Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- granite3.3/hotpotqa_skill_paraphrase_4_base/64_e1_3.0e-05/adapter_config.json +39 -0
- granite3.3/hotpotqa_skill_paraphrase_4_base/64_e1_3.0e-05/adapter_model.safetensors +3 -0
- granite3.3/hotpotqa_skill_paraphrase_4_base/64_e1_3.0e-05/added_tokens.json +9 -0
- granite3.3/hotpotqa_skill_paraphrase_4_base/64_e1_3.0e-05/all_results.json +9 -0
- granite3.3/hotpotqa_skill_paraphrase_4_base/64_e1_3.0e-05/chat_template.jinja +62 -0
- granite3.3/hotpotqa_skill_paraphrase_4_base/64_e1_3.0e-05/config.json +32 -0
- granite3.3/hotpotqa_skill_paraphrase_4_base/64_e1_3.0e-05/generation_config.json +7 -0
- granite3.3/hotpotqa_skill_paraphrase_4_base/64_e1_3.0e-05/merges.txt +0 -0
- granite3.3/hotpotqa_skill_paraphrase_4_base/64_e1_3.0e-05/special_tokens_map.json +33 -0
- granite3.3/hotpotqa_skill_paraphrase_4_base/64_e1_3.0e-05/tokenizer.json +0 -0
- granite3.3/hotpotqa_skill_paraphrase_4_base/64_e1_3.0e-05/tokenizer_config.json +234 -0
- granite3.3/hotpotqa_skill_paraphrase_4_base/64_e1_3.0e-05/train_results.json +9 -0
- granite3.3/hotpotqa_skill_paraphrase_4_base/64_e1_3.0e-05/trainer_state.json +295 -0
- granite3.3/hotpotqa_skill_paraphrase_4_base/64_e1_3.0e-05/training_args.bin +3 -0
- granite3.3/hotpotqa_skill_paraphrase_4_base/64_e1_3.0e-05/vocab.json +0 -0
- granite3.3/hotpotqa_skill_paraphrase_4_instruct/64_e1_3.0e-05/adapter_config.json +39 -0
- granite3.3/hotpotqa_skill_paraphrase_4_instruct/64_e1_3.0e-05/adapter_model.safetensors +3 -0
- granite3.3/hotpotqa_skill_paraphrase_4_instruct/64_e1_3.0e-05/added_tokens.json +9 -0
- granite3.3/hotpotqa_skill_paraphrase_4_instruct/64_e1_3.0e-05/all_results.json +9 -0
- granite3.3/hotpotqa_skill_paraphrase_4_instruct/64_e1_3.0e-05/chat_template.jinja +62 -0
- granite3.3/hotpotqa_skill_paraphrase_4_instruct/64_e1_3.0e-05/config.json +32 -0
- granite3.3/hotpotqa_skill_paraphrase_4_instruct/64_e1_3.0e-05/generation_config.json +7 -0
- granite3.3/hotpotqa_skill_paraphrase_4_instruct/64_e1_3.0e-05/merges.txt +0 -0
- granite3.3/hotpotqa_skill_paraphrase_4_instruct/64_e1_3.0e-05/special_tokens_map.json +33 -0
- granite3.3/hotpotqa_skill_paraphrase_4_instruct/64_e1_3.0e-05/tokenizer.json +0 -0
- granite3.3/hotpotqa_skill_paraphrase_4_instruct/64_e1_3.0e-05/tokenizer_config.json +234 -0
- granite3.3/hotpotqa_skill_paraphrase_4_instruct/64_e1_3.0e-05/train_results.json +9 -0
- granite3.3/hotpotqa_skill_paraphrase_4_instruct/64_e1_3.0e-05/trainer_state.json +295 -0
- granite3.3/hotpotqa_skill_paraphrase_4_instruct/64_e1_3.0e-05/training_args.bin +3 -0
- granite3.3/hotpotqa_skill_paraphrase_4_instruct/64_e1_3.0e-05/vocab.json +0 -0
- granite3.3/hotpotqa_test_knowledge_50_base/0_128_e3_3e-5/README.md +63 -0
- granite3.3/hotpotqa_test_knowledge_50_base/0_128_e3_3e-5/adapter_config.json +39 -0
- granite3.3/hotpotqa_test_knowledge_50_base/0_128_e3_3e-5/adapter_model.safetensors +3 -0
- granite3.3/hotpotqa_test_knowledge_50_base/0_128_e3_3e-5/all_results.json +9 -0
- granite3.3/hotpotqa_test_knowledge_50_base/0_128_e3_3e-5/config.json +32 -0
- granite3.3/hotpotqa_test_knowledge_50_base/0_128_e3_3e-5/merges.txt +0 -0
- granite3.3/hotpotqa_test_knowledge_50_base/0_128_e3_3e-5/special_tokens_map.json +45 -0
- granite3.3/hotpotqa_test_knowledge_50_base/0_128_e3_3e-5/tokenizer.json +0 -0
- granite3.3/hotpotqa_test_knowledge_50_base/0_128_e3_3e-5/tokenizer_config.json +188 -0
- granite3.3/hotpotqa_test_knowledge_50_base/0_128_e3_3e-5/train_results.json +9 -0
- granite3.3/hotpotqa_test_knowledge_50_base/0_128_e3_3e-5/trainer_state.json +1786 -0
- granite3.3/hotpotqa_test_knowledge_50_base/0_128_e3_3e-5/training_args.bin +3 -0
- granite3.3/hotpotqa_test_knowledge_50_base/0_128_e3_3e-5/vocab.json +0 -0
- granite3.3/hotpotqa_test_knowledge_50_base/1_128_e3_3e-5/README.md +63 -0
- granite3.3/hotpotqa_test_knowledge_50_base/1_128_e3_3e-5/adapter_config.json +39 -0
- granite3.3/hotpotqa_test_knowledge_50_base/1_128_e3_3e-5/adapter_model.safetensors +3 -0
- granite3.3/hotpotqa_test_knowledge_50_base/1_128_e3_3e-5/all_results.json +9 -0
- granite3.3/hotpotqa_test_knowledge_50_base/1_128_e3_3e-5/config.json +32 -0
- granite3.3/hotpotqa_test_knowledge_50_base/1_128_e3_3e-5/merges.txt +0 -0
- granite3.3/hotpotqa_test_knowledge_50_base/1_128_e3_3e-5/special_tokens_map.json +45 -0
granite3.3/hotpotqa_skill_paraphrase_4_base/64_e1_3.0e-05/adapter_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "ibm-granite/granite-3.3-8b-Instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": false,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 128,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.05,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 64,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"down_proj",
|
| 28 |
+
"o_proj",
|
| 29 |
+
"q_proj",
|
| 30 |
+
"k_proj",
|
| 31 |
+
"v_proj",
|
| 32 |
+
"up_proj",
|
| 33 |
+
"gate_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
+
"use_dora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
granite3.3/hotpotqa_skill_paraphrase_4_base/64_e1_3.0e-05/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71fbe9f5ddafa2e73f048349540563218666adf74e28543f1e5184d736286420
|
| 3 |
+
size 395913544
|
granite3.3/hotpotqa_skill_paraphrase_4_base/64_e1_3.0e-05/added_tokens.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|end_of_cite|>": 49156,
|
| 3 |
+
"<|end_of_plugin|>": 49158,
|
| 4 |
+
"<|end_of_role|>": 49153,
|
| 5 |
+
"<|start_of_cite|>": 49155,
|
| 6 |
+
"<|start_of_plugin|>": 49157,
|
| 7 |
+
"<|start_of_role|>": 49152,
|
| 8 |
+
"<|tool_call|>": 49154
|
| 9 |
+
}
|
granite3.3/hotpotqa_skill_paraphrase_4_base/64_e1_3.0e-05/all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 5.421179522126971e+17,
|
| 4 |
+
"train_loss": 1.5224524868859186,
|
| 5 |
+
"train_runtime": 209.6484,
|
| 6 |
+
"train_samples": 2871,
|
| 7 |
+
"train_samples_per_second": 13.694,
|
| 8 |
+
"train_steps_per_second": 0.859
|
| 9 |
+
}
|
granite3.3/hotpotqa_skill_paraphrase_4_base/64_e1_3.0e-05/chat_template.jinja
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{# Alias tools -> available_tools #}
|
| 2 |
+
{%- if tools and not available_tools -%}
|
| 3 |
+
{%- set available_tools = tools -%}
|
| 4 |
+
{%- endif -%}
|
| 5 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 6 |
+
{%- set system_message = messages[0]['content'] %}
|
| 7 |
+
{%- set loop_messages = messages[1:] %}
|
| 8 |
+
{%- else %}
|
| 9 |
+
{%- set system_message = "Knowledge Cutoff Date: April 2024.
|
| 10 |
+
Today's Date: " + strftime_now('%B %d, %Y') + ".
|
| 11 |
+
You are Granite, developed by IBM." %}
|
| 12 |
+
{%- if available_tools and documents %}
|
| 13 |
+
{%- 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.
|
| 14 |
+
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." %}
|
| 15 |
+
{%- elif available_tools %}
|
| 16 |
+
{%- 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." %}
|
| 17 |
+
{%- elif documents %}
|
| 18 |
+
{%- 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." %}
|
| 19 |
+
{%- elif thinking %}
|
| 20 |
+
{%- set system_message = system_message + " You are a helpful AI assistant.
