Upload folder using huggingface_hub

12_128_e3_3e-5/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "ibm-granite/granite-3.3-8b-instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "gate_proj",
+    "k_proj",
+    "o_proj",
+    "up_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

12_128_e3_3e-5/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96698c2687e239348d6e800868b421d865817fa673de30c1ef3ff8f3944a5364
+size 791751704

12_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
+}

12_128_e3_3e-5/all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 9.378169474315715e+17,
+    "train_loss": 0.3240591349500802,
+    "train_runtime": 459.0345,
+    "train_samples": 7907,
+    "train_samples_per_second": 51.676,
+    "train_steps_per_second": 1.621
+}

12_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 %}

12_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
+}

12_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
+  }
+}

12_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
+}

12_128_e3_3e-5/train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 9.378169474315715e+17,
+    "train_loss": 0.3240591349500802,
+    "train_runtime": 459.0345,
+    "train_samples": 7907,
+    "train_samples_per_second": 51.676,
+    "train_steps_per_second": 1.621
+}

12_128_e3_3e-5/trainer_state.json

@@ -0,0 +1,1079 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 744,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.020202020202020204,
+      "grad_norm": 2.3623080253601074,
+      "learning_rate": 3.157894736842105e-06,
+      "loss": 1.4852,
+      "step": 5
+    },
+    {
+      "epoch": 0.04040404040404041,
+      "grad_norm": 1.6796499490737915,
+      "learning_rate": 7.105263157894737e-06,
+      "loss": 1.458,
+      "step": 10
+    },
+    {
+      "epoch": 0.06060606060606061,
+      "grad_norm": 0.6700893044471741,
+      "learning_rate": 1.1052631578947368e-05,
+      "loss": 1.3987,
+      "step": 15
+    },
+    {
+      "epoch": 0.08080808080808081,
+      "grad_norm": 0.6007221341133118,
+      "learning_rate": 1.5e-05,
+      "loss": 1.346,
+      "step": 20
+    },
+    {
+      "epoch": 0.10101010101010101,
+      "grad_norm": 0.5144990086555481,
+      "learning_rate": 1.894736842105263e-05,
+      "loss": 1.3069,
+      "step": 25
+    },
+    {
+      "epoch": 0.12121212121212122,
+      "grad_norm": 0.48458826541900635,
+      "learning_rate": 2.2894736842105263e-05,
+      "loss": 1.2554,
+      "step": 30
+    },
+    {
+      "epoch": 0.1414141414141414,
+      "grad_norm": 0.4060455560684204,
+      "learning_rate": 2.6842105263157896e-05,
+      "loss": 1.2595,
+      "step": 35
+    },
+    {
+      "epoch": 0.16161616161616163,
+      "grad_norm": 0.43940654397010803,
+      "learning_rate": 2.9999851491644133e-05,
+      "loss": 1.1834,
+      "step": 40
+    },
+    {
+      "epoch": 0.18181818181818182,
+      "grad_norm": 0.5126445293426514,
+      "learning_rate": 2.999465400794852e-05,
+      "loss": 1.2111,
+      "step": 45
+    },
+    {
+      "epoch": 0.20202020202020202,
+      "grad_norm": 0.4316495358943939,
+      "learning_rate": 2.9982034046828747e-05,
+      "loss": 1.0804,
+      "step": 50
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.49812084436416626,
+      "learning_rate": 2.9961997855269662e-05,
+      "loss": 1.1218,
+      "step": 55
+    },
+    {
+      "epoch": 0.24242424242424243,
+      "grad_norm": 0.48510104417800903,
+      "learning_rate": 2.9934555351351374e-05,
+      "loss": 1.1152,
