Upload folder using huggingface_hub

115_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",
+    "q_proj",
+    "o_proj",
+    "k_proj",
+    "v_proj",
+    "up_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

115_128_e3_3e-5/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c72feac6b7a87aacb5f57a8564013541839bf5e491d76c09b19e21e45806039
+size 791751704

115_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
+}

115_128_e3_3e-5/all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.0029700814303396e+18,
+    "train_loss": 0.6438727126121521,
+    "train_runtime": 475.7024,
+    "train_samples": 7983,
+    "train_samples_per_second": 50.345,
+    "train_steps_per_second": 1.577
+}

115_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 %}

115_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
+}

115_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
+  }
+}

115_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
+}

115_128_e3_3e-5/train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.0029700814303396e+18,
+    "train_loss": 0.6438727126121521,
+    "train_runtime": 475.7024,
+    "train_samples": 7983,
+    "train_samples_per_second": 50.345,
+    "train_steps_per_second": 1.577
+}

115_128_e3_3e-5/trainer_state.json

@@ -0,0 +1,1093 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 750,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02004008016032064,
+      "grad_norm": 3.3200788497924805,
+      "learning_rate": 3.157894736842105e-06,
+      "loss": 1.6839,
+      "step": 5
+    },
+    {
+      "epoch": 0.04008016032064128,
+      "grad_norm": 1.7503838539123535,
+      "learning_rate": 7.105263157894737e-06,
+      "loss": 1.6462,
+      "step": 10
+    },
+    {
+      "epoch": 0.06012024048096192,
+      "grad_norm": 0.7024543881416321,
+      "learning_rate": 1.1052631578947368e-05,
+      "loss": 1.4963,
+      "step": 15
+    },
+    {
+      "epoch": 0.08016032064128256,
+      "grad_norm": 0.47365453839302063,
+      "learning_rate": 1.5e-05,
+      "loss": 1.4822,
+      "step": 20
+    },
+    {
+      "epoch": 0.10020040080160321,
+      "grad_norm": 0.42603984475135803,
+      "learning_rate": 1.894736842105263e-05,
+      "loss": 1.413,
+      "step": 25
+    },
+    {
+      "epoch": 0.12024048096192384,
+      "grad_norm": 0.40488094091415405,
+      "learning_rate": 2.2894736842105263e-05,
+      "loss": 1.4506,
+      "step": 30
+    },
+    {
+      "epoch": 0.1402805611222445,
+      "grad_norm": 0.43644070625305176,
+      "learning_rate": 2.6842105263157896e-05,
+      "loss": 1.3803,
+      "step": 35
+    },
+    {
+      "epoch": 0.16032064128256512,
+      "grad_norm": 0.37978091835975647,
+      "learning_rate": 2.999985398404377e-05,
+      "loss": 1.3786,
+      "step": 40
+    },
+    {
+      "epoch": 0.18036072144288579,
+      "grad_norm": 0.4362293481826782,
+      "learning_rate": 2.999474372405878e-05,
+      "loss": 1.3478,
+      "step": 45
+    },
+    {
+      "epoch": 0.20040080160320642,
+      "grad_norm": 0.4014089107513428,
+      "learning_rate": 2.9982335508768143e-05,
+      "loss": 1.282,
+      "step": 50
+    },
+    {
+      "epoch": 0.22044088176352705,
+      "grad_norm": 0.4273519217967987,
+      "learning_rate": 2.9962635377261457e-05,
+      "loss": 1.2687,
+      "step": 55
+    },
+    {
+      "epoch": 0.24048096192384769,
+      "grad_norm": 0.4610331356525421,
+      "learning_rate": 2.99356529176105e-05,
+      "loss": 1.3046,
+      "step": 60
+    },
+    {
+      "epoch": 0.2605210420841683,
+      "grad_norm": 0.38731348514556885,
