Upload folder using huggingface_hub

17_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": [
+    "k_proj",
+    "gate_proj",
+    "q_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

17_128_e3_3e-5/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ccb7491a08b8de095c83c31ccc23aacda1626a7dd2690913bae3ed4b82a4524
+size 791751704

17_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
+}

17_128_e3_3e-5/all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.1298912994076918e+18,
+    "train_loss": 0.5665953403028349,
+    "train_runtime": 552.775,
+    "train_samples": 8178,
+    "train_samples_per_second": 44.383,
+    "train_steps_per_second": 1.389
+}

17_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 %}

17_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
+}

17_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
+  }
+}

17_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
+}

17_128_e3_3e-5/train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.1298912994076918e+18,
+    "train_loss": 0.5665953403028349,
+    "train_runtime": 552.775,
+    "train_samples": 8178,
+    "train_samples_per_second": 44.383,
+    "train_steps_per_second": 1.389
+}

17_128_e3_3e-5/trainer_state.json

@@ -0,0 +1,1114 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 768,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01953125,
+      "grad_norm": 3.1383931636810303,
+      "learning_rate": 3.076923076923077e-06,
+      "loss": 1.5543,
+      "step": 5
+    },
+    {
+      "epoch": 0.0390625,
+      "grad_norm": 1.6390661001205444,
+      "learning_rate": 6.923076923076923e-06,
+      "loss": 1.4877,
+      "step": 10
+    },
+    {
+      "epoch": 0.05859375,
+      "grad_norm": 0.6421475410461426,
+      "learning_rate": 1.076923076923077e-05,
+      "loss": 1.3168,
+      "step": 15
+    },
+    {
+      "epoch": 0.078125,
+      "grad_norm": 0.48416709899902344,
+      "learning_rate": 1.4615384615384615e-05,
+      "loss": 1.2907,
+      "step": 20
+    },
+    {
+      "epoch": 0.09765625,
+      "grad_norm": 0.40633898973464966,
+      "learning_rate": 1.8461538461538465e-05,
+      "loss": 1.32,
+      "step": 25
+    },
+    {
+      "epoch": 0.1171875,
+      "grad_norm": 0.40214061737060547,
+      "learning_rate": 2.230769230769231e-05,
+      "loss": 1.3151,
+      "step": 30
+    },
+    {
+      "epoch": 0.13671875,
+      "grad_norm": 0.40871015191078186,
+      "learning_rate": 2.6153846153846157e-05,
+      "loss": 1.231,
+      "step": 35
+    },
+    {
+      "epoch": 0.15625,
+      "grad_norm": 0.34605494141578674,
+      "learning_rate": 3e-05,
+      "loss": 1.2512,
+      "step": 40
+    },
+    {
+      "epoch": 0.17578125,
+      "grad_norm": 0.33398985862731934,
+      "learning_rate": 2.999651799686565e-05,
+      "loss": 1.1721,
+      "step": 45
+    },
+    {
+      "epoch": 0.1953125,
+      "grad_norm": 0.35665401816368103,
+      "learning_rate": 2.9986073604042044e-05,
+      "loss": 1.2024,
+      "step": 50
+    },
+    {
+      "epoch": 0.21484375,
+      "grad_norm": 0.39820751547813416,
+      "learning_rate": 2.9968671670516984e-05,
+      "loss": 1.1245,
+      "step": 55
+    },
+    {
+      "epoch": 0.234375,
+      "grad_norm": 0.368132621049881,
+      "learning_rate": 2.9944320275435414e-05,
+      "loss": 1.1733,
+      "step": 60
+    },
+    {
+      "epoch": 0.25390625,
+      "grad_norm": 0.4207707643508911,
+      "learning_rate": 2.9913030724348538e-05,
+      "loss": 1.1472,
