Upload folder using huggingface_hub

109_128_e3_3e-5/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "ibm-granite/granite-3.3-8b-instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "down_proj",
+    "up_proj",
+    "o_proj",
+    "gate_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

109_128_e3_3e-5/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb222bafc341b554a18db7eae4341f2a85a6dc0d25c0171f831965e47b16ba5c
+size 791751704

109_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
+}

109_128_e3_3e-5/all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 9.597313091213722e+17,
+    "train_loss": 0.37897290995246485,
+    "train_runtime": 452.2093,
+    "train_samples": 7898,
+    "train_samples_per_second": 52.396,
+    "train_steps_per_second": 1.639
+}

109_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 %}

109_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
+}

109_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
+  }
+}

109_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
+}

109_128_e3_3e-5/train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 9.597313091213722e+17,
+    "train_loss": 0.37897290995246485,
+    "train_runtime": 452.2093,
+    "train_samples": 7898,
+    "train_samples_per_second": 52.396,
+    "train_steps_per_second": 1.639
+}

109_128_e3_3e-5/trainer_state.json

@@ -0,0 +1,1079 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 741,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.020242914979757085,
+      "grad_norm": 2.8289573192596436,
+      "learning_rate": 3.157894736842105e-06,
+      "loss": 1.6683,
+      "step": 5
+    },
+    {
+      "epoch": 0.04048582995951417,
+      "grad_norm": 1.391170859336853,
+      "learning_rate": 7.105263157894737e-06,
+      "loss": 1.5802,
+      "step": 10
+    },
+    {
+      "epoch": 0.06072874493927125,
+      "grad_norm": 0.5817340612411499,
+      "learning_rate": 1.1052631578947368e-05,
+      "loss": 1.4943,
+      "step": 15
+    },
+    {
+      "epoch": 0.08097165991902834,
+      "grad_norm": 0.5116495490074158,
+      "learning_rate": 1.5e-05,
+      "loss": 1.4213,
+      "step": 20
+    },
+    {
+      "epoch": 0.10121457489878542,
+      "grad_norm": 0.43772825598716736,
+      "learning_rate": 1.894736842105263e-05,
+      "loss": 1.4175,
+      "step": 25
+    },
+    {
+      "epoch": 0.1214574898785425,
+      "grad_norm": 0.4413267970085144,
+      "learning_rate": 2.2894736842105263e-05,
+      "loss": 1.3537,
+      "step": 30
+    },
+    {
+      "epoch": 0.1417004048582996,
+      "grad_norm": 0.4279823899269104,
+      "learning_rate": 2.6842105263157896e-05,
+      "loss": 1.4293,
+      "step": 35
+    },
+    {
+      "epoch": 0.16194331983805668,
+      "grad_norm": 0.40660929679870605,
+      "learning_rate": 2.999985022144514e-05,
+      "loss": 1.3134,
+      "step": 40
+    },
+    {
+      "epoch": 0.18218623481781376,
+      "grad_norm": 0.4414168894290924,
+      "learning_rate": 2.9994608286088872e-05,
+      "loss": 1.2979,
+      "step": 45
+    },
+    {
+      "epoch": 0.20242914979757085,
+      "grad_norm": 0.583496630191803,
+      "learning_rate": 2.9981880413869707e-05,
+      "loss": 1.2187,
+      "step": 50
+    },
+    {
+      "epoch": 0.22267206477732793,
+      "grad_norm": 0.4906906485557556,
+      "learning_rate": 2.9961672959074872e-05,
+      "loss": 1.2568,
+      "step": 55
+    },
+    {
+      "epoch": 0.242914979757085,
+      "grad_norm": 0.5154989361763,
+      "learning_rate": 2.993399601011266e-05,
+      "loss": 1.1901,
