Upload folder using huggingface_hub

114_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": [
+    "v_proj",
+    "up_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

114_128_e3_3e-5/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f3767e7582aeeaeea377453b662dc00c83f9729cb8750d3686c8428a234839d
+size 791751704

114_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
+}

114_128_e3_3e-5/all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 8.181798015200133e+17,
+    "train_loss": 0.3922736724356996,
+    "train_runtime": 396.0022,
+    "train_samples": 6835,
+    "train_samples_per_second": 51.78,
+    "train_steps_per_second": 1.621
+}

114_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 %}

114_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
+}

114_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
+  }
+}

114_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
+}

114_128_e3_3e-5/train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 8.181798015200133e+17,
+    "train_loss": 0.3922736724356996,
+    "train_runtime": 396.0022,
+    "train_samples": 6835,
+    "train_samples_per_second": 51.78,
+    "train_steps_per_second": 1.621
+}

114_128_e3_3e-5/trainer_state.json

@@ -0,0 +1,939 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 642,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02336448598130841,
+      "grad_norm": 2.394056797027588,
+      "learning_rate": 3.6363636363636366e-06,
+      "loss": 1.5722,
+      "step": 5
+    },
+    {
+      "epoch": 0.04672897196261682,
+      "grad_norm": 1.4779744148254395,
+      "learning_rate": 8.181818181818181e-06,
+      "loss": 1.5108,
+      "step": 10
+    },
+    {
+      "epoch": 0.07009345794392523,
+      "grad_norm": 0.5607652068138123,
+      "learning_rate": 1.2727272727272728e-05,
+      "loss": 1.4227,
+      "step": 15
+    },
+    {
+      "epoch": 0.09345794392523364,
+      "grad_norm": 0.42606180906295776,
+      "learning_rate": 1.7272727272727274e-05,
+      "loss": 1.3951,
+      "step": 20
+    },
+    {
+      "epoch": 0.11682242990654206,
+      "grad_norm": 0.5096513628959656,
+      "learning_rate": 2.1818181818181818e-05,
+      "loss": 1.3629,
+      "step": 25
+    },
+    {
+      "epoch": 0.14018691588785046,
+      "grad_norm": 0.4576520621776581,
+      "learning_rate": 2.6363636363636365e-05,
+      "loss": 1.3003,
+      "step": 30
+    },
+    {
+      "epoch": 0.16355140186915887,
+      "grad_norm": 0.41707563400268555,
+      "learning_rate": 2.9999800416120386e-05,
+      "loss": 1.3866,
+      "step": 35
+    },
+    {
+      "epoch": 0.18691588785046728,
+      "grad_norm": 0.40992990136146545,
+      "learning_rate": 2.9992815537990055e-05,
+      "loss": 1.2692,
+      "step": 40
+    },
+    {
+      "epoch": 0.2102803738317757,
+      "grad_norm": 1.6285532712936401,
+      "learning_rate": 2.9975856776406864e-05,
+      "loss": 1.2706,
+      "step": 45
+    },
+    {
+      "epoch": 0.2336448598130841,
+      "grad_norm": 0.4323791265487671,
+      "learning_rate": 2.9948935413088454e-05,
+      "loss": 1.2024,
+      "step": 50
+    },
+    {
+      "epoch": 0.2570093457943925,
+      "grad_norm": 0.5564969778060913,
+      "learning_rate": 2.9912069357315394e-05,
+      "loss": 1.1646,
+      "step": 55
+    },
+    {
+      "epoch": 0.2803738317757009,
+      "grad_norm": 0.4710974097251892,
+      "learning_rate": 2.9865283134017167e-05,
+      "loss": 1.2395,
+      "step": 60
+    },
+    {
+      "epoch": 0.3037383177570093,
