Upload folder using huggingface_hub

18_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",
+    "v_proj",
+    "q_proj",
+    "o_proj",
+    "up_proj",
+    "k_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

18_128_e3_3e-5/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00fd1ba0bd9825412f2137948dfb6a5736359f0509495e1e0d6c476ff82ac6ea
+size 791751704

18_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
+}

18_128_e3_3e-5/all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 8.71254915782017e+17,
+    "train_loss": 0.5303278984684571,
+    "train_runtime": 415.168,
+    "train_samples": 5964,
+    "train_samples_per_second": 43.096,
+    "train_steps_per_second": 1.351
+}

18_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 %}

18_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
+}

18_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
+  }
+}

18_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
+}

18_128_e3_3e-5/train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 8.71254915782017e+17,
+    "train_loss": 0.5303278984684571,
+    "train_runtime": 415.168,
+    "train_samples": 5964,
+    "train_samples_per_second": 43.096,
+    "train_steps_per_second": 1.351
+}

18_128_e3_3e-5/trainer_state.json

@@ -0,0 +1,827 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 561,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02680965147453083,
+      "grad_norm": 3.077638626098633,
+      "learning_rate": 4.137931034482758e-06,
+      "loss": 1.4892,
+      "step": 5
+    },
+    {
+      "epoch": 0.05361930294906166,
+      "grad_norm": 1.2297050952911377,
+      "learning_rate": 9.310344827586207e-06,
+      "loss": 1.3821,
+      "step": 10
+    },
+    {
+      "epoch": 0.08042895442359249,
+      "grad_norm": 0.517909586429596,
+      "learning_rate": 1.4482758620689657e-05,
+      "loss": 1.3461,
+      "step": 15
+    },
+    {
+      "epoch": 0.10723860589812333,
+      "grad_norm": 0.42348572611808777,
+      "learning_rate": 1.9655172413793102e-05,
+      "loss": 1.2691,
+      "step": 20
+    },
+    {
+      "epoch": 0.13404825737265416,
+      "grad_norm": 0.5127076506614685,
+      "learning_rate": 2.4827586206896553e-05,
+      "loss": 1.1961,
+      "step": 25
+    },
+    {
+      "epoch": 0.16085790884718498,
+      "grad_norm": 0.45731085538864136,
+      "learning_rate": 3e-05,
+      "loss": 1.1658,
+      "step": 30
+    },
+    {
+      "epoch": 0.1876675603217158,
+      "grad_norm": 0.3628169894218445,
+      "learning_rate": 2.999346198065638e-05,
+      "loss": 1.1439,
+      "step": 35
+    },
+    {
+      "epoch": 0.21447721179624665,
+      "grad_norm": 0.35066866874694824,
+      "learning_rate": 2.9973853622051763e-05,
+      "loss": 1.0985,
+      "step": 40
+    },
+    {
+      "epoch": 0.24128686327077747,
+      "grad_norm": 0.37680548429489136,
+      "learning_rate": 2.9941192017496545e-05,
+      "loss": 1.165,
+      "step": 45
+    },
+    {
+      "epoch": 0.2680965147453083,
+      "grad_norm": 0.40990781784057617,
+      "learning_rate": 2.989550563928436e-05,
+      "loss": 1.0919,
+      "step": 50
+    },
+    {
+      "epoch": 0.2949061662198391,
+      "grad_norm": 0.41313040256500244,
+      "learning_rate": 2.983683431387182e-05,
+      "loss": 1.0408,
+      "step": 55
+    },
+    {
+      "epoch": 0.32171581769436997,
+      "grad_norm": 0.39260512590408325,
+      "learning_rate": 2.9765229187160316e-05,
+      "loss": 1.0466,
+      "step": 60
+    },
+    {
+      "epoch": 0.3485254691689008,
+      "grad_norm": 0.3898566961288452,
+      "learning_rate": 2.968075267991032e-05,
+      "loss": 1.0667,
+      "step": 65