|
| 21 |
+
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." %}
|
| 22 |
+
{%- else %}
|
| 23 |
+
{%- set system_message = system_message + " You are a helpful AI assistant." %}
|
| 24 |
+
{%- endif %}
|
| 25 |
+
{%- if 'citations' in controls and documents %}
|
| 26 |
+
{%- set system_message = system_message + '
|
| 27 |
+
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.' %}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{%- if 'hallucinations' in controls and documents %}
|
| 30 |
+
{%- set system_message = system_message + '
|
| 31 |
+
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.' %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{%- set loop_messages = messages %}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{{- '<|start_of_role|>system<|end_of_role|>' + system_message + '<|end_of_text|>
|
| 36 |
+
' }}
|
| 37 |
+
{%- if available_tools %}
|
| 38 |
+
{{- '<|start_of_role|>available_tools<|end_of_role|>' }}
|
| 39 |
+
{{- available_tools | tojson(indent=4) }}
|
| 40 |
+
{{- '<|end_of_text|>
|
| 41 |
+
' }}
|
| 42 |
+
{%- endif %}
|
| 43 |
+
{%- if documents %}
|
| 44 |
+
{%- for document in documents %}
|
| 45 |
+
{{- '<|start_of_role|>document {"document_id": "' + document['doc_id'] | string + '"}<|end_of_role|>
|
| 46 |
+
' }}
|
| 47 |
+
{{- document['text'] }}
|
| 48 |
+
{{- '<|end_of_text|>
|
| 49 |
+
' }}
|
| 50 |
+
{%- endfor %}
|
| 51 |
+
{%- endif %}
|
| 52 |
+
{%- for message in loop_messages %}
|
| 53 |
+
{{- '<|start_of_role|>' + message['role'] + '<|end_of_role|>' + message['content'] + '<|end_of_text|>
|
| 54 |
+
' }}
|
| 55 |
+
{%- if loop.last and add_generation_prompt %}
|
| 56 |
+
{{- '<|start_of_role|>assistant' }}
|
| 57 |
+
{%- if controls %}
|
| 58 |
+
{{- ' ' + controls | tojson()}}
|
| 59 |
+
{%- endif %}
|
| 60 |
+
{{- '<|end_of_role|>' }}
|
| 61 |
+
{%- endif %}
|
| 62 |
+
{%- endfor %}
|
granite3.3/hotpotqa_skill_paraphrase_4_base/64_e1_3.0e-05/config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"GraniteForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"attention_multiplier": 0.0078125,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"embedding_multiplier": 12.0,
|
| 10 |
+
"eos_token_id": 0,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 4096,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 12800,
|
| 15 |
+
"logits_scaling": 16.0,
|
| 16 |
+
"max_position_embeddings": 131072,
|
| 17 |
+
"mlp_bias": false,
|
| 18 |
+
"model_type": "granite",
|
| 19 |
+
"num_attention_heads": 32,
|
| 20 |
+
"num_hidden_layers": 40,
|
| 21 |
+
"num_key_value_heads": 8,
|
| 22 |
+
"pad_token_id": 0,
|
| 23 |
+
"residual_multiplier": 0.22,
|
| 24 |
+
"rms_norm_eps": 1e-05,
|
| 25 |
+
"rope_scaling": null,
|
| 26 |
+
"rope_theta": 10000000.0,
|
| 27 |
+
"tie_word_embeddings": true,
|
| 28 |
+
"torch_dtype": "bfloat16",
|
| 29 |
+
"transformers_version": "4.52.4",
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 49159
|
| 32 |
+
}
|
granite3.3/hotpotqa_skill_paraphrase_4_base/64_e1_3.0e-05/generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 0,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.52.4"
|
| 7 |
+
}
|
granite3.3/hotpotqa_skill_paraphrase_4_base/64_e1_3.0e-05/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
granite3.3/hotpotqa_skill_paraphrase_4_base/64_e1_3.0e-05/special_tokens_map.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|start_of_role|>",
|
| 4 |
+
"<|end_of_role|>",
|
| 5 |
+
"<|tool_call|>",
|
| 6 |
+
"<|start_of_cite|>",
|
| 7 |
+
"<|end_of_cite|>",
|
| 8 |
+
"<|start_of_plugin|>",
|
| 9 |
+
"<|end_of_plugin|>"
|
| 10 |
+
],
|
| 11 |
+
"bos_token": {
|
| 12 |
+
"content": "<|end_of_text|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false
|
| 17 |
+
},
|
| 18 |
+
"eos_token": {
|
| 19 |
+
"content": "<|end_of_text|>",
|
| 20 |
+
"lstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
+
"rstrip": false,
|
| 23 |
+
"single_word": false
|
| 24 |
+
},
|
| 25 |
+
"pad_token": "<|end_of_plugin|>",
|
| 26 |
+
"unk_token": {
|
| 27 |
+
"content": "<|end_of_text|>",
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"normalized": false,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"single_word": false
|
| 32 |
+
}
|
| 33 |
+
}
|
granite3.3/hotpotqa_skill_paraphrase_4_base/64_e1_3.0e-05/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
granite3.3/hotpotqa_skill_paraphrase_4_base/64_e1_3.0e-05/tokenizer_config.json
ADDED
|
@@ -0,0 +1,234 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<|end_of_text|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<fim_prefix>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "<fim_middle>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"3": {
|
| 30 |
+
"content": "<fim_suffix>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"4": {
|
| 38 |
+
"content": "<fim_pad>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"5": {
|
| 46 |
+
"content": "<filename>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"6": {
|
| 54 |
+
"content": "<gh_stars>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"7": {
|
| 62 |
+
"content": "<issue_start>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"8": {
|
| 70 |
+
"content": "<issue_comment>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"9": {
|
| 78 |
+
"content": "<issue_closed>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"10": {
|
| 86 |
+
"content": "<jupyter_start>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"11": {
|
| 94 |
+
"content": "<jupyter_text>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"12": {
|
| 102 |
+
"content": "<jupyter_code>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"13": {
|
| 110 |
+
"content": "<jupyter_output>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"14": {
|
| 118 |
+
"content": "<empty_output>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": true
|
| 124 |
+
},
|
| 125 |
+
"15": {
|
| 126 |
+
"content": "<commit_before>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": true
|
| 132 |
+
},
|
| 133 |
+
"16": {
|
| 134 |
+
"content": "<commit_msg>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": true
|
| 140 |
+
},
|
| 141 |
+
"17": {
|
| 142 |
+
"content": "<commit_after>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": true
|
| 148 |
+
},
|
| 149 |
+
"18": {
|
| 150 |
+
"content": "<reponame>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": true
|
| 156 |
+
},
|
| 157 |
+
"49152": {
|
| 158 |
+
"content": "<|start_of_role|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": true
|
| 164 |
+
},
|
| 165 |
+
"49153": {
|
| 166 |
+
"content": "<|end_of_role|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": true
|
| 172 |
+
},
|
| 173 |
+
"49154": {
|
| 174 |
+
"content": "<|tool_call|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": true
|
| 180 |
+
},
|
| 181 |
+
"49155": {
|
| 182 |
+
"content": "<|start_of_cite|>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": true
|
| 188 |
+
},
|
| 189 |
+
"49156": {
|
| 190 |
+
"content": "<|end_of_cite|>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": true
|
| 196 |
+
},
|
| 197 |
+
"49157": {
|
| 198 |
+
"content": "<|start_of_plugin|>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": true
|
| 204 |
+
},
|
| 205 |
+
"49158": {
|
| 206 |
+
"content": "<|end_of_plugin|>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": true
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|start_of_role|>",
|
| 216 |
+
"<|end_of_role|>",
|
| 217 |
+
"<|tool_call|>",
|
| 218 |
+
"<|start_of_cite|>",
|
| 219 |
+
"<|end_of_cite|>",
|
| 220 |
+
"<|start_of_plugin|>",
|
| 221 |
+
"<|end_of_plugin|>"
|
| 222 |
+
],
|
| 223 |
+
"bos_token": "<|end_of_text|>",
|
| 224 |
+
"clean_up_tokenization_spaces": true,
|
| 225 |
+
"eos_token": "<|end_of_text|>",
|
| 226 |
+
"errors": "replace",
|
| 227 |
+
"extra_special_tokens": {},
|
| 228 |
+
"model_max_length": 8192,
|
| 229 |
+
"pad_token": "<|end_of_plugin|>",
|
| 230 |
+
"padding_side": "left",
|
| 231 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 232 |
+
"unk_token": "<|end_of_text|>",
|
| 233 |
+
"vocab_size": 49152
|
| 234 |
+
}
|
granite3.3/hotpotqa_skill_paraphrase_4_base/64_e1_3.0e-05/train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 5.421179522126971e+17,
|
| 4 |
+
"train_loss": 1.5224524868859186,
|
| 5 |
+
"train_runtime": 209.6484,
|
| 6 |
+
"train_samples": 2871,
|
| 7 |
+
"train_samples_per_second": 13.694,
|
| 8 |
+
"train_steps_per_second": 0.859
|
| 9 |
+
}
|
granite3.3/hotpotqa_skill_paraphrase_4_base/64_e1_3.0e-05/trainer_state.json
ADDED
|
@@ -0,0 +1,295 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 180,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.027855153203342618,
|
| 14 |
+
"grad_norm": 109.04389953613281,
|
| 15 |
+
"learning_rate": 6.666666666666667e-06,
|
| 16 |
+
"loss": 8.2158,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.055710306406685235,
|
| 21 |
+
"grad_norm": 45.263702392578125,
|
| 22 |
+
"learning_rate": 1.5e-05,
|
| 23 |
+
"loss": 5.5257,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.08356545961002786,
|
| 28 |
+
"grad_norm": 46.228538513183594,
|
| 29 |
+
"learning_rate": 2.3333333333333336e-05,
|
| 30 |
+
"loss": 3.5748,
|
| 31 |
+
"step": 15
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.11142061281337047,
|
| 35 |
+
"grad_norm": 19.68198585510254,
|
| 36 |
+
"learning_rate": 2.999717955672752e-05,
|
| 37 |
+
"loss": 2.5717,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.1392757660167131,
|
| 42 |
+
"grad_norm": 16.285852432250977,
|
| 43 |
+
"learning_rate": 2.9898575366129145e-05,
|
| 44 |
+
"loss": 1.7306,
|
| 45 |
+
"step": 25
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.1671309192200557,
|
| 49 |
+
"grad_norm": 17.22920799255371,
|
| 50 |
+
"learning_rate": 2.9660007873759537e-05,
|
| 51 |
+
"loss": 1.8033,
|
| 52 |
+
"step": 30
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.19498607242339833,
|
| 56 |
+
"grad_norm": 14.04590892791748,
