Upload folder using huggingface_hub

118_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",
+    "gate_proj",
+    "k_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

118_128_e3_3e-5/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f48a4879143d5fee33ec96db01ef888808f0623f66f9364ea78a64591dac823c
+size 791751704

118_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
+}

118_128_e3_3e-5/all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 7.680569906676367e+17,
+    "train_loss": 0.3947397977368444,
+    "train_runtime": 360.9762,
+    "train_samples": 6219,
+    "train_samples_per_second": 51.685,
+    "train_steps_per_second": 1.621
+}

118_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 %}

118_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
+}

118_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
+  }
+}

118_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
+}

118_128_e3_3e-5/train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 7.680569906676367e+17,
+    "train_loss": 0.3947397977368444,
+    "train_runtime": 360.9762,
+    "train_samples": 6219,
+    "train_samples_per_second": 51.685,
+    "train_steps_per_second": 1.621
+}

118_128_e3_3e-5/trainer_state.json

@@ -0,0 +1,862 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 585,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02570694087403599,
+      "grad_norm": 2.462559223175049,
+      "learning_rate": 4e-06,
+      "loss": 1.6212,
+      "step": 5
+    },
+    {
+      "epoch": 0.05141388174807198,
+      "grad_norm": 1.2706873416900635,
+      "learning_rate": 9e-06,
+      "loss": 1.5274,
+      "step": 10
+    },
+    {
+      "epoch": 0.07712082262210797,
+      "grad_norm": 0.5796677470207214,
+      "learning_rate": 1.4e-05,
+      "loss": 1.5288,
+      "step": 15
+    },
+    {
+      "epoch": 0.10282776349614396,
+      "grad_norm": 0.6078125834465027,
+      "learning_rate": 1.9e-05,
+      "loss": 1.4564,
+      "step": 20
+    },
+    {
+      "epoch": 0.12853470437017994,
+      "grad_norm": 0.5408655405044556,
+      "learning_rate": 2.4e-05,
+      "loss": 1.4093,
+      "step": 25
+    },
+    {
+      "epoch": 0.15424164524421594,
+      "grad_norm": 0.48828810453414917,
+      "learning_rate": 2.9e-05,
+      "loss": 1.434,
+      "step": 30
+    },
+    {
+      "epoch": 0.17994858611825193,
+      "grad_norm": 0.4132004678249359,
+      "learning_rate": 2.999615517594034e-05,
+      "loss": 1.3618,
+      "step": 35
+    },
+    {
+      "epoch": 0.20565552699228792,
+      "grad_norm": 0.4131932854652405,
+      "learning_rate": 2.998053895620817e-05,
+      "loss": 1.337,
+      "step": 40
+    },
+    {
+      "epoch": 0.23136246786632392,
+      "grad_norm": 0.4687134623527527,
+      "learning_rate": 2.995292353804467e-05,
+      "loss": 1.2988,
+      "step": 45
+    },
+    {
+      "epoch": 0.2570694087403599,
+      "grad_norm": 0.4360010325908661,
+      "learning_rate": 2.991333104100664e-05,
+      "loss": 1.2097,
+      "step": 50
+    },
+    {
+      "epoch": 0.2827763496143959,
+      "grad_norm": 0.4601917564868927,
+      "learning_rate": 2.9861793178120533e-05,
+      "loss": 1.2036,
+      "step": 55
+    },
+    {
+      "epoch": 0.30848329048843187,