+    },
+    {
+      "epoch": 0.3753351206434316,
+      "grad_norm": 0.44523099064826965,
+      "learning_rate": 2.958347843332696e-05,
+      "loss": 1.0396,
+      "step": 70
+    },
+    {
+      "epoch": 0.40214477211796246,
+      "grad_norm": 0.4939868152141571,
+      "learning_rate": 2.9473491244864347e-05,
+      "loss": 0.9434,
+      "step": 75
+    },
+    {
+      "epoch": 0.4289544235924933,
+      "grad_norm": 0.4144739806652069,
+      "learning_rate": 2.9350886994304572e-05,
+      "loss": 0.9358,
+      "step": 80
+    },
+    {
+      "epoch": 0.45576407506702415,
+      "grad_norm": 0.49549126625061035,
+      "learning_rate": 2.9215772560175877e-05,
+      "loss": 0.9126,
+      "step": 85
+    },
+    {
+      "epoch": 0.48257372654155495,
+      "grad_norm": 0.5313646197319031,
+      "learning_rate": 2.906826572658278e-05,
+      "loss": 0.9109,
+      "step": 90
+    },
+    {
+      "epoch": 0.5093833780160858,
+      "grad_norm": 0.46925896406173706,
+      "learning_rate": 2.8908495080529468e-05,
+      "loss": 0.9023,
+      "step": 95
+    },
+    {
+      "epoch": 0.5361930294906166,
+      "grad_norm": 0.5344696044921875,
+      "learning_rate": 2.873659989982586e-05,
+      "loss": 0.8489,
+      "step": 100
+    },
+    {
+      "epoch": 0.5630026809651475,
+      "grad_norm": 0.5579538345336914,
+      "learning_rate": 2.8552730031674164e-05,
+      "loss": 0.8704,
+      "step": 105
+    },
+    {
+      "epoch": 0.5898123324396782,
+      "grad_norm": 0.5828568935394287,
+      "learning_rate": 2.835704576204167e-05,
+      "loss": 0.8716,
+      "step": 110
+    },
+    {
+      "epoch": 0.6166219839142091,
+      "grad_norm": 0.6908984780311584,
+      "learning_rate": 2.814971767593372e-05,
+      "loss": 0.8295,
+      "step": 115
+    },
+    {
+      "epoch": 0.6434316353887399,
+      "grad_norm": 0.636009156703949,
+      "learning_rate": 2.7930926508688647e-05,
+      "loss": 0.7816,
+      "step": 120
+    },
+    {
+      "epoch": 0.6702412868632708,
+      "grad_norm": 0.6061617136001587,
+      "learning_rate": 2.770086298842426e-05,
+      "loss": 0.8153,
+      "step": 125
+    },
+    {
+      "epoch": 0.6970509383378016,
+      "grad_norm": 0.685501754283905,
+      "learning_rate": 2.7459727669773344e-05,
+      "loss": 0.7474,
+      "step": 130
+    },
+    {
+      "epoch": 0.7238605898123325,
+      "grad_norm": 0.632835865020752,
+      "learning_rate": 2.7207730759052925e-05,
+      "loss": 0.7809,
+      "step": 135
+    },
+    {
+      "epoch": 0.7506702412868632,
+      "grad_norm": 0.6810129284858704,
+      "learning_rate": 2.6945091931019916e-05,
+      "loss": 0.7307,
+      "step": 140
+    },
+    {
+      "epoch": 0.7774798927613941,
+      "grad_norm": 0.715189516544342,
+      "learning_rate": 2.667204013737272e-05,
+      "loss": 0.7168,
+      "step": 145
+    },
+    {
+      "epoch": 0.8042895442359249,
+      "grad_norm": 0.7452967166900635,
+      "learning_rate": 2.638881340716583e-05,
+      "loss": 0.6809,
+      "step": 150
+    },
+    {
+      "epoch": 0.8310991957104558,
+      "grad_norm": 0.7082217931747437,
+      "learning_rate": 2.6095658639311348e-05,
+      "loss": 0.6696,
+      "step": 155
+    },
+    {
+      "epoch": 0.8579088471849866,
+      "grad_norm": 0.6397304534912109,
+      "learning_rate": 2.5792831387348322e-05,
+      "loss": 0.6849,
+      "step": 160
+    },
+    {
+      "epoch": 0.8847184986595175,
+      "grad_norm": 0.7843431830406189,
+      "learning_rate": 2.548059563666757e-05,
+      "loss": 0.6662,
+      "step": 165
+    },
+    {
+      "epoch": 0.9115281501340483,