+      "step": 60
+    },
+    {
+      "epoch": 0.26262626262626265,
+      "grad_norm": 0.49269962310791016,
+      "learning_rate": 2.989972011933969e-05,
+      "loss": 1.0451,
+      "step": 65
+    },
+    {
+      "epoch": 0.2828282828282828,
+      "grad_norm": 0.5396036505699158,
+      "learning_rate": 2.9857509402961814e-05,
+      "loss": 0.9561,
+      "step": 70
+    },
+    {
+      "epoch": 0.30303030303030304,
+      "grad_norm": 0.6419937014579773,
+      "learning_rate": 2.9807944096870547e-05,
+      "loss": 0.8987,
+      "step": 75
+    },
+    {
+      "epoch": 0.32323232323232326,
+      "grad_norm": 0.617689311504364,
+      "learning_rate": 2.9751048736301263e-05,
+      "loss": 0.8974,
+      "step": 80
+    },
+    {
+      "epoch": 0.3434343434343434,
+      "grad_norm": 0.6480937004089355,
+      "learning_rate": 2.968685148492677e-05,
+      "loss": 0.9117,
+      "step": 85
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 0.6021052002906799,
+      "learning_rate": 2.9615384120916058e-05,
+      "loss": 0.8423,
+      "step": 90
+    },
+    {
+      "epoch": 0.3838383838383838,
+      "grad_norm": 0.6355756521224976,
+      "learning_rate": 2.9536682021203852e-05,
+      "loss": 0.8218,
+      "step": 95
+    },
+    {
+      "epoch": 0.40404040404040403,
+      "grad_norm": 0.7710731029510498,
+      "learning_rate": 2.945078414397871e-05,
+      "loss": 0.8257,
+      "step": 100
+    },
+    {
+      "epoch": 0.42424242424242425,
+      "grad_norm": 0.7060940861701965,
+      "learning_rate": 2.9357733009398432e-05,
+      "loss": 0.8378,
+      "step": 105
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.7279723882675171,
+      "learning_rate": 2.9257574678542205e-05,
+      "loss": 0.7733,
+      "step": 110
+    },
+    {
+      "epoch": 0.46464646464646464,
+      "grad_norm": 0.7253962159156799,
+      "learning_rate": 2.9150358730610013e-05,
+      "loss": 0.7074,
+      "step": 115
+    },
+    {
+      "epoch": 0.48484848484848486,
+      "grad_norm": 0.7535879015922546,
+      "learning_rate": 2.903613823838049e-05,
+      "loss": 0.6699,
+      "step": 120
+    },
+    {
+      "epoch": 0.5050505050505051,
+      "grad_norm": 0.76394122838974,
+      "learning_rate": 2.8914969741939498e-05,
+      "loss": 0.6673,
+      "step": 125
+    },
+    {
+      "epoch": 0.5252525252525253,
+      "grad_norm": 0.7604217529296875,
+      "learning_rate": 2.8786913220692286e-05,
+      "loss": 0.617,
+      "step": 130
+    },
+    {
+      "epoch": 0.5454545454545454,
+      "grad_norm": 0.9433379173278809,
+      "learning_rate": 2.86520320636732e-05,
+      "loss": 0.6114,
+      "step": 135
+    },
+    {
+      "epoch": 0.5656565656565656,
+      "grad_norm": 0.8848206400871277,
+      "learning_rate": 2.8510393038167604e-05,
+      "loss": 0.61,
+      "step": 140
+    },
+    {
+      "epoch": 0.5858585858585859,
+      "grad_norm": 0.8993581533432007,
+      "learning_rate": 2.8362066256661484e-05,
+      "loss": 0.5436,
+      "step": 145
+    },
+    {
+      "epoch": 0.6060606060606061,
+      "grad_norm": 0.8953577280044556,
+      "learning_rate": 2.820712514213524e-05,
+      "loss": 0.6125,
+      "step": 150
+    },
+    {
+      "epoch": 0.6262626262626263,
+      "grad_norm": 0.9957013130187988,
+      "learning_rate": 2.8045646391718654e-05,
+      "loss": 0.5719,
+      "step": 155
+    },
+    {
+      "epoch": 0.6464646464646465,
+      "grad_norm": 0.923275351524353,
+      "learning_rate": 2.7877709938725216e-05,
+      "loss": 0.5219,
