Upload folder using huggingface_hub

14_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",
+    "v_proj",
+    "q_proj",
+    "up_proj",
+    "gate_proj",
+    "down_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

14_128_e3_3e-5/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:427ec52d03ebf3b38bd8854971061cb6486dbe552f2b78409c3b87be50881a9a
+size 791751704

14_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
+}

14_128_e3_3e-5/all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 9.843483184421929e+17,
+    "train_loss": 0.5876927409928275,
+    "train_runtime": 479.7831,
+    "train_samples": 7251,
+    "train_samples_per_second": 45.339,
+    "train_steps_per_second": 1.419
+}

14_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 %}

14_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
+}

14_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
+  }
+}

14_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
+}

14_128_e3_3e-5/train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 9.843483184421929e+17,
+    "train_loss": 0.5876927409928275,
+    "train_runtime": 479.7831,
+    "train_samples": 7251,
+    "train_samples_per_second": 45.339,
+    "train_steps_per_second": 1.419
+}

14_128_e3_3e-5/trainer_state.json

@@ -0,0 +1,995 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 681,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.022026431718061675,
+      "grad_norm": 2.9401466846466064,
+      "learning_rate": 3.4285714285714285e-06,
+      "loss": 1.5831,
+      "step": 5
+    },
+    {
+      "epoch": 0.04405286343612335,
+      "grad_norm": 1.605501413345337,
+      "learning_rate": 7.714285714285714e-06,
+      "loss": 1.5328,
+      "step": 10
+    },
+    {
+      "epoch": 0.06607929515418502,
+      "grad_norm": 1.09455406665802,
+      "learning_rate": 1.2e-05,
+      "loss": 1.4174,
+      "step": 15
+    },
+    {
+      "epoch": 0.0881057268722467,
+      "grad_norm": 0.4365827143192291,
+      "learning_rate": 1.6285714285714283e-05,
+      "loss": 1.3878,
+      "step": 20
+    },
+    {
+      "epoch": 0.11013215859030837,
+      "grad_norm": 0.40829095244407654,
+      "learning_rate": 2.0571428571428573e-05,
+      "loss": 1.3176,
+      "step": 25
+    },
+    {
+      "epoch": 0.13215859030837004,
+      "grad_norm": 0.40602800250053406,
+      "learning_rate": 2.485714285714286e-05,
+      "loss": 1.3265,
+      "step": 30
+    },
+    {
+      "epoch": 0.15418502202643172,
+      "grad_norm": 0.44448837637901306,
+      "learning_rate": 2.9142857142857142e-05,
+      "loss": 1.2979,
+      "step": 35
+    },
+    {
+      "epoch": 0.1762114537444934,
+      "grad_norm": 0.3630085587501526,
+      "learning_rate": 2.9997162066199925e-05,
+      "loss": 1.2608,
+      "step": 40
+    },
+    {
+      "epoch": 0.19823788546255505,
+      "grad_norm": 0.3484284281730652,
+      "learning_rate": 2.998563480054719e-05,
+      "loss": 1.1802,
+      "step": 45
+    },
+    {
+      "epoch": 0.22026431718061673,
+      "grad_norm": 0.3873388171195984,
+      "learning_rate": 2.9965247642151582e-05,
+      "loss": 1.2347,
+      "step": 50
+    },
+    {
+      "epoch": 0.2422907488986784,
+      "grad_norm": 0.3421724736690521,
+      "learning_rate": 2.9936012644425518e-05,