+      "step": 60
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "grad_norm": 0.6087929010391235,
+      "learning_rate": 2.9898863384475917e-05,
+      "loss": 1.1499,
+      "step": 65
+    },
+    {
+      "epoch": 0.2834008097165992,
+      "grad_norm": 0.5353901386260986,
+      "learning_rate": 2.985629262184371e-05,
+      "loss": 1.1142,
+      "step": 70
+    },
+    {
+      "epoch": 0.30364372469635625,
+      "grad_norm": 0.6328024864196777,
+      "learning_rate": 2.9806304975324853e-05,
+      "loss": 1.0889,
+      "step": 75
+    },
+    {
+      "epoch": 0.32388663967611336,
+      "grad_norm": 0.6432482600212097,
+      "learning_rate": 2.97489254008474e-05,
+      "loss": 1.0598,
+      "step": 80
+    },
+    {
+      "epoch": 0.3441295546558704,
+      "grad_norm": 0.8061753511428833,
+      "learning_rate": 2.9684182544699645e-05,
+      "loss": 1.0013,
+      "step": 85
+    },
+    {
+      "epoch": 0.3643724696356275,
+      "grad_norm": 0.6597098112106323,
+      "learning_rate": 2.9612108729228678e-05,
+      "loss": 0.9614,
+      "step": 90
+    },
+    {
+      "epoch": 0.38461538461538464,
+      "grad_norm": 0.774358332157135,
+      "learning_rate": 2.9532739936703703e-05,
+      "loss": 0.9589,
+      "step": 95
+    },
+    {
+      "epoch": 0.4048582995951417,
+      "grad_norm": 0.7571013569831848,
+      "learning_rate": 2.9446115791352207e-05,
+      "loss": 0.9222,
+      "step": 100
+    },
+    {
+      "epoch": 0.4251012145748988,
+      "grad_norm": 0.7839725017547607,
+      "learning_rate": 2.935227953957787e-05,
+      "loss": 0.9083,
+      "step": 105
+    },
+    {
+      "epoch": 0.44534412955465585,
+      "grad_norm": 0.7715641260147095,
+      "learning_rate": 2.9251278028370137e-05,
+      "loss": 0.9057,
+      "step": 110
+    },
+    {
+      "epoch": 0.46558704453441296,
+      "grad_norm": 0.7811329364776611,
+      "learning_rate": 2.9143161681916264e-05,
+      "loss": 0.8725,
+      "step": 115
+    },
+    {
+      "epoch": 0.48582995951417,
+      "grad_norm": 0.8256909847259521,
+      "learning_rate": 2.9027984476427427e-05,
+      "loss": 0.8126,
+      "step": 120
+    },
+    {
+      "epoch": 0.5060728744939271,
+      "grad_norm": 0.9319804906845093,
+      "learning_rate": 2.8905803913191545e-05,
+      "loss": 0.7398,
+      "step": 125
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 1.301496148109436,
+      "learning_rate": 2.877668098986624e-05,
+      "loss": 0.7155,
+      "step": 130
+    },
+    {
+      "epoch": 0.5465587044534413,
+      "grad_norm": 0.9583051800727844,
+      "learning_rate": 2.864068017002621e-05,
+      "loss": 0.7992,
+      "step": 135
+    },
+    {
+      "epoch": 0.5668016194331984,
+      "grad_norm": 0.9819439053535461,
+      "learning_rate": 2.8497869350980376e-05,
+      "loss": 0.7147,
+      "step": 140
+    },
+    {
+      "epoch": 0.5870445344129555,
+      "grad_norm": 0.9111624360084534,
+      "learning_rate": 2.834831982987462e-05,
+      "loss": 0.7053,
+      "step": 145
+    },
+    {
+      "epoch": 0.6072874493927125,
+      "grad_norm": 0.9278939962387085,
+      "learning_rate": 2.8192106268097336e-05,
+      "loss": 0.6773,
+      "step": 150
+    },
+    {
+      "epoch": 0.6275303643724697,
+      "grad_norm": 0.9512412548065186,
+      "learning_rate": 2.8029306654005288e-05,
+      "loss": 0.6563,
+      "step": 155
+    },
+    {
+      "epoch": 0.6477732793522267,
+      "grad_norm": 1.066825032234192,
+      "learning_rate": 2.7860002263988565e-05,