+      "step": 160
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.9695852398872375,
+      "learning_rate": 2.770339891308446e-05,
+      "loss": 0.5199,
+      "step": 165
+    },
+    {
+      "epoch": 0.6868686868686869,
+      "grad_norm": 0.9630404114723206,
+      "learning_rate": 2.7522799600191955e-05,
+      "loss": 0.53,
+      "step": 170
+    },
+    {
+      "epoch": 0.7070707070707071,
+      "grad_norm": 0.9288520216941833,
+      "learning_rate": 2.733600139819735e-05,
+      "loss": 0.5041,
+      "step": 175
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 0.9270612597465515,
+      "learning_rate": 2.7143096773751516e-05,
+      "loss": 0.5145,
+      "step": 180
+    },
+    {
+      "epoch": 0.7474747474747475,
+      "grad_norm": 1.0020592212677002,
+      "learning_rate": 2.6944181216234816e-05,
+      "loss": 0.4697,
+      "step": 185
+    },
+    {
+      "epoch": 0.7676767676767676,
+      "grad_norm": 1.0269843339920044,
+      "learning_rate": 2.673935319048906e-05,
+      "loss": 0.4463,
+      "step": 190
+    },
+    {
+      "epoch": 0.7878787878787878,
+      "grad_norm": 0.9221213459968567,
+      "learning_rate": 2.6528714088076624e-05,
+      "loss": 0.4026,
+      "step": 195
+    },
+    {
+      "epoch": 0.8080808080808081,
+      "grad_norm": 1.1049884557724,
+      "learning_rate": 2.6312368177090742e-05,
+      "loss": 0.4356,
+      "step": 200
+    },
+    {
+      "epoch": 0.8282828282828283,
+      "grad_norm": 1.081520438194275,
+      "learning_rate": 2.6090422550541983e-05,
+      "loss": 0.3916,
+      "step": 205
+    },
+    {
+      "epoch": 0.8484848484848485,
+      "grad_norm": 1.1152207851409912,
+      "learning_rate": 2.5862987073346308e-05,
+      "loss": 0.3934,
+      "step": 210
+    },
+    {
+      "epoch": 0.8686868686868687,
+      "grad_norm": 1.0529792308807373,
+      "learning_rate": 2.563017432794104e-05,
+      "loss": 0.3398,
+      "step": 215
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 1.1853700876235962,
+      "learning_rate": 2.5392099558555607e-05,
+      "loss": 0.3713,
+      "step": 220
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 1.336120843887329,
+      "learning_rate": 2.5148880614164726e-05,
+      "loss": 0.3607,
+      "step": 225
+    },
+    {
+      "epoch": 0.9292929292929293,
+      "grad_norm": 1.0502896308898926,
+      "learning_rate": 2.4900637890152177e-05,
+      "loss": 0.4355,
+      "step": 230
+    },
+    {
+      "epoch": 0.9494949494949495,
+      "grad_norm": 1.4311589002609253,
+      "learning_rate": 2.464749426871408e-05,
+      "loss": 0.3132,
+      "step": 235
+    },
+    {
+      "epoch": 0.9696969696969697,
+      "grad_norm": 1.079078197479248,
+      "learning_rate": 2.438957505803123e-05,
+      "loss": 0.3729,
+      "step": 240
+    },
+    {
+      "epoch": 0.98989898989899,
+      "grad_norm": 1.2745417356491089,
+      "learning_rate": 2.4127007930240467e-05,
+      "loss": 0.3496,
+      "step": 245
+    },
+    {
+      "epoch": 1.0080808080808081,
+      "grad_norm": 1.0512338876724243,
+      "learning_rate": 2.385992285823596e-05,
+      "loss": 0.2959,
+      "step": 250
+    },
+    {
+      "epoch": 1.0282828282828282,
+      "grad_norm": 0.9419404864311218,
+      "learning_rate": 2.358845205133152e-05,
+      "loss": 0.2544,
+      "step": 255
+    },
+    {
+      "epoch": 1.0484848484848486,
+      "grad_norm": 1.2208236455917358,
+      "learning_rate": 2.3312729889815915e-05,
+      "loss": 0.2228,
+      "step": 260
+    },
+    {