+      "loss": 1.1721,
+      "step": 55
+    },
+    {
+      "epoch": 0.2643171806167401,
+      "grad_norm": 0.4196663796901703,
+      "learning_rate": 2.9897947091851618e-05,
+      "loss": 1.2168,
+      "step": 60
+    },
+    {
+      "epoch": 0.28634361233480177,
+      "grad_norm": 0.38196396827697754,
+      "learning_rate": 2.9851073489763658e-05,
+      "loss": 1.1077,
+      "step": 65
+    },
+    {
+      "epoch": 0.30837004405286345,
+      "grad_norm": 0.4067361652851105,
+      "learning_rate": 2.9795419551040836e-05,
+      "loss": 1.1198,
+      "step": 70
+    },
+    {
+      "epoch": 0.3303964757709251,
+      "grad_norm": 0.43515893816947937,
+      "learning_rate": 2.973101817972321e-05,
+      "loss": 1.132,
+      "step": 75
+    },
+    {
+      "epoch": 0.3524229074889868,
+      "grad_norm": 0.42240625619888306,
+      "learning_rate": 2.9657907451557993e-05,
+      "loss": 1.0984,
+      "step": 80
+    },
+    {
+      "epoch": 0.3744493392070485,
+      "grad_norm": 0.4701535105705261,
+      "learning_rate": 2.9576130591488164e-05,
+      "loss": 1.08,
+      "step": 85
+    },
+    {
+      "epoch": 0.3964757709251101,
+      "grad_norm": 0.4965592920780182,
+      "learning_rate": 2.9485735948096802e-05,
+      "loss": 1.0344,
+      "step": 90
+    },
+    {
+      "epoch": 0.4185022026431718,
+      "grad_norm": 0.5140933990478516,
+      "learning_rate": 2.9386776965022135e-05,
+      "loss": 1.0479,
+      "step": 95
+    },
+    {
+      "epoch": 0.44052863436123346,
+      "grad_norm": 0.48222577571868896,
+      "learning_rate": 2.9279312149360307e-05,
+      "loss": 0.9815,
+      "step": 100
+    },
+    {
+      "epoch": 0.46255506607929514,
+      "grad_norm": 0.5453588366508484,
+      "learning_rate": 2.9163405037074466e-05,
+      "loss": 0.9696,
+      "step": 105
+    },
+    {
+      "epoch": 0.4845814977973568,
+      "grad_norm": 0.5565158128738403,
+      "learning_rate": 2.9039124155430665e-05,
+      "loss": 1.012,
+      "step": 110
+    },
+    {
+      "epoch": 0.5066079295154186,
+      "grad_norm": 0.5354689359664917,
+      "learning_rate": 2.8906542982482782e-05,
+      "loss": 1.0113,
+      "step": 115
+    },
+    {
+      "epoch": 0.5286343612334802,
+      "grad_norm": 0.5841522216796875,
+      "learning_rate": 2.876573990363042e-05,
+      "loss": 0.9968,
+      "step": 120
+    },
+    {
+      "epoch": 0.5506607929515418,
+      "grad_norm": 0.5884144306182861,
+      "learning_rate": 2.8616798165275418e-05,
+      "loss": 0.9232,
+      "step": 125
+    },
+    {
+      "epoch": 0.5726872246696035,
+      "grad_norm": 0.5880234837532043,
+      "learning_rate": 2.8459805825604462e-05,
+      "loss": 0.9381,
+      "step": 130
+    },
+    {
+      "epoch": 0.5947136563876652,
+      "grad_norm": 0.6461393237113953,
+      "learning_rate": 2.8294855702526798e-05,
+      "loss": 0.9209,
+      "step": 135
+    },
+    {
+      "epoch": 0.6167400881057269,
+      "grad_norm": 0.5809102654457092,
+      "learning_rate": 2.81220453187979e-05,
+      "loss": 0.9237,
+      "step": 140
+    },
+    {
+      "epoch": 0.6387665198237885,
+      "grad_norm": 0.9713295102119446,
+      "learning_rate": 2.7941476844361532e-05,
+      "loss": 0.8971,
+      "step": 145
+    },
+    {
