Upload folder using huggingface_hub

19_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": [
+    "up_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "down_proj",
+    "gate_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

19_128_e3_3e-5/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a15d875f37a6367f0c00a15f5f695bae84e6376d5165b874bb354b8ba492ce03
+size 791751704

19_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
+}

19_128_e3_3e-5/all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 7.780499300139663e+17,
+    "train_loss": 0.5425458254478231,
+    "train_runtime": 390.8207,
+    "train_samples": 6195,
+    "train_samples_per_second": 47.554,
+    "train_steps_per_second": 1.489
+}

19_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 %}

19_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
+}

19_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
+  }
+}

19_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
+}

19_128_e3_3e-5/train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 7.780499300139663e+17,
+    "train_loss": 0.5425458254478231,
+    "train_runtime": 390.8207,
+    "train_samples": 6195,
+    "train_samples_per_second": 47.554,
+    "train_steps_per_second": 1.489
+}

19_128_e3_3e-5/trainer_state.json

@@ -0,0 +1,855 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 582,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02577319587628866,
+      "grad_norm": 3.3371453285217285,
+      "learning_rate": 4e-06,
+      "loss": 1.656,
+      "step": 5
+    },
+    {
+      "epoch": 0.05154639175257732,
+      "grad_norm": 1.3904811143875122,
+      "learning_rate": 9e-06,
+      "loss": 1.5328,
+      "step": 10
+    },
+    {
+      "epoch": 0.07731958762886598,
+      "grad_norm": 0.5369800925254822,
+      "learning_rate": 1.4e-05,
+      "loss": 1.4056,
+      "step": 15
+    },
+    {
+      "epoch": 0.10309278350515463,
+      "grad_norm": 0.43124017119407654,
+      "learning_rate": 1.9e-05,
+      "loss": 1.4141,
+      "step": 20
+    },
+    {
+      "epoch": 0.12886597938144329,
+      "grad_norm": 0.4748530089855194,
+      "learning_rate": 2.4e-05,
+      "loss": 1.3198,
+      "step": 25
+    },
+    {
+      "epoch": 0.15463917525773196,
+      "grad_norm": 0.3959720730781555,
+      "learning_rate": 2.9e-05,
+      "loss": 1.3656,
+      "step": 30
+    },
+    {
+      "epoch": 0.18041237113402062,
+      "grad_norm": 0.4064708650112152,
+      "learning_rate": 2.999611327262024e-05,
+      "loss": 1.2965,
+      "step": 35
+    },
+    {
+      "epoch": 0.20618556701030927,
+      "grad_norm": 0.4142211079597473,
+      "learning_rate": 2.9980326894682094e-05,
+      "loss": 1.2529,
+      "step": 40
+    },
+    {
+      "epoch": 0.23195876288659795,
+      "grad_norm": 0.4488871991634369,
+      "learning_rate": 2.9952410718358775e-05,
+      "loss": 1.2232,
+      "step": 45
+    },
+    {
+      "epoch": 0.25773195876288657,
+      "grad_norm": 0.41416242718696594,
+      "learning_rate": 2.9912387347802566e-05,
+      "loss": 1.2248,
+      "step": 50
+    },
+    {
+      "epoch": 0.28350515463917525,
+      "grad_norm": 0.4933653473854065,
+      "learning_rate": 2.986028919054496e-05,
+      "loss": 1.1901,