+      "step": 65
+    },
+    {
+      "epoch": 0.2734375,
+      "grad_norm": 0.43501046299934387,
+      "learning_rate": 2.9874817543965017e-05,
+      "loss": 1.105,
+      "step": 70
+    },
+    {
+      "epoch": 0.29296875,
+      "grad_norm": 0.4568362534046173,
+      "learning_rate": 2.98296984754067e-05,
+      "loss": 1.1228,
+      "step": 75
+    },
+    {
+      "epoch": 0.3125,
+      "grad_norm": 0.42272624373435974,
+      "learning_rate": 2.9777694465972e-05,
+      "loss": 1.0742,
+      "step": 80
+    },
+    {
+      "epoch": 0.33203125,
+      "grad_norm": 0.4641646444797516,
+      "learning_rate": 2.9718829659410772e-05,
+      "loss": 1.0501,
+      "step": 85
+    },
+    {
+      "epoch": 0.3515625,
+      "grad_norm": 0.4563515782356262,
+      "learning_rate": 2.965313138471513e-05,
+      "loss": 1.0682,
+      "step": 90
+    },
+    {
+      "epoch": 0.37109375,
+      "grad_norm": 0.44149050116539,
+      "learning_rate": 2.958063014343155e-05,
+      "loss": 1.0858,
+      "step": 95
+    },
+    {
+      "epoch": 0.390625,
+      "grad_norm": 0.5081347227096558,
+      "learning_rate": 2.9501359595499933e-05,
+      "loss": 0.9863,
+      "step": 100
+    },
+    {
+      "epoch": 0.41015625,
+      "grad_norm": 0.5404679775238037,
+      "learning_rate": 2.9415356543626463e-05,
+      "loss": 0.9541,
+      "step": 105
+    },
+    {
+      "epoch": 0.4296875,
+      "grad_norm": 0.5417282581329346,
+      "learning_rate": 2.93226609161973e-05,
+      "loss": 0.9818,
+      "step": 110
+    },
+    {
+      "epoch": 0.44921875,
+      "grad_norm": 0.5277360677719116,
+      "learning_rate": 2.9223315748741146e-05,
+      "loss": 0.9728,
+      "step": 115
+    },
+    {
+      "epoch": 0.46875,
+      "grad_norm": 0.5711668133735657,
+      "learning_rate": 2.9117367163949264e-05,
+      "loss": 1.0013,
+      "step": 120
+    },
+    {
+      "epoch": 0.48828125,
+      "grad_norm": 0.5627371072769165,
+      "learning_rate": 2.9004864350262227e-05,
+      "loss": 0.9992,
+      "step": 125
+    },
+    {
+      "epoch": 0.5078125,
+      "grad_norm": 0.561695396900177,
+      "learning_rate": 2.888585953903336e-05,
+      "loss": 0.9464,
+      "step": 130
+    },
+    {
+      "epoch": 0.52734375,
+      "grad_norm": 0.6736053824424744,
+      "learning_rate": 2.876040798027941e-05,
+      "loss": 0.9301,
+      "step": 135
+    },
+    {
+      "epoch": 0.546875,
+      "grad_norm": 0.5874242782592773,
+      "learning_rate": 2.862856791702982e-05,
+      "loss": 0.8846,
+      "step": 140
+    },
+    {
+      "epoch": 0.56640625,
+      "grad_norm": 0.7331199645996094,
+      "learning_rate": 2.8490400558286396e-05,
+      "loss": 0.889,
+      "step": 145
+    },
+    {
+      "epoch": 0.5859375,
+      "grad_norm": 0.6232196688652039,
+      "learning_rate": 2.8345970050605957e-05,
+      "loss": 0.8894,
+      "step": 150
+    },
+    {
+      "epoch": 0.60546875,
+      "grad_norm": 0.6326808929443359,
+      "learning_rate": 2.819534344831923e-05,
+      "loss": 0.8873,
+      "step": 155
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 0.6482338309288025,
+      "learning_rate": 2.8038590682399716e-05,
+      "loss": 0.8483,
+      "step": 160
+    },
+    {
+      "epoch": 0.64453125,
+      "grad_norm": 0.6995515823364258,
+      "learning_rate": 2.7875784527997054e-05,
+      "loss": 0.8213,
+      "step": 165
+    },
+    {
+      "epoch": 0.6640625,
+      "grad_norm": 0.6749407052993774,