+      "grad_norm": 0.4810018241405487,
+      "learning_rate": 2.9798351230480797e-05,
+      "loss": 1.112,
+      "step": 60
+    },
+    {
+      "epoch": 0.3341902313624679,
+      "grad_norm": 0.5113069415092468,
+      "learning_rate": 2.9723056014184295e-05,
+      "loss": 1.1488,
+      "step": 65
+    },
+    {
+      "epoch": 0.35989717223650386,
+      "grad_norm": 0.6189714074134827,
+      "learning_rate": 2.963596783962733e-05,
+      "loss": 1.0771,
+      "step": 70
+    },
+    {
+      "epoch": 0.3856041131105398,
+      "grad_norm": 0.6357444524765015,
+      "learning_rate": 2.953715646319787e-05,
+      "loss": 1.0296,
+      "step": 75
+    },
+    {
+      "epoch": 0.41131105398457585,
+      "grad_norm": 0.5980392694473267,
+      "learning_rate": 2.9426701031401707e-05,
+      "loss": 0.9921,
+      "step": 80
+    },
+    {
+      "epoch": 0.4370179948586118,
+      "grad_norm": 0.6075550317764282,
+      "learning_rate": 2.930469001746718e-05,
+      "loss": 0.9126,
+      "step": 85
+    },
+    {
+      "epoch": 0.46272493573264784,
+      "grad_norm": 0.8019831776618958,
+      "learning_rate": 2.9171221150479435e-05,
+      "loss": 0.8995,
+      "step": 90
+    },
+    {
+      "epoch": 0.4884318766066838,
+      "grad_norm": 0.7715163826942444,
+      "learning_rate": 2.9026401337100773e-05,
+      "loss": 0.888,
+      "step": 95
+    },
+    {
+      "epoch": 0.5141388174807198,
+      "grad_norm": 0.7547778487205505,
+      "learning_rate": 2.887034657593997e-05,
+      "loss": 0.7641,
+      "step": 100
+    },
+    {
+      "epoch": 0.5398457583547558,
+      "grad_norm": 0.8128002285957336,
+      "learning_rate": 2.8703181864639013e-05,
+      "loss": 0.7956,
+      "step": 105
+    },
+    {
+      "epoch": 0.5655526992287918,
+      "grad_norm": 0.7986507415771484,
+      "learning_rate": 2.852504109975179e-05,
+      "loss": 0.7376,
+      "step": 110
+    },
+    {
+      "epoch": 0.5912596401028277,
+      "grad_norm": 0.8133559226989746,
+      "learning_rate": 2.8336066969494855e-05,
+      "loss": 0.7394,
+      "step": 115
+    },
+    {
+      "epoch": 0.6169665809768637,
+      "grad_norm": 1.0161502361297607,
+      "learning_rate": 2.813641083945618e-05,
+      "loss": 0.7345,
+      "step": 120
+    },
+    {
+      "epoch": 0.6426735218508998,
+      "grad_norm": 0.8881458640098572,
+      "learning_rate": 2.79262326313535e-05,
+      "loss": 0.634,
+      "step": 125
+    },
+    {
+      "epoch": 0.6683804627249358,
+      "grad_norm": 0.9700175523757935,
+      "learning_rate": 2.7705700694939265e-05,
+      "loss": 0.6254,
+      "step": 130
+    },
+    {
+      "epoch": 0.6940874035989717,
+      "grad_norm": 1.0086627006530762,
+      "learning_rate": 2.747499167315491e-05,
+      "loss": 0.6124,
+      "step": 135
+    },
+    {
+      "epoch": 0.7197943444730077,
+      "grad_norm": 0.9843950867652893,
+      "learning_rate": 2.723429036064237e-05,
+      "loss": 0.5909,
+      "step": 140
+    },
+    {
+      "epoch": 0.7455012853470437,
+      "grad_norm": 0.9704286456108093,
+      "learning_rate": 2.6983789555726178e-05,
+      "loss": 0.6267,
+      "step": 145
+    },
+    {
+      "epoch": 0.7712082262210797,