+      "loss": 0.579,
+      "step": 160
+    },
+    {
+      "epoch": 0.6680161943319838,
+      "grad_norm": 1.1656990051269531,
+      "learning_rate": 2.768427762189402e-05,
+      "loss": 0.6585,
+      "step": 165
+    },
+    {
+      "epoch": 0.6882591093117408,
+      "grad_norm": 0.966322660446167,
+      "learning_rate": 2.75022204568274e-05,
+      "loss": 0.5861,
+      "step": 170
+    },
+    {
+      "epoch": 0.708502024291498,
+      "grad_norm": 1.1481801271438599,
+      "learning_rate": 2.7313921659355305e-05,
+      "loss": 0.6022,
+      "step": 175
+    },
+    {
+      "epoch": 0.728744939271255,
+      "grad_norm": 0.9786959886550903,
+      "learning_rate": 2.7119475236128816e-05,
+      "loss": 0.5276,
+      "step": 180
+    },
+    {
+      "epoch": 0.7489878542510121,
+      "grad_norm": 1.128067970275879,
+      "learning_rate": 2.691897826295143e-05,
+      "loss": 0.522,
+      "step": 185
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 1.0342376232147217,
+      "learning_rate": 2.6712530836314763e-05,
+      "loss": 0.5481,
+      "step": 190
+    },
+    {
+      "epoch": 0.7894736842105263,
+      "grad_norm": 1.3109385967254639,
+      "learning_rate": 2.650023602342614e-05,
+      "loss": 0.4967,
+      "step": 195
+    },
+    {
+      "epoch": 0.8097165991902834,
+      "grad_norm": 1.1816333532333374,
+      "learning_rate": 2.6282199810753192e-05,
+      "loss": 0.5294,
+      "step": 200
+    },
+    {
+      "epoch": 0.8299595141700404,
+      "grad_norm": 1.168026328086853,
+      "learning_rate": 2.6058531051110933e-05,
+      "loss": 0.5157,
+      "step": 205
+    },
+    {
+      "epoch": 0.8502024291497976,
+      "grad_norm": 1.3411718606948853,
+      "learning_rate": 2.5829341409317866e-05,
+      "loss": 0.4499,
+      "step": 210
+    },
+    {
+      "epoch": 0.8704453441295547,
+      "grad_norm": 1.1015444993972778,
+      "learning_rate": 2.559474530644825e-05,
+      "loss": 0.4635,
+      "step": 215
+    },
+    {
+      "epoch": 0.8906882591093117,
+      "grad_norm": 1.1771754026412964,
+      "learning_rate": 2.5354859862708276e-05,
+      "loss": 0.4539,
+      "step": 220
+    },
+    {
+      "epoch": 0.9109311740890689,
+      "grad_norm": 1.1771122217178345,
+      "learning_rate": 2.5109804838964785e-05,
+      "loss": 0.474,
+      "step": 225
+    },
+    {
+      "epoch": 0.9311740890688259,
+      "grad_norm": 1.2321745157241821,
+      "learning_rate": 2.4859702576955595e-05,
+      "loss": 0.4315,
+      "step": 230
+    },
+    {
+      "epoch": 0.951417004048583,
+      "grad_norm": 1.4300092458724976,
+      "learning_rate": 2.4604677938211394e-05,
+      "loss": 0.417,
+      "step": 235
+    },
+    {
+      "epoch": 0.97165991902834,
+      "grad_norm": 1.226932406425476,
+      "learning_rate": 2.4344858241719625e-05,
+      "loss": 0.4144,
+      "step": 240
+    },
+    {
+      "epoch": 0.9919028340080972,
+      "grad_norm": 1.3439360857009888,
+      "learning_rate": 2.4080373200361527e-05,
+      "loss": 0.38,
+      "step": 245
+    },
+    {
+      "epoch": 1.0121457489878543,
+      "grad_norm": 1.1570885181427002,
+      "learning_rate": 2.3811354856153996e-05,
+      "loss": 0.3702,
+      "step": 250
+    },
+    {
+      "epoch": 1.0323886639676114,
+      "grad_norm": 1.1813459396362305,
+      "learning_rate": 2.3537937514328704e-05,
+      "loss": 0.3205,
+      "step": 255
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "grad_norm": 1.1963030099868774,
+      "learning_rate": 2.326025767628129e-05,