+      "learning_rate": 2.77070005706499e-05,
+      "loss": 0.8177,
+      "step": 170
+    },
+    {
+      "epoch": 0.68359375,
+      "grad_norm": 0.781916081905365,
+      "learning_rate": 2.753231717119405e-05,
+      "loss": 0.7966,
+      "step": 175
+    },
+    {
+      "epoch": 0.703125,
+      "grad_norm": 0.8330166339874268,
+      "learning_rate": 2.7351815429382094e-05,
+      "loss": 0.7982,
+      "step": 180
+    },
+    {
+      "epoch": 0.72265625,
+      "grad_norm": 0.7608205080032349,
+      "learning_rate": 2.716557914623147e-05,
+      "loss": 0.7926,
+      "step": 185
+    },
+    {
+      "epoch": 0.7421875,
+      "grad_norm": 0.7750307321548462,
+      "learning_rate": 2.6973694785118392e-05,
+      "loss": 0.7875,
+      "step": 190
+    },
+    {
+      "epoch": 0.76171875,
+      "grad_norm": 0.7497373223304749,
+      "learning_rate": 2.677625143163578e-05,
+      "loss": 0.779,
+      "step": 195
+    },
+    {
+      "epoch": 0.78125,
+      "grad_norm": 0.7408276796340942,
+      "learning_rate": 2.6573340752233722e-05,
+      "loss": 0.777,
+      "step": 200
+    },
+    {
+      "epoch": 0.80078125,
+      "grad_norm": 0.7607304453849792,
+      "learning_rate": 2.636505695166177e-05,
+      "loss": 0.7468,
+      "step": 205
+    },
+    {
+      "epoch": 0.8203125,
+      "grad_norm": 0.7739957571029663,
+      "learning_rate": 2.6151496729232783e-05,
+      "loss": 0.7633,
+      "step": 210
+    },
+    {
+      "epoch": 0.83984375,
+      "grad_norm": 0.8870716691017151,
+      "learning_rate": 2.593275923392861e-05,
+      "loss": 0.7747,
+      "step": 215
+    },
+    {
+      "epoch": 0.859375,
+      "grad_norm": 0.8436111211776733,
+      "learning_rate": 2.570894601836849e-05,
+      "loss": 0.7267,
+      "step": 220
+    },
+    {
+      "epoch": 0.87890625,
+      "grad_norm": 0.8782322406768799,
+      "learning_rate": 2.5480160991661486e-05,
+      "loss": 0.7461,
+      "step": 225
+    },
+    {
+      "epoch": 0.8984375,
+      "grad_norm": 0.8208799958229065,
+      "learning_rate": 2.5246510371164962e-05,
+      "loss": 0.709,
+      "step": 230
+    },
+    {
+      "epoch": 0.91796875,
+      "grad_norm": 0.8468010425567627,
+      "learning_rate": 2.500810263317129e-05,
+      "loss": 0.6856,
+      "step": 235
+    },
+    {
+      "epoch": 0.9375,
+      "grad_norm": 0.8275279402732849,
+      "learning_rate": 2.4765048462545948e-05,
+      "loss": 0.6764,
+      "step": 240
+    },
+    {
+      "epoch": 0.95703125,
+      "grad_norm": 0.8666420578956604,
+      "learning_rate": 2.451746070134011e-05,
+      "loss": 0.6686,
+      "step": 245
+    },
+    {
+      "epoch": 0.9765625,
+      "grad_norm": 0.8077290058135986,
+      "learning_rate": 2.4265454296401857e-05,
+      "loss": 0.6925,
+      "step": 250
+    },
+    {
+      "epoch": 0.99609375,
+      "grad_norm": 0.8838790059089661,
+      "learning_rate": 2.4009146246010104e-05,
+      "loss": 0.6133,
+      "step": 255
+    },
+    {
+      "epoch": 1.015625,
+      "grad_norm": 1.0220916271209717,
+      "learning_rate": 2.374865554555616e-05,
+      "loss": 0.6312,
+      "step": 260
+    },
+    {
+      "epoch": 1.03515625,
+      "grad_norm": 0.9665728807449341,
+      "learning_rate": 2.3484103132298082e-05,
+      "loss": 0.5275,
+      "step": 265
+    },
+    {
+      "epoch": 1.0546875,
+      "grad_norm": 0.9312376976013184,
+      "learning_rate": 2.3215611829213494e-05,
+      "loss": 0.5827,