+      "grad_norm": 0.5212734341621399,
+      "learning_rate": 2.980860786745706e-05,
+      "loss": 1.078,
+      "step": 65
+    },
+    {
+      "epoch": 0.32710280373831774,
+      "grad_norm": 0.5346776843070984,
+      "learning_rate": 2.9742081260526968e-05,
+      "loss": 1.1052,
+      "step": 70
+    },
+    {
+      "epoch": 0.35046728971962615,
+      "grad_norm": 0.548423707485199,
+      "learning_rate": 2.9665747569665735e-05,
+      "loss": 1.049,
+      "step": 75
+    },
+    {
+      "epoch": 0.37383177570093457,
+      "grad_norm": 0.6231434345245361,
+      "learning_rate": 2.957965757541784e-05,
+      "loss": 1.0394,
+      "step": 80
+    },
+    {
+      "epoch": 0.397196261682243,
+      "grad_norm": 0.593290388584137,
+      "learning_rate": 2.948386854865191e-05,
+      "loss": 0.9723,
+      "step": 85
+    },
+    {
+      "epoch": 0.4205607476635514,
+      "grad_norm": 0.5931947827339172,
+      "learning_rate": 2.937844421246162e-05,
+      "loss": 0.9395,
+      "step": 90
+    },
+    {
+      "epoch": 0.4439252336448598,
+      "grad_norm": 0.5959659814834595,
+      "learning_rate": 2.926345469977428e-05,
+      "loss": 0.9402,
+      "step": 95
+    },
+    {
+      "epoch": 0.4672897196261682,
+      "grad_norm": 0.7404563426971436,
+      "learning_rate": 2.9138976506695307e-05,
+      "loss": 0.8553,
+      "step": 100
+    },
+    {
+      "epoch": 0.49065420560747663,
+      "grad_norm": 0.6448763012886047,
+      "learning_rate": 2.9005092441619627e-05,
+      "loss": 0.9253,
+      "step": 105
+    },
+    {
+      "epoch": 0.514018691588785,
+      "grad_norm": 0.8752307295799255,
+      "learning_rate": 2.8861891570143885e-05,
+      "loss": 0.8566,
+      "step": 110
+    },
+    {
+      "epoch": 0.5373831775700935,
+      "grad_norm": 0.7256718277931213,
+      "learning_rate": 2.8709469155816066e-05,
+      "loss": 0.7779,
+      "step": 115
+    },
+    {
+      "epoch": 0.5607476635514018,
+      "grad_norm": 0.8161791563034058,
+      "learning_rate": 2.854792659676198e-05,
+      "loss": 0.7579,
+      "step": 120
+    },
+    {
+      "epoch": 0.5841121495327103,
+      "grad_norm": 0.8757849931716919,
+      "learning_rate": 2.8377371358230733e-05,
+      "loss": 0.7505,
+      "step": 125
+    },
+    {
+      "epoch": 0.6074766355140186,
+      "grad_norm": 0.8687119483947754,
+      "learning_rate": 2.819791690110412e-05,
+      "loss": 0.7253,
+      "step": 130
+    },
+    {
+      "epoch": 0.6308411214953271,
+      "grad_norm": 0.8262975215911865,
+      "learning_rate": 2.8009682606417397e-05,
+      "loss": 0.7319,
+      "step": 135
+    },
+    {
+      "epoch": 0.6542056074766355,
+      "grad_norm": 0.9814523458480835,
+      "learning_rate": 2.781279369594177e-05,
+      "loss": 0.6432,
+      "step": 140
+    },
+    {
+      "epoch": 0.677570093457944,
+      "grad_norm": 0.9001941680908203,
+      "learning_rate": 2.7607381148881345e-05,
+      "loss": 0.6002,
+      "step": 145
+    },
+    {
+      "epoch": 0.7009345794392523,
+      "grad_norm": 0.9991686940193176,
+      "learning_rate": 2.7393581614739924e-05,
+      "loss": 0.6134,
+      "step": 150
+    },
+    {
+      "epoch": 0.7242990654205608,
+      "grad_norm": 0.9385070204734802,
+      "learning_rate": 2.7171537322415777e-05,
+      "loss": 0.5621,
+      "step": 155
+    },
+    {
+      "epoch": 0.7476635514018691,
+      "grad_norm": 1.0593597888946533,
+      "learning_rate": 2.6941395985584656e-05,
+      "loss": 0.5929,
+      "step": 160
+    },
+    {