+      "learning_rate": 2.9901401262202743e-05,
+      "loss": 1.2288,
+      "step": 65
+    },
+    {
+      "epoch": 0.280561122244489,
+      "grad_norm": 0.4429171085357666,
+      "learning_rate": 2.9859897081349793e-05,
+      "loss": 1.2249,
+      "step": 70
+    },
+    {
+      "epoch": 0.30060120240480964,
+      "grad_norm": 0.49021974205970764,
+      "learning_rate": 2.981116057517393e-05,
+      "loss": 1.1765,
+      "step": 75
+    },
+    {
+      "epoch": 0.32064128256513025,
+      "grad_norm": 0.40991291403770447,
+      "learning_rate": 2.9755215463776702e-05,
+      "loss": 1.2516,
+      "step": 80
+    },
+    {
+      "epoch": 0.3406813627254509,
+      "grad_norm": 0.5414031744003296,
+      "learning_rate": 2.969208897569433e-05,
+      "loss": 1.1813,
+      "step": 85
+    },
+    {
+      "epoch": 0.36072144288577157,
+      "grad_norm": 0.5517223477363586,
+      "learning_rate": 2.9621811834645543e-05,
+      "loss": 1.1842,
+      "step": 90
+    },
+    {
+      "epoch": 0.3807615230460922,
+      "grad_norm": 0.5835243463516235,
+      "learning_rate": 2.954441824457832e-05,
+      "loss": 1.1538,
+      "step": 95
+    },
+    {
+      "epoch": 0.40080160320641284,
+      "grad_norm": 0.5459833145141602,
+      "learning_rate": 2.945994587302282e-05,
+      "loss": 1.127,
+      "step": 100
+    },
+    {
+      "epoch": 0.42084168336673344,
+      "grad_norm": 0.5214282870292664,
+      "learning_rate": 2.936843583275852e-05,
+      "loss": 1.1215,
+      "step": 105
+    },
+    {
+      "epoch": 0.4408817635270541,
+      "grad_norm": 0.5345780253410339,
+      "learning_rate": 2.9269932661804623e-05,
+      "loss": 1.1132,
+      "step": 110
+    },
+    {
+      "epoch": 0.46092184368737477,
+      "grad_norm": 0.5967327356338501,
+      "learning_rate": 2.9164484301743336e-05,
+      "loss": 1.1231,
+      "step": 115
+    },
+    {
+      "epoch": 0.48096192384769537,
+      "grad_norm": 0.5445071458816528,
+      "learning_rate": 2.9052142074386702e-05,
+      "loss": 1.0795,
+      "step": 120
+    },
+    {
+      "epoch": 0.501002004008016,
+      "grad_norm": 0.6122811436653137,
+      "learning_rate": 2.8932960656798166e-05,
+      "loss": 1.0385,
+      "step": 125
+    },
+    {
+      "epoch": 0.5210420841683366,
+      "grad_norm": 0.6005417704582214,
+      "learning_rate": 2.880699805468126e-05,
+      "loss": 0.9809,
+      "step": 130
+    },
+    {
+      "epoch": 0.5410821643286573,
+      "grad_norm": 0.6102535724639893,
+      "learning_rate": 2.8674315574148126e-05,
+      "loss": 1.0284,
+      "step": 135
+    },
+    {
+      "epoch": 0.561122244488978,
+      "grad_norm": 0.6601172089576721,
+      "learning_rate": 2.8534977791881816e-05,
+      "loss": 0.9798,
+      "step": 140
+    },
+    {
+      "epoch": 0.5811623246492986,
+      "grad_norm": 0.6648281812667847,
+      "learning_rate": 2.8389052523706733e-05,
+      "loss": 0.9965,
+      "step": 145
+    },
+    {
+      "epoch": 0.6012024048096193,
+      "grad_norm": 0.6806595921516418,
+      "learning_rate": 2.823661079158261e-05,
+      "loss": 1.0158,
+      "step": 150
+    },
+    {
+      "epoch": 0.6212424849699398,
+      "grad_norm": 0.7179291248321533,
+      "learning_rate": 2.8077726789038077e-05,
+      "loss": 0.9686,
+      "step": 155
+    },
+    {
+      "epoch": 0.6412825651302605,
+      "grad_norm": 0.7424024343490601,
+      "learning_rate": 2.79124778450606e-05,
+      "loss": 0.9648,
+      "step": 160
+    },
+    {
+      "epoch": 0.6613226452905812,
+      "grad_norm": 0.6682973504066467,