+      "epoch": 0.6607929515418502,
+      "grad_norm": 0.6912427544593811,
+      "learning_rate": 2.7753257035944216e-05,
+      "loss": 0.8934,
+      "step": 150
+    },
+    {
+      "epoch": 0.6828193832599119,
+      "grad_norm": 0.7335177063941956,
+      "learning_rate": 2.7557497173937928e-05,
+      "loss": 0.8096,
+      "step": 155
+    },
+    {
+      "epoch": 0.7048458149779736,
+      "grad_norm": 0.7138782143592834,
+      "learning_rate": 2.7354312996608276e-05,
+      "loss": 0.8364,
+      "step": 160
+    },
+    {
+      "epoch": 0.7268722466960352,
+      "grad_norm": 0.7722578048706055,
+      "learning_rate": 2.7143824631667043e-05,
+      "loss": 0.8277,
+      "step": 165
+    },
+    {
+      "epoch": 0.748898678414097,
+      "grad_norm": 0.8209335803985596,
+      "learning_rate": 2.6926156525249596e-05,
+      "loss": 0.7394,
+      "step": 170
+    },
+    {
+      "epoch": 0.7709251101321586,
+      "grad_norm": 0.8079976439476013,
+      "learning_rate": 2.6701437368339137e-05,
+      "loss": 0.8451,
+      "step": 175
+    },
+    {
+      "epoch": 0.7929515418502202,
+      "grad_norm": 0.7861381769180298,
+      "learning_rate": 2.6469800020681277e-05,
+      "loss": 0.73,
+      "step": 180
+    },
+    {
+      "epoch": 0.8149779735682819,
+      "grad_norm": 0.6906131505966187,
+      "learning_rate": 2.623138143223396e-05,
+      "loss": 0.7579,
+      "step": 185
+    },
+    {
+      "epoch": 0.8370044052863436,
+      "grad_norm": 0.7661092281341553,
+      "learning_rate": 2.598632256219908e-05,
+      "loss": 0.7812,
+      "step": 190
+    },
+    {
+      "epoch": 0.8590308370044053,
+      "grad_norm": 0.827968955039978,
+      "learning_rate": 2.5734768295683825e-05,
+      "loss": 0.8078,
+      "step": 195
+    },
+    {
+      "epoch": 0.8810572687224669,
+      "grad_norm": 0.8416321277618408,
+      "learning_rate": 2.547686735804083e-05,
+      "loss": 0.7136,
+      "step": 200
+    },
+    {
+      "epoch": 0.9030837004405287,
+      "grad_norm": 0.7770540714263916,
+      "learning_rate": 2.5212772226937962e-05,
+      "loss": 0.7805,
+      "step": 205
+    },
+    {
+      "epoch": 0.9251101321585903,
+      "grad_norm": 0.8592027425765991,
+      "learning_rate": 2.494263904220958e-05,
+      "loss": 0.7161,
+      "step": 210
+    },
+    {
+      "epoch": 0.947136563876652,
+      "grad_norm": 0.8240308165550232,
+      "learning_rate": 2.466662751354265e-05,
+      "loss": 0.7195,
+      "step": 215
+    },
+    {
+      "epoch": 0.9691629955947136,
+      "grad_norm": 0.7898277640342712,
+      "learning_rate": 2.4384900826052264e-05,
+      "loss": 0.7183,
+      "step": 220
+    },
+    {
+      "epoch": 0.9911894273127754,
+      "grad_norm": 0.8771491646766663,
+      "learning_rate": 2.4097625543802436e-05,
+      "loss": 0.6718,
+      "step": 225
+    },
+    {
+      "epoch": 1.013215859030837,
+      "grad_norm": 0.9152331948280334,
+      "learning_rate": 2.3804971511329088e-05,
+      "loss": 0.6157,
+      "step": 230
+    },
+    {
+      "epoch": 1.0352422907488987,
+      "grad_norm": 1.0206756591796875,
+      "learning_rate": 2.350711175322364e-05,
+      "loss": 0.5976,
+      "step": 235
+    },
+    {
+      "epoch": 1.0572687224669604,