+      "loss": 0.2857,
+      "step": 260
+    },
+    {
+      "epoch": 1.0728744939271255,
+      "grad_norm": 1.3866466283798218,
+      "learning_rate": 2.297845397142415e-05,
+      "loss": 0.3079,
+      "step": 265
+    },
+    {
+      "epoch": 1.0931174089068827,
+      "grad_norm": 1.2871726751327515,
+      "learning_rate": 2.2692667087976803e-05,
+      "loss": 0.3287,
+      "step": 270
+    },
+    {
+      "epoch": 1.1133603238866396,
+      "grad_norm": 1.344159483909607,
+      "learning_rate": 2.2403039702728466e-05,
+      "loss": 0.2678,
+      "step": 275
+    },
+    {
+      "epoch": 1.1336032388663968,
+      "grad_norm": 1.1413447856903076,
+      "learning_rate": 2.2109716409807804e-05,
+      "loss": 0.3005,
+      "step": 280
+    },
+    {
+      "epoch": 1.1538461538461537,
+      "grad_norm": 1.3377690315246582,
+      "learning_rate": 2.1812843648495465e-05,
+      "loss": 0.2764,
+      "step": 285
+    },
+    {
+      "epoch": 1.174089068825911,
+      "grad_norm": 1.1025853157043457,
+      "learning_rate": 2.1512569630115507e-05,
+      "loss": 0.244,
+      "step": 290
+    },
+    {
+      "epoch": 1.194331983805668,
+      "grad_norm": 1.3570576906204224,
+      "learning_rate": 2.1209044264042016e-05,
+      "loss": 0.3048,
+      "step": 295
+    },
+    {
+      "epoch": 1.214574898785425,
+      "grad_norm": 1.1793861389160156,
+      "learning_rate": 2.0902419082858142e-05,
+      "loss": 0.2586,
+      "step": 300
+    },
+    {
+      "epoch": 1.2348178137651822,
+      "grad_norm": 1.1302578449249268,
+      "learning_rate": 2.059284716670463e-05,
+      "loss": 0.2423,
+      "step": 305
+    },
+    {
+      "epoch": 1.2550607287449393,
+      "grad_norm": 1.348034381866455,
+      "learning_rate": 2.0280483066855823e-05,
+      "loss": 0.2719,
+      "step": 310
+    },
+    {
+      "epoch": 1.2753036437246963,
+      "grad_norm": 1.1223900318145752,
+      "learning_rate": 1.996548272856117e-05,
+      "loss": 0.2494,
+      "step": 315
+    },
+    {
+      "epoch": 1.2955465587044535,
+      "grad_norm": 1.2410658597946167,
+      "learning_rate": 1.9648003413190858e-05,
+      "loss": 0.2222,
+      "step": 320
+    },
+    {
+      "epoch": 1.3157894736842106,
+      "grad_norm": 1.2068846225738525,
+      "learning_rate": 1.9328203619724297e-05,
+      "loss": 0.2113,
+      "step": 325
+    },
+    {
+      "epoch": 1.3360323886639676,
+      "grad_norm": 1.4179112911224365,
+      "learning_rate": 1.9006243005620825e-05,
+      "loss": 0.2567,
+      "step": 330
+    },
+    {
+      "epoch": 1.3562753036437247,
+      "grad_norm": 1.527790904045105,
+      "learning_rate": 1.8682282307111988e-05,
+      "loss": 0.2131,
+      "step": 335
+    },
+    {
+      "epoch": 1.376518218623482,
+      "grad_norm": 1.1818265914916992,
+      "learning_rate": 1.8356483258955302e-05,
+      "loss": 0.2394,
+      "step": 340
+    },
+    {
+      "epoch": 1.3967611336032388,
+      "grad_norm": 1.2762672901153564,
+      "learning_rate": 1.802900851368946e-05,
+      "loss": 0.2433,
+      "step": 345
+    },
+    {
+      "epoch": 1.417004048582996,
+      "grad_norm": 1.179250717163086,
+      "learning_rate": 1.770002156043138e-05,
+      "loss": 0.2136,
+      "step": 350
+    },
+    {
+      "epoch": 1.4372469635627532,
+      "grad_norm": 1.1492518186569214,
+      "learning_rate": 1.73696866432556e-05,
+      "loss": 0.2121,
+      "step": 355
+    },
+    {
+      "epoch": 1.45748987854251,
+      "grad_norm": 1.3767096996307373,