+      "step": 55
+    },
+    {
+      "epoch": 0.30927835051546393,
+      "grad_norm": 0.46860361099243164,
+      "learning_rate": 2.9796158431255773e-05,
+      "loss": 1.1546,
+      "step": 60
+    },
+    {
+      "epoch": 0.33505154639175255,
+      "grad_norm": 0.4644382894039154,
+      "learning_rate": 2.9720046997585575e-05,
+      "loss": 1.1283,
+      "step": 65
+    },
+    {
+      "epoch": 0.36082474226804123,
+      "grad_norm": 0.46769848465919495,
+      "learning_rate": 2.9632016518119094e-05,
+      "loss": 1.0918,
+      "step": 70
+    },
+    {
+      "epoch": 0.3865979381443299,
+      "grad_norm": 0.5332866907119751,
+      "learning_rate": 2.9532138272473598e-05,
+      "loss": 1.0671,
+      "step": 75
+    },
+    {
+      "epoch": 0.41237113402061853,
+      "grad_norm": 0.5228053331375122,
+      "learning_rate": 2.9420493133582718e-05,
+      "loss": 1.0163,
+      "step": 80
+    },
+    {
+      "epoch": 0.4381443298969072,
+      "grad_norm": 0.5511900186538696,
+      "learning_rate": 2.9297171502212413e-05,
+      "loss": 0.9884,
+      "step": 85
+    },
+    {
+      "epoch": 0.4639175257731959,
+      "grad_norm": 0.536442756652832,
+      "learning_rate": 2.9162273233762062e-05,
+      "loss": 1.0139,
+      "step": 90
+    },
+    {
+      "epoch": 0.4896907216494845,
+      "grad_norm": 0.5790107250213623,
+      "learning_rate": 2.9015907557410065e-05,
+      "loss": 1.0168,
+      "step": 95
+    },
+    {
+      "epoch": 0.5154639175257731,
+      "grad_norm": 0.5532541275024414,
+      "learning_rate": 2.8858192987669303e-05,
+      "loss": 0.901,
+      "step": 100
+    },
+    {
+      "epoch": 0.5412371134020618,
+      "grad_norm": 0.590708315372467,
+      "learning_rate": 2.8689257228424124e-05,
+      "loss": 0.8846,
+      "step": 105
+    },
+    {
+      "epoch": 0.5670103092783505,
+      "grad_norm": 0.6129378080368042,
+      "learning_rate": 2.8509237069526588e-05,
+      "loss": 0.8371,
+      "step": 110
+    },
+    {
+      "epoch": 0.5927835051546392,
+      "grad_norm": 0.6879262328147888,
+      "learning_rate": 2.8318278276035626e-05,
+      "loss": 0.8786,
+      "step": 115
+    },
+    {
+      "epoch": 0.6185567010309279,
+      "grad_norm": 0.7168922424316406,
+      "learning_rate": 2.8116535470188883e-05,
+      "loss": 0.8579,
+      "step": 120
+    },
+    {
+      "epoch": 0.6443298969072165,
+      "grad_norm": 0.6872289776802063,
+      "learning_rate": 2.7904172006202707e-05,
+      "loss": 0.8895,
+      "step": 125
+    },
+    {
+      "epoch": 0.6701030927835051,
+      "grad_norm": 0.7295854687690735,
+      "learning_rate": 2.7681359838001767e-05,
+      "loss": 0.7937,
+      "step": 130
+    },
+    {
+      "epoch": 0.6958762886597938,
+      "grad_norm": 0.7478352785110474,
+      "learning_rate": 2.744827937998538e-05,
+      "loss": 0.7875,
+      "step": 135
+    },
+    {
+      "epoch": 0.7216494845360825,
+      "grad_norm": 0.6469711065292358,
+      "learning_rate": 2.7205119360943175e-05,
+      "loss": 0.8586,
+      "step": 140
+    },
+    {
+      "epoch": 0.7474226804123711,
+      "grad_norm": 0.7704457640647888,
+      "learning_rate": 2.6952076671238567e-05,