+      "step": 270
+    },
+    {
+      "epoch": 1.07421875,
+      "grad_norm": 0.9194116592407227,
+      "learning_rate": 2.294330628797692e-05,
+      "loss": 0.5304,
+      "step": 275
+    },
+    {
+      "epoch": 1.09375,
+      "grad_norm": 0.9477877616882324,
+      "learning_rate": 2.2667312931088098e-05,
+      "loss": 0.5353,
+      "step": 280
+    },
+    {
+      "epoch": 1.11328125,
+      "grad_norm": 0.9735198020935059,
+      "learning_rate": 2.2387759893178198e-05,
+      "loss": 0.5398,
+      "step": 285
+    },
+    {
+      "epoch": 1.1328125,
+      "grad_norm": 1.0165029764175415,
+      "learning_rate": 2.2104776961521112e-05,
+      "loss": 0.4841,
+      "step": 290
+    },
+    {
+      "epoch": 1.15234375,
+      "grad_norm": 0.9267258644104004,
+      "learning_rate": 2.181849551577751e-05,
+      "loss": 0.5252,
+      "step": 295
+    },
+    {
+      "epoch": 1.171875,
+      "grad_norm": 0.9795359969139099,
+      "learning_rate": 2.1529048466999575e-05,
+      "loss": 0.5555,
+      "step": 300
+    },
+    {
+      "epoch": 1.19140625,
+      "grad_norm": 0.9942501783370972,
+      "learning_rate": 2.123657019592479e-05,
+      "loss": 0.6176,
+      "step": 305
+    },
+    {
+      "epoch": 1.2109375,
+      "grad_norm": 1.1302388906478882,
+      "learning_rate": 2.0941196490587352e-05,
+      "loss": 0.4788,
+      "step": 310
+    },
+    {
+      "epoch": 1.23046875,
+      "grad_norm": 1.0195372104644775,
+      "learning_rate": 2.064306448327632e-05,
+      "loss": 0.5016,
+      "step": 315
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 1.001145839691162,
+      "learning_rate": 2.034231258686954e-05,
+      "loss": 0.5129,
+      "step": 320
+    },
+    {
+      "epoch": 1.26953125,
+      "grad_norm": 0.9527642726898193,
+      "learning_rate": 2.0039080430573133e-05,
+      "loss": 0.4693,
+      "step": 325
+    },
+    {
+      "epoch": 1.2890625,
+      "grad_norm": 1.0448925495147705,
+      "learning_rate": 1.9733508795096263e-05,
+      "loss": 0.5064,
+      "step": 330
+    },
+    {
+      "epoch": 1.30859375,
+      "grad_norm": 1.031494140625,
+      "learning_rate": 1.942573954729126e-05,
+      "loss": 0.5264,
+      "step": 335
+    },
+    {
+      "epoch": 1.328125,
+      "grad_norm": 1.0759159326553345,
+      "learning_rate": 1.9115915574289523e-05,
+      "loss": 0.5117,
+      "step": 340
+    },
+    {
+      "epoch": 1.34765625,
+      "grad_norm": 1.0379421710968018,
+      "learning_rate": 1.8804180717163732e-05,
+      "loss": 0.5027,
+      "step": 345
+    },
+    {
+      "epoch": 1.3671875,
+      "grad_norm": 1.0447694063186646,
+      "learning_rate": 1.849067970414717e-05,
+      "loss": 0.4846,
+      "step": 350
+    },
+    {
+      "epoch": 1.38671875,
+      "grad_norm": 0.9789708256721497,
+      "learning_rate": 1.8175558083441162e-05,
+      "loss": 0.4882,
+      "step": 355
+    },
+    {
+      "epoch": 1.40625,
+      "grad_norm": 1.023229718208313,
+      "learning_rate": 1.7858962155641842e-05,
+      "loss": 0.4598,
+      "step": 360
+    },
+    {
+      "epoch": 1.42578125,
+      "grad_norm": 1.1130712032318115,
+      "learning_rate": 1.754103890581759e-05,
+      "loss": 0.4585,
+      "step": 365
+    },
+    {
+      "epoch": 1.4453125,
+      "grad_norm": 1.1177476644515991,
+      "learning_rate": 1.7221935935268736e-05,
+      "loss": 0.498,
+      "step": 370
+    },
+    {
+      "epoch": 1.46484375,
+      "grad_norm": 1.0728689432144165,