+      "grad_norm": 0.7372881770133972,
+      "learning_rate": 2.5159223574386117e-05,
+      "loss": 0.6777,
+      "step": 170
+    },
+    {
+      "epoch": 0.938337801608579,
+      "grad_norm": 0.8526647686958313,
+      "learning_rate": 2.4828995352071927e-05,
+      "loss": 0.6247,
+      "step": 175
+    },
+    {
+      "epoch": 0.9651474530831099,
+      "grad_norm": 0.8327404856681824,
+      "learning_rate": 2.4490198841525708e-05,
+      "loss": 0.654,
+      "step": 180
+    },
+    {
+      "epoch": 0.9919571045576407,
+      "grad_norm": 0.7939515709877014,
+      "learning_rate": 2.414312938383272e-05,
+      "loss": 0.5769,
+      "step": 185
+    },
+    {
+      "epoch": 1.0160857908847185,
+      "grad_norm": 0.7502666115760803,
+      "learning_rate": 2.3788089531903372e-05,
+      "loss": 0.5539,
+      "step": 190
+    },
+    {
+      "epoch": 1.0428954423592494,
+      "grad_norm": 0.7506025433540344,
+      "learning_rate": 2.3425388786726944e-05,
+      "loss": 0.5419,
+      "step": 195
+    },
+    {
+      "epoch": 1.0697050938337802,
+      "grad_norm": 0.8200737833976746,
+      "learning_rate": 2.305534332756849e-05,
+      "loss": 0.528,
+      "step": 200
+    },
+    {
+      "epoch": 1.096514745308311,
+      "grad_norm": 0.8865842223167419,
+      "learning_rate": 2.2678275736344014e-05,
+      "loss": 0.4819,
+      "step": 205
+    },
+    {
+      "epoch": 1.123324396782842,
+      "grad_norm": 0.9966821074485779,
+      "learning_rate": 2.229451471641422e-05,
+      "loss": 0.5024,
+      "step": 210
+    },
+    {
+      "epoch": 1.1501340482573728,
+      "grad_norm": 0.7705747485160828,
+      "learning_rate": 2.190439480604199e-05,
+      "loss": 0.4797,
+      "step": 215
+    },
+    {
+      "epoch": 1.1769436997319036,
+      "grad_norm": 0.8594604730606079,
+      "learning_rate": 2.1508256086763372e-05,
+      "loss": 0.4881,
+      "step": 220
+    },
+    {
+      "epoch": 1.2037533512064342,
+      "grad_norm": 0.8787497878074646,
+      "learning_rate": 2.1106443886926288e-05,
+      "loss": 0.5361,
+      "step": 225
+    },
+    {
+      "epoch": 1.230563002680965,
+      "grad_norm": 0.8467434048652649,
+      "learning_rate": 2.0699308480655397e-05,
+      "loss": 0.4813,
+      "step": 230
+    },
+    {
+      "epoch": 1.257372654155496,
+      "grad_norm": 0.8163837194442749,
+      "learning_rate": 2.028720478250561e-05,
+      "loss": 0.4474,
+      "step": 235
+    },
+    {
+      "epoch": 1.2841823056300268,
+      "grad_norm": 0.8756049275398254,
+      "learning_rate": 1.9870492038070255e-05,
+      "loss": 0.459,
+      "step": 240
+    },
+    {
+      "epoch": 1.3109919571045576,
+      "grad_norm": 0.8299089074134827,
+      "learning_rate": 1.944953351081385e-05,
+      "loss": 0.4494,
+      "step": 245
+    },
+    {
+      "epoch": 1.3378016085790885,
+      "grad_norm": 0.9665119647979736,
+      "learning_rate": 1.9024696165402272e-05,
+      "loss": 0.4377,
+      "step": 250
+    },
+    {
+      "epoch": 1.3646112600536193,
+      "grad_norm": 0.9445621967315674,
+      "learning_rate": 1.859635034780648e-05,
+      "loss": 0.45,
+      "step": 255
+    },
+    {
+      "epoch": 1.3914209115281502,
+      "grad_norm": 0.9457170963287354,
+      "learning_rate": 1.8164869462458635e-05,
+      "loss": 0.44,
+      "step": 260
+    },
+    {
+      "epoch": 1.418230563002681,
+      "grad_norm": 0.9954326748847961,
+      "learning_rate": 1.7730629646742038e-05,
+      "loss": 0.4149,
+      "step": 265
+    },
+    {
+      "epoch": 1.4450402144772119,
+      "grad_norm": 0.9106288552284241,
+      "learning_rate": 1.729400944309869e-05,