+      "grad_norm": 0.8107870221138,
+      "learning_rate": 2.320422237183641e-05,
+      "loss": 0.5908,
+      "step": 240
+    },
+    {
+      "epoch": 1.079295154185022,
+      "grad_norm": 0.958835244178772,
+      "learning_rate": 2.2896482443160337e-05,
+      "loss": 0.5809,
+      "step": 245
+    },
+    {
+      "epoch": 1.1013215859030836,
+      "grad_norm": 0.9627093076705933,
+      "learning_rate": 2.2584073910956724e-05,
+      "loss": 0.5708,
+      "step": 250
+    },
+    {
+      "epoch": 1.1233480176211454,
+      "grad_norm": 0.9750155210494995,
+      "learning_rate": 2.2267181479185323e-05,
+      "loss": 0.599,
+      "step": 255
+    },
+    {
+      "epoch": 1.145374449339207,
+      "grad_norm": 0.9447664618492126,
+      "learning_rate": 2.194599250280266e-05,
+      "loss": 0.5155,
+      "step": 260
+    },
+    {
+      "epoch": 1.1674008810572687,
+      "grad_norm": 0.9090636372566223,
+      "learning_rate": 2.162069687699295e-05,
+      "loss": 0.537,
+      "step": 265
+    },
+    {
+      "epoch": 1.1894273127753303,
+      "grad_norm": 1.0212293863296509,
+      "learning_rate": 2.1291486924897162e-05,
+      "loss": 0.5411,
+      "step": 270
+    },
+    {
+      "epoch": 1.2114537444933922,
+      "grad_norm": 0.9540414214134216,
+      "learning_rate": 2.0958557283906672e-05,
+      "loss": 0.5327,
+      "step": 275
+    },
+    {
+      "epoch": 1.2334801762114538,
+      "grad_norm": 0.9351039528846741,
+      "learning_rate": 2.062210479058857e-05,
+      "loss": 0.5194,
+      "step": 280
+    },
+    {
+      "epoch": 1.2555066079295154,
+      "grad_norm": 1.0063831806182861,
+      "learning_rate": 2.0282328364310887e-05,
+      "loss": 0.5029,
+      "step": 285
+    },
+    {
+      "epoch": 1.277533039647577,
+      "grad_norm": 1.0426006317138672,
+      "learning_rate": 1.9939428889636303e-05,
+      "loss": 0.544,
+      "step": 290
+    },
+    {
+      "epoch": 1.2995594713656389,
+      "grad_norm": 0.9950483441352844,
+      "learning_rate": 1.9593609097554027e-05,
+      "loss": 0.5284,
+      "step": 295
+    },
+    {
+      "epoch": 1.3215859030837005,
+      "grad_norm": 1.0217667818069458,
+      "learning_rate": 1.9245073445620055e-05,
+      "loss": 0.5313,
+      "step": 300
+    },
+    {
+      "epoch": 1.3436123348017621,
+      "grad_norm": 1.0965392589569092,
+      "learning_rate": 1.889402799707657e-05,
+      "loss": 0.4681,
+      "step": 305
+    },
+    {
+      "epoch": 1.3656387665198237,
+      "grad_norm": 0.9708188772201538,
+      "learning_rate": 1.8540680299022064e-05,
+      "loss": 0.5174,
+      "step": 310
+    },
+    {
+      "epoch": 1.3876651982378854,
+      "grad_norm": 1.2204405069351196,
+      "learning_rate": 1.8185239259704164e-05,
+      "loss": 0.5106,
+      "step": 315
+    },
+    {
+      "epoch": 1.4096916299559472,
+      "grad_norm": 0.9907987117767334,
+      "learning_rate": 1.782791502500769e-05,
+      "loss": 0.5136,
+      "step": 320
+    },
+    {
+      "epoch": 1.4317180616740088,
+      "grad_norm": 1.0257529020309448,
+      "learning_rate": 1.746891885421101e-05,
+      "loss": 0.4935,
+      "step": 325
+    },
+    {
+      "epoch": 1.4537444933920705,
+      "grad_norm": 1.0849453210830688,
+      "learning_rate": 1.7108462995084118e-05,