+      "epoch": 1.0686868686868687,
+      "grad_norm": 0.9114877581596375,
+      "learning_rate": 2.3032892858433515e-05,
+      "loss": 0.2692,
+      "step": 265
+    },
+    {
+      "epoch": 1.0888888888888888,
+      "grad_norm": 1.0464757680892944,
+      "learning_rate": 2.2749079478823224e-05,
+      "loss": 0.245,
+      "step": 270
+    },
+    {
+      "epoch": 1.1090909090909091,
+      "grad_norm": 1.0523908138275146,
+      "learning_rate": 2.24614302409491e-05,
+      "loss": 0.244,
+      "step": 275
+    },
+    {
+      "epoch": 1.1292929292929292,
+      "grad_norm": 1.1505963802337646,
+      "learning_rate": 2.217008753355671e-05,
+      "loss": 0.2266,
+      "step": 280
+    },
+    {
+      "epoch": 1.1494949494949496,
+      "grad_norm": 1.0628602504730225,
+      "learning_rate": 2.1875195573689476e-05,
+      "loss": 0.228,
+      "step": 285
+    },
+    {
+      "epoch": 1.1696969696969697,
+      "grad_norm": 0.9546335935592651,
+      "learning_rate": 2.157690033530009e-05,
+      "loss": 0.2308,
+      "step": 290
+    },
+    {
+      "epoch": 1.1898989898989898,
+      "grad_norm": 1.212188720703125,
+      "learning_rate": 2.1275349476992168e-05,
+      "loss": 0.1922,
+      "step": 295
+    },
+    {
+      "epoch": 1.2101010101010101,
+      "grad_norm": 1.1382962465286255,
+      "learning_rate": 2.0970692268928065e-05,
+      "loss": 0.1925,
+      "step": 300
+    },
+    {
+      "epoch": 1.2303030303030302,
+      "grad_norm": 1.131581425666809,
+      "learning_rate": 2.066307951893887e-05,
+      "loss": 0.2064,
+      "step": 305
+    },
+    {
+      "epoch": 1.2505050505050506,
+      "grad_norm": 0.9147361516952515,
+      "learning_rate": 2.0352663497873313e-05,
+      "loss": 0.2046,
+      "step": 310
+    },
+    {
+      "epoch": 1.2707070707070707,
+      "grad_norm": 1.103432059288025,
+      "learning_rate": 2.0039597864222423e-05,
+      "loss": 0.191,
+      "step": 315
+    },
+    {
+      "epoch": 1.290909090909091,
+      "grad_norm": 1.0171513557434082,
+      "learning_rate": 1.9724037588057334e-05,
+      "loss": 0.1959,
+      "step": 320
+    },
+    {
+      "epoch": 1.3111111111111111,
+      "grad_norm": 0.9062812328338623,
+      "learning_rate": 1.9406138874317777e-05,
+      "loss": 0.1698,
+      "step": 325
+    },
+    {
+      "epoch": 1.3313131313131312,
+      "grad_norm": 0.9124303460121155,
+      "learning_rate": 1.9086059085489393e-05,
+      "loss": 0.1768,
+      "step": 330
+    },
+    {
+      "epoch": 1.3515151515151516,
+      "grad_norm": 0.8741326332092285,
+      "learning_rate": 1.876395666370798e-05,
+      "loss": 0.1815,
+      "step": 335
+    },
+    {
+      "epoch": 1.3717171717171717,
+      "grad_norm": 0.8971191644668579,
+      "learning_rate": 1.8439991052329318e-05,
+      "loss": 0.1969,
+      "step": 340
+    },
+    {
+      "epoch": 1.391919191919192,
+      "grad_norm": 0.9709845781326294,
+      "learning_rate": 1.8114322617003417e-05,
+      "loss": 0.1654,
+      "step": 345
+    },
+    {
+      "epoch": 1.412121212121212,
+      "grad_norm": 1.1708210706710815,
+      "learning_rate": 1.7787112566292195e-05,
+      "loss": 0.1816,
+      "step": 350
+    },
+    {
+      "epoch": 1.4323232323232324,
+      "grad_norm": 1.0238475799560547,
+      "learning_rate": 1.745852287186989e-05,
+      "loss": 0.1605,
+      "step": 355
+    },
+    {
+      "epoch": 1.4525252525252526,
+      "grad_norm": 0.9854441285133362,
+      "learning_rate": 1.712871618834577e-05,
+      "loss": 0.1502,