+      "learning_rate": 1.70381686791967e-05,
+      "loss": 0.2258,
+      "step": 360
+    },
+    {
+      "epoch": 1.4777327935222673,
+      "grad_norm": 1.3511375188827515,
+      "learning_rate": 1.670563317591589e-05,
+      "loss": 0.1974,
+      "step": 365
+    },
+    {
+      "epoch": 1.4979757085020242,
+      "grad_norm": 1.319981336593628,
+      "learning_rate": 1.6372246149072572e-05,
+      "loss": 0.1992,
+      "step": 370
+    },
+    {
+      "epoch": 1.5182186234817814,
+      "grad_norm": 1.193726658821106,
+      "learning_rate": 1.6038174039442408e-05,
+      "loss": 0.195,
+      "step": 375
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 1.3207732439041138,
+      "learning_rate": 1.570358362982309e-05,
+      "loss": 0.1845,
+      "step": 380
+    },
+    {
+      "epoch": 1.5587044534412957,
+      "grad_norm": 1.3221644163131714,
+      "learning_rate": 1.5368641961769404e-05,
+      "loss": 0.182,
+      "step": 385
+    },
+    {
+      "epoch": 1.5789473684210527,
+      "grad_norm": 1.1301093101501465,
+      "learning_rate": 1.5033516252199047e-05,
+      "loss": 0.1777,
+      "step": 390
+    },
+    {
+      "epoch": 1.5991902834008096,
+      "grad_norm": 1.105190634727478,
+      "learning_rate": 1.4698373809910964e-05,
+      "loss": 0.1538,
+      "step": 395
+    },
+    {
+      "epoch": 1.6194331983805668,
+      "grad_norm": 1.2285429239273071,
+      "learning_rate": 1.4363381952057779e-05,
+      "loss": 0.1815,
+      "step": 400
+    },
+    {
+      "epoch": 1.639676113360324,
+      "grad_norm": 1.2153966426849365,
+      "learning_rate": 1.402870792061404e-05,
+      "loss": 0.1836,
+      "step": 405
+    },
+    {
+      "epoch": 1.6599190283400809,
+      "grad_norm": 1.1106749773025513,
+      "learning_rate": 1.3694518798882041e-05,
+      "loss": 0.1695,
+      "step": 410
+    },
+    {
+      "epoch": 1.680161943319838,
+      "grad_norm": 1.0664726495742798,
+      "learning_rate": 1.3360981428076837e-05,
+      "loss": 0.1555,
+      "step": 415
+    },
+    {
+      "epoch": 1.7004048582995952,
+      "grad_norm": 1.2539761066436768,
+      "learning_rate": 1.3028262324032083e-05,
+      "loss": 0.1738,
+      "step": 420
+    },
+    {
+      "epoch": 1.7206477732793521,
+      "grad_norm": 1.1291399002075195,
+      "learning_rate": 1.269652759406839e-05,
+      "loss": 0.15,
+      "step": 425
+    },
+    {
+      "epoch": 1.7408906882591093,
+      "grad_norm": 0.9693400263786316,
+      "learning_rate": 1.236594285406557e-05,
+      "loss": 0.1497,
+      "step": 430
+    },
+    {
+      "epoch": 1.7611336032388665,
+      "grad_norm": 0.9691015481948853,
+      "learning_rate": 1.2036673145780251e-05,
+      "loss": 0.1258,
+      "step": 435
+    },
+    {
+      "epoch": 1.7813765182186234,
+      "grad_norm": 1.0339523553848267,
+      "learning_rate": 1.1708882854450123e-05,
+      "loss": 0.1602,
+      "step": 440
+    },
+    {
+      "epoch": 1.8016194331983806,
+      "grad_norm": 1.0432922840118408,
+      "learning_rate": 1.1382735626725916e-05,
+      "loss": 0.1476,
+      "step": 445
+    },
+    {
+      "epoch": 1.8218623481781377,
+      "grad_norm": 0.9907374382019043,
+      "learning_rate": 1.105839428897216e-05,
+      "loss": 0.1348,
+      "step": 450
+    },
+    {
+      "epoch": 1.8421052631578947,
+      "grad_norm": 1.3727444410324097,
+      "learning_rate": 1.0736020765977434e-05,
+      "loss": 0.138,
+      "step": 455
+    },
+    {
+      "epoch": 1.8623481781376519,
+      "grad_norm": 0.8381685018539429,