+      "loss": 0.7651,
+      "step": 145
+    },
+    {
+      "epoch": 0.7731958762886598,
+      "grad_norm": 0.7963151931762695,
+      "learning_rate": 2.6689356203383624e-05,
+      "loss": 0.717,
+      "step": 150
+    },
+    {
+      "epoch": 0.7989690721649485,
+      "grad_norm": 0.925319492816925,
+      "learning_rate": 2.641717068613447e-05,
+      "loss": 0.7192,
+      "step": 155
+    },
+    {
+      "epoch": 0.8247422680412371,
+      "grad_norm": 0.8700096607208252,
+      "learning_rate": 2.6135740512241603e-05,
+      "loss": 0.7039,
+      "step": 160
+    },
+    {
+      "epoch": 0.8505154639175257,
+      "grad_norm": 0.9271858334541321,
+      "learning_rate": 2.584529355999451e-05,
+      "loss": 0.7193,
+      "step": 165
+    },
+    {
+      "epoch": 0.8762886597938144,
+      "grad_norm": 0.9839221239089966,
+      "learning_rate": 2.554606500870518e-05,
+      "loss": 0.665,
+      "step": 170
+    },
+    {
+      "epoch": 0.9020618556701031,
+      "grad_norm": 0.8845900893211365,
+      "learning_rate": 2.5238297148279813e-05,
+      "loss": 0.6152,
+      "step": 175
+    },
+    {
+      "epoch": 0.9278350515463918,
+      "grad_norm": 0.8099294900894165,
+      "learning_rate": 2.492223918303302e-05,
+      "loss": 0.6055,
+      "step": 180
+    },
+    {
+      "epoch": 0.9536082474226805,
+      "grad_norm": 0.8934437036514282,
+      "learning_rate": 2.459814702990328e-05,
+      "loss": 0.6809,
+      "step": 185
+    },
+    {
+      "epoch": 0.979381443298969,
+      "grad_norm": 0.9493690729141235,
+      "learning_rate": 2.426628311123315e-05,
+      "loss": 0.6561,
+      "step": 190
+    },
+    {
+      "epoch": 1.0051546391752577,
+      "grad_norm": 0.9457970857620239,
+      "learning_rate": 2.3926916142281847e-05,
+      "loss": 0.638,
+      "step": 195
+    },
+    {
+      "epoch": 1.0309278350515463,
+      "grad_norm": 0.9784163236618042,
+      "learning_rate": 2.358032091364245e-05,
+      "loss": 0.5106,
+      "step": 200
+    },
+    {
+      "epoch": 1.056701030927835,
+      "grad_norm": 0.9069936275482178,
+      "learning_rate": 2.3226778068739782e-05,
+      "loss": 0.5561,
+      "step": 205
+    },
+    {
+      "epoch": 1.0824742268041236,
+      "grad_norm": 1.0932109355926514,
+      "learning_rate": 2.2866573876589157e-05,
+      "loss": 0.5159,
+      "step": 210
+    },
+    {
+      "epoch": 1.1082474226804124,
+      "grad_norm": 0.9185000061988831,
+      "learning_rate": 2.25e-05,
+      "loss": 0.5104,
+      "step": 215
+    },
+    {
+      "epoch": 1.134020618556701,
+      "grad_norm": 0.9988956451416016,
+      "learning_rate": 2.2127353259412055e-05,
+      "loss": 0.4867,
+      "step": 220
+    },
+    {
+      "epoch": 1.1597938144329896,
+      "grad_norm": 0.9698680639266968,
+      "learning_rate": 2.1748935392555346e-05,
+      "loss": 0.4881,
+      "step": 225
+    },
+    {
+      "epoch": 1.1855670103092784,
+      "grad_norm": 0.9426619410514832,
+      "learning_rate": 2.1365052810128554e-05,
+      "loss": 0.4878,
+      "step": 230
+    },
+    {
+      "epoch": 1.211340206185567,
+      "grad_norm": 1.0130360126495361,
+      "learning_rate": 2.0976016347693626e-05,
+      "loss": 0.4811,