+      "grad_norm": 1.0702846050262451,
+      "learning_rate": 2.6723689905984783e-05,
+      "loss": 0.5893,
+      "step": 150
+    },
+    {
+      "epoch": 0.7969151670951157,
+      "grad_norm": 1.0272799730300903,
+      "learning_rate": 2.645419974753469e-05,
+      "loss": 0.5452,
+      "step": 155
+    },
+    {
+      "epoch": 0.8226221079691517,
+      "grad_norm": 0.932231605052948,
+      "learning_rate": 2.6175534938156176e-05,
+      "loss": 0.5135,
+      "step": 160
+    },
+    {
+      "epoch": 0.8483290488431876,
+      "grad_norm": 1.005792498588562,
+      "learning_rate": 2.5887918684394306e-05,
+      "loss": 0.481,
+      "step": 165
+    },
+    {
+      "epoch": 0.8740359897172236,
+      "grad_norm": 1.0027400255203247,
+      "learning_rate": 2.559158136277365e-05,
+      "loss": 0.5081,
+      "step": 170
+    },
+    {
+      "epoch": 0.8997429305912596,
+      "grad_norm": 1.1090096235275269,
+      "learning_rate": 2.5286760335269973e-05,
+      "loss": 0.4802,
+      "step": 175
+    },
+    {
+      "epoch": 0.9254498714652957,
+      "grad_norm": 1.123046636581421,
+      "learning_rate": 2.497369975918669e-05,
+      "loss": 0.4538,
+      "step": 180
+    },
+    {
+      "epoch": 0.9511568123393316,
+      "grad_norm": 1.182647943496704,
+      "learning_rate": 2.4652650391588297e-05,
+      "loss": 0.4151,
+      "step": 185
+    },
+    {
+      "epoch": 0.9768637532133676,
+      "grad_norm": 1.1062380075454712,
+      "learning_rate": 2.4323869388447583e-05,
+      "loss": 0.4019,
+      "step": 190
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.5823050737380981,
+      "learning_rate": 2.3987620098667326e-05,
+      "loss": 0.4449,
+      "step": 195
+    },
+    {
+      "epoch": 1.025706940874036,
+      "grad_norm": 1.1867868900299072,
+      "learning_rate": 2.364417185314158e-05,
+      "loss": 0.3762,
+      "step": 200
+    },
+    {
+      "epoch": 1.051413881748072,
+      "grad_norm": 1.153962254524231,
+      "learning_rate": 2.329379974902545e-05,
+      "loss": 0.3115,
+      "step": 205
+    },
+    {
+      "epoch": 1.077120822622108,
+      "grad_norm": 1.3199880123138428,
+      "learning_rate": 2.293678442938623e-05,
+      "loss": 0.3186,
+      "step": 210
+    },
+    {
+      "epoch": 1.1028277634961439,
+      "grad_norm": 1.107765555381775,
+      "learning_rate": 2.2573411858412235e-05,
+      "loss": 0.3445,
+      "step": 215
+    },
+    {
+      "epoch": 1.1285347043701799,
+      "grad_norm": 1.1296532154083252,
+      "learning_rate": 2.2203973092359614e-05,
+      "loss": 0.2967,
+      "step": 220
+    },
+    {
+      "epoch": 1.154241645244216,
+      "grad_norm": 1.1329461336135864,
+      "learning_rate": 2.182876404642041e-05,
+      "loss": 0.3098,
+      "step": 225
+    },
+    {
+      "epoch": 1.179948586118252,
+      "grad_norm": 1.2530066967010498,
+      "learning_rate": 2.1448085257698696e-05,
+      "loss": 0.281,
+      "step": 230
+    },
+    {
+      "epoch": 1.205655526992288,
+      "grad_norm": 1.0034352540969849,
+      "learning_rate": 2.106224164448466e-05,
+      "loss": 0.2695,
+      "step": 235
+    },
+    {
+      "epoch": 1.231362467866324,
+      "grad_norm": 1.265865445137024,