+      "epoch": 0.7710280373831776,
+      "grad_norm": 1.0321978330612183,
+      "learning_rate": 2.6703310704434144e-05,
+      "loss": 0.6102,
+      "step": 165
+    },
+    {
+      "epoch": 0.794392523364486,
+      "grad_norm": 1.1172053813934326,
+      "learning_rate": 2.6457439863814637e-05,
+      "loss": 0.5499,
+      "step": 170
+    },
+    {
+      "epoch": 0.8177570093457944,
+      "grad_norm": 1.0350509881973267,
+      "learning_rate": 2.6203947027874753e-05,
+      "loss": 0.5534,
+      "step": 175
+    },
+    {
+      "epoch": 0.8411214953271028,
+      "grad_norm": 1.1137152910232544,
+      "learning_rate": 2.5943000831251215e-05,
+      "loss": 0.5356,
+      "step": 180
+    },
+    {
+      "epoch": 0.8644859813084113,
+      "grad_norm": 1.082862138748169,
+      "learning_rate": 2.5674774866885664e-05,
+      "loss": 0.4747,
+      "step": 185
+    },
+    {
+      "epoch": 0.8878504672897196,
+      "grad_norm": 1.1490403413772583,
+      "learning_rate": 2.539944757054293e-05,
+      "loss": 0.4886,
+      "step": 190
+    },
+    {
+      "epoch": 0.9112149532710281,
+      "grad_norm": 1.083483338356018,
+      "learning_rate": 2.5117202102107707e-05,
+      "loss": 0.5022,
+      "step": 195
+    },
+    {
+      "epoch": 0.9345794392523364,
+      "grad_norm": 1.007580041885376,
+      "learning_rate": 2.4828226223738493e-05,
+      "loss": 0.4111,
+      "step": 200
+    },
+    {
+      "epoch": 0.9579439252336449,
+      "grad_norm": 1.1426090002059937,
+      "learning_rate": 2.4532712174959882e-05,
+      "loss": 0.4419,
+      "step": 205
+    },
+    {
+      "epoch": 0.9813084112149533,
+      "grad_norm": 1.2074663639068604,
+      "learning_rate": 2.4230856544776377e-05,
+      "loss": 0.4161,
+      "step": 210
+    },
+    {
+      "epoch": 1.0046728971962617,
+      "grad_norm": 1.0917161703109741,
+      "learning_rate": 2.3922860140892667e-05,
+      "loss": 0.3758,
+      "step": 215
+    },
+    {
+      "epoch": 1.02803738317757,
+      "grad_norm": 1.426063060760498,
+      "learning_rate": 2.3608927856127483e-05,
+      "loss": 0.3323,
+      "step": 220
+    },
+    {
+      "epoch": 1.0514018691588785,
+      "grad_norm": 1.082567572593689,
+      "learning_rate": 2.3289268532109828e-05,
+      "loss": 0.3688,
+      "step": 225
+    },
+    {
+      "epoch": 1.074766355140187,
+      "grad_norm": 1.2942150831222534,
+      "learning_rate": 2.2964094820348302e-05,
+      "loss": 0.3247,
+      "step": 230
+    },
+    {
+      "epoch": 1.0981308411214954,
+      "grad_norm": 0.9273058772087097,
+      "learning_rate": 2.2633623040765936e-05,
+      "loss": 0.3236,
+      "step": 235
+    },
+    {
+      "epoch": 1.1214953271028036,
+      "grad_norm": 1.3827800750732422,
+      "learning_rate": 2.2298073037794585e-05,
+      "loss": 0.3188,
+      "step": 240
+    },
+    {
+      "epoch": 1.144859813084112,
+      "grad_norm": 1.0251104831695557,
+      "learning_rate": 2.1957668034124732e-05,
+      "loss": 0.3176,
+      "step": 245
+    },
+    {
+      "epoch": 1.1682242990654206,
+      "grad_norm": 1.2389192581176758,
+      "learning_rate": 2.1612634482207874e-05,
+      "loss": 0.262,
+      "step": 250
+    },
+    {
+      "epoch": 1.191588785046729,
+      "grad_norm": 1.3050047159194946,
+      "learning_rate": 2.1263201913610343e-05,
+      "loss": 0.2895,
+      "step": 255
+    },
+    {
+      "epoch": 1.2149532710280373,
+      "grad_norm": 1.1179063320159912,
+      "learning_rate": 2.0909602786318757e-05,
+      "loss": 0.2841,