+      "step": 360
+    },
+    {
+      "epoch": 1.4727272727272727,
+      "grad_norm": 0.9589694142341614,
+      "learning_rate": 1.6797855772748735e-05,
+      "loss": 0.148,
+      "step": 365
+    },
+    {
+      "epoch": 1.492929292929293,
+      "grad_norm": 0.9422476887702942,
+      "learning_rate": 1.646610540371375e-05,
+      "loss": 0.1535,
+      "step": 370
+    },
+    {
+      "epoch": 1.513131313131313,
+      "grad_norm": 1.0757137537002563,
+      "learning_rate": 1.613362930041009e-05,
+      "loss": 0.1484,
+      "step": 375
+    },
+    {
+      "epoch": 1.5333333333333332,
+      "grad_norm": 0.8407421708106995,
+      "learning_rate": 1.580059204125148e-05,
+      "loss": 0.1296,
+      "step": 380
+    },
+    {
+      "epoch": 1.5535353535353535,
+      "grad_norm": 1.0586841106414795,
+      "learning_rate": 1.5467158482428396e-05,
+      "loss": 0.1373,
+      "step": 385
+    },
+    {
+      "epoch": 1.5737373737373739,
+      "grad_norm": 0.9639503955841064,
+      "learning_rate": 1.5133493676302943e-05,
+      "loss": 0.1609,
+      "step": 390
+    },
+    {
+      "epoch": 1.593939393939394,
+      "grad_norm": 0.9714932441711426,
+      "learning_rate": 1.4799762789706533e-05,
+      "loss": 0.1239,
+      "step": 395
+    },
+    {
+      "epoch": 1.614141414141414,
+      "grad_norm": 0.9090800285339355,
+      "learning_rate": 1.4466131022180969e-05,
+      "loss": 0.1484,
+      "step": 400
+    },
+    {
+      "epoch": 1.6343434343434344,
+      "grad_norm": 0.8829744458198547,
+      "learning_rate": 1.4132763524203282e-05,
+      "loss": 0.1149,
+      "step": 405
+    },
+    {
+      "epoch": 1.6545454545454545,
+      "grad_norm": 0.8722601532936096,
+      "learning_rate": 1.3799825315434915e-05,
+      "loss": 0.1089,
+      "step": 410
+    },
+    {
+      "epoch": 1.6747474747474747,
+      "grad_norm": 0.9233741760253906,
+      "learning_rate": 1.3467481203035596e-05,
+      "loss": 0.1244,
+      "step": 415
+    },
+    {
+      "epoch": 1.694949494949495,
+      "grad_norm": 0.9405210018157959,
+      "learning_rate": 1.3135895700082447e-05,
+      "loss": 0.1311,
+      "step": 420
+    },
+    {
+      "epoch": 1.7151515151515153,
+      "grad_norm": 0.9141501784324646,
+      "learning_rate": 1.280523294413467e-05,
+      "loss": 0.1248,
+      "step": 425
+    },
+    {
+      "epoch": 1.7353535353535352,
+      "grad_norm": 0.8744235634803772,
+      "learning_rate": 1.2475656615984087e-05,
+      "loss": 0.1062,
+      "step": 430
+    },
+    {
+      "epoch": 1.7555555555555555,
+      "grad_norm": 0.9677907228469849,
+      "learning_rate": 1.214732985863178e-05,
+      "loss": 0.1,
+      "step": 435
+    },
+    {
+      "epoch": 1.7757575757575759,
+      "grad_norm": 0.980177104473114,
+      "learning_rate": 1.1820415196531006e-05,
+      "loss": 0.1099,
+      "step": 440
+    },
+    {
+      "epoch": 1.795959595959596,
+      "grad_norm": 0.915195882320404,
+      "learning_rate": 1.1495074455136192e-05,
+      "loss": 0.1075,
+      "step": 445
+    },
+    {
+      "epoch": 1.816161616161616,
+      "grad_norm": 0.9488334059715271,
+      "learning_rate": 1.1171468680798063e-05,
+      "loss": 0.1056,
+      "step": 450
+    },
+    {
+      "epoch": 1.8363636363636364,
+      "grad_norm": 0.8250184655189514,
+      "learning_rate": 1.0849758061044325e-05,
+      "loss": 0.1157,
+      "step": 455
+    },
+    {
+      "epoch": 1.8565656565656565,
+      "grad_norm": 0.6576221585273743,
+      "learning_rate": 1.0530101845285524e-05,