+      "step": 235
+    },
+    {
+      "epoch": 1.2371134020618557,
+      "grad_norm": 0.9892734289169312,
+      "learning_rate": 2.058214101398748e-05,
+      "loss": 0.4403,
+      "step": 240
+    },
+    {
+      "epoch": 1.2628865979381443,
+      "grad_norm": 1.1032499074935913,
+      "learning_rate": 2.018374573585467e-05,
+      "loss": 0.4787,
+      "step": 245
+    },
+    {
+      "epoch": 1.2886597938144329,
+      "grad_norm": 0.9830612540245056,
+      "learning_rate": 1.978115310000744e-05,
+      "loss": 0.4723,
+      "step": 250
+    },
+    {
+      "epoch": 1.3144329896907216,
+      "grad_norm": 1.1581668853759766,
+      "learning_rate": 1.9374689091822376e-05,
+      "loss": 0.4188,
+      "step": 255
+    },
+    {
+      "epoch": 1.3402061855670104,
+      "grad_norm": 1.0185214281082153,
+      "learning_rate": 1.8964682831385097e-05,
+      "loss": 0.4379,
+      "step": 260
+    },
+    {
+      "epoch": 1.365979381443299,
+      "grad_norm": 1.2045397758483887,
+      "learning_rate": 1.85514663069967e-05,
+      "loss": 0.3893,
+      "step": 265
+    },
+    {
+      "epoch": 1.3917525773195876,
+      "grad_norm": 1.0649877786636353,
+      "learning_rate": 1.813537410635782e-05,
+      "loss": 0.4422,
+      "step": 270
+    },
+    {
+      "epoch": 1.4175257731958764,
+      "grad_norm": 1.1870522499084473,
+      "learning_rate": 1.7716743145647837e-05,
+      "loss": 0.401,
+      "step": 275
+    },
+    {
+      "epoch": 1.443298969072165,
+      "grad_norm": 0.950062096118927,
+      "learning_rate": 1.7295912396718768e-05,
+      "loss": 0.3971,
+      "step": 280
+    },
+    {
+      "epoch": 1.4690721649484537,
+      "grad_norm": 0.9439635276794434,
+      "learning_rate": 1.6873222612624575e-05,
+      "loss": 0.3919,
+      "step": 285
+    },
+    {
+      "epoch": 1.4948453608247423,
+      "grad_norm": 1.165956735610962,
+      "learning_rate": 1.644901605170826e-05,
+      "loss": 0.4053,
+      "step": 290
+    },
+    {
+      "epoch": 1.5206185567010309,
+      "grad_norm": 1.17833411693573,
+      "learning_rate": 1.6023636200470068e-05,
+      "loss": 0.3925,
+      "step": 295
+    },
+    {
+      "epoch": 1.5463917525773194,
+      "grad_norm": 1.0232280492782593,
+      "learning_rate": 1.5597427495441244e-05,
+      "loss": 0.4006,
+      "step": 300
+    },
+    {
+      "epoch": 1.5721649484536082,
+      "grad_norm": 1.0091692209243774,
+      "learning_rate": 1.5170735044288564e-05,
+      "loss": 0.353,
+      "step": 305
+    },
+    {
+      "epoch": 1.597938144329897,
+      "grad_norm": 1.0597478151321411,
+      "learning_rate": 1.474390434637538e-05,
+      "loss": 0.391,
+      "step": 310
+    },
+    {
+      "epoch": 1.6237113402061856,
+      "grad_norm": 0.9946566820144653,
+      "learning_rate": 1.431728101300555e-05,
+      "loss": 0.3677,
+      "step": 315
+    },
+    {
+      "epoch": 1.6494845360824741,
+      "grad_norm": 0.975480854511261,
+      "learning_rate": 1.38912104875767e-05,
+      "loss": 0.3645,
+      "step": 320
+    },
+    {
+      "epoch": 1.675257731958763,
+      "grad_norm": 1.1661028861999512,
+      "learning_rate": 1.3466037765869487e-05,
+      "loss": 0.3948,
+      "step": 325