+      "learning_rate": 1.0415776000114716e-05,
+      "loss": 0.1205,
+      "step": 460
+    },
+    {
+      "epoch": 1.882591093117409,
+      "grad_norm": 1.226954698562622,
+      "learning_rate": 1.0097819870992196e-05,
+      "loss": 0.1286,
+      "step": 465
+    },
+    {
+      "epoch": 1.902834008097166,
+      "grad_norm": 1.1794142723083496,
+      "learning_rate": 9.782311115634706e-06,
+      "loss": 0.1307,
+      "step": 470
+    },
+    {
+      "epoch": 1.9230769230769231,
+      "grad_norm": 1.1647013425827026,
+      "learning_rate": 9.469407249235532e-06,
+      "loss": 0.1161,
+      "step": 475
+    },
+    {
+      "epoch": 1.9433198380566803,
+      "grad_norm": 0.8942193388938904,
+      "learning_rate": 9.1592644865182e-06,
+      "loss": 0.1275,
+      "step": 480
+    },
+    {
+      "epoch": 1.9635627530364372,
+      "grad_norm": 1.0155425071716309,
+      "learning_rate": 8.852037663747595e-06,
+      "loss": 0.1149,
+      "step": 485
+    },
+    {
+      "epoch": 1.9838056680161942,
+      "grad_norm": 1.2870362997055054,
+      "learning_rate": 8.54788016142915e-06,
+      "loss": 0.1024,
+      "step": 490
+    },
+    {
+      "epoch": 2.0040485829959516,
+      "grad_norm": 0.8725767731666565,
+      "learning_rate": 8.246943827734899e-06,
+      "loss": 0.1038,
+      "step": 495
+    },
+    {
+      "epoch": 2.0242914979757085,
+      "grad_norm": 0.7810032367706299,
+      "learning_rate": 7.94937890269453e-06,
+      "loss": 0.0719,
+      "step": 500
+    },
+    {
+      "epoch": 2.0445344129554655,
+      "grad_norm": 0.8347038626670837,
+      "learning_rate": 7.655333943189218e-06,
+      "loss": 0.0925,
+      "step": 505
+    },
+    {
+      "epoch": 2.064777327935223,
+      "grad_norm": 0.7739137411117554,
+      "learning_rate": 7.364955748785817e-06,
+      "loss": 0.0933,
+      "step": 510
+    },
+    {
+      "epoch": 2.08502024291498,
+      "grad_norm": 0.864008903503418,
+      "learning_rate": 7.078389288448384e-06,
+      "loss": 0.082,
+      "step": 515
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "grad_norm": 0.9412100911140442,
+      "learning_rate": 6.795777628163599e-06,
+      "loss": 0.0867,
+      "step": 520
+    },
+    {
+      "epoch": 2.125506072874494,
+      "grad_norm": 0.9862967729568481,
+      "learning_rate": 6.517261859516188e-06,
+      "loss": 0.0805,
+      "step": 525
+    },
+    {
+      "epoch": 2.145748987854251,
+      "grad_norm": 0.900925874710083,
+      "learning_rate": 6.242981029250131e-06,
+      "loss": 0.0813,
+      "step": 530
+    },
+    {
+      "epoch": 2.165991902834008,
+      "grad_norm": 0.9090055227279663,
+      "learning_rate": 5.973072069850686e-06,
+      "loss": 0.0867,
+      "step": 535
+    },
+    {
+      "epoch": 2.1862348178137654,
+      "grad_norm": 0.8485679030418396,
+      "learning_rate": 5.707669731181955e-06,
+      "loss": 0.0782,
+      "step": 540
+    },
+    {
+      "epoch": 2.2064777327935223,
+      "grad_norm": 0.8982809782028198,
+      "learning_rate": 5.4469065132141025e-06,
+      "loss": 0.0749,
+      "step": 545
+    },
+    {
+      "epoch": 2.2267206477732793,
+      "grad_norm": 0.8604884743690491,
+      "learning_rate": 5.190912599873818e-06,
+      "loss": 0.0849,
+      "step": 550
+    },
+    {
+      "epoch": 2.246963562753036,
+      "grad_norm": 0.7159515023231506,
+      "learning_rate": 4.93981579405105e-06,
+      "loss": 0.0867,
+      "step": 555
+    },
+    {
+      "epoch": 2.2672064777327936,
+      "grad_norm": 0.9456787109375,