|
| 57 |
+
"learning_rate": 2.928371828007623e-05,
|
| 58 |
+
"loss": 1.7235,
|
| 59 |
+
"step": 35
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.22284122562674094,
|
| 63 |
+
"grad_norm": 11.508750915527344,
|
| 64 |
+
"learning_rate": 2.877324160320411e-05,
|
| 65 |
+
"loss": 1.5581,
|
| 66 |
+
"step": 40
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.25069637883008355,
|
| 70 |
+
"grad_norm": 8.927129745483398,
|
| 71 |
+
"learning_rate": 2.8133373469531362e-05,
|
| 72 |
+
"loss": 1.7076,
|
| 73 |
+
"step": 45
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.2785515320334262,
|
| 77 |
+
"grad_norm": 11.466785430908203,
|
| 78 |
+
"learning_rate": 2.7370125061636605e-05,
|
| 79 |
+
"loss": 1.2535,
|
| 80 |
+
"step": 50
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.3064066852367688,
|
| 84 |
+
"grad_norm": 7.3343095779418945,
|
| 85 |
+
"learning_rate": 2.649066664678467e-05,
|
| 86 |
+
"loss": 1.2799,
|
| 87 |
+
"step": 55
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.3342618384401114,
|
| 91 |
+
"grad_norm": 8.947710037231445,
|
| 92 |
+
"learning_rate": 2.5503260216507528e-05,
|
| 93 |
+
"loss": 1.2821,
|
| 94 |
+
"step": 60
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.362116991643454,
|
| 98 |
+
"grad_norm": 9.888595581054688,
|
| 99 |
+
"learning_rate": 2.441718187008148e-05,
|
| 100 |
+
"loss": 1.2928,
|
| 101 |
+
"step": 65
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.38997214484679665,
|
| 105 |
+
"grad_norm": 12.757842063903809,
|
| 106 |
+
"learning_rate": 2.324263467106209e-05,
|
| 107 |
+
"loss": 1.2693,
|
| 108 |
+
"step": 70
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.4178272980501393,
|
| 112 |
+
"grad_norm": 9.170050621032715,
|
| 113 |
+
"learning_rate": 2.1990652795538085e-05,
|
| 114 |
+
"loss": 1.1103,
|
| 115 |
+
"step": 75
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.4456824512534819,
|
| 119 |
+
"grad_norm": 8.47827434539795,
|
| 120 |
+
"learning_rate": 2.0672997872574638e-05,
|
| 121 |
+
"loss": 1.2,
|
| 122 |
+
"step": 80
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.4735376044568245,
|
| 126 |
+
"grad_norm": 8.74962329864502,
|
| 127 |
+
"learning_rate": 1.9302048490666356e-05,
|
| 128 |
+
"loss": 1.1675,
|
| 129 |
+
"step": 85
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.5013927576601671,
|
| 133 |
+
"grad_norm": 10.761241912841797,
|
| 134 |
+
"learning_rate": 1.789068390822135e-05,
|
| 135 |
+
"loss": 1.3508,
|
| 136 |
+
"step": 90
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.5292479108635098,
|
| 140 |
+
"grad_norm": 7.833252906799316,
|
| 141 |
+
"learning_rate": 1.6452163060547687e-05,
|
| 142 |
+
"loss": 1.0017,
|
| 143 |
+
"step": 95
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.5571030640668524,
|
| 147 |
+
"grad_norm": 8.034213066101074,
|
| 148 |
+
"learning_rate": 1.5e-05,
|
| 149 |
+
"loss": 1.1291,
|
| 150 |
+
"step": 100
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.584958217270195,
|
| 154 |
+
"grad_norm": 8.789913177490234,
|
| 155 |
+
"learning_rate": 1.3547836939452315e-05,
|
| 156 |
+
"loss": 0.9142,
|
| 157 |
+
"step": 105
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.6128133704735376,
|
| 161 |
+
"grad_norm": 9.596579551696777,
|
| 162 |
+
"learning_rate": 1.2109316091778652e-05,
|
| 163 |
+
"loss": 0.9676,
|
| 164 |
+
"step": 110
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.6406685236768802,
|
| 168 |
+
"grad_norm": 10.293736457824707,
|
| 169 |
+
"learning_rate": 1.069795150933365e-05,
|
| 170 |
+
"loss": 0.9773,
|
| 171 |
+
"step": 115
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.6685236768802229,
|
| 175 |
+
"grad_norm": 11.923694610595703,
|
| 176 |
+
"learning_rate": 9.327002127425364e-06,
|
| 177 |
+
"loss": 1.0306,
|
| 178 |
+
"step": 120
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.6963788300835655,
|
| 182 |
+
"grad_norm": 6.11435079574585,
|
| 183 |
+
"learning_rate": 8.009347204461922e-06,
|
| 184 |
+
"loss": 0.5947,
|
| 185 |
+
"step": 125
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.724233983286908,
|
| 189 |
+
"grad_norm": 9.760638236999512,
|
| 190 |
+
"learning_rate": 6.75736532893791e-06,
|
| 191 |
+
"loss": 0.9825,
|
| 192 |
+
"step": 130
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.7520891364902507,
|
| 196 |
+
"grad_norm": 8.288309097290039,
|
| 197 |
+
"learning_rate": 5.582818129918525e-06,
|
| 198 |
+
"loss": 0.8286,
|
| 199 |
+
"step": 135
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.7799442896935933,
|
| 203 |
+
"grad_norm": 7.735269069671631,
|
| 204 |
+
"learning_rate": 4.496739783492473e-06,
|
| 205 |
+
"loss": 0.7621,
|
| 206 |
+
"step": 140
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.807799442896936,
|
| 210 |
+
"grad_norm": 10.805869102478027,
|
| 211 |
+
"learning_rate": 3.5093333532153316e-06,
|
| 212 |
+
"loss": 0.7373,
|
| 213 |
+
"step": 145
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.8356545961002786,
|
| 217 |
+
"grad_norm": 7.783030033111572,
|
| 218 |
+
"learning_rate": 2.6298749383633987e-06,
|
| 219 |
+
"loss": 0.7113,
|
| 220 |
+
"step": 150
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.8635097493036211,
|
| 224 |
+
"grad_norm": 10.817440032958984,
|
| 225 |
+
"learning_rate": 1.8666265304686387e-06,
|
| 226 |
+
"loss": 0.7279,
|
| 227 |
+
"step": 155
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.8913649025069638,
|
| 231 |
+
"grad_norm": 9.175583839416504,
|
| 232 |
+
"learning_rate": 1.2267583967958918e-06,
|
| 233 |
+
"loss": 0.7935,
|
| 234 |
+
"step": 160
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.9192200557103064,
|
| 238 |
+
"grad_norm": 8.405351638793945,
|
| 239 |
+
"learning_rate": 7.162817199237703e-07,
|
| 240 |
+
"loss": 0.9017,
|
| 241 |
+
"step": 165
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.947075208913649,
|
| 245 |
+
"grad_norm": 7.8916521072387695,
|
| 246 |
+
"learning_rate": 3.399921262404665e-07,
|
| 247 |
+
"loss": 0.8397,
|
| 248 |
+
"step": 170
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.9749303621169917,
|
| 252 |
+
"grad_norm": 8.173842430114746,
|
| 253 |
+
"learning_rate": 1.0142463387085465e-07,
|
| 254 |
+
"loss": 0.8007,
|
| 255 |
+
"step": 175
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.0,
|
| 259 |
+
"grad_norm": 4.2151923179626465,
|
| 260 |
+
"learning_rate": 2.8204432724798777e-09,
|
| 261 |
+
"loss": 0.4907,
|
| 262 |
+
"step": 180
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.0,
|
| 266 |
+
"step": 180,
|
| 267 |
+
"total_flos": 5.421179522126971e+17,
|
| 268 |
+
"train_loss": 1.5224524868859186,
|
| 269 |
+
"train_runtime": 209.6484,
|
| 270 |
+
"train_samples_per_second": 13.694,
|
| 271 |
+
"train_steps_per_second": 0.859
|
| 272 |
+
}
|
| 273 |
+
],
|
| 274 |
+
"logging_steps": 5,
|
| 275 |
+
"max_steps": 180,
|
| 276 |
+
"num_input_tokens_seen": 0,
|
| 277 |
+
"num_train_epochs": 1,
|
| 278 |
+
"save_steps": 500,
|
| 279 |
+
"stateful_callbacks": {
|
| 280 |
+
"TrainerControl": {
|
| 281 |
+
"args": {
|
| 282 |
+
"should_epoch_stop": false,
|
| 283 |
+
"should_evaluate": false,
|
| 284 |
+
"should_log": false,
|
| 285 |
+
"should_save": false,
|
| 286 |
+
"should_training_stop": false
|
| 287 |
+
},
|
| 288 |
+
"attributes": {}
|
| 289 |
+
}
|
| 290 |
+
},
|
| 291 |
+
"total_flos": 5.421179522126971e+17,
|
| 292 |
+
"train_batch_size": 1,
|
| 293 |
+
"trial_name": null,
|
| 294 |
+
"trial_params": null
|
| 295 |
+
}
|
granite3.3/hotpotqa_skill_paraphrase_4_base/64_e1_3.0e-05/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0f3e6347c0927b511cfeda28264c86a654927f8d68451fd4b48834467cda501
|
| 3 |
+
size 8017
|
granite3.3/hotpotqa_skill_paraphrase_4_base/64_e1_3.0e-05/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
granite3.3/hotpotqa_skill_paraphrase_4_instruct/64_e1_3.0e-05/adapter_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "ibm-granite/granite-3.3-8b-instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": false,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 128,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.05,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 64,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"q_proj",
|
| 28 |
+
"v_proj",
|
| 29 |
+
"k_proj",
|
| 30 |
+
"down_proj",
|
| 31 |
+
"up_proj",
|
| 32 |
+
"o_proj",
|
| 33 |
+
"gate_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
+
"use_dora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
granite3.3/hotpotqa_skill_paraphrase_4_instruct/64_e1_3.0e-05/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:38c48e2a3ae503db9493cdf06668ad9973de42fd1bd0f3baffeb47bee5b0e6c5
|
| 3 |
+
size 395913544
|
granite3.3/hotpotqa_skill_paraphrase_4_instruct/64_e1_3.0e-05/added_tokens.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|end_of_cite|>": 49156,
|
| 3 |
+
"<|end_of_plugin|>": 49158,
|
| 4 |
+
"<|end_of_role|>": 49153,
|
| 5 |
+
"<|start_of_cite|>": 49155,
|
| 6 |
+
"<|start_of_plugin|>": 49157,
|
| 7 |
+
"<|start_of_role|>": 49152,
|
| 8 |
+
"<|tool_call|>": 49154
|
| 9 |
+
}
|
granite3.3/hotpotqa_skill_paraphrase_4_instruct/64_e1_3.0e-05/all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 5.421179522126971e+17,
|
| 4 |
+
"train_loss": 1.4018334786097209,
|
| 5 |
+
"train_runtime": 211.1842,
|
| 6 |
+
"train_samples": 2871,
|
| 7 |
+
"train_samples_per_second": 13.595,
|
| 8 |
+
"train_steps_per_second": 0.852
|
| 9 |
+
}
|
granite3.3/hotpotqa_skill_paraphrase_4_instruct/64_e1_3.0e-05/chat_template.jinja
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{# Alias tools -> available_tools #}
|
| 2 |
+
{%- if tools and not available_tools -%}
|
| 3 |
+
{%- set available_tools = tools -%}
|
| 4 |
+
{%- endif -%}
|
| 5 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 6 |
+
{%- set system_message = messages[0]['content'] %}
|
| 7 |
+
{%- set loop_messages = messages[1:] %}
|
| 8 |
+
{%- else %}
|
| 9 |
+
{%- set system_message = "Knowledge Cutoff Date: April 2024.