+      "learning_rate": 1.6901801393001082e-05,
+      "loss": 0.5079,
+      "step": 375
+    },
+    {
+      "epoch": 1.484375,
+      "grad_norm": 1.0094231367111206,
+      "learning_rate": 1.658078390694526e-05,
+      "loss": 0.4234,
+      "step": 380
+    },
+    {
+      "epoch": 1.50390625,
+      "grad_norm": 0.9503285884857178,
+      "learning_rate": 1.62590325149536e-05,
+      "loss": 0.4814,
+      "step": 385
+    },
+    {
+      "epoch": 1.5234375,
+      "grad_norm": 1.0814573764801025,
+      "learning_rate": 1.593669659560684e-05,
+      "loss": 0.4231,
+      "step": 390
+    },
+    {
+      "epoch": 1.54296875,
+      "grad_norm": 1.0490305423736572,
+      "learning_rate": 1.5613925798862497e-05,
+      "loss": 0.5019,
+      "step": 395
+    },
+    {
+      "epoch": 1.5625,
+      "grad_norm": 0.9533276557922363,
+      "learning_rate": 1.5290869976577365e-05,
+      "loss": 0.4156,
+      "step": 400
+    },
+    {
+      "epoch": 1.58203125,
+      "grad_norm": 1.1729451417922974,
+      "learning_rate": 1.4967679112936222e-05,
+      "loss": 0.436,
+      "step": 405
+    },
+    {
+      "epoch": 1.6015625,
+      "grad_norm": 1.0673277378082275,
+      "learning_rate": 1.4644503254819081e-05,
+      "loss": 0.4336,
+      "step": 410
+    },
+    {
+      "epoch": 1.62109375,
+      "grad_norm": 1.1203042268753052,
+      "learning_rate": 1.4321492442139406e-05,
+      "loss": 0.4462,
+      "step": 415
+    },
+    {
+      "epoch": 1.640625,
+      "grad_norm": 1.1950432062149048,
+      "learning_rate": 1.3998796638185483e-05,
+      "loss": 0.3728,
+      "step": 420
+    },
+    {
+      "epoch": 1.66015625,
+      "grad_norm": 1.0610283613204956,
+      "learning_rate": 1.3676565659997423e-05,
+      "loss": 0.4328,
+      "step": 425
+    },
+    {
+      "epoch": 1.6796875,
+      "grad_norm": 1.142575740814209,
+      "learning_rate": 1.3354949108812026e-05,
+      "loss": 0.3976,
+      "step": 430
+    },
+    {
+      "epoch": 1.69921875,
+      "grad_norm": 1.069541096687317,
+      "learning_rate": 1.3034096300607871e-05,
+      "loss": 0.4525,
+      "step": 435
+    },
+    {
+      "epoch": 1.71875,
+      "grad_norm": 1.0276211500167847,
+      "learning_rate": 1.2714156196782793e-05,
+      "loss": 0.3761,
+      "step": 440
+    },
+    {
+      "epoch": 1.73828125,
+      "grad_norm": 1.1425074338912964,
+      "learning_rate": 1.2395277334996045e-05,
+      "loss": 0.392,
+      "step": 445
+    },
+    {
+      "epoch": 1.7578125,
+      "grad_norm": 1.103362798690796,
+      "learning_rate": 1.2077607760207115e-05,
+      "loss": 0.3657,
+      "step": 450
+    },
+    {
+      "epoch": 1.77734375,
+      "grad_norm": 1.0173449516296387,
+      "learning_rate": 1.1761294955943357e-05,
+      "loss": 0.3954,
+      "step": 455
+    },
+    {
+      "epoch": 1.796875,
+      "grad_norm": 1.0743807554244995,
+      "learning_rate": 1.1446485775828212e-05,
+      "loss": 0.4214,
+      "step": 460
+    },
+    {
+      "epoch": 1.81640625,
+      "grad_norm": 1.2360502481460571,
+      "learning_rate": 1.1133326375401943e-05,
+      "loss": 0.4028,
+      "step": 465
+    },
+    {
+      "epoch": 1.8359375,
+      "grad_norm": 1.13153076171875,
+      "learning_rate": 1.0821962144266382e-05,
+      "loss": 0.3762,
+      "step": 470
+    },
+    {
+      "epoch": 1.85546875,
+      "grad_norm": 1.0574029684066772,
+      "learning_rate": 1.0512537638585379e-05,
+      "loss": 0.3832,