+      "learning_rate": 2.0671542262019368e-05,
+      "loss": 0.266,
+      "step": 240
+    },
+    {
+      "epoch": 1.2570694087403598,
+      "grad_norm": 0.9585506916046143,
+      "learning_rate": 2.0276300054945917e-05,
+      "loss": 0.25,
+      "step": 245
+    },
+    {
+      "epoch": 1.2827763496143958,
+      "grad_norm": 1.1127073764801025,
+      "learning_rate": 1.987683160664525e-05,
+      "loss": 0.2266,
+      "step": 250
+    },
+    {
+      "epoch": 1.3084832904884318,
+      "grad_norm": 0.9920097589492798,
+      "learning_rate": 1.947345688565738e-05,
+      "loss": 0.2575,
+      "step": 255
+    },
+    {
+      "epoch": 1.3341902313624678,
+      "grad_norm": 1.091744303703308,
+      "learning_rate": 1.9066498989391107e-05,
+      "loss": 0.2512,
+      "step": 260
+    },
+    {
+      "epoch": 1.3598971722365039,
+      "grad_norm": 1.0938419103622437,
+      "learning_rate": 1.8656283885327625e-05,
+      "loss": 0.2479,
+      "step": 265
+    },
+    {
+      "epoch": 1.3856041131105399,
+      "grad_norm": 1.0284051895141602,
+      "learning_rate": 1.8243140149925205e-05,
+      "loss": 0.2327,
+      "step": 270
+    },
+    {
+      "epoch": 1.411311053984576,
+      "grad_norm": 1.2660396099090576,
+      "learning_rate": 1.7827398705434123e-05,
+      "loss": 0.2254,
+      "step": 275
+    },
+    {
+      "epoch": 1.437017994858612,
+      "grad_norm": 1.111435890197754,
+      "learning_rate": 1.7409392554832657e-05,
+      "loss": 0.232,
+      "step": 280
+    },
+    {
+      "epoch": 1.462724935732648,
+      "grad_norm": 1.1362228393554688,
+      "learning_rate": 1.6989456515096436e-05,
+      "loss": 0.22,
+      "step": 285
+    },
+    {
+      "epoch": 1.4884318766066837,
+      "grad_norm": 1.0959265232086182,
+      "learning_rate": 1.6567926949014805e-05,
+      "loss": 0.2008,
+      "step": 290
+    },
+    {
+      "epoch": 1.5141388174807198,
+      "grad_norm": 1.0802184343338013,
+      "learning_rate": 1.6145141495769022e-05,
+      "loss": 0.2011,
+      "step": 295
+    },
+    {
+      "epoch": 1.5398457583547558,
+      "grad_norm": 1.058629035949707,
+      "learning_rate": 1.572143880048811e-05,
+      "loss": 0.1866,
+      "step": 300
+    },
+    {
+      "epoch": 1.5655526992287918,
+      "grad_norm": 1.2011915445327759,
+      "learning_rate": 1.5297158242998867e-05,
+      "loss": 0.1966,
+      "step": 305
+    },
+    {
+      "epoch": 1.5912596401028276,
+      "grad_norm": 1.1538809537887573,
+      "learning_rate": 1.487263966598752e-05,
+      "loss": 0.1854,
+      "step": 310
+    },
+    {
+      "epoch": 1.6169665809768636,
+      "grad_norm": 1.0332131385803223,
+      "learning_rate": 1.444822310279053e-05,
+      "loss": 0.2066,
+      "step": 315
+    },
+    {
+      "epoch": 1.6426735218508997,
+      "grad_norm": 0.9321181774139404,
+      "learning_rate": 1.4024248505032754e-05,
+      "loss": 0.1715,
+      "step": 320
+    },
+    {
+      "epoch": 1.6683804627249357,
+      "grad_norm": 1.2622590065002441,
+      "learning_rate": 1.3601055470331024e-05,
+      "loss": 0.1791,
+      "step": 325
+    },
+    {
+      "epoch": 1.6940874035989717,
+      "grad_norm": 1.0806361436843872,
+      "learning_rate": 1.317898297028128e-05,