|
| 10 |
+
Today's Date: " + strftime_now('%B %d, %Y') + ".
|
| 11 |
+
You are Granite, developed by IBM." %}
|
| 12 |
+
{%- if available_tools and documents %}
|
| 13 |
+
{%- 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.
|
| 14 |
+
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." %}
|
| 15 |
+
{%- elif available_tools %}
|
| 16 |
+
{%- 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." %}
|
| 17 |
+
{%- elif documents %}
|
| 18 |
+
{%- 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." %}
|
| 19 |
+
{%- elif thinking %}
|
| 20 |
+
{%- set system_message = system_message + " You are a helpful AI assistant.
|
| 21 |
+
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." %}
|
| 22 |
+
{%- else %}
|
| 23 |
+
{%- set system_message = system_message + " You are a helpful AI assistant." %}
|
| 24 |
+
{%- endif %}
|
| 25 |
+
{%- if 'citations' in controls and documents %}
|
| 26 |
+
{%- set system_message = system_message + '
|
| 27 |
+
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.' %}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{%- if 'hallucinations' in controls and documents %}
|
| 30 |
+
{%- set system_message = system_message + '
|
| 31 |
+
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.' %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{%- set loop_messages = messages %}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{{- '<|start_of_role|>system<|end_of_role|>' + system_message + '<|end_of_text|>
|
| 36 |
+
' }}
|
| 37 |
+
{%- if available_tools %}
|
| 38 |
+
{{- '<|start_of_role|>available_tools<|end_of_role|>' }}
|
| 39 |
+
{{- available_tools | tojson(indent=4) }}
|
| 40 |
+
{{- '<|end_of_text|>
|
| 41 |
+
' }}
|
| 42 |
+
{%- endif %}
|
| 43 |
+
{%- if documents %}
|
| 44 |
+
{%- for document in documents %}
|
| 45 |
+
{{- '<|start_of_role|>document {"document_id": "' + document['doc_id'] | string + '"}<|end_of_role|>
|
| 46 |
+
' }}
|
| 47 |
+
{{- document['text'] }}
|
| 48 |
+
{{- '<|end_of_text|>
|
| 49 |
+
' }}
|
| 50 |
+
{%- endfor %}
|
| 51 |
+
{%- endif %}
|
| 52 |
+
{%- for message in loop_messages %}
|
| 53 |
+
{{- '<|start_of_role|>' + message['role'] + '<|end_of_role|>' + message['content'] + '<|end_of_text|>
|
| 54 |
+
' }}
|
| 55 |
+
{%- if loop.last and add_generation_prompt %}
|
| 56 |
+
{{- '<|start_of_role|>assistant' }}
|
| 57 |
+
{%- if controls %}
|
| 58 |
+
{{- ' ' + controls | tojson()}}
|
| 59 |
+
{%- endif %}
|
| 60 |
+
{{- '<|end_of_role|>' }}
|
| 61 |
+
{%- endif %}
|
| 62 |
+
{%- endfor %}
|
granite3.3/hotpotqa_skill_paraphrase_4_instruct/64_e1_3.0e-05/config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"GraniteForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"attention_multiplier": 0.0078125,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"embedding_multiplier": 12.0,
|
| 10 |
+
"eos_token_id": 0,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 4096,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 12800,
|
| 15 |
+
"logits_scaling": 16.0,
|
| 16 |
+
"max_position_embeddings": 131072,
|
| 17 |
+
"mlp_bias": false,
|
| 18 |
+
"model_type": "granite",
|
| 19 |
+
"num_attention_heads": 32,
|
| 20 |
+
"num_hidden_layers": 40,
|
| 21 |
+
"num_key_value_heads": 8,
|
| 22 |
+
"pad_token_id": 0,
|
| 23 |
+
"residual_multiplier": 0.22,
|
| 24 |
+
"rms_norm_eps": 1e-05,
|
| 25 |
+
"rope_scaling": null,
|
| 26 |
+
"rope_theta": 10000000.0,
|
| 27 |
+
"tie_word_embeddings": true,
|
| 28 |
+
"torch_dtype": "bfloat16",
|
| 29 |
+
"transformers_version": "4.52.4",
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 49159
|
| 32 |
+
}
|
granite3.3/hotpotqa_skill_paraphrase_4_instruct/64_e1_3.0e-05/generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 0,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.52.4"
|
| 7 |
+
}
|
granite3.3/hotpotqa_skill_paraphrase_4_instruct/64_e1_3.0e-05/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
granite3.3/hotpotqa_skill_paraphrase_4_instruct/64_e1_3.0e-05/special_tokens_map.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|start_of_role|>",
|
| 4 |
+
"<|end_of_role|>",
|
| 5 |
+
"<|tool_call|>",
|
| 6 |
+
"<|start_of_cite|>",
|
| 7 |
+
"<|end_of_cite|>",
|
| 8 |
+
"<|start_of_plugin|>",
|
| 9 |
+
"<|end_of_plugin|>"
|
| 10 |
+
],
|
| 11 |
+
"bos_token": {
|
| 12 |
+
"content": "<|end_of_text|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false
|
| 17 |
+
},
|
| 18 |
+
"eos_token": {
|
| 19 |
+
"content": "<|end_of_text|>",
|
| 20 |
+
"lstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
+
"rstrip": false,
|
| 23 |
+
"single_word": false
|
| 24 |
+
},
|
| 25 |
+
"pad_token": "<|end_of_plugin|>",
|
| 26 |
+
"unk_token": {
|
| 27 |
+
"content": "<|end_of_text|>",
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"normalized": false,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"single_word": false
|
| 32 |
+
}
|
| 33 |
+
}
|
granite3.3/hotpotqa_skill_paraphrase_4_instruct/64_e1_3.0e-05/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
granite3.3/hotpotqa_skill_paraphrase_4_instruct/64_e1_3.0e-05/tokenizer_config.json
ADDED
|
@@ -0,0 +1,234 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<|end_of_text|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<fim_prefix>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "<fim_middle>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"3": {
|
| 30 |
+
"content": "<fim_suffix>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"4": {
|
| 38 |
+
"content": "<fim_pad>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"5": {
|
| 46 |
+
"content": "<filename>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"6": {
|
| 54 |
+
"content": "<gh_stars>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"7": {
|
| 62 |
+
"content": "<issue_start>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"8": {
|
| 70 |
+
"content": "<issue_comment>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"9": {
|
| 78 |
+
"content": "<issue_closed>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"10": {
|
| 86 |
+
"content": "<jupyter_start>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"11": {
|
| 94 |
+
"content": "<jupyter_text>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"12": {
|
| 102 |
+
"content": "<jupyter_code>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"13": {
|
| 110 |
+
"content": "<jupyter_output>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"14": {
|
| 118 |
+
"content": "<empty_output>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": true
|
| 124 |
+
},
|
| 125 |
+
"15": {
|
| 126 |
+
"content": "<commit_before>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": true
|
| 132 |
+
},
|
| 133 |
+
"16": {
|
| 134 |
+
"content": "<commit_msg>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": true
|
| 140 |
+
},
|
| 141 |
+
"17": {
|
| 142 |
+
"content": "<commit_after>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": true
|
| 148 |
+
},
|
| 149 |
+
"18": {
|
| 150 |
+
"content": "<reponame>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": true
|
| 156 |
+
},
|
| 157 |
+
"49152": {
|
| 158 |
+
"content": "<|start_of_role|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": true
|
| 164 |
+
},
|
| 165 |
+
"49153": {
|
| 166 |
+
"content": "<|end_of_role|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": true
|
| 172 |
+
},
|
| 173 |
+
"49154": {
|
| 174 |
+
"content": "<|tool_call|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": true
|
| 180 |
+
},
|
| 181 |
+
"49155": {
|
| 182 |
+
"content": "<|start_of_cite|>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": true
|
| 188 |
+
},
|
| 189 |
+
"49156": {
|
| 190 |
+
"content": "<|end_of_cite|>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": true
|
| 196 |
+
},
|
| 197 |
+
"49157": {
|
| 198 |
+
"content": "<|start_of_plugin|>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": true
|
| 204 |
+
},
|
| 205 |
+
"49158": {
|
| 206 |
+
"content": "<|end_of_plugin|>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": true
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|start_of_role|>",
|
| 216 |
+
"<|end_of_role|>",
|
| 217 |
+
"<|tool_call|>",
|
| 218 |
+
"<|start_of_cite|>",
|
| 219 |
+
"<|end_of_cite|>",
|
| 220 |
+
"<|start_of_plugin|>",
|
| 221 |
+
"<|end_of_plugin|>"
|
| 222 |
+
],
|
| 223 |
+
"bos_token": "<|end_of_text|>",
|
| 224 |
+
"clean_up_tokenization_spaces": true,
|
| 225 |
+
"eos_token": "<|end_of_text|>",