+      "step": 260
+    },
+    {
+      "epoch": 1.2383177570093458,
+      "grad_norm": 1.0498738288879395,
+      "learning_rate": 2.055207233009872e-05,
+      "loss": 0.2874,
+      "step": 265
+    },
+    {
+      "epoch": 1.2616822429906542,
+      "grad_norm": 1.0453853607177734,
+      "learning_rate": 2.0190848390009556e-05,
+      "loss": 0.2606,
+      "step": 270
+    },
+    {
+      "epoch": 1.2850467289719627,
+      "grad_norm": 1.1275442838668823,
+      "learning_rate": 1.9826171268179302e-05,
+      "loss": 0.2423,
+      "step": 275
+    },
+    {
+      "epoch": 1.308411214953271,
+      "grad_norm": 1.299269437789917,
+      "learning_rate": 1.9458283563945063e-05,
+      "loss": 0.234,
+      "step": 280
+    },
+    {
+      "epoch": 1.3317757009345794,
+      "grad_norm": 1.1573830842971802,
+      "learning_rate": 1.9087430012465264e-05,
+      "loss": 0.2403,
+      "step": 285
+    },
+    {
+      "epoch": 1.355140186915888,
+      "grad_norm": 1.1889029741287231,
+      "learning_rate": 1.8713857321910968e-05,
+      "loss": 0.26,
+      "step": 290
+    },
+    {
+      "epoch": 1.3785046728971961,
+      "grad_norm": 1.2217601537704468,
+      "learning_rate": 1.8337814009344716e-05,
+      "loss": 0.2454,
+      "step": 295
+    },
+    {
+      "epoch": 1.4018691588785046,
+      "grad_norm": 1.1743645668029785,
+      "learning_rate": 1.7959550235396002e-05,
+      "loss": 0.239,
+      "step": 300
+    },
+    {
+      "epoch": 1.425233644859813,
+      "grad_norm": 1.3167074918746948,
+      "learning_rate": 1.7579317637843344e-05,
+      "loss": 0.224,
+      "step": 305
+    },
+    {
+      "epoch": 1.4485981308411215,
+      "grad_norm": 1.0133246183395386,
+      "learning_rate": 1.719736916421374e-05,
+      "loss": 0.1906,
+      "step": 310
+    },
+    {
+      "epoch": 1.47196261682243,
+      "grad_norm": 0.9746128916740417,
+      "learning_rate": 1.6813958903510767e-05,
+      "loss": 0.1861,
+      "step": 315
+    },
+    {
+      "epoch": 1.4953271028037383,
+      "grad_norm": 1.125864863395691,
+      "learning_rate": 1.6429341917183377e-05,
+      "loss": 0.1897,
+      "step": 320
+    },
+    {
+      "epoch": 1.5186915887850467,
+      "grad_norm": 1.2703579664230347,
+      "learning_rate": 1.604377406944772e-05,
+      "loss": 0.2038,
+      "step": 325
+    },
+    {
+      "epoch": 1.542056074766355,
+      "grad_norm": 1.224549651145935,
+      "learning_rate": 1.5657511857074988e-05,
+      "loss": 0.1812,
+      "step": 330
+    },
+    {
+      "epoch": 1.5654205607476634,
+      "grad_norm": 0.8722062110900879,
+      "learning_rate": 1.5270812238758407e-05,
+      "loss": 0.2247,
+      "step": 335
+    },
+    {
+      "epoch": 1.588785046728972,
+      "grad_norm": 1.1795073747634888,
+      "learning_rate": 1.4883932464172968e-05,
+      "loss": 0.1901,
+      "step": 340
+    },
+    {
+      "epoch": 1.6121495327102804,
+      "grad_norm": 1.1773940324783325,
+      "learning_rate": 1.4497129902841576e-05,
+      "loss": 0.1764,
+      "step": 345
+    },
+    {
+      "epoch": 1.6355140186915889,
+      "grad_norm": 1.059206485748291,
+      "learning_rate": 1.411066187292147e-05,
+      "loss": 0.1691,
+      "step": 350
+    },
+    {
+      "epoch": 1.6588785046728973,
+      "grad_norm": 1.0430490970611572,
+      "learning_rate": 1.3724785470024793e-05,
+      "loss": 0.205,
+      "step": 355
+    },
+    {
+      "epoch": 1.6822429906542056,
+      "grad_norm": 1.0765695571899414,
+      "learning_rate": 1.333975739618727e-05,
