 0.1442,
+      "step": 515
+    },
+    {
+      "epoch": 1.9566854990583804,
+      "grad_norm": 1.1189625263214111,
+      "learning_rate": 8.959589991892915e-06,
+      "loss": 0.1333,
+      "step": 520
+    },
+    {
+      "epoch": 1.975517890772128,
+      "grad_norm": 1.2041877508163452,
+      "learning_rate": 8.676381381308668e-06,
+      "loss": 0.1466,
+      "step": 525
+    },
+    {
+      "epoch": 1.9943502824858759,
+      "grad_norm": 1.0796655416488647,
+      "learning_rate": 8.395888281123787e-06,
+      "loss": 0.1436,
+      "step": 530
+    },
+    {
+      "epoch": 2.0112994350282487,
+      "grad_norm": 0.9424678087234497,
+      "learning_rate": 8.118231141665289e-06,
+      "loss": 0.1107,
+      "step": 535
+    },
+    {
+      "epoch": 2.030131826741996,
+      "grad_norm": 0.8010274767875671,
+      "learning_rate": 7.84352919543201e-06,
+      "loss": 0.0952,
+      "step": 540
+    },
+    {
+      "epoch": 2.048964218455744,
+      "grad_norm": 0.9501699209213257,
+      "learning_rate": 7.571900405893404e-06,
+      "loss": 0.0981,
+      "step": 545
+    },
+    {
+      "epoch": 2.0677966101694913,
+      "grad_norm": 1.0504757165908813,
+      "learning_rate": 7.3034614168332384e-06,
+      "loss": 0.0904,
+      "step": 550
+    },
+    {
+      "epoch": 2.086629001883239,
+      "grad_norm": 0.9691651463508606,
+      "learning_rate": 7.038327502259999e-06,
+      "loss": 0.1058,
+      "step": 555
+    },
+    {
+      "epoch": 2.105461393596987,
+      "grad_norm": 0.9054400324821472,
+      "learning_rate": 6.7766125169055576e-06,
+      "loss": 0.0879,
+      "step": 560
+    },
+    {
+      "epoch": 2.1242937853107344,
+      "grad_norm": 1.0800732374191284,
+      "learning_rate": 6.518428847333255e-06,
+      "loss": 0.093,
+      "step": 565
+    },
+    {
+      "epoch": 2.1431261770244823,
+      "grad_norm": 1.0012534856796265,
+      "learning_rate": 6.263887363676457e-06,
+      "loss": 0.1012,
+      "step": 570
+    },
+    {
+      "epoch": 2.1619585687382297,
+      "grad_norm": 0.8311655521392822,
+      "learning_rate": 6.013097372028343e-06,
+      "loss": 0.1034,
+      "step": 575
+    },
+    {
+      "epoch": 2.1807909604519775,
+      "grad_norm": 1.0120432376861572,
+      "learning_rate": 5.7661665675032895e-06,
+      "loss": 0.0895,
+      "step": 580
+    },
+    {
+      "epoch": 2.199623352165725,
+      "grad_norm": 0.9776325821876526,
+      "learning_rate": 5.523200987990041e-06,
+      "loss": 0.0861,
+      "step": 585
+    },
+    {
+      "epoch": 2.2184557438794728,
+      "grad_norm": 0.8606070876121521,
+      "learning_rate": 5.284304968616585e-06,
+      "loss": 0.0789,
+      "step": 590
+    },
+    {
+      "epoch": 2.23728813559322,
+      "grad_norm": 0.9240632653236389,
+      "learning_rate": 5.049581096946152e-06,
+      "loss": 0.083,
+      "step": 595
+    },
+    {
+      "epoch": 2.256120527306968,
+      "grad_norm": 0.984783947467804,
+      "learning_rate": 4.8191301689237575e-06,
+      "loss": 0.0805,
+      "step": 600
+    },
+    {
+      "epoch": 2.2749529190207154,
+      "grad_norm": 0.9497507810592651,
+      "learning_rate": 4.593051145592002e-06,
+      "loss": 0.0892,
+      "step": 605
+    },
+    {
+      "epoch": 2.2937853107344632,
+      "grad_norm": 0.8375605940818787,
+      "learning_rate": 4.3714411105949225e-06,
+      "loss": 0.0845,
+      "step": 610
+    },
+    {
+      "epoch": 2.312617702448211,
+      "grad_norm": 0.813740611076355,