+      "learning_rate": 2.7740944386460365e-05,
+      "loss": 0.9568,
+      "step": 165
+    },
+    {
+      "epoch": 0.6813627254509018,
+      "grad_norm": 0.8077454566955566,
+      "learning_rate": 2.7563209898726516e-05,
+      "loss": 0.9468,
+      "step": 170
+    },
+    {
+      "epoch": 0.7014028056112225,
+      "grad_norm": 0.7717909216880798,
+      "learning_rate": 2.7379360885394664e-05,
+      "loss": 0.9086,
+      "step": 175
+    },
+    {
+      "epoch": 0.7214428857715431,
+      "grad_norm": 0.7511861324310303,
+      "learning_rate": 2.7189486825945547e-05,
+      "loss": 0.8653,
+      "step": 180
+    },
+    {
+      "epoch": 0.7414829659318637,
+      "grad_norm": 0.7697199583053589,
+      "learning_rate": 2.6993680132255295e-05,
+      "loss": 0.9085,
+      "step": 185
+    },
+    {
+      "epoch": 0.7615230460921844,
+      "grad_norm": 0.8253837823867798,
+      "learning_rate": 2.6792036103618474e-05,
+      "loss": 0.845,
+      "step": 190
+    },
+    {
+      "epoch": 0.781563126252505,
+      "grad_norm": 0.8070823550224304,
+      "learning_rate": 2.6584652880365833e-05,
+      "loss": 0.8553,
+      "step": 195
+    },
+    {
+      "epoch": 0.8016032064128257,
+      "grad_norm": 0.7676147222518921,
+      "learning_rate": 2.6371631396099333e-05,
+      "loss": 0.8187,
+      "step": 200
+    },
+    {
+      "epoch": 0.8216432865731463,
+      "grad_norm": 0.9684513211250305,
+      "learning_rate": 2.615307532856764e-05,
+      "loss": 0.8288,
+      "step": 205
+    },
+    {
+      "epoch": 0.8416833667334669,
+      "grad_norm": 0.9055765271186829,
+      "learning_rate": 2.5929091049206117e-05,
+      "loss": 0.829,
+      "step": 210
+    },
+    {
+      "epoch": 0.8617234468937875,
+      "grad_norm": 0.8487976789474487,
+      "learning_rate": 2.5699787571365704e-05,
+      "loss": 0.8395,
+      "step": 215
+    },
+    {
+      "epoch": 0.8817635270541082,
+      "grad_norm": 0.8775982856750488,
+      "learning_rate": 2.5465276497256048e-05,
+      "loss": 0.8031,
+      "step": 220
+    },
+    {
+      "epoch": 0.9018036072144289,
+      "grad_norm": 0.8825764060020447,
+      "learning_rate": 2.52256719636286e-05,
+      "loss": 0.7715,
+      "step": 225
+    },
+    {
+      "epoch": 0.9218436873747495,
+      "grad_norm": 0.9472184181213379,
+      "learning_rate": 2.4981090586226166e-05,
+      "loss": 0.826,
+      "step": 230
+    },
+    {
+      "epoch": 0.9418837675350702,
+      "grad_norm": 0.8982250094413757,
+      "learning_rate": 2.4731651403025895e-05,
+      "loss": 0.7925,
+      "step": 235
+    },
+    {
+      "epoch": 0.9619238476953907,
+      "grad_norm": 0.826982855796814,
+      "learning_rate": 2.4477475816303404e-05,
+      "loss": 0.7411,
+      "step": 240
+    },
+    {
+      "epoch": 0.9819639278557114,
+      "grad_norm": 1.0849860906600952,
+      "learning_rate": 2.4218687533546193e-05,
+      "loss": 0.7503,
+      "step": 245
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.2125478982925415,
+      "learning_rate": 2.3955412507245078e-05,
+      "loss": 0.7728,
+      "step": 250
+    },
+    {
+      "epoch": 1.0200400801603207,
+      "grad_norm": 1.2186928987503052,
+      "learning_rate": 2.3687778873593e-05,
+      "loss": 0.6625,
+      "step": 255
+    },
+    {
+      "epoch": 1.0400801603206413,
+      "grad_norm": 0.9570342302322388,
+      "learning_rate": 2.3415916890121047e-05,
+      "loss": 0.6553,
+      "step": 260
+    },
+    {
+      "epoch": 1.060120240480962,
+      "grad_norm": 1.1315847635269165,