+    },
+    {
+      "epoch": 1.7010309278350515,
+      "grad_norm": 1.0427396297454834,
+      "learning_rate": 1.304210711669923e-05,
+      "loss": 0.385,
+      "step": 330
+    },
+    {
+      "epoch": 1.7268041237113403,
+      "grad_norm": 1.0629898309707642,
+      "learning_rate": 1.261976180315623e-05,
+      "loss": 0.3863,
+      "step": 335
+    },
+    {
+      "epoch": 1.7525773195876289,
+      "grad_norm": 1.0982991456985474,
+      "learning_rate": 1.2199343804660457e-05,
+      "loss": 0.3241,
+      "step": 340
+    },
+    {
+      "epoch": 1.7783505154639174,
+      "grad_norm": 1.3040047883987427,
+      "learning_rate": 1.1781193540055574e-05,
+      "loss": 0.3346,
+      "step": 345
+    },
+    {
+      "epoch": 1.8041237113402062,
+      "grad_norm": 0.9589328169822693,
+      "learning_rate": 1.1365649591966642e-05,
+      "loss": 0.3212,
+      "step": 350
+    },
+    {
+      "epoch": 1.829896907216495,
+      "grad_norm": 1.131953477859497,
+      "learning_rate": 1.0953048432644634e-05,
+      "loss": 0.3345,
+      "step": 355
+    },
+    {
+      "epoch": 1.8556701030927836,
+      "grad_norm": 1.07698655128479,
+      "learning_rate": 1.0543724151519733e-05,
+      "loss": 0.3459,
+      "step": 360
+    },
+    {
+      "epoch": 1.8814432989690721,
+      "grad_norm": 1.0469233989715576,
+      "learning_rate": 1.0138008184684012e-05,
+      "loss": 0.3574,
+      "step": 365
+    },
+    {
+      "epoch": 1.9072164948453607,
+      "grad_norm": 1.1065460443496704,
+      "learning_rate": 9.73622904652265e-06,
+      "loss": 0.3437,
+      "step": 370
+    },
+    {
+      "epoch": 1.9329896907216495,
+      "grad_norm": 1.0524650812149048,
+      "learning_rate": 9.338712063710786e-06,
+      "loss": 0.3337,
+      "step": 375
+    },
+    {
+      "epoch": 1.9587628865979383,
+      "grad_norm": 1.104760766029358,
+      "learning_rate": 8.945779111791596e-06,
+      "loss": 0.3334,
+      "step": 380
+    },
+    {
+      "epoch": 1.9845360824742269,
+      "grad_norm": 1.1348456144332886,
+      "learning_rate": 8.557748354548773e-06,
+      "loss": 0.3262,
+      "step": 385
+    },
+    {
+      "epoch": 2.0103092783505154,
+      "grad_norm": 0.8536417484283447,
+      "learning_rate": 8.174933986384459e-06,
+      "loss": 0.2597,
+      "step": 390
+    },
+    {
+      "epoch": 2.036082474226804,
+      "grad_norm": 1.1393781900405884,
+      "learning_rate": 7.797645977911268e-06,
+      "loss": 0.2625,
+      "step": 395
+    },
+    {
+      "epoch": 2.0618556701030926,
+      "grad_norm": 1.0353103876113892,
+      "learning_rate": 7.426189824964384e-06,
+      "loss": 0.2779,
+      "step": 400
+    },
+    {
+      "epoch": 2.0876288659793816,
+      "grad_norm": 1.1357743740081787,
+      "learning_rate": 7.060866301236919e-06,
+      "loss": 0.2515,
+      "step": 405
+    },
+    {
+      "epoch": 2.11340206185567,
+      "grad_norm": 1.0975826978683472,
+      "learning_rate": 6.7019712147388935e-06,
+      "loss": 0.2284,
+      "step": 410
+    },
+    {
+      "epoch": 2.1391752577319587,
+      "grad_norm": 1.1204084157943726,
+      "learning_rate": 6.349795168276994e-06,
+      "loss": 0.2144,
+      "step": 415
+    },