+      "loss": 0.0971,
+      "step": 460
+    },
+    {
+      "epoch": 1.8767676767676766,
+      "grad_norm": 1.0479968786239624,
+      "learning_rate": 1.02126582659853e-05,
+      "loss": 0.0976,
+      "step": 465
+    },
+    {
+      "epoch": 1.896969696969697,
+      "grad_norm": 0.8208566308021545,
+      "learning_rate": 9.897584460333978e-06,
+      "loss": 0.1144,
+      "step": 470
+    },
+    {
+      "epoch": 1.9171717171717173,
+      "grad_norm": 0.7009485960006714,
+      "learning_rate": 9.585036392464382e-06,
+      "loss": 0.0883,
+      "step": 475
+    },
+    {
+      "epoch": 1.9373737373737374,
+      "grad_norm": 0.9521411061286926,
+      "learning_rate": 9.275168776248316e-06,
+      "loss": 0.1043,
+      "step": 480
+    },
+    {
+      "epoch": 1.9575757575757575,
+      "grad_norm": 0.7295394539833069,
+      "learning_rate": 8.968134998711877e-06,
+      "loss": 0.0983,
+      "step": 485
+    },
+    {
+      "epoch": 1.9777777777777779,
+      "grad_norm": 0.8923431634902954,
+      "learning_rate": 8.664087044107664e-06,
+      "loss": 0.0886,
+      "step": 490
+    },
+    {
+      "epoch": 1.997979797979798,
+      "grad_norm": 0.8398289680480957,
+      "learning_rate": 8.363175418681276e-06,
+      "loss": 0.097,
+      "step": 495
+    },
+    {
+      "epoch": 2.0161616161616163,
+      "grad_norm": 0.7890457510948181,
+      "learning_rate": 8.065549076169506e-06,
+      "loss": 0.0703,
+      "step": 500
+    },
+    {
+      "epoch": 2.036363636363636,
+      "grad_norm": 0.7598493695259094,
+      "learning_rate": 7.77135534406701e-06,
+      "loss": 0.0681,
+      "step": 505
+    },
+    {
+      "epoch": 2.0565656565656565,
+      "grad_norm": 0.639715313911438,
+      "learning_rate": 7.48073985069796e-06,
+      "loss": 0.0637,
+      "step": 510
+    },
+    {
+      "epoch": 2.076767676767677,
+      "grad_norm": 0.5689536929130554,
+      "learning_rate": 7.193846453128853e-06,
+      "loss": 0.077,
+      "step": 515
+    },
+    {
+      "epoch": 2.096969696969697,
+      "grad_norm": 0.618879497051239,
+      "learning_rate": 6.910817165958064e-06,
+      "loss": 0.0652,
+      "step": 520
+    },
+    {
+      "epoch": 2.117171717171717,
+      "grad_norm": 0.6915852427482605,
+      "learning_rate": 6.631792091017424e-06,
+      "loss": 0.0664,
+      "step": 525
+    },
+    {
+      "epoch": 2.1373737373737374,
+      "grad_norm": 0.5904918909072876,
+      "learning_rate": 6.356909348020708e-06,
+      "loss": 0.0683,
+      "step": 530
+    },
+    {
+      "epoch": 2.1575757575757577,
+      "grad_norm": 0.5817981958389282,
+      "learning_rate": 6.086305006193188e-06,
+      "loss": 0.0633,
+      "step": 535
+    },
+    {
+      "epoch": 2.1777777777777776,
+      "grad_norm": 0.6204066276550293,
+      "learning_rate": 5.820113016916266e-06,
+      "loss": 0.0624,
+      "step": 540
+    },
+    {
+      "epoch": 2.197979797979798,
+      "grad_norm": 0.4501434564590454,
+      "learning_rate": 5.55846514742045e-06,
+      "loss": 0.0585,
+      "step": 545
+    },
+    {
+      "epoch": 2.2181818181818183,
+      "grad_norm": 0.6880552172660828,
+      "learning_rate": 5.301490915559458e-06,
+      "loss": 0.0678,
+      "step": 550
+    },
+    {
+      "epoch": 2.2383838383838386,
+      "grad_norm": 0.5709707736968994,
+      "learning_rate": 5.049317525697824e-06,
+      "loss": 0.0569,
+      "step": 555
+    },
+    {
+      "epoch": 2.2585858585858585,
+      "grad_norm": 0.4669952988624573,