+      "learning_rate": 2.313995887230197e-05,
+      "loss": 0.6475,
+      "step": 265
+    },
+    {
+      "epoch": 1.0801603206412826,
+      "grad_norm": 1.0117372274398804,
+      "learning_rate": 2.2860039129152136e-05,
+      "loss": 0.651,
+      "step": 270
+    },
+    {
+      "epoch": 1.1002004008016033,
+      "grad_norm": 0.9991538524627686,
+      "learning_rate": 2.257629389786321e-05,
+      "loss": 0.6313,
+      "step": 275
+    },
+    {
+      "epoch": 1.1202404809619237,
+      "grad_norm": 1.1838078498840332,
+      "learning_rate": 2.2288861277495382e-05,
+      "loss": 0.6213,
+      "step": 280
+    },
+    {
+      "epoch": 1.1402805611222444,
+      "grad_norm": 1.0087109804153442,
+      "learning_rate": 2.1997881161764448e-05,
+      "loss": 0.6076,
+      "step": 285
+    },
+    {
+      "epoch": 1.160320641282565,
+      "grad_norm": 1.0252777338027954,
+      "learning_rate": 2.1703495170955382e-05,
+      "loss": 0.5886,
+      "step": 290
+    },
+    {
+      "epoch": 1.1803607214428857,
+      "grad_norm": 0.9676551818847656,
+      "learning_rate": 2.140584658299564e-05,
+      "loss": 0.6595,
+      "step": 295
+    },
+    {
+      "epoch": 1.2004008016032064,
+      "grad_norm": 1.0769116878509521,
+      "learning_rate": 2.1105080263721663e-05,
+      "loss": 0.6259,
+      "step": 300
+    },
+    {
+      "epoch": 1.220440881763527,
+      "grad_norm": 1.087152123451233,
+      "learning_rate": 2.0801342596372522e-05,
+      "loss": 0.6027,
+      "step": 305
+    },
+    {
+      "epoch": 1.2404809619238477,
+      "grad_norm": 1.2080010175704956,
+      "learning_rate": 2.0494781410345098e-05,
+      "loss": 0.5857,
+      "step": 310
+    },
+    {
+      "epoch": 1.2605210420841684,
+      "grad_norm": 1.17201566696167,
+      "learning_rate": 2.0185545909245344e-05,
+      "loss": 0.5834,
+      "step": 315
+    },
+    {
+      "epoch": 1.280561122244489,
+      "grad_norm": 1.0871398448944092,
+      "learning_rate": 1.9873786598270786e-05,
+      "loss": 0.5998,
+      "step": 320
+    },
+    {
+      "epoch": 1.3006012024048097,
+      "grad_norm": 1.059487223625183,
+      "learning_rate": 1.955965521095948e-05,
+      "loss": 0.577,
+      "step": 325
+    },
+    {
+      "epoch": 1.3206412825651301,
+      "grad_norm": 1.1104919910430908,
+      "learning_rate": 1.9243304635341182e-05,
+      "loss": 0.5861,
+      "step": 330
+    },
+    {
+      "epoch": 1.340681362725451,
+      "grad_norm": 1.1382052898406982,
+      "learning_rate": 1.8924888839526612e-05,
+      "loss": 0.5507,
+      "step": 335
+    },
+    {
+      "epoch": 1.3607214428857715,
+      "grad_norm": 1.0925004482269287,
+      "learning_rate": 1.8604562796771006e-05,
+      "loss": 0.5843,
+      "step": 340
+    },
+    {
+      "epoch": 1.3807615230460921,
+      "grad_norm": 0.9554914236068726,
+      "learning_rate": 1.828248241004852e-05,
+      "loss": 0.5775,
+      "step": 345
+    },
+    {
+      "epoch": 1.4008016032064128,
+      "grad_norm": 1.2553672790527344,
+      "learning_rate": 1.7958804436174103e-05,
+      "loss": 0.5528,
+      "step": 350
+    },
+    {
+      "epoch": 1.4208416833667334,
+      "grad_norm": 1.1677736043930054,
+      "learning_rate": 1.763368640950981e-05,
+      "loss": 0.5472,
+      "step": 355
+    },
+    {
+      "epoch": 1.440881763527054,
+      "grad_norm": 1.1018515825271606,
+      "learning_rate": 1.7307286565292687e-05,
+      "loss": 0.5607,
+      "step": 360
+    },
+    {
+      "epoch": 1.4609218436873748,
+      "grad_norm": 1.053301215171814,
+      "learning_rate": 1.6979763762621545e-05,