+      "loss": 0.457,
+      "step": 330
+    },
+    {
+      "epoch": 1.475770925110132,
+      "grad_norm": 1.0605039596557617,
+      "learning_rate": 1.6746760558402294e-05,
+      "loss": 0.4709,
+      "step": 335
+    },
+    {
+      "epoch": 1.497797356828194,
+      "grad_norm": 1.0056084394454956,
+      "learning_rate": 1.638402539194953e-05,
+      "loss": 0.4487,
+      "step": 340
+    },
+    {
+      "epoch": 1.5198237885462555,
+      "grad_norm": 1.0775991678237915,
+      "learning_rate": 1.6020471954086227e-05,
+      "loss": 0.4697,
+      "step": 345
+    },
+    {
+      "epoch": 1.5418502202643172,
+      "grad_norm": 1.2277886867523193,
+      "learning_rate": 1.5656315186955888e-05,
+      "loss": 0.4426,
+      "step": 350
+    },
+    {
+      "epoch": 1.5638766519823788,
+      "grad_norm": 1.027424931526184,
+      "learning_rate": 1.5291770389405792e-05,
+      "loss": 0.4575,
+      "step": 355
+    },
+    {
+      "epoch": 1.5859030837004404,
+      "grad_norm": 1.060658574104309,
+      "learning_rate": 1.4927053089696787e-05,
+      "loss": 0.4377,
+      "step": 360
+    },
+    {
+      "epoch": 1.607929515418502,
+      "grad_norm": 1.0731483697891235,
+      "learning_rate": 1.4562378918077437e-05,
+      "loss": 0.4425,
+      "step": 365
+    },
+    {
+      "epoch": 1.6299559471365639,
+      "grad_norm": 1.179704189300537,
+      "learning_rate": 1.4197963479297871e-05,
+      "loss": 0.4417,
+      "step": 370
+    },
+    {
+      "epoch": 1.6519823788546255,
+      "grad_norm": 1.0248568058013916,
+      "learning_rate": 1.3834022225138701e-05,
+      "loss": 0.4043,
+      "step": 375
+    },
+    {
+      "epoch": 1.6740088105726874,
+      "grad_norm": 0.9538683295249939,
+      "learning_rate": 1.3470770327030391e-05,
+      "loss": 0.4227,
+      "step": 380
+    },
+    {
+      "epoch": 1.696035242290749,
+      "grad_norm": 1.1992961168289185,
+      "learning_rate": 1.31084225488384e-05,
+      "loss": 0.3944,
+      "step": 385
+    },
+    {
+      "epoch": 1.7180616740088106,
+      "grad_norm": 1.0340512990951538,
+      "learning_rate": 1.2747193119889209e-05,
+      "loss": 0.4362,
+      "step": 390
+    },
+    {
+      "epoch": 1.7400881057268722,
+      "grad_norm": 1.1911242008209229,
+      "learning_rate": 1.2387295608312483e-05,
+      "loss": 0.4095,
+      "step": 395
+    },
+    {
+      "epoch": 1.7621145374449338,
+      "grad_norm": 1.133638858795166,
+      "learning_rate": 1.2028942794774065e-05,
+      "loss": 0.3844,
+      "step": 400
+    },
+    {
+      "epoch": 1.7841409691629955,
+      "grad_norm": 1.033832311630249,
+      "learning_rate": 1.167234654667458e-05,
+      "loss": 0.4191,
+      "step": 405
+    },
+    {
+      "epoch": 1.8061674008810573,
+      "grad_norm": 1.0981718301773071,
+      "learning_rate": 1.1317717692888014e-05,
+      "loss": 0.38,
+      "step": 410
+    },
+    {
+      "epoch": 1.828193832599119,
+      "grad_norm": 1.0969401597976685,
+      "learning_rate": 1.09652658991142e-05,
+      "loss": 0.4457,
+      "step": 415
+    },
+    {
+      "epoch": 1.8502202643171806,
+      "grad_norm": 1.1406123638153076,
+      "learning_rate": 1.0615199543919107e-05,
+      "loss": 0.4143,
+      "step": 420
+    },