+      "loss": 0.1646,
+      "step": 360
+    },
+    {
+      "epoch": 1.705607476635514,
+      "grad_norm": 0.9505099654197693,
+      "learning_rate": 1.2955833789098634e-05,
+      "loss": 0.1673,
+      "step": 365
+    },
+    {
+      "epoch": 1.7289719626168223,
+      "grad_norm": 1.0387061834335327,
+      "learning_rate": 1.2573270051708529e-05,
+      "loss": 0.1539,
+      "step": 370
+    },
+    {
+      "epoch": 1.7523364485981308,
+      "grad_norm": 1.066915512084961,
+      "learning_rate": 1.2192320682321189e-05,
+      "loss": 0.1517,
+      "step": 375
+    },
+    {
+      "epoch": 1.7757009345794392,
+      "grad_norm": 1.015774130821228,
+      "learning_rate": 1.18132391052919e-05,
+      "loss": 0.1397,
+      "step": 380
+    },
+    {
+      "epoch": 1.7990654205607477,
+      "grad_norm": 1.138801097869873,
+      "learning_rate": 1.1436277502437936e-05,
+      "loss": 0.1558,
+      "step": 385
+    },
+    {
+      "epoch": 1.8224299065420562,
+      "grad_norm": 0.9590781927108765,
+      "learning_rate": 1.1061686645276063e-05,
+      "loss": 0.1525,
+      "step": 390
+    },
+    {
+      "epoch": 1.8457943925233646,
+      "grad_norm": 0.9794244170188904,
+      "learning_rate": 1.0689715728198248e-05,
+      "loss": 0.1691,
+      "step": 395
+    },
+    {
+      "epoch": 1.8691588785046729,
+      "grad_norm": 0.8544830083847046,
+      "learning_rate": 1.0320612202696533e-05,
+      "loss": 0.1219,
+      "step": 400
+    },
+    {
+      "epoch": 1.8925233644859814,
+      "grad_norm": 0.9108457565307617,
+      "learning_rate": 9.954621612747371e-06,
+      "loss": 0.1256,
+      "step": 405
+    },
+    {
+      "epoch": 1.9158878504672896,
+      "grad_norm": 1.1352508068084717,
+      "learning_rate": 9.591987431464917e-06,
+      "loss": 0.1258,
+      "step": 410
+    },
+    {
+      "epoch": 1.939252336448598,
+      "grad_norm": 1.080597996711731,
+      "learning_rate": 9.232950899131958e-06,
+      "loss": 0.1461,
+      "step": 415
+    },
+    {
+      "epoch": 1.9626168224299065,
+      "grad_norm": 0.9829815030097961,
+      "learning_rate": 8.877750862716208e-06,
+      "loss": 0.1489,
+      "step": 420
+    },
+    {
+      "epoch": 1.985981308411215,
+      "grad_norm": 0.9096085429191589,
+      "learning_rate": 8.526623616978763e-06,
+      "loss": 0.1271,
+      "step": 425
+    },
+    {
+      "epoch": 2.0093457943925235,
+      "grad_norm": 0.8181402683258057,
+      "learning_rate": 8.179802747280367e-06,
+      "loss": 0.1105,
+      "step": 430
+    },
+    {
+      "epoch": 2.032710280373832,
+      "grad_norm": 0.7595987915992737,
+      "learning_rate": 7.837518974190136e-06,
+      "loss": 0.087,
+      "step": 435
+    },
+    {
+      "epoch": 2.05607476635514,
+      "grad_norm": 0.8177846074104309,
+      "learning_rate": 7.500000000000004e-06,
+      "loss": 0.0917,
+      "step": 440
+    },
+    {
+      "epoch": 2.0794392523364484,
+      "grad_norm": 0.8108243942260742,
+      "learning_rate": 7.167470357247111e-06,
+      "loss": 0.0911,
+      "step": 445
+    },
+    {
+      "epoch": 2.102803738317757,
+      "grad_norm": 0.8202070593833923,
+      "learning_rate": 6.840151259344844e-06,
+      "loss": 0.0893,
+      "step": 450
+    },
+    {
+      "epoch": 2.1261682242990654,
+      "grad_norm": 0.7582007646560669,
+      "learning_rate": 6.5182604534218964e-06,
+      "loss": 0.0998,
+      "step": 455
+    },
+    {
+      "epoch": 2.149532710280374,
+      "grad_norm": 0.8919277191162109,