+      "loss": 0.5196,
+      "step": 365
+    },
+    {
+      "epoch": 1.4809619238476954,
+      "grad_norm": 1.2030258178710938,
+      "learning_rate": 1.6651277407140086e-05,
+      "loss": 0.5234,
+      "step": 370
+    },
+    {
+      "epoch": 1.5010020040080159,
+      "grad_norm": 1.147634744644165,
+      "learning_rate": 1.632198737345403e-05,
+      "loss": 0.4913,
+      "step": 375
+    },
+    {
+      "epoch": 1.5210420841683367,
+      "grad_norm": 1.0710277557373047,
+      "learning_rate": 1.5992053927320006e-05,
+      "loss": 0.4986,
+      "step": 380
+    },
+    {
+      "epoch": 1.5410821643286572,
+      "grad_norm": 1.2427271604537964,
+      "learning_rate": 1.5661637647644072e-05,
+      "loss": 0.5093,
+      "step": 385
+    },
+    {
+      "epoch": 1.561122244488978,
+      "grad_norm": 1.1794772148132324,
+      "learning_rate": 1.5330899348327798e-05,
+      "loss": 0.5041,
+      "step": 390
+    },
+    {
+      "epoch": 1.5811623246492985,
+      "grad_norm": 1.2393157482147217,
+      "learning_rate": 1.5e-05,
+      "loss": 0.5192,
+      "step": 395
+    },
+    {
+      "epoch": 1.6012024048096194,
+      "grad_norm": 1.1379992961883545,
+      "learning_rate": 1.4669100651672204e-05,
+      "loss": 0.493,
+      "step": 400
+    },
+    {
+      "epoch": 1.6212424849699398,
+      "grad_norm": 1.1212973594665527,
+      "learning_rate": 1.4338362352355932e-05,
+      "loss": 0.448,
+      "step": 405
+    },
+    {
+      "epoch": 1.6412825651302605,
+      "grad_norm": 1.3343461751937866,
+      "learning_rate": 1.4007946072679995e-05,
+      "loss": 0.5138,
+      "step": 410
+    },
+    {
+      "epoch": 1.6613226452905812,
+      "grad_norm": 1.0492912530899048,
+      "learning_rate": 1.3678012626545978e-05,
+      "loss": 0.478,
+      "step": 415
+    },
+    {
+      "epoch": 1.6813627254509018,
+      "grad_norm": 1.2217761278152466,
+      "learning_rate": 1.3348722592859918e-05,
+      "loss": 0.4647,
+      "step": 420
+    },
+    {
+      "epoch": 1.7014028056112225,
+      "grad_norm": 1.162033200263977,
+      "learning_rate": 1.3020236237378454e-05,
+      "loss": 0.4822,
+      "step": 425
+    },
+    {
+      "epoch": 1.7214428857715431,
+      "grad_norm": 1.3511017560958862,
+      "learning_rate": 1.2692713434707316e-05,
+      "loss": 0.4501,
+      "step": 430
+    },
+    {
+      "epoch": 1.7414829659318638,
+      "grad_norm": 1.142655611038208,
+      "learning_rate": 1.236631359049019e-05,
+      "loss": 0.4602,
+      "step": 435
+    },
+    {
+      "epoch": 1.7615230460921842,
+      "grad_norm": 1.209466814994812,
+      "learning_rate": 1.2041195563825898e-05,
+      "loss": 0.4552,
+      "step": 440
+    },
+    {
+      "epoch": 1.7815631262525051,
+      "grad_norm": 1.1695128679275513,
+      "learning_rate": 1.1717517589951479e-05,
+      "loss": 0.5039,
+      "step": 445
+    },
+    {
+      "epoch": 1.8016032064128256,
+      "grad_norm": 1.2609868049621582,
+      "learning_rate": 1.1395437203228997e-05,
+      "loss": 0.4429,
+      "step": 450
+    },
+    {
+      "epoch": 1.8216432865731464,
+      "grad_norm": 1.2701613903045654,
+      "learning_rate": 1.1075111160473392e-05,
+      "loss": 0.4727,
+      "step": 455
+    },
+    {
+      "epoch": 1.8416833667334669,
+      "grad_norm": 1.0969090461730957,
+      "learning_rate": 1.0756695364658818e-05,
+      "loss": 0.4435,
+      "step": 460
+    },
+    {
+      "epoch": 1.8617234468937875,
+      "grad_norm": 1.2653807401657104,
+      "learning_rate": 1.0440344789040528e-05,