|
| 226 |
+
"errors": "replace",
|
| 227 |
+
"extra_special_tokens": {},
|
| 228 |
+
"model_max_length": 8192,
|
| 229 |
+
"pad_token": "<|end_of_plugin|>",
|
| 230 |
+
"padding_side": "left",
|
| 231 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 232 |
+
"unk_token": "<|end_of_text|>",
|
| 233 |
+
"vocab_size": 49152
|
| 234 |
+
}
|
granite3.3/hotpotqa_skill_paraphrase_4_instruct/64_e1_3.0e-05/train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 5.421179522126971e+17,
|
| 4 |
+
"train_loss": 1.4018334786097209,
|
| 5 |
+
"train_runtime": 211.1842,
|
| 6 |
+
"train_samples": 2871,
|
| 7 |
+
"train_samples_per_second": 13.595,
|
| 8 |
+
"train_steps_per_second": 0.852
|
| 9 |
+
}
|
granite3.3/hotpotqa_skill_paraphrase_4_instruct/64_e1_3.0e-05/trainer_state.json
ADDED
|
@@ -0,0 +1,295 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 180,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.027855153203342618,
|
| 14 |
+
"grad_norm": 79.84217071533203,
|
| 15 |
+
"learning_rate": 6.666666666666667e-06,
|
| 16 |
+
"loss": 5.9851,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.055710306406685235,
|
| 21 |
+
"grad_norm": 38.694671630859375,
|
| 22 |
+
"learning_rate": 1.5e-05,
|
| 23 |
+
"loss": 4.594,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.08356545961002786,
|
| 28 |
+
"grad_norm": 36.49879837036133,
|
| 29 |
+
"learning_rate": 2.3333333333333336e-05,
|
| 30 |
+
"loss": 3.2181,
|
| 31 |
+
"step": 15
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.11142061281337047,
|
| 35 |
+
"grad_norm": 19.724285125732422,
|
| 36 |
+
"learning_rate": 2.999717955672752e-05,
|
| 37 |
+
"loss": 2.285,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.1392757660167131,
|
| 42 |
+
"grad_norm": 13.453296661376953,
|
| 43 |
+
"learning_rate": 2.9898575366129145e-05,
|
| 44 |
+
"loss": 1.7213,
|
| 45 |
+
"step": 25
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.1671309192200557,
|
| 49 |
+
"grad_norm": 15.410880088806152,
|
| 50 |
+
"learning_rate": 2.9660007873759537e-05,
|
| 51 |
+
"loss": 1.7989,
|
| 52 |
+
"step": 30
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.19498607242339833,
|
| 56 |
+
"grad_norm": 13.07196044921875,
|
| 57 |
+
"learning_rate": 2.928371828007623e-05,
|
| 58 |
+
"loss": 1.7061,
|
| 59 |
+
"step": 35
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.22284122562674094,
|
| 63 |
+
"grad_norm": 12.913140296936035,
|
| 64 |
+
"learning_rate": 2.877324160320411e-05,
|
| 65 |
+
"loss": 1.5197,
|
| 66 |
+
"step": 40
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.25069637883008355,
|
| 70 |
+
"grad_norm": 8.160432815551758,
|
| 71 |
+
"learning_rate": 2.8133373469531362e-05,
|
| 72 |
+
"loss": 1.687,
|
| 73 |
+
"step": 45
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.2785515320334262,
|
| 77 |
+
"grad_norm": 10.046469688415527,
|
| 78 |
+
"learning_rate": 2.7370125061636605e-05,
|
| 79 |
+
"loss": 1.2803,
|
| 80 |
+
"step": 50
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.3064066852367688,
|
| 84 |
+
"grad_norm": 8.558515548706055,
|
| 85 |
+
"learning_rate": 2.649066664678467e-05,
|
| 86 |
+
"loss": 1.1875,
|
| 87 |
+
"step": 55
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.3342618384401114,
|
| 91 |
+
"grad_norm": 10.013181686401367,
|
| 92 |
+
"learning_rate": 2.5503260216507528e-05,
|
| 93 |
+
"loss": 1.2438,
|
| 94 |
+
"step": 60
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.362116991643454,
|
| 98 |
+
"grad_norm": 10.209836959838867,
|
| 99 |
+
"learning_rate": 2.441718187008148e-05,
|
| 100 |
+
"loss": 1.353,
|
| 101 |
+
"step": 65
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.38997214484679665,
|
| 105 |
+
"grad_norm": 10.300915718078613,
|
| 106 |
+
"learning_rate": 2.324263467106209e-05,
|
| 107 |
+
"loss": 1.2598,
|
| 108 |
+
"step": 70
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.4178272980501393,
|
| 112 |
+
"grad_norm": 9.67536449432373,
|
| 113 |
+
"learning_rate": 2.1990652795538085e-05,
|
| 114 |
+
"loss": 1.1185,
|
| 115 |
+
"step": 75
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.4456824512534819,
|
| 119 |
+
"grad_norm": 7.931994915008545,
|
| 120 |
+
"learning_rate": 2.0672997872574638e-05,
|
| 121 |
+
"loss": 1.2288,
|
| 122 |
+
"step": 80
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.4735376044568245,
|
| 126 |
+
"grad_norm": 8.109315872192383,
|
| 127 |
+
"learning_rate": 1.9302048490666356e-05,
|
| 128 |
+
"loss": 1.1172,
|
| 129 |
+
"step": 85
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.5013927576601671,
|
| 133 |
+
"grad_norm": 11.00154972076416,
|
| 134 |
+
"learning_rate": 1.789068390822135e-05,
|
| 135 |
+
"loss": 1.3139,
|
| 136 |
+
"step": 90
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.5292479108635098,
|
| 140 |
+
"grad_norm": 8.602248191833496,
|
| 141 |
+
"learning_rate": 1.6452163060547687e-05,
|
| 142 |
+
"loss": 0.9831,
|
| 143 |
+
"step": 95
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.5571030640668524,
|
| 147 |
+
"grad_norm": 8.124135971069336,
|
| 148 |
+
"learning_rate": 1.5e-05,
|
| 149 |
+
"loss": 1.1763,
|
| 150 |
+
"step": 100
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.584958217270195,
|
| 154 |
+
"grad_norm": 7.796338081359863,
|
| 155 |
+
"learning_rate": 1.3547836939452315e-05,
|
| 156 |
+
"loss": 0.8513,
|
| 157 |
+
"step": 105
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.6128133704735376,
|
| 161 |
+
"grad_norm": 9.259586334228516,
|
| 162 |
+
"learning_rate": 1.2109316091778652e-05,
|
| 163 |
+
"loss": 0.9192,
|
| 164 |
+
"step": 110
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.6406685236768802,
|
| 168 |
+
"grad_norm": 15.356439590454102,
|
| 169 |
+
"learning_rate": 1.069795150933365e-05,
|
| 170 |
+
"loss": 1.0044,
|
| 171 |
+
"step": 115
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.6685236768802229,
|
| 175 |
+
"grad_norm": 10.163902282714844,
|
| 176 |
+
"learning_rate": 9.327002127425364e-06,
|
| 177 |
+
"loss": 1.0645,
|
| 178 |
+
"step": 120
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.6963788300835655,
|
| 182 |
+
"grad_norm": 6.349460124969482,
|
| 183 |
+
"learning_rate": 8.009347204461922e-06,
|
| 184 |
+
"loss": 0.5956,
|
| 185 |
+
"step": 125
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.724233983286908,
|
| 189 |
+
"grad_norm": 10.912324905395508,
|
| 190 |
+
"learning_rate": 6.75736532893791e-06,
|
| 191 |
+
"loss": 0.9551,
|
| 192 |
+
"step": 130
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.7520891364902507,
|
| 196 |
+
"grad_norm": 5.631737232208252,
|
| 197 |
+
"learning_rate": 5.582818129918525e-06,
|
| 198 |
+
"loss": 0.737,
|
| 199 |
+
"step": 135
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.7799442896935933,
|
| 203 |
+
"grad_norm": 6.901148319244385,
|
| 204 |
+
"learning_rate": 4.496739783492473e-06,
|
| 205 |
+
"loss": 0.7107,
|
| 206 |
+
"step": 140
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.807799442896936,
|
| 210 |
+
"grad_norm": 8.347553253173828,
|
| 211 |
+
"learning_rate": 3.5093333532153316e-06,
|
| 212 |
+
"loss": 0.7643,
|
| 213 |
+
"step": 145
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.8356545961002786,
|
| 217 |
+
"grad_norm": 8.509891510009766,
|
| 218 |
+
"learning_rate": 2.6298749383633987e-06,
|
| 219 |
+
"loss": 0.629,
|
| 220 |
+
"step": 150
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.8635097493036211,
|
| 224 |
+
"grad_norm": 8.216154098510742,
|
| 225 |
+
"learning_rate": 1.8666265304686387e-06,
|
| 226 |
+
"loss": 0.7443,
|
| 227 |
+
"step": 155
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.8913649025069638,
|
| 231 |
+
"grad_norm": 9.096197128295898,
|
| 232 |
+
"learning_rate": 1.2267583967958918e-06,
|
| 233 |
+
"loss": 0.7817,
|
| 234 |
+
"step": 160
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.9192200557103064,
|
| 238 |
+
"grad_norm": 16.19647979736328,
|
| 239 |
+
"learning_rate": 7.162817199237703e-07,
|
| 240 |
+
"loss": 0.8574,
|
| 241 |
+
"step": 165
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.947075208913649,
|
| 245 |
+
"grad_norm": 8.682914733886719,
|
| 246 |
+
"learning_rate": 3.399921262404665e-07,
|
| 247 |
+
"loss": 0.8128,
|
| 248 |
+
"step": 170
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.9749303621169917,
|
| 252 |
+
"grad_norm": 8.104104995727539,
|
| 253 |
+
"learning_rate": 1.0142463387085465e-07,
|
| 254 |
+
"loss": 0.7977,
|
| 255 |
+
"step": 175