+      "learning_rate": 4.8020698057437066e-06,
+      "loss": 0.063,
+      "step": 560
+    },
+    {
+      "epoch": 2.278787878787879,
+      "grad_norm": 0.5587053298950195,
+      "learning_rate": 4.559870145358008e-06,
+      "loss": 0.0673,
+      "step": 565
+    },
+    {
+      "epoch": 2.298989898989899,
+      "grad_norm": 0.5415369868278503,
+      "learning_rate": 4.32283843537052e-06,
+      "loss": 0.0635,
+      "step": 570
+    },
+    {
+      "epoch": 2.319191919191919,
+      "grad_norm": 0.6544260382652283,
+      "learning_rate": 4.091092008432955e-06,
+      "loss": 0.0591,
+      "step": 575
+    },
+    {
+      "epoch": 2.3393939393939394,
+      "grad_norm": 0.5746409296989441,
+      "learning_rate": 3.864745580938301e-06,
+      "loss": 0.059,
+      "step": 580
+    },
+    {
+      "epoch": 2.3595959595959597,
+      "grad_norm": 0.6202763915061951,
+      "learning_rate": 3.643911196235302e-06,
+      "loss": 0.0661,
+      "step": 585
+    },
+    {
+      "epoch": 2.3797979797979796,
+      "grad_norm": 0.4987029731273651,
+      "learning_rate": 3.4286981691660307e-06,
+      "loss": 0.0584,
+      "step": 590
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.4316190779209137,
+      "learning_rate": 3.2192130319541656e-06,
+      "loss": 0.0625,
+      "step": 595
+    },
+    {
+      "epoch": 2.4202020202020202,
+      "grad_norm": 0.5163561701774597,
+      "learning_rate": 3.0155594814706715e-06,
+      "loss": 0.0663,
+      "step": 600
+    },
+    {
+      "epoch": 2.4404040404040406,
+      "grad_norm": 0.5109818577766418,
+      "learning_rate": 2.8178383279029563e-06,
+      "loss": 0.0548,
+      "step": 605
+    },
+    {
+      "epoch": 2.4606060606060605,
+      "grad_norm": 0.4645656943321228,
+      "learning_rate": 2.6261474448530358e-06,
+      "loss": 0.0547,
+      "step": 610
+    },
+    {
+      "epoch": 2.480808080808081,
+      "grad_norm": 0.6087458729743958,
+      "learning_rate": 2.440581720889263e-06,
+      "loss": 0.0666,
+      "step": 615
+    },
+    {
+      "epoch": 2.501010101010101,
+      "grad_norm": 0.5689340829849243,
+      "learning_rate": 2.261233012575727e-06,
+      "loss": 0.0528,
+      "step": 620
+    },
+    {
+      "epoch": 2.5212121212121215,
+      "grad_norm": 0.509185254573822,
+      "learning_rate": 2.0881900990024843e-06,
+      "loss": 0.0537,
+      "step": 625
+    },
+    {
+      "epoch": 2.5414141414141413,
+      "grad_norm": 0.5946642160415649,
+      "learning_rate": 1.9215386378391763e-06,
+      "loss": 0.0614,
+      "step": 630
+    },
+    {
+      "epoch": 2.5616161616161617,
+      "grad_norm": 0.5521068572998047,
+      "learning_rate": 1.761361122933774e-06,
+      "loss": 0.0642,
+      "step": 635
+    },
+    {
+      "epoch": 2.581818181818182,
+      "grad_norm": 0.5498470664024353,
+      "learning_rate": 1.6077368434774598e-06,
+      "loss": 0.0563,
+      "step": 640
+    },
+    {
+      "epoch": 2.602020202020202,
+      "grad_norm": 0.5059285759925842,
+      "learning_rate": 1.4607418447557973e-06,
+      "loss": 0.057,
+      "step": 645
+    },
+    {
+      "epoch": 2.6222222222222222,
+      "grad_norm": 0.5822315812110901,
+      "learning_rate": 1.3204488905057161e-06,
+      "loss": 0.0488,
+      "step": 650
+    },
+    {
+      "epoch": 2.6424242424242426,
+      "grad_norm": 0.5468267202377319,
+      "learning_rate": 1.1869274268968355e-06,
+      "loss": 0.0554,
+      "step": 655
+    },
+    {
+      "epoch": 2.6626262626262625,
+      "grad_norm": 0.5982303023338318,