+    {
+      "epoch": 1.8722466960352424,
+      "grad_norm": 1.3279160261154175,
+      "learning_rate": 1.0267725595536063e-05,
+      "loss": 0.4239,
+      "step": 425
+    },
+    {
+      "epoch": 1.894273127753304,
+      "grad_norm": 1.2672303915023804,
+      "learning_rate": 9.923049489500801e-06,
+      "loss": 0.399,
+      "step": 430
+    },
+    {
+      "epoch": 1.9162995594713657,
+      "grad_norm": 1.192007303237915,
+      "learning_rate": 9.581375007192707e-06,
+      "loss": 0.3749,
+      "step": 435
+    },
+    {
+      "epoch": 1.9383259911894273,
+      "grad_norm": 1.0572453737258911,
+      "learning_rate": 9.242904155353998e-06,
+      "loss": 0.3796,
+      "step": 440
+    },
+    {
+      "epoch": 1.960352422907489,
+      "grad_norm": 1.014243483543396,
+      "learning_rate": 8.907837046658169e-06,
+      "loss": 0.405,
+      "step": 445
+    },
+    {
+      "epoch": 1.9823788546255505,
+      "grad_norm": 1.212935209274292,
+      "learning_rate": 8.576371781398215e-06,
+      "loss": 0.3827,
+      "step": 450
+    },
+    {
+      "epoch": 2.004405286343612,
+      "grad_norm": 1.1122121810913086,
+      "learning_rate": 8.248704330364634e-06,
+      "loss": 0.329,
+      "step": 455
+    },
+    {
+      "epoch": 2.026431718061674,
+      "grad_norm": 1.1853020191192627,
+      "learning_rate": 7.925028418982509e-06,
+      "loss": 0.295,
+      "step": 460
+    },
+    {
+      "epoch": 2.048458149779736,
+      "grad_norm": 1.0080333948135376,
+      "learning_rate": 7.605535412775968e-06,
+      "loss": 0.302,
+      "step": 465
+    },
+    {
+      "epoch": 2.0704845814977975,
+      "grad_norm": 1.061188817024231,
+      "learning_rate": 7.290414204228038e-06,
+      "loss": 0.2765,
+      "step": 470
+    },
+    {
+      "epoch": 2.092511013215859,
+      "grad_norm": 1.1788150072097778,
+      "learning_rate": 6.979851101102519e-06,
+      "loss": 0.3201,
+      "step": 475
+    },
+    {
+      "epoch": 2.1145374449339207,
+      "grad_norm": 1.1109647750854492,
+      "learning_rate": 6.674029716294022e-06,
+      "loss": 0.2921,
+      "step": 480
+    },
+    {
+      "epoch": 2.1365638766519823,
+      "grad_norm": 1.132834553718567,
+      "learning_rate": 6.3731308592713684e-06,
+      "loss": 0.3388,
+      "step": 485
+    },
+    {
+      "epoch": 2.158590308370044,
+      "grad_norm": 1.3638838529586792,
+      "learning_rate": 6.077332429178297e-06,
+      "loss": 0.318,
+      "step": 490
+    },
+    {
+      "epoch": 2.1806167400881056,
+      "grad_norm": 1.4544788599014282,
+      "learning_rate": 5.786809309654983e-06,
+      "loss": 0.3113,
+      "step": 495
+    },
+    {
+      "epoch": 2.202643171806167,
+      "grad_norm": 1.1365785598754883,
+      "learning_rate": 5.501733265442301e-06,
+      "loss": 0.3018,
+      "step": 500
+    },
+    {
+      "epoch": 2.2246696035242293,
+      "grad_norm": 1.2192156314849854,
+      "learning_rate": 5.2222728408300835e-06,
+      "loss": 0.2981,
+      "step": 505
+    },
+    {
+      "epoch": 2.246696035242291,
+      "grad_norm": 0.9936226606369019,
+      "learning_rate": 4.948593260009428e-06,
+      "loss": 0.287,
+      "step": 510
+    },
+    {
+      "epoch": 2.2687224669603525,
+      "grad_norm": 1.1586830615997314,