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.0,
|
| 259 |
+
"grad_norm": 3.9723000526428223,
|
| 260 |
+
"learning_rate": 2.8204432724798777e-09,
|
| 261 |
+
"loss": 0.4636,
|
| 262 |
+
"step": 180
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.0,
|
| 266 |
+
"step": 180,
|
| 267 |
+
"total_flos": 5.421179522126971e+17,
|
| 268 |
+
"train_loss": 1.4018334786097209,
|
| 269 |
+
"train_runtime": 211.1842,
|
| 270 |
+
"train_samples_per_second": 13.595,
|
| 271 |
+
"train_steps_per_second": 0.852
|
| 272 |
+
}
|
| 273 |
+
],
|
| 274 |
+
"logging_steps": 5,
|
| 275 |
+
"max_steps": 180,
|
| 276 |
+
"num_input_tokens_seen": 0,
|
| 277 |
+
"num_train_epochs": 1,
|
| 278 |
+
"save_steps": 500,
|
| 279 |
+
"stateful_callbacks": {
|
| 280 |
+
"TrainerControl": {
|
| 281 |
+
"args": {
|
| 282 |
+
"should_epoch_stop": false,
|
| 283 |
+
"should_evaluate": false,
|
| 284 |
+
"should_log": false,
|
| 285 |
+
"should_save": false,
|
| 286 |
+
"should_training_stop": false
|
| 287 |
+
},
|
| 288 |
+
"attributes": {}
|
| 289 |
+
}
|
| 290 |
+
},
|
| 291 |
+
"total_flos": 5.421179522126971e+17,
|
| 292 |
+
"train_batch_size": 1,
|
| 293 |
+
"trial_name": null,
|
| 294 |
+
"trial_params": null
|
| 295 |
+
}
|
granite3.3/hotpotqa_skill_paraphrase_4_instruct/64_e1_3.0e-05/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2719d3ca7261bd89567d880e418e72d2ca41062d0e9e451a3eb7d56b6a792ef8
|
| 3 |
+
size 8017
|
granite3.3/hotpotqa_skill_paraphrase_4_instruct/64_e1_3.0e-05/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
granite3.3/hotpotqa_test_knowledge_50_base/0_128_e3_3e-5/README.md
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: ibm-granite/granite-3.3-8b-base
|
| 5 |
+
tags:
|
| 6 |
+
- alignment-handbook
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
datasets:
|
| 9 |
+
- data/hotpotqa/test/processed/knowledge_50
|
| 10 |
+
model-index:
|
| 11 |
+
- name: 0_128_e3_3e-5
|
| 12 |
+
results: []
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 16 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 17 |
+
|
| 18 |
+
# 0_128_e3_3e-5
|
| 19 |
+
|
| 20 |
+
This model is a fine-tuned version of [ibm-granite/granite-3.3-8b-base](https://huggingface.co/ibm-granite/granite-3.3-8b-base) on the data/hotpotqa/test/processed/knowledge_50 dataset.
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 3e-05
|
| 40 |
+
- train_batch_size: 2
|
| 41 |
+
- eval_batch_size: 1
|
| 42 |
+
- seed: 42
|
| 43 |
+
- distributed_type: multi-GPU
|
| 44 |
+
- num_devices: 8
|
| 45 |
+
- gradient_accumulation_steps: 2
|
| 46 |
+
- total_train_batch_size: 32
|
| 47 |
+
- total_eval_batch_size: 8
|
| 48 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 49 |
+
- lr_scheduler_type: cosine
|
| 50 |
+
- lr_scheduler_warmup_ratio: 0.05
|
| 51 |
+
- num_epochs: 3.0
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
|
| 56 |
+
|
| 57 |
+
### Framework versions
|
| 58 |
+
|
| 59 |
+
- PEFT 0.15.2
|
| 60 |
+
- Transformers 4.52.4
|
| 61 |
+
- Pytorch 2.7.0+cu126
|
| 62 |
+
- Datasets 3.6.0
|
| 63 |
+
- Tokenizers 0.21.2
|
granite3.3/hotpotqa_test_knowledge_50_base/0_128_e3_3e-5/adapter_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "ibm-granite/granite-3.3-8b-base",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 256,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.05,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 128,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"v_proj",
|
| 28 |
+
"up_proj",
|
| 29 |
+
"o_proj",
|
| 30 |
+
"k_proj",
|
| 31 |
+
"down_proj",
|
| 32 |
+
"gate_proj",
|
| 33 |
+
"q_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
+
"use_dora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
granite3.3/hotpotqa_test_knowledge_50_base/0_128_e3_3e-5/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ac0cb68e3a455f159cb30a4e367e7379ab03ea3f0c29a495a859faddf8b55a6
|
| 3 |
+
size 791751704
|
granite3.3/hotpotqa_test_knowledge_50_base/0_128_e3_3e-5/all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 2.1835948407453123e+18,
|
| 4 |
+
"train_loss": 0.35027236877104795,
|
| 5 |
+
"train_runtime": 993.3547,
|
| 6 |
+
"train_samples": 13304,
|
| 7 |
+
"train_samples_per_second": 40.179,
|
| 8 |
+
"train_steps_per_second": 1.256
|
| 9 |
+
}
|
granite3.3/hotpotqa_test_knowledge_50_base/0_128_e3_3e-5/config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"GraniteForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0,
|
| 7 |
+
"attention_multiplier": 0.0078125,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"embedding_multiplier": 12.0,
|
| 10 |
+
"eos_token_id": 0,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 4096,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 12800,
|
| 15 |
+
"logits_scaling": 16.0,
|
| 16 |
+
"max_position_embeddings": 131072,
|
| 17 |
+
"mlp_bias": false,
|
| 18 |
+
"model_type": "granite",
|
| 19 |
+
"num_attention_heads": 32,
|
| 20 |
+
"num_hidden_layers": 40,
|
| 21 |
+
"num_key_value_heads": 8,
|
| 22 |
+
"pad_token_id": 0,
|
| 23 |
+
"residual_multiplier": 0.22,
|
| 24 |
+
"rms_norm_eps": 1e-05,
|
| 25 |
+
"rope_scaling": null,
|
| 26 |
+
"rope_theta": 10000000.0,
|
| 27 |
+
"tie_word_embeddings": true,
|
| 28 |
+
"torch_dtype": "bfloat16",
|
| 29 |
+
"transformers_version": "4.52.4",
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 49152
|
| 32 |
+
}
|
granite3.3/hotpotqa_test_knowledge_50_base/0_128_e3_3e-5/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
granite3.3/hotpotqa_test_knowledge_50_base/0_128_e3_3e-5/special_tokens_map.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|endoftext|>",
|
| 4 |
+
"<fim_prefix>",
|
| 5 |
+
"<fim_middle>",
|
| 6 |
+
"<fim_suffix>",
|
| 7 |
+
"<fim_pad>",
|
| 8 |
+
"<filename>",
|
| 9 |
+
"<gh_stars>",
|
| 10 |
+
"<issue_start>",
|
| 11 |
+
"<issue_comment>",
|
| 12 |
+
"<issue_closed>",
|
| 13 |
+
"<jupyter_start>",
|
| 14 |
+
"<jupyter_text>",
|
| 15 |
+
"<jupyter_code>",
|
| 16 |
+
"<jupyter_output>",
|
| 17 |
+
"<empty_output>",
|
| 18 |
+
"<commit_before>",
|
| 19 |
+
"<commit_msg>",
|
| 20 |
+
"<commit_after>",
|
| 21 |
+
"<reponame>"
|
| 22 |
+
],
|
| 23 |
+
"bos_token": {
|
| 24 |
+
"content": "<|endoftext|>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"eos_token": {
|
| 31 |
+
"content": "<|endoftext|>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"pad_token": "<reponame>",
|
| 38 |
+
"unk_token": {
|
| 39 |
+
"content": "<|endoftext|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false
|
| 44 |
+
}
|
| 45 |
+
}
|
granite3.3/hotpotqa_test_knowledge_50_base/0_128_e3_3e-5/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
granite3.3/hotpotqa_test_knowledge_50_base/0_128_e3_3e-5/tokenizer_config.json
ADDED
|
@@ -0,0 +1,188 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<fim_prefix>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "<fim_middle>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<fim_suffix>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"4": {
|
| 37 |
+
"content": "<fim_pad>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"5": {
|
| 45 |
+
"content": "<filename>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"6": {
|
| 53 |
+
"content": "<gh_stars>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"7": {
|
| 61 |
+
"content": "<issue_start>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"8": {
|
| 69 |
+
"content": "<issue_comment>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"9": {
|
| 77 |
+
"content": "<issue_closed>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"10": {
|
| 85 |
+
"content": "<jupyter_start>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"11": {
|
| 93 |
+
"content": "<jupyter_text>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"12": {
|
| 101 |
+
"content": "<jupyter_code>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"13": {
|
| 109 |
+
"content": "<jupyter_output>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"14": {
|
| 117 |
+
"content": "<empty_output>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": true
|
| 123 |
+
},
|
| 124 |
+
"15": {
|
| 125 |
+
"content": "<commit_before>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": true
|
| 131 |
+
},
|
| 132 |
+
"16": {
|
| 133 |
+
"content": "<commit_msg>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": true
|
| 139 |
+
},
|
| 140 |
+
"17": {
|
| 141 |
+
"content": "<commit_after>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": true
|
| 147 |
+
},
|
| 148 |