+      "learning_rate": 1.0602435481550532e-06,
+      "loss": 0.0532,
+      "step": 660
+    },
+    {
+      "epoch": 2.682828282828283,
+      "grad_norm": 0.48310360312461853,
+      "learning_rate": 9.404599638453598e-07,
+      "loss": 0.0555,
+      "step": 665
+    },
+    {
+      "epoch": 2.703030303030303,
+      "grad_norm": 0.4655357301235199,
+      "learning_rate": 8.276359678300754e-07,
+      "loss": 0.0513,
+      "step": 670
+    },
+    {
+      "epoch": 2.723232323232323,
+      "grad_norm": 0.5590468645095825,
+      "learning_rate": 7.218274089179094e-07,
+      "loss": 0.0535,
+      "step": 675
+    },
+    {
+      "epoch": 2.7434343434343433,
+      "grad_norm": 0.5310546159744263,
+      "learning_rate": 6.230866632183346e-07,
+      "loss": 0.0591,
+      "step": 680
+    },
+    {
+      "epoch": 2.7636363636363637,
+      "grad_norm": 0.49370062351226807,
+      "learning_rate": 5.314626082149765e-07,
+      "loss": 0.0549,
+      "step": 685
+    },
+    {
+      "epoch": 2.783838383838384,
+      "grad_norm": 0.5669305324554443,
+      "learning_rate": 4.470005985708669e-07,
+      "loss": 0.053,
+      "step": 690
+    },
+    {
+      "epoch": 2.804040404040404,
+      "grad_norm": 0.45064178109169006,
+      "learning_rate": 3.697424436775032e-07,
+      "loss": 0.0557,
+      "step": 695
+    },
+    {
+      "epoch": 2.824242424242424,
+      "grad_norm": 0.464415967464447,
+      "learning_rate": 2.9972638695885455e-07,
+      "loss": 0.0599,
+      "step": 700
+    },
+    {
+      "epoch": 2.8444444444444446,
+      "grad_norm": 0.495160847902298,
+      "learning_rate": 2.3698708694055883e-07,
+      "loss": 0.0561,
+      "step": 705
+    },
+    {
+      "epoch": 2.864646464646465,
+      "grad_norm": 0.41633203625679016,
+      "learning_rate": 1.8155560009365746e-07,
+      "loss": 0.0507,
+      "step": 710
+    },
+    {
+      "epoch": 2.8848484848484848,
+      "grad_norm": 0.5706247687339783,
+      "learning_rate": 1.334593654613897e-07,
+      "loss": 0.0578,
+      "step": 715
+    },
+    {
+      "epoch": 2.905050505050505,
+      "grad_norm": 0.49245262145996094,
+      "learning_rate": 9.272219107664403e-08,
+      "loss": 0.0599,
+      "step": 720
+    },
+    {
+      "epoch": 2.9252525252525254,
+      "grad_norm": 0.5039171576499939,
+      "learning_rate": 5.936424217678038e-08,
+      "loss": 0.0568,
+      "step": 725
+    },
+    {
+      "epoch": 2.9454545454545453,
+      "grad_norm": 0.45153215527534485,
+      "learning_rate": 3.340203122167152e-08,
+      "loss": 0.0545,
+      "step": 730
+    },
+    {
+      "epoch": 2.9656565656565657,
+      "grad_norm": 0.5878562927246094,
+      "learning_rate": 1.4848409719901423e-08,
+      "loss": 0.0554,
+      "step": 735
+    },
+    {
+      "epoch": 2.985858585858586,
+      "grad_norm": 0.44086387753486633,
+      "learning_rate": 3.7125618671624004e-09,
+      "loss": 0.0505,
+      "step": 740
+    },
+    {
+      "epoch": 3.0,
+      "step": 744,
+      "total_flos": 9.378169474315715e+17,
+      "train_loss": 0.3240591349500802,
+      "train_runtime": 459.0345,
+      "train_samples_per_second": 51.676,
+      "train_steps_per_second": 1.621
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 744,
+  "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": 9.378169474315715e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

12_128_e3_3e-5/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b571840f3e27b36787a170b1fa652fef1f7d54c8de0f195672505dadd353d275
+size 8273