+      "loss": 0.1613,
+      "step": 330
+    },
+    {
+      "epoch": 1.7197943444730077,
+      "grad_norm": 1.107562780380249,
+      "learning_rate": 1.2758369078947182e-05,
+      "loss": 0.1571,
+      "step": 335
+    },
+    {
+      "epoch": 1.7455012853470437,
+      "grad_norm": 0.9073730707168579,
+      "learning_rate": 1.2339550702067539e-05,
+      "loss": 0.1596,
+      "step": 340
+    },
+    {
+      "epoch": 1.7712082262210798,
+      "grad_norm": 1.0006639957427979,
+      "learning_rate": 1.1922863307199673e-05,
+      "loss": 0.1582,
+      "step": 345
+    },
+    {
+      "epoch": 1.7969151670951158,
+      "grad_norm": 1.0531697273254395,
+      "learning_rate": 1.150864065501464e-05,
+      "loss": 0.1485,
+      "step": 350
+    },
+    {
+      "epoch": 1.8226221079691518,
+      "grad_norm": 0.8763147592544556,
+      "learning_rate": 1.1097214531959706e-05,
+      "loss": 0.125,
+      "step": 355
+    },
+    {
+      "epoch": 1.8483290488431876,
+      "grad_norm": 1.087363600730896,
+      "learning_rate": 1.0688914484502106e-05,
+      "loss": 0.1316,
+      "step": 360
+    },
+    {
+      "epoch": 1.8740359897172236,
+      "grad_norm": 1.0356113910675049,
+      "learning_rate": 1.0284067555167037e-05,
+      "loss": 0.1153,
+      "step": 365
+    },
+    {
+      "epoch": 1.8997429305912596,
+      "grad_norm": 0.8378418684005737,
+      "learning_rate": 9.882998020581228e-06,
+      "loss": 0.1301,
+      "step": 370
+    },
+    {
+      "epoch": 1.9254498714652957,
+      "grad_norm": 1.0206042528152466,
+      "learning_rate": 9.486027131732003e-06,
+      "loss": 0.1145,
+      "step": 375
+    },
+    {
+      "epoch": 1.9511568123393315,
+      "grad_norm": 0.9937468767166138,
+      "learning_rate": 9.093472856649794e-06,
+      "loss": 0.1228,
+      "step": 380
+    },
+    {
+      "epoch": 1.9768637532133675,
+      "grad_norm": 0.9551673531532288,
+      "learning_rate": 8.70564962572029e-06,
+      "loss": 0.1243,
+      "step": 385
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.2650110721588135,
+      "learning_rate": 8.322868079830162e-06,
+      "loss": 0.1014,
+      "step": 390
+    },
+    {
+      "epoch": 2.025706940874036,
+      "grad_norm": 0.6941744685173035,
+      "learning_rate": 7.945434821548152e-06,
+      "loss": 0.0915,
+      "step": 395
+    },
+    {
+      "epoch": 2.051413881748072,
+      "grad_norm": 0.6612865328788757,
+      "learning_rate": 7.573652169540747e-06,
+      "loss": 0.0866,
+      "step": 400
+    },
+    {
+      "epoch": 2.077120822622108,
+      "grad_norm": 0.8367739319801331,
+      "learning_rate": 7.207817916419276e-06,
+      "loss": 0.0926,
+      "step": 405
+    },
+    {
+      "epoch": 2.102827763496144,
+      "grad_norm": 0.9863636493682861,
+      "learning_rate": 6.848225090212234e-06,
+      "loss": 0.0819,
+      "step": 410
+    },
+    {
+      "epoch": 2.12853470437018,
+      "grad_norm": 0.7339490056037903,
+      "learning_rate": 6.4951617196540244e-06,
+      "loss": 0.079,
+      "step": 415
+    },
+    {
+      "epoch": 2.154241645244216,
+      "grad_norm": 1.0929278135299683,
+      "learning_rate": 6.148910603478027e-06,
+      "loss": 0.0906,