+
"18": {
|
| 149 |
+
"content": "<reponame>",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": true
|
| 155 |
+
}
|
| 156 |
+
},
|
| 157 |
+
"additional_special_tokens": [
|
| 158 |
+
"<|endoftext|>",
|
| 159 |
+
"<fim_prefix>",
|
| 160 |
+
"<fim_middle>",
|
| 161 |
+
"<fim_suffix>",
|
| 162 |
+
"<fim_pad>",
|
| 163 |
+
"<filename>",
|
| 164 |
+
"<gh_stars>",
|
| 165 |
+
"<issue_start>",
|
| 166 |
+
"<issue_comment>",
|
| 167 |
+
"<issue_closed>",
|
| 168 |
+
"<jupyter_start>",
|
| 169 |
+
"<jupyter_text>",
|
| 170 |
+
"<jupyter_code>",
|
| 171 |
+
"<jupyter_output>",
|
| 172 |
+
"<empty_output>",
|
| 173 |
+
"<commit_before>",
|
| 174 |
+
"<commit_msg>",
|
| 175 |
+
"<commit_after>",
|
| 176 |
+
"<reponame>"
|
| 177 |
+
],
|
| 178 |
+
"bos_token": "<|endoftext|>",
|
| 179 |
+
"clean_up_tokenization_spaces": true,
|
| 180 |
+
"eos_token": "<|endoftext|>",
|
| 181 |
+
"extra_special_tokens": {},
|
| 182 |
+
"model_max_length": 8192,
|
| 183 |
+
"pad_token": "<reponame>",
|
| 184 |
+
"padding_side": "left",
|
| 185 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 186 |
+
"unk_token": "<|endoftext|>",
|
| 187 |
+
"vocab_size": 49152
|
| 188 |
+
}
|
granite3.3/hotpotqa_test_knowledge_50_base/0_128_e3_3e-5/train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 2.1835948407453123e+18,
|
| 4 |
+
"train_loss": 0.35027236877104795,
|
| 5 |
+
"train_runtime": 993.3547,
|
| 6 |
+
"train_samples": 13304,
|
| 7 |
+
"train_samples_per_second": 40.179,
|
| 8 |
+
"train_steps_per_second": 1.256
|
| 9 |
+
}
|
granite3.3/hotpotqa_test_knowledge_50_base/0_128_e3_3e-5/trainer_state.json
ADDED
|
@@ -0,0 +1,1786 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 1248,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.01201923076923077,
|
| 14 |
+
"grad_norm": 0.7992493510246277,
|
| 15 |
+
"learning_rate": 1.9047619047619047e-06,
|
| 16 |
+
"loss": 1.3498,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.02403846153846154,
|
| 21 |
+
"grad_norm": 0.7139345407485962,
|
| 22 |
+
"learning_rate": 4.2857142857142855e-06,
|
| 23 |
+
"loss": 1.312,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.036057692307692304,
|
| 28 |
+
"grad_norm": 0.5560569763183594,
|
| 29 |
+
"learning_rate": 6.666666666666667e-06,
|
| 30 |
+
"loss": 1.34,
|
| 31 |
+
"step": 15
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.04807692307692308,
|
| 35 |
+
"grad_norm": 0.9837707877159119,
|
| 36 |
+
"learning_rate": 9.047619047619047e-06,
|
| 37 |
+
"loss": 1.3088,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.06009615384615385,
|
| 42 |
+
"grad_norm": 0.570275068283081,
|
| 43 |
+
"learning_rate": 1.1428571428571429e-05,
|
| 44 |
+
"loss": 1.2392,
|
| 45 |
+
"step": 25
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.07211538461538461,
|
| 49 |
+
"grad_norm": 0.4455273151397705,
|
| 50 |
+
"learning_rate": 1.380952380952381e-05,
|
| 51 |
+
"loss": 1.277,
|
| 52 |
+
"step": 30
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.08413461538461539,
|
| 56 |
+
"grad_norm": 0.44045498967170715,
|
| 57 |
+
"learning_rate": 1.619047619047619e-05,
|
| 58 |
+
"loss": 1.2425,
|
| 59 |
+
"step": 35
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.09615384615384616,
|
| 63 |
+
"grad_norm": 0.4414880871772766,
|
| 64 |
+
"learning_rate": 1.8571428571428572e-05,
|
| 65 |
+
"loss": 1.2201,
|
| 66 |
+
"step": 40
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.10817307692307693,
|
| 70 |
+
"grad_norm": 0.43076056241989136,
|
| 71 |
+
"learning_rate": 2.095238095238095e-05,
|
| 72 |
+
"loss": 1.2094,
|
| 73 |
+
"step": 45
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.1201923076923077,
|
| 77 |
+
"grad_norm": 0.48338383436203003,
|
| 78 |
+
"learning_rate": 2.3333333333333336e-05,
|
| 79 |
+
"loss": 1.2105,
|
| 80 |
+
"step": 50
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.13221153846153846,
|
| 84 |
+
"grad_norm": 0.40512895584106445,
|
| 85 |
+
"learning_rate": 2.5714285714285714e-05,
|
| 86 |
+
"loss": 1.1678,
|
| 87 |
+
"step": 55
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.14423076923076922,
|
| 91 |
+
"grad_norm": 0.39393433928489685,
|
| 92 |
+
"learning_rate": 2.8095238095238096e-05,
|
| 93 |
+
"loss": 1.2197,
|
| 94 |
+
"step": 60
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.15625,
|
| 98 |
+
"grad_norm": 0.48222100734710693,
|
| 99 |
+
"learning_rate": 2.999994728623287e-05,
|
| 100 |
+
"loss": 1.137,
|
| 101 |
+
"step": 65
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.16826923076923078,
|
| 105 |
+
"grad_norm": 0.4608806371688843,
|
| 106 |
+
"learning_rate": 2.9998102343285288e-05,
|
| 107 |
+
"loss": 1.1067,
|
| 108 |
+
"step": 70
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.18028846153846154,
|
| 112 |
+
"grad_norm": 0.5111000537872314,
|
| 113 |
+
"learning_rate": 2.9993622082468165e-05,
|
| 114 |
+
"loss": 1.0933,
|
| 115 |
+
"step": 75
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.19230769230769232,
|
| 119 |
+
"grad_norm": 0.5229451060295105,
|
| 120 |
+
"learning_rate": 2.9986507291008524e-05,
|
| 121 |
+
"loss": 1.0899,
|
| 122 |
+
"step": 80
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.20432692307692307,
|
| 126 |
+
"grad_norm": 0.522977888584137,
|
| 127 |
+
"learning_rate": 2.9976759219046988e-05,
|
| 128 |
+
"loss": 1.0801,
|
| 129 |
+
"step": 85
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.21634615384615385,
|
| 133 |
+
"grad_norm": 0.5710195302963257,
|
| 134 |
+
"learning_rate": 2.9964379579418136e-05,
|
| 135 |
+
"loss": 1.089,
|
| 136 |
+
"step": 90
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.2283653846153846,
|
| 140 |
+
"grad_norm": 0.6306738257408142,
|
| 141 |
+
"learning_rate": 2.994937054734952e-05,
|
| 142 |
+
"loss": 1.0705,
|
| 143 |
+
"step": 95
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.2403846153846154,
|
| 147 |
+
"grad_norm": 0.6814161539077759,
|
| 148 |
+
"learning_rate": 2.993173476007947e-05,
|
| 149 |
+
"loss": 0.9783,
|
| 150 |
+
"step": 100
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.25240384615384615,
|
| 154 |
+
"grad_norm": 0.6979741454124451,
|
| 155 |
+
"learning_rate": 2.991147531639371e-05,
|
| 156 |
+
"loss": 0.973,
|
| 157 |
+
"step": 105
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.2644230769230769,
|
| 161 |
+
"grad_norm": 0.7390486598014832,
|
| 162 |
+
"learning_rate": 2.9888595776080856e-05,
|
| 163 |
+
"loss": 0.9799,
|
| 164 |
+
"step": 110
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.2764423076923077,
|
| 168 |
+
"grad_norm": 0.6985456943511963,
|
| 169 |
+
"learning_rate": 2.9863100159306923e-05,
|
| 170 |
+
"loss": 0.9214,
|
| 171 |
+
"step": 115
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.28846153846153844,
|
| 175 |
+
"grad_norm": 0.8002734184265137,
|
| 176 |
+
"learning_rate": 2.9834992945908966e-05,
|
| 177 |
+
"loss": 0.9719,
|
| 178 |
+
"step": 120
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.3004807692307692,
|
| 182 |
+
"grad_norm": 0.6572631597518921,
|
| 183 |
+
"learning_rate": 2.9804279074607893e-05,
|
| 184 |
+
"loss": 0.9003,
|
| 185 |
+
"step": 125
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.3125,
|
| 189 |
+
"grad_norm": 0.7747898101806641,
|
| 190 |
+
"learning_rate": 2.977096394214071e-05,
|
| 191 |
+
"loss": 0.8976,
|
| 192 |
+
"step": 130
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.3245192307692308,
|
| 196 |
+
"grad_norm": 0.7800673246383667,
|
| 197 |
+
"learning_rate": 2.9735053402312234e-05,
|
| 198 |
+
"loss": 0.8785,
|
| 199 |
+
"step": 135
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.33653846153846156,
|
| 203 |
+
"grad_norm": 0.9005689024925232,
|
| 204 |
+
"learning_rate": 2.9696553764966562e-05,
|
| 205 |
+
"loss": 0.8284,
|
| 206 |
+
"step": 140
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.3485576923076923,
|
| 210 |
+
"grad_norm": 0.8709399104118347,
|
| 211 |
+
"learning_rate": 2.9655471794878325e-05,
|
| 212 |
+
"loss": 0.8418,
|
| 213 |
+
"step": 145
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.3605769230769231,
|
| 217 |
+
"grad_norm": 1.2006804943084717,
|
| 218 |
+
"learning_rate": 2.961181471056406e-05,
|
| 219 |
+
"loss": 0.8865,
|
| 220 |
+
"step": 150
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.37259615384615385,
|
| 224 |
+
"grad_norm": 0.7847079634666443,
|
| 225 |
+
"learning_rate": 2.9565590183013855e-05,
|
| 226 |
+
"loss": 0.824,
|
| 227 |
+
"step": 155