+      "learning_rate": 4.1543952284879524e-06,
+      "loss": 0.0908,
+      "step": 615
+    },
+    {
+      "epoch": 2.3314500941619585,
+      "grad_norm": 0.96030193567276,
+      "learning_rate": 3.9420067038720644e-06,
+      "loss": 0.0934,
+      "step": 620
+    },
+    {
+      "epoch": 2.3502824858757063,
+      "grad_norm": 0.8405802249908447,
+      "learning_rate": 3.734366741369488e-06,
+      "loss": 0.0802,
+      "step": 625
+    },
+    {
+      "epoch": 2.3691148775894537,
+      "grad_norm": 0.6796116232872009,
+      "learning_rate": 3.531564506458336e-06,
+      "loss": 0.0705,
+      "step": 630
+    },
+    {
+      "epoch": 2.3879472693032016,
+      "grad_norm": 0.8491054177284241,
+      "learning_rate": 3.3336870871828336e-06,
+      "loss": 0.0748,
+      "step": 635
+    },
+    {
+      "epoch": 2.406779661016949,
+      "grad_norm": 0.7147884964942932,
+      "learning_rate": 3.1408194567556626e-06,
+      "loss": 0.088,
+      "step": 640
+    },
+    {
+      "epoch": 2.425612052730697,
+      "grad_norm": 0.8609221577644348,
+      "learning_rate": 2.9530444370684844e-06,
+      "loss": 0.0739,
+      "step": 645
+    },
+    {
+      "epoch": 2.4444444444444446,
+      "grad_norm": 0.7736169695854187,
+      "learning_rate": 2.770442663126266e-06,
+      "loss": 0.0784,
+      "step": 650
+    },
+    {
+      "epoch": 2.463276836158192,
+      "grad_norm": 0.8317406177520752,
+      "learning_rate": 2.5930925484207012e-06,
+      "loss": 0.0775,
+      "step": 655
+    },
+    {
+      "epoch": 2.48210922787194,
+      "grad_norm": 0.6601701974868774,
+      "learning_rate": 2.421070251257641e-06,
+      "loss": 0.0762,
+      "step": 660
+    },
+    {
+      "epoch": 2.5009416195856873,
+      "grad_norm": 0.6766661405563354,
+      "learning_rate": 2.254449642052911e-06,
+      "loss": 0.0761,
+      "step": 665
+    },
+    {
+      "epoch": 2.519774011299435,
+      "grad_norm": 0.7915741801261902,
+      "learning_rate": 2.093302271610611e-06,
+      "loss": 0.0755,
+      "step": 670
+    },
+    {
+      "epoch": 2.5386064030131825,
+      "grad_norm": 0.6937366127967834,
+      "learning_rate": 1.937697340397546e-06,
+      "loss": 0.0707,
+      "step": 675
+    },
+    {
+      "epoch": 2.5574387947269304,
+      "grad_norm": 0.7490200400352478,
+      "learning_rate": 1.7877016688268977e-06,
+      "loss": 0.0681,
+      "step": 680
+    },
+    {
+      "epoch": 2.576271186440678,
+      "grad_norm": 0.9667361378669739,
+      "learning_rate": 1.6433796685639718e-06,
+      "loss": 0.0838,
+      "step": 685
+    },
+    {
+      "epoch": 2.5951035781544256,
+      "grad_norm": 0.6469211578369141,
+      "learning_rate": 1.504793314866323e-06,
+      "loss": 0.0701,
+      "step": 690
+    },
+    {
+      "epoch": 2.613935969868173,
+      "grad_norm": 0.6053743958473206,
+      "learning_rate": 1.372002119970125e-06,
+      "loss": 0.0664,
+      "step": 695
+    },
+    {
+      "epoch": 2.632768361581921,
+      "grad_norm": 0.5228593349456787,
+      "learning_rate": 1.2450631075342028e-06,
+      "loss": 0.0767,
+      "step": 700
+    },
+    {
+      "epoch": 2.6516007532956687,
+      "grad_norm": 0.6333230137825012,
+      "learning_rate": 1.1240307881527516e-06,
+      "loss": 0.0704,
+      "step": 705
+    },
+    {
+      "epoch": 2.670433145009416,
+      "grad_norm": 0.6582266688346863,
+      "learning_rate": 1.0089571359471982e-06,
+      "loss": 0.0672,
+      "step": 710
+    },
+    {
+      "epoch": 2.689265536723164,