+      "step": 475
+    },
+    {
+      "epoch": 1.875,
+      "grad_norm": 1.1452330350875854,
+      "learning_rate": 1.0205196513972067e-05,
+      "loss": 0.348,
+      "step": 480
+    },
+    {
+      "epoch": 1.89453125,
+      "grad_norm": 1.1096911430358887,
+      "learning_rate": 9.900081458794346e-06,
+      "loss": 0.3522,
+      "step": 485
+    },
+    {
+      "epoch": 1.9140625,
+      "grad_norm": 1.1626777648925781,
+      "learning_rate": 9.597334127929346e-06,
+      "loss": 0.3866,
+      "step": 490
+    },
+    {
+      "epoch": 1.93359375,
+      "grad_norm": 1.1333059072494507,
+      "learning_rate": 9.297095076997733e-06,
+      "loss": 0.3973,
+      "step": 495
+    },
+    {
+      "epoch": 1.953125,
+      "grad_norm": 1.1854597330093384,
+      "learning_rate": 8.99950369710836e-06,
+      "loss": 0.3954,
+      "step": 500
+    },
+    {
+      "epoch": 1.97265625,
+      "grad_norm": 1.1135122776031494,
+      "learning_rate": 8.704698150143564e-06,
+      "loss": 0.3486,
+      "step": 505
+    },
+    {
+      "epoch": 1.9921875,
+      "grad_norm": 1.3198022842407227,
+      "learning_rate": 8.412815304615157e-06,
+      "loss": 0.3737,
+      "step": 510
+    },
+    {
+      "epoch": 2.01171875,
+      "grad_norm": 0.957240104675293,
+      "learning_rate": 8.123990672120862e-06,
+      "loss": 0.3315,
+      "step": 515
+    },
+    {
+      "epoch": 2.03125,
+      "grad_norm": 1.2183798551559448,
+      "learning_rate": 7.838358344430765e-06,
+      "loss": 0.2561,
+      "step": 520
+    },
+    {
+      "epoch": 2.05078125,
+      "grad_norm": 1.1712363958358765,
+      "learning_rate": 7.55605093123291e-06,
+      "loss": 0.2915,
+      "step": 525
+    },
+    {
+      "epoch": 2.0703125,
+      "grad_norm": 1.0194687843322754,
+      "learning_rate": 7.277199498566976e-06,
+      "loss": 0.2766,
+      "step": 530
+    },
+    {
+      "epoch": 2.08984375,
+      "grad_norm": 1.0474824905395508,
+      "learning_rate": 7.001933507974635e-06,
+      "loss": 0.2813,
+      "step": 535
+    },
+    {
+      "epoch": 2.109375,
+      "grad_norm": 1.0934371948242188,
+      "learning_rate": 6.730380756394818e-06,
+      "loss": 0.2959,
+      "step": 540
+    },
+    {
+      "epoch": 2.12890625,
+      "grad_norm": 1.0281903743743896,
+      "learning_rate": 6.462667316831824e-06,
+      "loss": 0.2755,
+      "step": 545
+    },
+    {
+      "epoch": 2.1484375,
+      "grad_norm": 1.1825693845748901,
+      "learning_rate": 6.198917479823733e-06,
+      "loss": 0.2693,
+      "step": 550
+    },
+    {
+      "epoch": 2.16796875,
+      "grad_norm": 1.270400881767273,
+      "learning_rate": 5.939253695738434e-06,
+      "loss": 0.2416,
+      "step": 555
+    },
+    {
+      "epoch": 2.1875,
+      "grad_norm": 1.0473029613494873,
+      "learning_rate": 5.68379651792393e-06,
+      "loss": 0.2838,
+      "step": 560
+    },
+    {
+      "epoch": 2.20703125,
+      "grad_norm": 1.0587785243988037,
+      "learning_rate": 5.4326645467394085e-06,
+      "loss": 0.2838,
+      "step": 565
+    },
+    {
+      "epoch": 2.2265625,
+      "grad_norm": 1.0841484069824219,
+      "learning_rate": 5.185974374492979e-06,
+      "loss": 0.279,
+      "step": 570
+    },
+    {
+      "epoch": 2.24609375,
+      "grad_norm": 1.2056200504302979,
+      "learning_rate": 4.943840531311686e-06,
+      "loss": 0.2708,
+      "step": 575
+    },
+    {
+      "epoch": 2.265625,
+      "grad_norm": 1.3920224905014038,