+      "learning_rate": 6.202012075467255e-06,
+      "loss": 0.0958,
+      "step": 460
+    },
+    {
+      "epoch": 2.1728971962616823,
+      "grad_norm": 0.9116399884223938,
+      "learning_rate": 5.891616507877458e-06,
+      "loss": 0.088,
+      "step": 465
+    },
+    {
+      "epoch": 2.196261682242991,
+      "grad_norm": 0.870235025882721,
+      "learning_rate": 5.587280239500953e-06,
+      "loss": 0.0863,
+      "step": 470
+    },
+    {
+      "epoch": 2.2196261682242993,
+      "grad_norm": 0.9147254824638367,
+      "learning_rate": 5.289205728272587e-06,
+      "loss": 0.0692,
+      "step": 475
+    },
+    {
+      "epoch": 2.2429906542056073,
+      "grad_norm": 0.7716091275215149,
+      "learning_rate": 4.997591266529623e-06,
+      "loss": 0.0872,
+      "step": 480
+    },
+    {
+      "epoch": 2.2663551401869158,
+      "grad_norm": 0.708633303642273,
+      "learning_rate": 4.7126308490989334e-06,
+      "loss": 0.086,
+      "step": 485
+    },
+    {
+      "epoch": 2.289719626168224,
+      "grad_norm": 0.8522292375564575,
+      "learning_rate": 4.434514044243055e-06,
+      "loss": 0.0814,
+      "step": 490
+    },
+    {
+      "epoch": 2.3130841121495327,
+      "grad_norm": 0.6582695841789246,
+      "learning_rate": 4.16342586755102e-06,
+      "loss": 0.0912,
+      "step": 495
+    },
+    {
+      "epoch": 2.336448598130841,
+      "grad_norm": 1.0254162549972534,
+      "learning_rate": 3.899546658857791e-06,
+      "loss": 0.1012,
+      "step": 500
+    },
+    {
+      "epoch": 2.3598130841121496,
+      "grad_norm": 0.6211466789245605,
+      "learning_rate": 3.6430519622742387e-06,
+      "loss": 0.0794,
+      "step": 505
+    },
+    {
+      "epoch": 2.383177570093458,
+      "grad_norm": 0.685267448425293,
+      "learning_rate": 3.394112409407455e-06,
+      "loss": 0.0715,
+      "step": 510
+    },
+    {
+      "epoch": 2.406542056074766,
+      "grad_norm": 0.756571352481842,
+      "learning_rate": 3.152893605849053e-06,
+      "loss": 0.0743,
+      "step": 515
+    },
+    {
+      "epoch": 2.4299065420560746,
+      "grad_norm": 0.584126353263855,
+      "learning_rate": 2.9195560210070117e-06,
+      "loss": 0.0772,
+      "step": 520
+    },
+    {
+      "epoch": 2.453271028037383,
+      "grad_norm": 0.6750658750534058,
+      "learning_rate": 2.6942548813543354e-06,
+      "loss": 0.0705,
+      "step": 525
+    },
+    {
+      "epoch": 2.4766355140186915,
+      "grad_norm": 0.7240349650382996,
+      "learning_rate": 2.4771400671655413e-06,
+      "loss": 0.0669,
+      "step": 530
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.7256758213043213,
+      "learning_rate": 2.268356012809696e-06,
+      "loss": 0.0788,
+      "step": 535
+    },
+    {
+      "epoch": 2.5233644859813085,
+      "grad_norm": 0.6662060618400574,
+      "learning_rate": 2.06804161066626e-06,
+      "loss": 0.0628,
+      "step": 540
+    },
+    {
+      "epoch": 2.546728971962617,
+      "grad_norm": 0.597332775592804,
+      "learning_rate": 1.8763301187277554e-06,
+      "loss": 0.0721,
+      "step": 545
+    },
+    {
+      "epoch": 2.5700934579439254,
+      "grad_norm": 0.7129970788955688,
+      "learning_rate": 1.69334907195067e-06,
+      "loss": 0.083,
+      "step": 550
+    },
+    {
+      "epoch": 2.593457943925234,
+      "grad_norm": 0.6022635698318481,
+      "learning_rate": 1.5192201974135506e-06,
+      "loss": 0.064,
+      "step": 555
+    },
+    {
+      "epoch": 2.616822429906542,
+      "grad_norm": 0.6566118001937866,