+    {
+      "epoch": 2.1649484536082473,
+      "grad_norm": 0.9059160947799683,
+      "learning_rate": 6.0046233241490596e-06,
+      "loss": 0.2271,
+      "step": 420
+    },
+    {
+      "epoch": 2.1907216494845363,
+      "grad_norm": 0.9593297839164734,
+      "learning_rate": 5.666735173243836e-06,
+      "loss": 0.232,
+      "step": 425
+    },
+    {
+      "epoch": 2.216494845360825,
+      "grad_norm": 1.002112627029419,
+      "learning_rate": 5.3364043087329565e-06,
+      "loss": 0.2331,
+      "step": 430
+    },
+    {
+      "epoch": 2.2422680412371134,
+      "grad_norm": 1.0720884799957275,
+      "learning_rate": 5.013898204538392e-06,
+      "loss": 0.2452,
+      "step": 435
+    },
+    {
+      "epoch": 2.268041237113402,
+      "grad_norm": 1.1171693801879883,
+      "learning_rate": 4.69947799875475e-06,
+      "loss": 0.2407,
+      "step": 440
+    },
+    {
+      "epoch": 2.2938144329896906,
+      "grad_norm": 1.0597730875015259,
+      "learning_rate": 4.393398282201788e-06,
+      "loss": 0.2367,
+      "step": 445
+    },
+    {
+      "epoch": 2.319587628865979,
+      "grad_norm": 1.0805095434188843,
+      "learning_rate": 4.095906892278365e-06,
+      "loss": 0.236,
+      "step": 450
+    },
+    {
+      "epoch": 2.345360824742268,
+      "grad_norm": 1.0155326128005981,
+      "learning_rate": 3.807244712284718e-06,
+      "loss": 0.2027,
+      "step": 455
+    },
+    {
+      "epoch": 2.3711340206185567,
+      "grad_norm": 1.12794029712677,
+      "learning_rate": 3.5276454763756105e-06,
+      "loss": 0.2307,
+      "step": 460
+    },
+    {
+      "epoch": 2.3969072164948453,
+      "grad_norm": 0.8833988308906555,
+      "learning_rate": 3.257335580302221e-06,
+      "loss": 0.2247,
+      "step": 465
+    },
+    {
+      "epoch": 2.422680412371134,
+      "grad_norm": 0.9332590699195862,
+      "learning_rate": 2.996533898096065e-06,
+      "loss": 0.2359,
+      "step": 470
+    },
+    {
+      "epoch": 2.448453608247423,
+      "grad_norm": 1.1466366052627563,
+      "learning_rate": 2.7454516048433704e-06,
+      "loss": 0.2502,
+      "step": 475
+    },
+    {
+      "epoch": 2.4742268041237114,
+      "grad_norm": 0.9704514741897583,
+      "learning_rate": 2.5042920056933926e-06,
+      "loss": 0.2201,
+      "step": 480
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.9922817945480347,
+      "learning_rate": 2.273250371239152e-06,
+      "loss": 0.2469,
+      "step": 485
+    },
+    {
+      "epoch": 2.5257731958762886,
+      "grad_norm": 1.0179280042648315,
+      "learning_rate": 2.05251377940386e-06,
+      "loss": 0.2256,
+      "step": 490
+    },
+    {
+      "epoch": 2.551546391752577,
+      "grad_norm": 1.0571855306625366,
+      "learning_rate": 1.842260963961086e-06,
+      "loss": 0.2382,
+      "step": 495
+    },
+    {
+      "epoch": 2.5773195876288657,
+      "grad_norm": 0.9058892130851746,
+      "learning_rate": 1.6426621698113054e-06,
+      "loss": 0.2359,
+      "step": 500
+    },
+    {
+      "epoch": 2.6030927835051547,
+      "grad_norm": 1.054587960243225,
+      "learning_rate": 1.4538790151320092e-06,
+      "loss": 0.2388,
+      "step": 505
+    },
+    {
+      "epoch": 2.6288659793814433,