+      "loss": 0.4644,
+      "step": 465
+    },
+    {
+      "epoch": 1.8817635270541082,
+      "grad_norm": 1.1458615064620972,
+      "learning_rate": 1.0126213401729218e-05,
+      "loss": 0.42,
+      "step": 470
+    },
+    {
+      "epoch": 1.9018036072144289,
+      "grad_norm": 1.1465989351272583,
+      "learning_rate": 9.814454090754654e-06,
+      "loss": 0.4458,
+      "step": 475
+    },
+    {
+      "epoch": 1.9218436873747495,
+      "grad_norm": 1.1481294631958008,
+      "learning_rate": 9.505218589654904e-06,
+      "loss": 0.4722,
+      "step": 480
+    },
+    {
+      "epoch": 1.9418837675350702,
+      "grad_norm": 1.4207531213760376,
+      "learning_rate": 9.198657403627477e-06,
+      "loss": 0.3764,
+      "step": 485
+    },
+    {
+      "epoch": 1.9619238476953909,
+      "grad_norm": 1.1853859424591064,
+      "learning_rate": 8.894919736278343e-06,
+      "loss": 0.427,
+      "step": 490
+    },
+    {
+      "epoch": 1.9819639278557113,
+      "grad_norm": 1.1927540302276611,
+      "learning_rate": 8.594153417004359e-06,
+      "loss": 0.4064,
+      "step": 495
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.6930960416793823,
+      "learning_rate": 8.296504829044619e-06,
+      "loss": 0.426,
+      "step": 500
+    },
+    {
+      "epoch": 2.0200400801603204,
+      "grad_norm": 1.2124725580215454,
+      "learning_rate": 8.002118838235551e-06,
+      "loss": 0.3522,
+      "step": 505
+    },
+    {
+      "epoch": 2.0400801603206413,
+      "grad_norm": 1.454325556755066,
+      "learning_rate": 7.711138722504615e-06,
+      "loss": 0.3769,
+      "step": 510
+    },
+    {
+      "epoch": 2.0601202404809618,
+      "grad_norm": 1.1478029489517212,
+      "learning_rate": 7.423706102136791e-06,
+      "loss": 0.3556,
+      "step": 515
+    },
+    {
+      "epoch": 2.0801603206412826,
+      "grad_norm": 1.279224157333374,
+      "learning_rate": 7.139960870847866e-06,
+      "loss": 0.3299,
+      "step": 520
+    },
+    {
+      "epoch": 2.100200400801603,
+      "grad_norm": 1.3238208293914795,
+      "learning_rate": 6.860041127698033e-06,
+      "loss": 0.327,
+      "step": 525
+    },
+    {
+      "epoch": 2.120240480961924,
+      "grad_norm": 1.1876386404037476,
+      "learning_rate": 6.584083109878955e-06,
+      "loss": 0.3133,
+      "step": 530
+    },
+    {
+      "epoch": 2.1402805611222444,
+      "grad_norm": 1.2439100742340088,
+      "learning_rate": 6.312221126406996e-06,
+      "loss": 0.3103,
+      "step": 535
+    },
+    {
+      "epoch": 2.1603206412825653,
+      "grad_norm": 1.3915127515792847,
+      "learning_rate": 6.044587492754926e-06,
+      "loss": 0.3429,
+      "step": 540
+    },
+    {
+      "epoch": 2.1803607214428857,
+      "grad_norm": 1.2462666034698486,
+      "learning_rate": 5.781312466453806e-06,
+      "loss": 0.3926,
+      "step": 545
+    },
+    {
+      "epoch": 2.2004008016032066,
+      "grad_norm": 1.1474131345748901,
+      "learning_rate": 5.522524183696602e-06,
+      "loss": 0.3337,
+      "step": 550
+    },
+    {
+      "epoch": 2.220440881763527,
+      "grad_norm": 1.4559454917907715,
+      "learning_rate": 5.26834859697411e-06,
+      "loss": 0.3275,
+      "step": 555
+    },
+    {
+      "epoch": 2.2404809619238475,
+      "grad_norm": 1.334267497062683,
+      "learning_rate": 5.018909413773837e-06,
+      "loss": 0.2858,
+      "step": 560
+    },
+    {
+      "epoch": 2.2605210420841684,
+      "grad_norm": 1.2736464738845825,
+      "learning_rate": 4.7743280363714e-06,
+      "loss": 0.3152,
+      "step": 565