+      "learning_rate": 1.354059333338773e-06,
+      "loss": 0.0724,
+      "step": 560
+    },
+    {
+      "epoch": 2.6401869158878504,
+      "grad_norm": 0.5555174350738525,
+      "learning_rate": 1.197976352031851e-06,
+      "loss": 0.068,
+      "step": 565
+    },
+    {
+      "epoch": 2.663551401869159,
+      "grad_norm": 0.6660773754119873,
+      "learning_rate": 1.0510750867895152e-06,
+      "loss": 0.0745,
+      "step": 570
+    },
+    {
+      "epoch": 2.6869158878504673,
+      "grad_norm": 0.7666870355606079,
+      "learning_rate": 9.13453262825209e-07,
+      "loss": 0.0738,
+      "step": 575
+    },
+    {
+      "epoch": 2.710280373831776,
+      "grad_norm": 0.5860276222229004,
+      "learning_rate": 7.852024322579649e-07,
+      "loss": 0.0737,
+      "step": 580
+    },
+    {
+      "epoch": 2.7336448598130842,
+      "grad_norm": 0.5104982852935791,
+      "learning_rate": 6.664079132078881e-07,
+      "loss": 0.0726,
+      "step": 585
+    },
+    {
+      "epoch": 2.7570093457943923,
+      "grad_norm": 0.7017063498497009,
+      "learning_rate": 5.571487330387803e-07,
+      "loss": 0.0717,
+      "step": 590
+    },
+    {
+      "epoch": 2.7803738317757007,
+      "grad_norm": 0.6351404786109924,
+      "learning_rate": 4.574975757856287e-07,
+      "loss": 0.0732,
+      "step": 595
+    },
+    {
+      "epoch": 2.803738317757009,
+      "grad_norm": 0.6491110324859619,
+      "learning_rate": 3.6752073380198314e-07,
+      "loss": 0.0651,
+      "step": 600
+    },
+    {
+      "epoch": 2.8271028037383177,
+      "grad_norm": 0.7560405135154724,
+      "learning_rate": 2.8727806365935806e-07,
+      "loss": 0.0739,
+      "step": 605
+    },
+    {
+      "epoch": 2.850467289719626,
+      "grad_norm": 0.6051733493804932,
+      "learning_rate": 2.1682294632798582e-07,
+      "loss": 0.068,
+      "step": 610
+    },
+    {
+      "epoch": 2.8738317757009346,
+      "grad_norm": 0.6319546699523926,
+      "learning_rate": 1.5620225166544155e-07,
+      "loss": 0.0635,
+      "step": 615
+    },
+    {
+      "epoch": 2.897196261682243,
+      "grad_norm": 0.5380659699440002,
+      "learning_rate": 1.0545630723674093e-07,
+      "loss": 0.066,
+      "step": 620
+    },
+    {
+      "epoch": 2.9205607476635516,
+      "grad_norm": 0.5821147561073303,
+      "learning_rate": 6.461887148666523e-08,
+      "loss": 0.0655,
+      "step": 625
+    },
+    {
+      "epoch": 2.94392523364486,
+      "grad_norm": 0.6386025547981262,
+      "learning_rate": 3.371711128214883e-08,
+      "loss": 0.073,
+      "step": 630
+    },
+    {
+      "epoch": 2.9672897196261685,
+      "grad_norm": 0.6391260623931885,
+      "learning_rate": 1.2771583839679136e-08,
+      "loss": 0.0668,
+      "step": 635
+    },
+    {
+      "epoch": 2.9906542056074765,
+      "grad_norm": 0.5918943881988525,
+      "learning_rate": 1.7962230497275966e-09,
+      "loss": 0.069,
+      "step": 640
+    },
+    {
+      "epoch": 3.0,
+      "step": 642,
+      "total_flos": 8.181798015200133e+17,
+      "train_loss": 0.3922736724356996,
+      "train_runtime": 396.0022,
+      "train_samples_per_second": 51.78,
+      "train_steps_per_second": 1.621
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 642,
+  "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": 8.181798015200133e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

114_128_e3_3e-5/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfa3fec68087ad63044416f0b43b54517455058c070544ecf700b084f5d58b30
+size 8273