+      "loss": 0.4258,
+      "step": 270
+    },
+    {
+      "epoch": 1.4718498659517425,
+      "grad_norm": 0.8927768468856812,
+      "learning_rate": 1.6855389469040217e-05,
+      "loss": 0.422,
+      "step": 275
+    },
+    {
+      "epoch": 1.4986595174262733,
+      "grad_norm": 0.9409456849098206,
+      "learning_rate": 1.6415152085349934e-05,
+      "loss": 0.4157,
+      "step": 280
+    },
+    {
+      "epoch": 1.5254691689008042,
+      "grad_norm": 0.9150331020355225,
+      "learning_rate": 1.597368106276523e-05,
+      "loss": 0.4201,
+      "step": 285
+    },
+    {
+      "epoch": 1.552278820375335,
+      "grad_norm": 0.9597664475440979,
+      "learning_rate": 1.553136124743081e-05,
+      "loss": 0.4277,
+      "step": 290
+    },
+    {
+      "epoch": 1.579088471849866,
+      "grad_norm": 0.9807479381561279,
+      "learning_rate": 1.50885782254145e-05,
+      "loss": 0.4464,
+      "step": 295
+    },
+    {
+      "epoch": 1.6058981233243967,
+      "grad_norm": 0.8866353631019592,
+      "learning_rate": 1.464571798657803e-05,
+      "loss": 0.362,
+      "step": 300
+    },
+    {
+      "epoch": 1.6327077747989276,
+      "grad_norm": 0.9367548823356628,
+      "learning_rate": 1.4203166588095816e-05,
+      "loss": 0.3591,
+      "step": 305
+    },
+    {
+      "epoch": 1.6595174262734584,
+      "grad_norm": 0.9340230822563171,
+      "learning_rate": 1.3761309817915017e-05,
+      "loss": 0.3717,
+      "step": 310
+    },
+    {
+      "epoch": 1.6863270777479893,
+      "grad_norm": 0.9089266061782837,
+      "learning_rate": 1.3320532858450382e-05,
+      "loss": 0.3745,
+      "step": 315
+    },
+    {
+      "epoch": 1.7131367292225201,
+      "grad_norm": 0.9951624274253845,
+      "learning_rate": 1.2881219950806875e-05,
+      "loss": 0.403,
+      "step": 320
+    },
+    {
+      "epoch": 1.739946380697051,
+      "grad_norm": 0.9589396119117737,
+      "learning_rate": 1.2443754059822901e-05,
+      "loss": 0.3701,
+      "step": 325
+    },
+    {
+      "epoch": 1.7667560321715818,
+      "grad_norm": 0.9249691367149353,
+      "learning_rate": 1.2008516540226115e-05,
+      "loss": 0.3448,
+      "step": 330
+    },
+    {
+      "epoch": 1.7935656836461127,
+      "grad_norm": 1.0270546674728394,
+      "learning_rate": 1.1575886804192816e-05,
+      "loss": 0.3529,
+      "step": 335
+    },
+    {
+      "epoch": 1.8203753351206435,
+      "grad_norm": 1.0956830978393555,
+      "learning_rate": 1.1146241990600713e-05,
+      "loss": 0.3469,
+      "step": 340
+    },
+    {
+      "epoch": 1.8471849865951744,
+      "grad_norm": 0.9199484586715698,
+      "learning_rate": 1.0719956636263424e-05,
+      "loss": 0.3623,
+      "step": 345
+    },
+    {
+      "epoch": 1.8739946380697052,
+      "grad_norm": 1.1874014139175415,
+      "learning_rate": 1.0297402349433286e-05,
+      "loss": 0.3441,
+      "step": 350
+    },
+    {
+      "epoch": 1.900804289544236,
+      "grad_norm": 1.0195046663284302,
+      "learning_rate": 9.878947485857104e-06,
+      "loss": 0.3678,
+      "step": 355
+    },
+    {
+      "epoch": 1.9276139410187667,
+      "grad_norm": 1.132421612739563,
+      "learning_rate": 9.464956827667216e-06,
+      "loss": 0.3183,
+      "step": 360
+    },
+    {
+      "epoch": 1.9544235924932976,
+      "grad_norm": 1.0497463941574097,
+      "learning_rate": 9.05579126538779e-06,
+      "loss": 0.322,
+      "step": 365
+    },
+    {
+      "epoch": 1.9812332439678284,
+      "grad_norm": 0.9322401285171509,
+      "learning_rate": 8.651807483333627e-06,
+      "loss": 0.3408,
+      "step": 370
+    },
+    {
+      "epoch": 2.005361930294906,