+      "grad_norm": 0.8268848061561584,
+      "learning_rate": 8.998915662472906e-07,
+      "loss": 0.0684,
+      "step": 715
+    },
+    {
+      "epoch": 2.7080979284369113,
+      "grad_norm": 0.6300130486488342,
+      "learning_rate": 7.968809143710026e-07,
+      "loss": 0.0651,
+      "step": 720
+    },
+    {
+      "epoch": 2.726930320150659,
+      "grad_norm": 0.7363877296447754,
+      "learning_rate": 6.999694155123371e-07,
+      "loss": 0.075,
+      "step": 725
+    },
+    {
+      "epoch": 2.7457627118644066,
+      "grad_norm": 0.6780223846435547,
+      "learning_rate": 6.091986857457072e-07,
+      "loss": 0.0779,
+      "step": 730
+    },
+    {
+      "epoch": 2.7645951035781544,
+      "grad_norm": 0.5510390400886536,
+      "learning_rate": 5.246077041549985e-07,
+      "loss": 0.066,
+      "step": 735
+    },
+    {
+      "epoch": 2.7834274952919023,
+      "grad_norm": 0.6693576574325562,
+      "learning_rate": 4.4623279609505687e-07,
+      "loss": 0.0686,
+      "step": 740
+    },
+    {
+      "epoch": 2.8022598870056497,
+      "grad_norm": 0.638079047203064,
+      "learning_rate": 3.741076175927094e-07,
+      "loss": 0.0649,
+      "step": 745
+    },
+    {
+      "epoch": 2.8210922787193975,
+      "grad_norm": 0.618250846862793,
+      "learning_rate": 3.082631408940839e-07,
+      "loss": 0.0748,
+      "step": 750
+    },
+    {
+      "epoch": 2.839924670433145,
+      "grad_norm": 0.6578984260559082,
+      "learning_rate": 2.487276411643996e-07,
+      "loss": 0.0777,
+      "step": 755
+    },
+    {
+      "epoch": 2.8587570621468927,
+      "grad_norm": 0.7457256317138672,
+      "learning_rate": 1.9552668434594135e-07,
+      "loss": 0.0719,
+      "step": 760
+    },
+    {
+      "epoch": 2.87758945386064,
+      "grad_norm": 0.4675346314907074,
+      "learning_rate": 1.4868311617944997e-07,
+      "loss": 0.0653,
+      "step": 765
+    },
+    {
+      "epoch": 2.896421845574388,
+      "grad_norm": 0.6095754504203796,
+      "learning_rate": 1.082170523936199e-07,
+      "loss": 0.0643,
+      "step": 770
+    },
+    {
+      "epoch": 2.915254237288136,
+      "grad_norm": 0.7005231380462646,
+      "learning_rate": 7.414587006693064e-08,
+      "loss": 0.0675,
+      "step": 775
+    },
+    {
+      "epoch": 2.934086629001883,
+      "grad_norm": 0.6846628785133362,
+      "learning_rate": 4.648420016553245e-08,
+      "loss": 0.0778,
+      "step": 780
+    },
+    {
+      "epoch": 2.9529190207156306,
+      "grad_norm": 0.7896483540534973,
+      "learning_rate": 2.5243921260348913e-08,
+      "loss": 0.0738,
+      "step": 785
+    },
+    {
+      "epoch": 2.9717514124293785,
+      "grad_norm": 0.7839155793190002,
+      "learning_rate": 1.0434154426155473e-08,
+      "loss": 0.0682,
+      "step": 790
+    },
+    {
+      "epoch": 2.9905838041431263,
+      "grad_norm": 0.6540113091468811,
+      "learning_rate": 2.061259324762643e-09,
+      "loss": 0.0687,
+      "step": 795
+    },
+    {
+      "epoch": 3.0,
+      "step": 798,
+      "total_flos": 9.985970482718966e+17,
+      "train_loss": 0.40675276741945654,
+      "train_runtime": 475.847,
+      "train_samples_per_second": 53.513,
+      "train_steps_per_second": 1.677
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 798,
+  "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": 9.985970482718966e+17,
+  "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:f31a34c6411aa3e6a04d02b2d0354fa922609d275b141fef430d8a1a52d0ece6
+size 8273