+    },
+    {
+      "epoch": 2.280561122244489,
+      "grad_norm": 1.3075700998306274,
+      "learning_rate": 4.534723502743956e-06,
+      "loss": 0.3106,
+      "step": 570
+    },
+    {
+      "epoch": 2.3006012024048097,
+      "grad_norm": 1.2601113319396973,
+      "learning_rate": 4.300212428634301e-06,
+      "loss": 0.3366,
+      "step": 575
+    },
+    {
+      "epoch": 2.32064128256513,
+      "grad_norm": 1.1969159841537476,
+      "learning_rate": 4.0709089507938815e-06,
+      "loss": 0.3464,
+      "step": 580
+    },
+    {
+      "epoch": 2.340681362725451,
+      "grad_norm": 1.2641717195510864,
+      "learning_rate": 3.846924671432358e-06,
+      "loss": 0.3145,
+      "step": 585
+    },
+    {
+      "epoch": 2.3607214428857715,
+      "grad_norm": 1.3206663131713867,
+      "learning_rate": 3.628368603900671e-06,
+      "loss": 0.3232,
+      "step": 590
+    },
+    {
+      "epoch": 2.3807615230460923,
+      "grad_norm": 1.208651065826416,
+      "learning_rate": 3.4153471196341686e-06,
+      "loss": 0.3652,
+      "step": 595
+    },
+    {
+      "epoch": 2.400801603206413,
+      "grad_norm": 1.1498212814331055,
+      "learning_rate": 3.207963896381528e-06,
+      "loss": 0.311,
+      "step": 600
+    },
+    {
+      "epoch": 2.420841683366733,
+      "grad_norm": 1.2342705726623535,
+      "learning_rate": 3.006319867744707e-06,
+      "loss": 0.3427,
+      "step": 605
+    },
+    {
+      "epoch": 2.440881763527054,
+      "grad_norm": 1.3062251806259155,
+      "learning_rate": 2.8105131740544525e-06,
+      "loss": 0.3127,
+      "step": 610
+    },
+    {
+      "epoch": 2.460921843687375,
+      "grad_norm": 1.2560538053512573,
+      "learning_rate": 2.6206391146053416e-06,
+      "loss": 0.3071,
+      "step": 615
+    },
+    {
+      "epoch": 2.4809619238476954,
+      "grad_norm": 1.3003733158111572,
+      "learning_rate": 2.436790101273485e-06,
+      "loss": 0.3336,
+      "step": 620
+    },
+    {
+      "epoch": 2.501002004008016,
+      "grad_norm": 1.3885016441345215,
+      "learning_rate": 2.259055613539638e-06,
+      "loss": 0.3195,
+      "step": 625
+    },
+    {
+      "epoch": 2.5210420841683367,
+      "grad_norm": 1.2585527896881104,
+      "learning_rate": 2.0875221549394015e-06,
+      "loss": 0.3334,
+      "step": 630
+    },
+    {
+      "epoch": 2.541082164328657,
+      "grad_norm": 1.2443827390670776,
+      "learning_rate": 1.9222732109619205e-06,
+      "loss": 0.301,
+      "step": 635
+    },
+    {
+      "epoch": 2.561122244488978,
+      "grad_norm": 1.2620984315872192,
+      "learning_rate": 1.7633892084173926e-06,
+      "loss": 0.3245,
+      "step": 640
+    },
+    {
+      "epoch": 2.5811623246492985,
+      "grad_norm": 1.281148076057434,
+      "learning_rate": 1.6109474762932703e-06,
+      "loss": 0.3243,
+      "step": 645
+    },
+    {
+      "epoch": 2.6012024048096194,
+      "grad_norm": 1.1994389295578003,
+      "learning_rate": 1.465022208118183e-06,
+      "loss": 0.3268,
+      "step": 650
+    },
+    {
+      "epoch": 2.62124248496994,
+      "grad_norm": 1.1724731922149658,
+      "learning_rate": 1.3256844258518742e-06,
+      "loss": 0.3316,
+      "step": 655
+    },
+    {
+      "epoch": 2.6412825651302603,
+      "grad_norm": 1.121740698814392,
+      "learning_rate": 1.1930019453187413e-06,
+      "loss": 0.2934,
+      "step": 660
+    },
+    {
+      "epoch": 2.661322645290581,
+      "grad_norm": 1.2212955951690674,
+      "learning_rate": 1.0670393432018355e-06,
+      "loss": 0.2923,
+      "step": 665
+    },
+    {