+      "grad_norm": 0.9538334608078003,
+      "learning_rate": 8.253357648675594e-06,
+      "loss": 0.3186,
+      "step": 375
+    },
+    {
+      "epoch": 2.032171581769437,
+      "grad_norm": 0.9463244676589966,
+      "learning_rate": 7.860789104443897e-06,
+      "loss": 0.2741,
+      "step": 380
+    },
+    {
+      "epoch": 2.058981233243968,
+      "grad_norm": 0.9529656171798706,
+      "learning_rate": 7.474444066736647e-06,
+      "loss": 0.2949,
+      "step": 385
+    },
+    {
+      "epoch": 2.0857908847184987,
+      "grad_norm": 0.9381195902824402,
+      "learning_rate": 7.094659326397818e-06,
+      "loss": 0.2847,
+      "step": 390
+    },
+    {
+      "epoch": 2.1126005361930296,
+      "grad_norm": 1.0908279418945312,
+      "learning_rate": 6.721765955424589e-06,
+      "loss": 0.2553,
+      "step": 395
+    },
+    {
+      "epoch": 2.1394101876675604,
+      "grad_norm": 0.8843140006065369,
+      "learning_rate": 6.35608901835995e-06,
+      "loss": 0.2432,
+      "step": 400
+    },
+    {
+      "epoch": 2.1662198391420913,
+      "grad_norm": 0.9052540063858032,
+      "learning_rate": 5.99794728892232e-06,
+      "loss": 0.272,
+      "step": 405
+    },
+    {
+      "epoch": 2.193029490616622,
+      "grad_norm": 1.0966142416000366,
+      "learning_rate": 5.647652972118998e-06,
+      "loss": 0.2511,
+      "step": 410
+    },
+    {
+      "epoch": 2.219839142091153,
+      "grad_norm": 1.0332447290420532,
+      "learning_rate": 5.305511432085885e-06,
+      "loss": 0.2368,
+      "step": 415
+    },
+    {
+      "epoch": 2.246648793565684,
+      "grad_norm": 0.9348694086074829,
+      "learning_rate": 4.9718209258905865e-06,
+      "loss": 0.257,
+      "step": 420
+    },
+    {
+      "epoch": 2.2734584450402147,
+      "grad_norm": 1.0803208351135254,
+      "learning_rate": 4.646872343530999e-06,
+      "loss": 0.2709,
+      "step": 425
+    },
+    {
+      "epoch": 2.3002680965147455,
+      "grad_norm": 0.9880493879318237,
+      "learning_rate": 4.330948954356076e-06,
+      "loss": 0.2288,
+      "step": 430
+    },
+    {
+      "epoch": 2.327077747989276,
+      "grad_norm": 0.9348580837249756,
+      "learning_rate": 4.024326160129761e-06,
+      "loss": 0.2401,
+      "step": 435
+    },
+    {
+      "epoch": 2.353887399463807,
+      "grad_norm": 1.1886968612670898,
+      "learning_rate": 3.7272712549533568e-06,
+      "loss": 0.2605,
+      "step": 440
+    },
+    {
+      "epoch": 2.3806970509383376,
+      "grad_norm": 1.035274624824524,
+      "learning_rate": 3.440043192255693e-06,
+      "loss": 0.2151,
+      "step": 445
+    },
+    {
+      "epoch": 2.4075067024128685,
+      "grad_norm": 0.9064087867736816,
+      "learning_rate": 3.162892359054098e-06,
+      "loss": 0.2268,
+      "step": 450
+    },
+    {
+      "epoch": 2.4343163538873993,
+      "grad_norm": 0.8626986145973206,
+      "learning_rate": 2.8960603576830408e-06,
+      "loss": 0.2447,
+      "step": 455
+    },
+    {
+      "epoch": 2.46112600536193,
+      "grad_norm": 0.9454755783081055,
+      "learning_rate": 2.63977979518072e-06,
+      "loss": 0.256,
+      "step": 460
+    },
+    {
+      "epoch": 2.487935656836461,
+      "grad_norm": 1.000161051750183,
+      "learning_rate": 2.394274080517143e-06,
+      "loss": 0.2456,
+      "step": 465
+    },
+    {
+      "epoch": 2.514745308310992,
+      "grad_norm": 1.0376123189926147,
+      "learning_rate": 2.1597572298405e-06,
+      "loss": 0.2331,
+      "step": 470
+    },
+    {
+      "epoch": 2.5415549597855227,
+      "grad_norm": 1.0289422273635864,
+      "learning_rate": 1.936433679911604e-06,