+      "learning_rate": 4.680856329387888e-06,
+      "loss": 0.2615,
+      "step": 515
+    },
+    {
+      "epoch": 2.290748898678414,
+      "grad_norm": 1.1719970703125,
+      "learning_rate": 4.41922034192537e-06,
+      "loss": 0.3219,
+      "step": 520
+    },
+    {
+      "epoch": 2.3127753303964758,
+      "grad_norm": 1.0870250463485718,
+      "learning_rate": 4.163839983547259e-06,
+      "loss": 0.3022,
+      "step": 525
+    },
+    {
+      "epoch": 2.3348017621145374,
+      "grad_norm": 1.119413137435913,
+      "learning_rate": 3.914866241690115e-06,
+      "loss": 0.2917,
+      "step": 530
+    },
+    {
+      "epoch": 2.356828193832599,
+      "grad_norm": 1.1864994764328003,
+      "learning_rate": 3.6724463160340377e-06,
+      "loss": 0.2917,
+      "step": 535
+    },
+    {
+      "epoch": 2.3788546255506606,
+      "grad_norm": 1.064591407775879,
+      "learning_rate": 3.43672353147441e-06,
+      "loss": 0.3042,
+      "step": 540
+    },
+    {
+      "epoch": 2.4008810572687223,
+      "grad_norm": 1.0908355712890625,
+      "learning_rate": 3.207837253384539e-06,
+      "loss": 0.277,
+      "step": 545
+    },
+    {
+      "epoch": 2.4229074889867843,
+      "grad_norm": 1.127847671508789,
+      "learning_rate": 2.9859228052192732e-06,
+      "loss": 0.2532,
+      "step": 550
+    },
+    {
+      "epoch": 2.444933920704846,
+      "grad_norm": 1.0845614671707153,
+      "learning_rate": 2.7711113885082666e-06,
+      "loss": 0.3465,
+      "step": 555
+    },
+    {
+      "epoch": 2.4669603524229076,
+      "grad_norm": 1.1460652351379395,
+      "learning_rate": 2.5635300052862963e-06,
+      "loss": 0.2721,
+      "step": 560
+    },
+    {
+      "epoch": 2.488986784140969,
+      "grad_norm": 1.2167898416519165,
+      "learning_rate": 2.363301383006369e-06,
+      "loss": 0.2992,
+      "step": 565
+    },
+    {
+      "epoch": 2.511013215859031,
+      "grad_norm": 1.1077433824539185,
+      "learning_rate": 2.170543901980102e-06,
+      "loss": 0.2875,
+      "step": 570
+    },
+    {
+      "epoch": 2.5330396475770924,
+      "grad_norm": 1.152856469154358,
+      "learning_rate": 1.9853715253882355e-06,
+      "loss": 0.3186,
+      "step": 575
+    },
+    {
+      "epoch": 2.555066079295154,
+      "grad_norm": 1.180096983909607,
+      "learning_rate": 1.8078937319026655e-06,
+      "loss": 0.2785,
+      "step": 580
+    },
+    {
+      "epoch": 2.577092511013216,
+      "grad_norm": 1.1503738164901733,
+      "learning_rate": 1.638215450959849e-06,
+      "loss": 0.295,
+      "step": 585
+    },
+    {
+      "epoch": 2.5991189427312777,
+      "grad_norm": 1.0105490684509277,
+      "learning_rate": 1.47643700072381e-06,
+      "loss": 0.2722,
+      "step": 590
+    },
+    {
+      "epoch": 2.6211453744493394,
+      "grad_norm": 1.0941814184188843,
+      "learning_rate": 1.32265402877547e-06,
+      "loss": 0.2995,
+      "step": 595
+    },
+    {
+      "epoch": 2.643171806167401,
+      "grad_norm": 1.1381118297576904,
+      "learning_rate": 1.17695745556333e-06,
+      "loss": 0.2334,
+      "step": 600
+    },
+    {
+      "epoch": 2.6651982378854626,
+      "grad_norm": 1.1673427820205688,
+      "learning_rate": 1.0394334206489647e-06,
+      "loss": 0.2759,