+      "epoch": 2.681362725450902,
+      "grad_norm": 1.2103770971298218,
+      "learning_rate": 9.478579256133018e-07,
+      "loss": 0.3315,
+      "step": 670
+    },
+    {
+      "epoch": 2.7014028056112225,
+      "grad_norm": 1.2891243696212769,
+      "learning_rate": 8.355156982566642e-07,
+      "loss": 0.2837,
+      "step": 675
+    },
+    {
+      "epoch": 2.721442885771543,
+      "grad_norm": 1.279935598373413,
+      "learning_rate": 7.300673381953827e-07,
+      "loss": 0.3013,
+      "step": 680
+    },
+    {
+      "epoch": 2.741482965931864,
+      "grad_norm": 1.339373230934143,
+      "learning_rate": 6.31564167241479e-07,
+      "loss": 0.3161,
+      "step": 685
+    },
+    {
+      "epoch": 2.7615230460921842,
+      "grad_norm": 1.2601087093353271,
+      "learning_rate": 5.400541269771808e-07,
+      "loss": 0.2813,
+      "step": 690
+    },
+    {
+      "epoch": 2.781563126252505,
+      "grad_norm": 1.2471266984939575,
+      "learning_rate": 4.555817554216774e-07,
+      "loss": 0.3151,
+      "step": 695
+    },
+    {
+      "epoch": 2.8016032064128256,
+      "grad_norm": 1.3486889600753784,
+      "learning_rate": 3.781881653544611e-07,
+      "loss": 0.3029,
+      "step": 700
+    },
+    {
+      "epoch": 2.8216432865731464,
+      "grad_norm": 1.0886106491088867,
+      "learning_rate": 3.079110243056721e-07,
+      "loss": 0.3056,
+      "step": 705
+    },
+    {
+      "epoch": 2.841683366733467,
+      "grad_norm": 1.2064608335494995,
+      "learning_rate": 2.447845362232992e-07,
+      "loss": 0.3216,
+      "step": 710
+    },
+    {
+      "epoch": 2.8617234468937873,
+      "grad_norm": 1.3721826076507568,
+      "learning_rate": 1.888394248260733e-07,
+      "loss": 0.3004,
+      "step": 715
+    },
+    {
+      "epoch": 2.881763527054108,
+      "grad_norm": 1.1835554838180542,
+      "learning_rate": 1.4010291865020842e-07,
+      "loss": 0.2928,
+      "step": 720
+    },
+    {
+      "epoch": 2.901803607214429,
+      "grad_norm": 1.3124585151672363,
+      "learning_rate": 9.85987377972558e-08,
+      "loss": 0.3091,
+      "step": 725
+    },
+    {
+      "epoch": 2.9218436873747495,
+      "grad_norm": 1.095642328262329,
+      "learning_rate": 6.434708238949871e-08,
+      "loss": 0.3247,
+      "step": 730
+    },
+    {
+      "epoch": 2.94188376753507,
+      "grad_norm": 1.3501590490341187,
+      "learning_rate": 3.736462273854324e-08,
+      "loss": 0.3207,
+      "step": 735
+    },
+    {
+      "epoch": 2.961923847695391,
+      "grad_norm": 1.2240146398544312,
+      "learning_rate": 1.7664491231855208e-08,
+      "loss": 0.3121,
+      "step": 740
+    },
+    {
+      "epoch": 2.9819639278557113,
+      "grad_norm": 1.2801709175109863,
+      "learning_rate": 5.256275941222799e-09,
+      "loss": 0.2788,
+      "step": 745
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.7804031372070312,
+      "learning_rate": 1.460159562294283e-10,
+      "loss": 0.3665,
+      "step": 750
+    },
+    {
+      "epoch": 3.0,
+      "step": 750,
+      "total_flos": 1.0029700814303396e+18,
+      "train_loss": 0.6438727126121521,
+      "train_runtime": 475.7024,
+      "train_samples_per_second": 50.345,
+      "train_steps_per_second": 1.577
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 750,
+  "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": 1.0029700814303396e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

115_128_e3_3e-5/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a60a740142b294d849882e72982324d1193a90831e1d1a4cc33961195f71b44f
+size 8273