+      "learning_rate": 4.693741453794433e-06,
+      "loss": 0.0803,
+      "step": 560
+    },
+    {
+      "epoch": 2.2874493927125505,
+      "grad_norm": 0.7104689478874207,
+      "learning_rate": 4.452812429727313e-06,
+      "loss": 0.0827,
+      "step": 565
+    },
+    {
+      "epoch": 2.3076923076923075,
+      "grad_norm": 0.6977279782295227,
+      "learning_rate": 4.21714900371556e-06,
+      "loss": 0.0771,
+      "step": 570
+    },
+    {
+      "epoch": 2.327935222672065,
+      "grad_norm": 0.741640567779541,
+      "learning_rate": 3.986868828817818e-06,
+      "loss": 0.0812,
+      "step": 575
+    },
+    {
+      "epoch": 2.348178137651822,
+      "grad_norm": 0.7973425984382629,
+      "learning_rate": 3.7620868705481586e-06,
+      "loss": 0.0738,
+      "step": 580
+    },
+    {
+      "epoch": 2.3684210526315788,
+      "grad_norm": 0.8517425656318665,
+      "learning_rate": 3.5429153494805087e-06,
+      "loss": 0.0763,
+      "step": 585
+    },
+    {
+      "epoch": 2.388663967611336,
+      "grad_norm": 0.8154937624931335,
+      "learning_rate": 3.329463685223411e-06,
+      "loss": 0.0695,
+      "step": 590
+    },
+    {
+      "epoch": 2.408906882591093,
+      "grad_norm": 0.728950023651123,
+      "learning_rate": 3.12183844179316e-06,
+      "loss": 0.0721,
+      "step": 595
+    },
+    {
+      "epoch": 2.42914979757085,
+      "grad_norm": 0.7380397915840149,
+      "learning_rate": 2.9201432744126074e-06,
+      "loss": 0.066,
+      "step": 600
+    },
+    {
+      "epoch": 2.4493927125506074,
+      "grad_norm": 0.6809558868408203,
+      "learning_rate": 2.7244788777621326e-06,
+      "loss": 0.0704,
+      "step": 605
+    },
+    {
+      "epoch": 2.4696356275303644,
+      "grad_norm": 0.7693683505058289,
+      "learning_rate": 2.5349429357085952e-06,
+      "loss": 0.0699,
+      "step": 610
+    },
+    {
+      "epoch": 2.4898785425101213,
+      "grad_norm": 0.9658976793289185,
+      "learning_rate": 2.3516300725375016e-06,
+      "loss": 0.0682,
+      "step": 615
+    },
+    {
+      "epoch": 2.5101214574898787,
+      "grad_norm": 0.8384422659873962,
+      "learning_rate": 2.174631805712576e-06,
+      "loss": 0.073,
+      "step": 620
+    },
+    {
+      "epoch": 2.5303643724696356,
+      "grad_norm": 0.7254630923271179,
+      "learning_rate": 2.0040365001864074e-06,
+      "loss": 0.0589,
+      "step": 625
+    },
+    {
+      "epoch": 2.5506072874493926,
+      "grad_norm": 0.7859408855438232,
+      "learning_rate": 1.8399293242849635e-06,
+      "loss": 0.0692,
+      "step": 630
+    },
+    {
+      "epoch": 2.57085020242915,
+      "grad_norm": 0.8682908415794373,
+      "learning_rate": 1.6823922071879932e-06,
+      "loss": 0.0794,
+      "step": 635
+    },
+    {
+      "epoch": 2.591093117408907,
+      "grad_norm": 0.8448325395584106,
+      "learning_rate": 1.5315037980265478e-06,
+      "loss": 0.067,
+      "step": 640
+    },
+    {
+      "epoch": 2.611336032388664,
+      "grad_norm": 0.6050984859466553,
+      "learning_rate": 1.3873394266180377e-06,
+      "loss": 0.0629,
+      "step": 645
+    },
+    {
+      "epoch": 2.6315789473684212,
+      "grad_norm": 0.6703817248344421,
+      "learning_rate": 1.2499710658584296e-06,
+      "loss": 0.066,
+      "step": 650
+    },
+    {
+      "epoch": 2.651821862348178,
+      "grad_norm": 0.7048584222793579,
+      "learning_rate": 1.119467295790363e-06,
+      "loss": 0.0604,
+      "step": 655
+    },
+    {
+      "epoch": 2.672064777327935,
+      "grad_norm": 0.7447172999382019,