+      "loss": 0.2432,
+      "step": 475
+    },
+    {
+      "epoch": 2.5683646112600536,
+      "grad_norm": 0.9290884137153625,
+      "learning_rate": 1.724498109889039e-06,
+      "loss": 0.272,
+      "step": 480
+    },
+    {
+      "epoch": 2.5951742627345844,
+      "grad_norm": 0.9730431437492371,
+      "learning_rate": 1.5241352716203173e-06,
+      "loss": 0.2729,
+      "step": 485
+    },
+    {
+      "epoch": 2.6219839142091153,
+      "grad_norm": 0.8988018035888672,
+      "learning_rate": 1.3355198285870935e-06,
+      "loss": 0.2338,
+      "step": 490
+    },
+    {
+      "epoch": 2.648793565683646,
+      "grad_norm": 1.0071823596954346,
+      "learning_rate": 1.1588162036447003e-06,
+      "loss": 0.2592,
+      "step": 495
+    },
+    {
+      "epoch": 2.675603217158177,
+      "grad_norm": 0.9541079998016357,
+      "learning_rate": 9.941784356888717e-07,
+      "loss": 0.2638,
+      "step": 500
+    },
+    {
+      "epoch": 2.702412868632708,
+      "grad_norm": 0.9871037006378174,
+      "learning_rate": 8.417500453744864e-07,
+      "loss": 0.252,
+      "step": 505
+    },
+    {
+      "epoch": 2.7292225201072386,
+      "grad_norm": 0.9317362904548645,
+      "learning_rate": 7.016639100034627e-07,
+      "loss": 0.227,
+      "step": 510
+    },
+    {
+      "epoch": 2.7560321715817695,
+      "grad_norm": 0.9173758029937744,
+      "learning_rate": 5.740421476908391e-07,
+      "loss": 0.2182,
+      "step": 515
+    },
+    {
+      "epoch": 2.7828418230563003,
+      "grad_norm": 0.9487306475639343,
+      "learning_rate": 4.589960109100444e-07,
+      "loss": 0.2371,
+      "step": 520
+    },
+    {
+      "epoch": 2.809651474530831,
+      "grad_norm": 0.9200378656387329,
+      "learning_rate": 3.566257895101005e-07,
+      "loss": 0.223,
+      "step": 525
+    },
+    {
+      "epoch": 2.836461126005362,
+      "grad_norm": 1.0162935256958008,
+      "learning_rate": 2.670207232893684e-07,
+      "loss": 0.2528,
+      "step": 530
+    },
+    {
+      "epoch": 2.863270777479893,
+      "grad_norm": 0.9906324744224548,
+      "learning_rate": 1.9025892420201807e-07,
+      "loss": 0.239,
+      "step": 535
+    },
+    {
+      "epoch": 2.8900804289544237,
+      "grad_norm": 0.8695020079612732,
+      "learning_rate": 1.264073082650169e-07,
+      "loss": 0.2407,
+      "step": 540
+    },
+    {
+      "epoch": 2.9168900804289546,
+      "grad_norm": 0.9133169651031494,
+      "learning_rate": 7.55215372250484e-08,
+      "loss": 0.2277,
+      "step": 545
+    },
+    {
+      "epoch": 2.943699731903485,
+      "grad_norm": 0.9620723128318787,
+      "learning_rate": 3.764597003616421e-08,
+      "loss": 0.2358,
+      "step": 550
+    },
+    {
+      "epoch": 2.9705093833780163,
+      "grad_norm": 0.9701035618782043,
+      "learning_rate": 1.2813624190484707e-08,
+      "loss": 0.2485,
+      "step": 555
+    },
+    {
+      "epoch": 2.9973190348525467,
+      "grad_norm": 0.9545600414276123,
+      "learning_rate": 1.0461469356776165e-09,
+      "loss": 0.2642,
+      "step": 560
+    },
+    {
+      "epoch": 3.0,
+      "step": 561,
+      "total_flos": 8.71254915782017e+17,
+      "train_loss": 0.5303278984684571,
+      "train_runtime": 415.168,
+      "train_samples_per_second": 43.096,
+      "train_steps_per_second": 1.351
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 561,
+  "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": 8.71254915782017e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

18_128_e3_3e-5/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0267f7be5b4dc8c42ea7967d865d3f3f135abe0c9a716b5d9cd1906d208e5cb
+size 8209