+      "learning_rate": 4.706375431968998e-06,
+      "loss": 0.251,
+      "step": 580
+    },
+    {
+      "epoch": 2.28515625,
+      "grad_norm": 1.1235448122024536,
+      "learning_rate": 4.4736893236942735e-06,
+      "loss": 0.2767,
+      "step": 585
+    },
+    {
+      "epoch": 2.3046875,
+      "grad_norm": 1.3568105697631836,
+      "learning_rate": 4.245890234988621e-06,
+      "loss": 0.2959,
+      "step": 590
+    },
+    {
+      "epoch": 2.32421875,
+      "grad_norm": 1.1306527853012085,
+      "learning_rate": 4.0230839254708196e-06,
+      "loss": 0.2786,
+      "step": 595
+    },
+    {
+      "epoch": 2.34375,
+      "grad_norm": 1.2573482990264893,
+      "learning_rate": 3.8053738367766254e-06,
+      "loss": 0.293,
+      "step": 600
+    },
+    {
+      "epoch": 2.36328125,
+      "grad_norm": 1.0662962198257446,
+      "learning_rate": 3.5928610445341937e-06,
+      "loss": 0.3002,
+      "step": 605
+    },
+    {
+      "epoch": 2.3828125,
+      "grad_norm": 1.02361261844635,
+      "learning_rate": 3.3856442114380132e-06,
+      "loss": 0.278,
+      "step": 610
+    },
+    {
+      "epoch": 2.40234375,
+      "grad_norm": 1.1286258697509766,
+      "learning_rate": 3.183819541443068e-06,
+      "loss": 0.3143,
+      "step": 615
+    },
+    {
+      "epoch": 2.421875,
+      "grad_norm": 1.2413147687911987,
+      "learning_rate": 2.98748073510049e-06,
+      "loss": 0.285,
+      "step": 620
+    },
+    {
+      "epoch": 2.44140625,
+      "grad_norm": 1.1101950407028198,
+      "learning_rate": 2.7967189460554876e-06,
+      "loss": 0.2858,
+      "step": 625
+    },
+    {
+      "epoch": 2.4609375,
+      "grad_norm": 1.1539525985717773,
+      "learning_rate": 2.6116227387277087e-06,
+      "loss": 0.2704,
+      "step": 630
+    },
+    {
+      "epoch": 2.48046875,
+      "grad_norm": 1.1819263696670532,
+      "learning_rate": 2.432278047193703e-06,
+      "loss": 0.2748,
+      "step": 635
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 1.0345772504806519,
+      "learning_rate": 2.2587681352905404e-06,
+      "loss": 0.2743,
+      "step": 640
+    },
+    {
+      "epoch": 2.51953125,
+      "grad_norm": 1.1466171741485596,
+      "learning_rate": 2.091173557959164e-06,
+      "loss": 0.2891,
+      "step": 645
+    },
+    {
+      "epoch": 2.5390625,
+      "grad_norm": 1.061362624168396,
+      "learning_rate": 1.9295721238453816e-06,
+      "loss": 0.2778,
+      "step": 650
+    },
+    {
+      "epoch": 2.55859375,
+      "grad_norm": 1.122710943222046,
+      "learning_rate": 1.77403885917588e-06,
+      "loss": 0.2942,
+      "step": 655
+    },
+    {
+      "epoch": 2.578125,
+      "grad_norm": 1.1733002662658691,
+      "learning_rate": 1.6246459729259978e-06,
+      "loss": 0.2701,
+      "step": 660
+    },
+    {
+      "epoch": 2.59765625,
+      "grad_norm": 1.1695150136947632,
+      "learning_rate": 1.481462823295492e-06,
+      "loss": 0.2342,
+      "step": 665
+    },
+    {
+      "epoch": 2.6171875,
+      "grad_norm": 1.2957613468170166,
+      "learning_rate": 1.3445558855078017e-06,
+      "loss": 0.2958,
+      "step": 670
+    },
+    {
+      "epoch": 2.63671875,
+      "grad_norm": 1.117563247680664,
+      "learning_rate": 1.2139887209477923e-06,
+      "loss": 0.277,
+      "step": 675
+    },
+    {
+      "epoch": 2.65625,
+      "grad_norm": 1.1406030654907227,
+      "learning_rate": 1.0898219476522992e-06,
+      "loss": 0.2934,
+      "step": 680