+      "learning_rate": 9.958932693651168e-07,
+      "loss": 0.0679,
+      "step": 660
+    },
+    {
+      "epoch": 2.6923076923076925,
+      "grad_norm": 0.789459228515625,
+      "learning_rate": 8.793106799155187e-07,
+      "loss": 0.065,
+      "step": 665
+    },
+    {
+      "epoch": 2.7125506072874495,
+      "grad_norm": 0.440491646528244,
+      "learning_rate": 7.697777303560699e-07,
+      "loss": 0.055,
+      "step": 670
+    },
+    {
+      "epoch": 2.7327935222672064,
+      "grad_norm": 0.6782566905021667,
+      "learning_rate": 6.673491041255874e-07,
+      "loss": 0.0676,
+      "step": 675
+    },
+    {
+      "epoch": 2.753036437246964,
+      "grad_norm": 0.6501054167747498,
+      "learning_rate": 5.720759378869455e-07,
+      "loss": 0.072,
+      "step": 680
+    },
+    {
+      "epoch": 2.7732793522267207,
+      "grad_norm": 0.6169021725654602,
+      "learning_rate": 4.840057959975169e-07,
+      "loss": 0.0604,
+      "step": 685
+    },
+    {
+      "epoch": 2.7935222672064777,
+      "grad_norm": 0.6344029903411865,
+      "learning_rate": 4.031826467630545e-07,
+      "loss": 0.0584,
+      "step": 690
+    },
+    {
+      "epoch": 2.813765182186235,
+      "grad_norm": 0.6110345125198364,
+      "learning_rate": 3.2964684048685523e-07,
+      "loss": 0.0644,
+      "step": 695
+    },
+    {
+      "epoch": 2.834008097165992,
+      "grad_norm": 0.7080497741699219,
+      "learning_rate": 2.6343508932521243e-07,
+      "loss": 0.0591,
+      "step": 700
+    },
+    {
+      "epoch": 2.854251012145749,
+      "grad_norm": 0.8108674883842468,
+      "learning_rate": 2.0458044895916516e-07,
+      "loss": 0.0655,
+      "step": 705
+    },
+    {
+      "epoch": 2.8744939271255063,
+      "grad_norm": 0.5349428057670593,
+      "learning_rate": 1.5311230209171078e-07,
+      "loss": 0.0664,
+      "step": 710
+    },
+    {
+      "epoch": 2.8947368421052633,
+      "grad_norm": 0.7437654137611389,
+      "learning_rate": 1.0905634377873563e-07,
+      "loss": 0.0665,
+      "step": 715
+    },
+    {
+      "epoch": 2.91497975708502,
+      "grad_norm": 0.7719464898109436,
+      "learning_rate": 7.243456860096476e-08,
+      "loss": 0.0671,
+      "step": 720
+    },
+    {
+      "epoch": 2.9352226720647776,
+      "grad_norm": 0.7235406637191772,
+      "learning_rate": 4.326525968334216e-08,
+      "loss": 0.0644,
+      "step": 725
+    },
+    {
+      "epoch": 2.9554655870445345,
+      "grad_norm": 0.5301565527915955,
+      "learning_rate": 2.1562979567330554e-08,
+      "loss": 0.0677,
+      "step": 730
+    },
+    {
+      "epoch": 2.9757085020242915,
+      "grad_norm": 0.5968860387802124,
+      "learning_rate": 7.338562940680249e-09,
+      "loss": 0.0607,
+      "step": 735
+    },
+    {
+      "epoch": 2.9959514170040484,
+      "grad_norm": 0.7047298550605774,
+      "learning_rate": 5.991112283026956e-10,
+      "loss": 0.064,
+      "step": 740
+    },
+    {
+      "epoch": 3.0,
+      "step": 741,
+      "total_flos": 9.597313091213722e+17,
+      "train_loss": 0.37897290995246485,
+      "train_runtime": 452.2093,
+      "train_samples_per_second": 52.396,
+      "train_steps_per_second": 1.639
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 741,
+  "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": 9.597313091213722e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

109_128_e3_3e-5/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04eaa9878f2d428b6edf05ba33e3bc3b7e2e0d981855ad12cba343e4545ac11d
+size 8273