+      "step": 605
+    },
+    {
+      "epoch": 2.6872246696035242,
+      "grad_norm": 1.0389903783798218,
+      "learning_rate": 9.101632317790998e-07,
+      "loss": 0.2909,
+      "step": 610
+    },
+    {
+      "epoch": 2.709251101321586,
+      "grad_norm": 1.1912908554077148,
+      "learning_rate": 7.892233168143853e-07,
+      "loss": 0.2522,
+      "step": 615
+    },
+    {
+      "epoch": 2.7312775330396475,
+      "grad_norm": 1.2068308591842651,
+      "learning_rate": 6.766851785432698e-07,
+      "loss": 0.3119,
+      "step": 620
+    },
+    {
+      "epoch": 2.753303964757709,
+      "grad_norm": 0.9462194442749023,
+      "learning_rate": 5.726153524077144e-07,
+      "loss": 0.2653,
+      "step": 625
+    },
+    {
+      "epoch": 2.7753303964757707,
+      "grad_norm": 1.0062333345413208,
+      "learning_rate": 4.770753671657357e-07,
+      "loss": 0.2387,
+      "step": 630
+    },
+    {
+      "epoch": 2.7973568281938324,
+      "grad_norm": 1.1131367683410645,
+      "learning_rate": 3.9012170851401406e-07,
+      "loss": 0.2814,
+      "step": 635
+    },
+    {
+      "epoch": 2.8193832599118944,
+      "grad_norm": 1.2274373769760132,
+      "learning_rate": 3.1180578569209807e-07,
+      "loss": 0.2604,
+      "step": 640
+    },
+    {
+      "epoch": 2.841409691629956,
+      "grad_norm": 1.0255389213562012,
+      "learning_rate": 2.421739010879398e-07,
+      "loss": 0.2753,
+      "step": 645
+    },
+    {
+      "epoch": 2.8634361233480177,
+      "grad_norm": 1.0927162170410156,
+      "learning_rate": 1.81267222862736e-07,
+      "loss": 0.275,
+      "step": 650
+    },
+    {
+      "epoch": 2.8854625550660793,
+      "grad_norm": 1.2236757278442383,
+      "learning_rate": 1.2912176061124604e-07,
+      "loss": 0.2389,
+      "step": 655
+    },
+    {
+      "epoch": 2.907488986784141,
+      "grad_norm": 1.0639089345932007,
+      "learning_rate": 8.576834407199696e-08,
+      "loss": 0.2504,
+      "step": 660
+    },
+    {
+      "epoch": 2.9295154185022025,
+      "grad_norm": 1.1123826503753662,
+      "learning_rate": 5.1232604899952296e-08,
+      "loss": 0.249,
+      "step": 665
+    },
+    {
+      "epoch": 2.951541850220264,
+      "grad_norm": 1.1235257387161255,
+      "learning_rate": 2.5534961512410637e-08,
+      "loss": 0.2685,
+      "step": 670
+    },
+    {
+      "epoch": 2.9735682819383262,
+      "grad_norm": 1.033311367034912,
+      "learning_rate": 8.690607017115548e-09,
+      "loss": 0.2594,
+      "step": 675
+    },
+    {
+      "epoch": 2.995594713656388,
+      "grad_norm": 1.1088478565216064,
+      "learning_rate": 7.095002297041741e-10,
+      "loss": 0.2575,
+      "step": 680
+    },
+    {
+      "epoch": 3.0,
+      "step": 681,
+      "total_flos": 9.843483184421929e+17,
+      "train_loss": 0.5876927409928275,
+      "train_runtime": 479.7831,
+      "train_samples_per_second": 45.339,
+      "train_steps_per_second": 1.419
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 681,
+  "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": 9.843483184421929e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

14_128_e3_3e-5/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18fee9b220a9f3190901a053431bffd0f4a82452a3eaf6f7bd60fccb357cb5de
+size 8209