+    },
+    {
+      "epoch": 2.67578125,
+      "grad_norm": 1.0905430316925049,
+      "learning_rate": 9.721132121671556e-07,
+      "loss": 0.2513,
+      "step": 685
+    },
+    {
+      "epoch": 2.6953125,
+      "grad_norm": 1.0716758966445923,
+      "learning_rate": 8.609171627838202e-07,
+      "loss": 0.2734,
+      "step": 690
+    },
+    {
+      "epoch": 2.71484375,
+      "grad_norm": 1.1891450881958008,
+      "learning_rate": 7.562854241679573e-07,
+      "loss": 0.2958,
+      "step": 695
+    },
+    {
+      "epoch": 2.734375,
+      "grad_norm": 1.1458114385604858,
+      "learning_rate": 6.582665733918064e-07,
+      "loss": 0.2705,
+      "step": 700
+    },
+    {
+      "epoch": 2.75390625,
+      "grad_norm": 1.0290416479110718,
+      "learning_rate": 5.669061173814499e-07,
+      "loss": 0.2657,
+      "step": 705
+    },
+    {
+      "epoch": 2.7734375,
+      "grad_norm": 1.1414786577224731,
+      "learning_rate": 4.822464717894482e-07,
+      "loss": 0.2572,
+      "step": 710
+    },
+    {
+      "epoch": 2.79296875,
+      "grad_norm": 1.1263461112976074,
+      "learning_rate": 4.043269413026429e-07,
+      "loss": 0.2522,
+      "step": 715
+    },
+    {
+      "epoch": 2.8125,
+      "grad_norm": 1.1186355352401733,
+      "learning_rate": 3.331837013942829e-07,
+      "loss": 0.301,
+      "step": 720
+    },
+    {
+      "epoch": 2.83203125,
+      "grad_norm": 0.9675784707069397,
+      "learning_rate": 2.688497815289465e-07,
+      "loss": 0.2976,
+      "step": 725
+    },
+    {
+      "epoch": 2.8515625,
+      "grad_norm": 1.213611125946045,
+      "learning_rate": 2.113550498280531e-07,
+      "loss": 0.2591,
+      "step": 730
+    },
+    {
+      "epoch": 2.87109375,
+      "grad_norm": 1.110132098197937,
+      "learning_rate": 1.6072619920306563e-07,
+      "loss": 0.2649,
+      "step": 735
+    },
+    {
+      "epoch": 2.890625,
+      "grad_norm": 1.1303397417068481,
+      "learning_rate": 1.1698673496285839e-07,
+      "loss": 0.2387,
+      "step": 740
+    },
+    {
+      "epoch": 2.91015625,
+      "grad_norm": 1.0428801774978638,
+      "learning_rate": 8.015696390097805e-08,
+      "loss": 0.2489,
+      "step": 745
+    },
+    {
+      "epoch": 2.9296875,
+      "grad_norm": 1.0938302278518677,
+      "learning_rate": 5.025398486786015e-08,
+      "loss": 0.2592,
+      "step": 750
+    },
+    {
+      "epoch": 2.94921875,
+      "grad_norm": 1.0481960773468018,
+      "learning_rate": 2.7291680832400854e-08,
+      "loss": 0.2683,
+      "step": 755
+    },
+    {
+      "epoch": 2.96875,
+      "grad_norm": 1.132848858833313,
+      "learning_rate": 1.1280712436549379e-08,
+      "loss": 0.2604,
+      "step": 760
+    },
+    {
+      "epoch": 2.98828125,
+      "grad_norm": 1.0351567268371582,
+      "learning_rate": 2.2285130459237523e-09,
+      "loss": 0.2619,
+      "step": 765
+    },
+    {
+      "epoch": 3.0,
+      "step": 768,
+      "total_flos": 1.1298912994076918e+18,
+      "train_loss": 0.5665953403028349,
+      "train_runtime": 552.775,
+      "train_samples_per_second": 44.383,
+      "train_steps_per_second": 1.389
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 768,
+  "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": 1.1298912994076918e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

17_128_e3_3e-5/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e13fb8b4c7d02172e2c79f54e5cf374ea4dc9eb7b964898fffbeb5883e014daf
+size 8209