+      "step": 420
+    },
+    {
+      "epoch": 2.179948586118252,
+      "grad_norm": 0.6473608016967773,
+      "learning_rate": 5.8097490838988365e-06,
+      "loss": 0.0838,
+      "step": 425
+    },
+    {
+      "epoch": 2.2056555269922877,
+      "grad_norm": 0.8154418468475342,
+      "learning_rate": 5.477948824465118e-06,
+      "loss": 0.0812,
+      "step": 430
+    },
+    {
+      "epoch": 2.2313624678663238,
+      "grad_norm": 0.7326850295066833,
+      "learning_rate": 5.153775592460958e-06,
+      "loss": 0.0773,
+      "step": 435
+    },
+    {
+      "epoch": 2.2570694087403598,
+      "grad_norm": 0.6823248863220215,
+      "learning_rate": 4.837489046030053e-06,
+      "loss": 0.0827,
+      "step": 440
+    },
+    {
+      "epoch": 2.282776349614396,
+      "grad_norm": 1.0743191242218018,
+      "learning_rate": 4.529342526193235e-06,
+      "loss": 0.0814,
+      "step": 445
+    },
+    {
+      "epoch": 2.308483290488432,
+      "grad_norm": 0.8445592522621155,
+      "learning_rate": 4.229582853925924e-06,
+      "loss": 0.0875,
+      "step": 450
+    },
+    {
+      "epoch": 2.334190231362468,
+      "grad_norm": 0.8527880907058716,
+      "learning_rate": 3.938450132458028e-06,
+      "loss": 0.0707,
+      "step": 455
+    },
+    {
+      "epoch": 2.359897172236504,
+      "grad_norm": 0.6945133209228516,
+      "learning_rate": 3.656177554954693e-06,
+      "loss": 0.0738,
+      "step": 460
+    },
+    {
+      "epoch": 2.38560411311054,
+      "grad_norm": 0.719367504119873,
+      "learning_rate": 3.3829912177318863e-06,
+      "loss": 0.0676,
+      "step": 465
+    },
+    {
+      "epoch": 2.411311053984576,
+      "grad_norm": 0.6606858968734741,
+      "learning_rate": 3.1191099391564665e-06,
+      "loss": 0.0748,
+      "step": 470
+    },
+    {
+      "epoch": 2.437017994858612,
+      "grad_norm": 0.714175283908844,
+      "learning_rate": 2.86474508437579e-06,
+      "loss": 0.0707,
+      "step": 475
+    },
+    {
+      "epoch": 2.462724935732648,
+      "grad_norm": 0.7783403992652893,
+      "learning_rate": 2.6201003960172327e-06,
+      "loss": 0.0647,
+      "step": 480
+    },
+    {
+      "epoch": 2.488431876606684,
+      "grad_norm": 0.6540095806121826,
+      "learning_rate": 2.385371830993251e-06,
+      "loss": 0.0724,
+      "step": 485
+    },
+    {
+      "epoch": 2.5141388174807195,
+      "grad_norm": 0.6916401386260986,
+      "learning_rate": 2.160747403542686e-06,
+      "loss": 0.0661,
+      "step": 490
+    },
+    {
+      "epoch": 2.5398457583547556,
+      "grad_norm": 0.5440326929092407,
+      "learning_rate": 1.9464070346340203e-06,
+      "loss": 0.0584,
+      "step": 495
+    },
+    {
+      "epoch": 2.5655526992287916,
+      "grad_norm": 0.8200917840003967,
+      "learning_rate": 1.7425224078512674e-06,
+      "loss": 0.0725,
+      "step": 500
+    },
+    {
+      "epoch": 2.5912596401028276,
+      "grad_norm": 0.5884963274002075,
+      "learning_rate": 1.549256831877846e-06,
+      "loss": 0.0708,
+      "step": 505
+    },
+    {
+      "epoch": 2.6169665809768636,
+      "grad_norm": 0.7560333013534546,
+      "learning_rate": 1.366765109688658e-06,
+      "loss": 0.0758,
+      "step": 510
+    },
+    {