+      "grad_norm": 1.0302919149398804,
+      "learning_rate": 1.276064360513015e-06,
+      "loss": 0.2222,
+      "step": 510
+    },
+    {
+      "epoch": 2.654639175257732,
+      "grad_norm": 1.2213265895843506,
+      "learning_rate": 1.109362185182921e-06,
+      "loss": 0.2431,
+      "step": 515
+    },
+    {
+      "epoch": 2.680412371134021,
+      "grad_norm": 1.0215009450912476,
+      "learning_rate": 9.539074704269396e-07,
+      "loss": 0.2069,
+      "step": 520
+    },
+    {
+      "epoch": 2.7061855670103094,
+      "grad_norm": 1.0206140279769897,
+      "learning_rate": 8.098260902904941e-07,
+      "loss": 0.2237,
+      "step": 525
+    },
+    {
+      "epoch": 2.731958762886598,
+      "grad_norm": 1.1378391981124878,
+      "learning_rate": 6.772347096570969e-07,
+      "loss": 0.2094,
+      "step": 530
+    },
+    {
+      "epoch": 2.7577319587628866,
+      "grad_norm": 1.041870355606079,
+      "learning_rate": 5.56240689783013e-07,
+      "loss": 0.2265,
+      "step": 535
+    },
+    {
+      "epoch": 2.783505154639175,
+      "grad_norm": 0.9455012083053589,
+      "learning_rate": 4.4694200136521923e-07,
+      "loss": 0.22,
+      "step": 540
+    },
+    {
+      "epoch": 2.8092783505154637,
+      "grad_norm": 1.0562723875045776,
+      "learning_rate": 3.4942714521305816e-07,
+      "loss": 0.2117,
+      "step": 545
+    },
+    {
+      "epoch": 2.8350515463917527,
+      "grad_norm": 1.1549808979034424,
+      "learning_rate": 2.6377508058776256e-07,
+      "loss": 0.2549,
+      "step": 550
+    },
+    {
+      "epoch": 2.8608247422680413,
+      "grad_norm": 1.0527653694152832,
+      "learning_rate": 1.9005516126795574e-07,
+      "loss": 0.2429,
+      "step": 555
+    },
+    {
+      "epoch": 2.88659793814433,
+      "grad_norm": 1.0415107011795044,
+      "learning_rate": 1.2832707939284428e-07,
+      "loss": 0.2369,
+      "step": 560
+    },
+    {
+      "epoch": 2.9123711340206184,
+      "grad_norm": 1.088728904724121,
+      "learning_rate": 7.86408171285774e-08,
+      "loss": 0.2242,
+      "step": 565
+    },
+    {
+      "epoch": 2.9381443298969074,
+      "grad_norm": 1.0853710174560547,
+      "learning_rate": 4.1036606196935834e-08,
+      "loss": 0.2154,
+      "step": 570
+    },
+    {
+      "epoch": 2.963917525773196,
+      "grad_norm": 1.1450273990631104,
+      "learning_rate": 1.5544895299086646e-08,
+      "loss": 0.223,
+      "step": 575
+    },
+    {
+      "epoch": 2.9896907216494846,
+      "grad_norm": 1.1838741302490234,
+      "learning_rate": 2.1863254608150974e-09,
+      "loss": 0.1986,
+      "step": 580
+    },
+    {
+      "epoch": 3.0,
+      "step": 582,
+      "total_flos": 7.780499300139663e+17,
+      "train_loss": 0.5425458254478231,
+      "train_runtime": 390.8207,
+      "train_samples_per_second": 47.554,
+      "train_steps_per_second": 1.489
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 582,
+  "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": 7.780499300139663e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

19_128_e3_3e-5/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c37d2fa9b744538fada6f50c779622f7a714edc0313eade1ff8a61922ff0c604
+size 8209