+      "epoch": 2.6426735218508997,
+      "grad_norm": 0.5637240409851074,
+      "learning_rate": 1.1951934145551086e-06,
+      "loss": 0.0604,
+      "step": 515
+    },
+    {
+      "epoch": 2.6683804627249357,
+      "grad_norm": 0.7189124822616577,
+      "learning_rate": 1.0346791729623928e-06,
+      "loss": 0.0695,
+      "step": 520
+    },
+    {
+      "epoch": 2.6940874035989717,
+      "grad_norm": 0.717718780040741,
+      "learning_rate": 8.853509545328442e-07,
+      "loss": 0.0673,
+      "step": 525
+    },
+    {
+      "epoch": 2.7197943444730077,
+      "grad_norm": 0.6439788341522217,
+      "learning_rate": 7.473283690434907e-07,
+      "loss": 0.0636,
+      "step": 530
+    },
+    {
+      "epoch": 2.7455012853470437,
+      "grad_norm": 0.5992586612701416,
+      "learning_rate": 6.207219706203326e-07,
+      "loss": 0.0671,
+      "step": 535
+    },
+    {
+      "epoch": 2.7712082262210798,
+      "grad_norm": 0.6907675266265869,
+      "learning_rate": 5.056331691860577e-07,
+      "loss": 0.0711,
+      "step": 540
+    },
+    {
+      "epoch": 2.796915167095116,
+      "grad_norm": 0.522859513759613,
+      "learning_rate": 4.0215414923213287e-07,
+      "loss": 0.0555,
+      "step": 545
+    },
+    {
+      "epoch": 2.822622107969152,
+      "grad_norm": 0.6274727582931519,
+      "learning_rate": 3.1036779598034914e-07,
+      "loss": 0.0653,
+      "step": 550
+    },
+    {
+      "epoch": 2.848329048843188,
+      "grad_norm": 0.5393765568733215,
+      "learning_rate": 2.3034762899293294e-07,
+      "loss": 0.0645,
+      "step": 555
+    },
+    {
+      "epoch": 2.874035989717224,
+      "grad_norm": 0.7296293377876282,
+      "learning_rate": 1.6215774328442012e-07,
+      "loss": 0.0728,
+      "step": 560
+    },
+    {
+      "epoch": 2.89974293059126,
+      "grad_norm": 0.5906640887260437,
+      "learning_rate": 1.0585275798246974e-07,
+      "loss": 0.0624,
+      "step": 565
+    },
+    {
+      "epoch": 2.925449871465296,
+      "grad_norm": 0.6212802529335022,
+      "learning_rate": 6.147777257871468e-08,
+      "loss": 0.0681,
+      "step": 570
+    },
+    {
+      "epoch": 2.9511568123393315,
+      "grad_norm": 0.7387581467628479,
+      "learning_rate": 2.9068330804711276e-08,
+      "loss": 0.0705,
+      "step": 575
+    },
+    {
+      "epoch": 2.9768637532133675,
+      "grad_norm": 0.6287196278572083,
+      "learning_rate": 8.650392161921317e-09,
+      "loss": 0.0673,
+      "step": 580
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.7085381150245667,
+      "learning_rate": 2.403111285115278e-10,
+      "loss": 0.0686,
+      "step": 585
+    },
+    {
+      "epoch": 3.0,
+      "step": 585,
+      "total_flos": 7.680569906676367e+17,
+      "train_loss": 0.3947397977368444,
+      "train_runtime": 360.9762,
+      "train_samples_per_second": 51.685,
+      "train_steps_per_second": 1.621
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 585,
+  "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": 7.680569906676367e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

118_128_e3_3e-5/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8fc7905795a3229d9ebb019cee712ac992d700e82c8ce31f1bbb2af77272ebc
+size 8273