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.38461538461538464,
|
| 231 |
+
"grad_norm": 1.273431420326233,
|
| 232 |
+
"learning_rate": 2.9516806334343482e-05,
|
| 233 |
+
"loss": 0.7238,
|
| 234 |
+
"step": 160
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.39663461538461536,
|
| 238 |
+
"grad_norm": 0.8723351359367371,
|
| 239 |
+
"learning_rate": 2.9465471736367234e-05,
|
| 240 |
+
"loss": 0.7761,
|
| 241 |
+
"step": 165
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.40865384615384615,
|
| 245 |
+
"grad_norm": 1.0148437023162842,
|
| 246 |
+
"learning_rate": 2.94115954090918e-05,
|
| 247 |
+
"loss": 0.8031,
|
| 248 |
+
"step": 170
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.4206730769230769,
|
| 252 |
+
"grad_norm": 0.9723730683326721,
|
| 253 |
+
"learning_rate": 2.9355186819131334e-05,
|
| 254 |
+
"loss": 0.7789,
|
| 255 |
+
"step": 175
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.4326923076923077,
|
| 259 |
+
"grad_norm": 0.8780352473258972,
|
| 260 |
+
"learning_rate": 2.9296255878044094e-05,
|
| 261 |
+
"loss": 0.7354,
|
| 262 |
+
"step": 180
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.44471153846153844,
|
| 266 |
+
"grad_norm": 0.9776846766471863,
|
| 267 |
+
"learning_rate": 2.9234812940590877e-05,
|
| 268 |
+
"loss": 0.7227,
|
| 269 |
+
"step": 185
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.4567307692307692,
|
| 273 |
+
"grad_norm": 0.9706979393959045,
|
| 274 |
+
"learning_rate": 2.9170868802915576e-05,
|
| 275 |
+
"loss": 0.7729,
|
| 276 |
+
"step": 190
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.46875,
|
| 280 |
+
"grad_norm": 0.97734135389328,
|
| 281 |
+
"learning_rate": 2.9104434700648187e-05,
|
| 282 |
+
"loss": 0.7642,
|
| 283 |
+
"step": 195
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.4807692307692308,
|
| 287 |
+
"grad_norm": 0.9069945216178894,
|
| 288 |
+
"learning_rate": 2.9035522306930612e-05,
|
| 289 |
+
"loss": 0.7071,
|
| 290 |
+
"step": 200
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.49278846153846156,
|
| 294 |
+
"grad_norm": 1.0940104722976685,
|
| 295 |
+
"learning_rate": 2.8964143730365564e-05,
|
| 296 |
+
"loss": 0.7162,
|
| 297 |
+
"step": 205
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.5048076923076923,
|
| 301 |
+
"grad_norm": 1.0215709209442139,
|
| 302 |
+
"learning_rate": 2.8890311512888933e-05,
|
| 303 |
+
"loss": 0.6953,
|
| 304 |
+
"step": 210
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.5168269230769231,
|
| 308 |
+
"grad_norm": 1.031449556350708,
|
| 309 |
+
"learning_rate": 2.88140386275661e-05,
|
| 310 |
+
"loss": 0.6522,
|
| 311 |
+
"step": 215
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.5288461538461539,
|
| 315 |
+
"grad_norm": 1.1397559642791748,
|
| 316 |
+
"learning_rate": 2.8735338476312386e-05,
|
| 317 |
+
"loss": 0.6663,
|
| 318 |
+
"step": 220
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.5408653846153846,
|
| 322 |
+
"grad_norm": 0.9379346966743469,
|
| 323 |
+
"learning_rate": 2.8654224887538222e-05,
|
| 324 |
+
"loss": 0.6622,
|
| 325 |
+
"step": 225
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.5528846153846154,
|
| 329 |
+
"grad_norm": 1.2060980796813965,
|
| 330 |
+
"learning_rate": 2.857071211371936e-05,
|
| 331 |
+
"loss": 0.6319,
|
| 332 |
+
"step": 230
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.5649038461538461,
|
| 336 |
+
"grad_norm": 0.9556930661201477,
|
| 337 |
+
"learning_rate": 2.8484814828892568e-05,
|
| 338 |
+
"loss": 0.6174,
|
| 339 |
+
"step": 235
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.5769230769230769,
|
| 343 |
+
"grad_norm": 1.042279601097107,
|
| 344 |
+
"learning_rate": 2.8396548126077245e-05,
|
| 345 |
+
"loss": 0.6617,
|
| 346 |
+
"step": 240
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.5889423076923077,
|
| 350 |
+
"grad_norm": 1.0397286415100098,
|
| 351 |
+
"learning_rate": 2.8305927514623432e-05,
|
| 352 |
+
"loss": 0.6331,
|
| 353 |
+
"step": 245
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.6009615384615384,
|
| 357 |
+
"grad_norm": 0.9931198358535767,
|
| 358 |
+
"learning_rate": 2.8212968917486666e-05,
|
| 359 |
+
"loss": 0.6524,
|
| 360 |
+
"step": 250
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.6129807692307693,
|
| 364 |
+
"grad_norm": 1.1163089275360107,
|
| 365 |
+
"learning_rate": 2.8117688668430142e-05,
|
| 366 |
+
"loss": 0.5164,
|
| 367 |
+
"step": 255
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.625,
|
| 371 |
+
"grad_norm": 1.1626168489456177,
|
| 372 |
+
"learning_rate": 2.8020103509154738e-05,
|
| 373 |
+
"loss": 0.5657,
|
| 374 |
+
"step": 260
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.6370192307692307,
|
| 378 |
+
"grad_norm": 1.2860921621322632,
|
| 379 |
+
"learning_rate": 2.7920230586357283e-05,
|
| 380 |
+
"loss": 0.5757,
|
| 381 |
+
"step": 265
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.6490384615384616,
|
| 385 |
+
"grad_norm": 1.0856633186340332,
|
| 386 |
+
"learning_rate": 2.7818087448717742e-05,
|
| 387 |
+
"loss": 0.552,
|
| 388 |
+
"step": 270
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.6610576923076923,
|
| 392 |
+
"grad_norm": 1.0244907140731812,
|
| 393 |
+
"learning_rate": 2.7713692043815737e-05,
|
| 394 |
+
"loss": 0.5609,
|
| 395 |
+
"step": 275
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.6730769230769231,
|
| 399 |
+
"grad_norm": 1.0819729566574097,
|
| 400 |
+
"learning_rate": 2.760706271497695e-05,
|
| 401 |
+
"loss": 0.5316,
|
| 402 |
+
"step": 280
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.6850961538461539,
|
| 406 |
+
"grad_norm": 1.1790964603424072,
|
| 407 |
+
"learning_rate": 2.7498218198050055e-05,
|
| 408 |
+
"loss": 0.5508,
|
| 409 |
+
"step": 285
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.6971153846153846,
|
| 413 |
+
"grad_norm": 0.9592273235321045,
|
| 414 |
+
"learning_rate": 2.738717761811459e-05,
|
| 415 |
+
"loss": 0.5276,
|
| 416 |
+
"step": 290
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.7091346153846154,
|
| 420 |
+
"grad_norm": 1.267228364944458,
|
| 421 |
+
"learning_rate": 2.7273960486120547e-05,
|
| 422 |
+
"loss": 0.5189,
|
| 423 |
+
"step": 295
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.7211538461538461,
|
| 427 |
+
"grad_norm": 1.1094183921813965,
|
| 428 |
+
"learning_rate": 2.7158586695460036e-05,
|
| 429 |
+
"loss": 0.523,
|
| 430 |
+
"step": 300
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.7331730769230769,
|
| 434 |
+
"grad_norm": 1.2535171508789062,
|
| 435 |
+
"learning_rate": 2.7041076518471878e-05,
|
| 436 |
+
"loss": 0.4811,
|
| 437 |
+
"step": 305
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.7451923076923077,
|
| 441 |
+
"grad_norm": 1.100150465965271,
|
| 442 |
+
"learning_rate": 2.6921450602879505e-05,
|
| 443 |
+
"loss": 0.5152,
|
| 444 |
+
"step": 310
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.7572115384615384,
|
| 448 |
+
"grad_norm": 1.204069972038269,
|
| 449 |
+
"learning_rate": 2.6799729968162975e-05,
|
| 450 |
+
"loss": 0.505,
|
| 451 |
+
"step": 315
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.7692307692307693,
|
| 455 |
+
"grad_norm": 1.2997931241989136,
|
| 456 |
+
"learning_rate": 2.6675936001865615e-05,
|
| 457 |
+
"loss": 0.4633,
|
| 458 |
+
"step": 320
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.78125,
|
| 462 |
+
"grad_norm": 1.2581266164779663,
|
| 463 |
+
"learning_rate": 2.655009045583603e-05,
|
| 464 |
+
"loss": 0.4788,
|
| 465 |
+
"step": 325
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.7932692307692307,
|
| 469 |
+
"grad_norm": 1.058752179145813,
|
| 470 |
+
"learning_rate": 2.6422215442406078e-05,
|
| 471 |
+
"loss": 0.4621,
|
| 472 |
+
"step": 330
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.8052884615384616,
|
| 476 |
+
"grad_norm": 1.2290775775909424,
|
| 477 |
+
"learning_rate": 2.6292333430505508e-05,
|
| 478 |
+
"loss": 0.5058,
|
| 479 |
+
"step": 335
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.8173076923076923,
|
| 483 |
+
"grad_norm": 1.1277260780334473,
|
| 484 |
+
"learning_rate": 2.6160467241713954e-05,
|
| 485 |
+
"loss": 0.5003,
|
| 486 |
+
"step": 340
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.8293269230769231,
|
| 490 |
+
"grad_norm": 1.1429057121276855,
|
| 491 |
+
"learning_rate": 2.6026640046250935e-05,
|
| 492 |
+
"loss": 0.5114,
|
| 493 |
+
"step": 345
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.8413461538461539,
|
| 497 |
+
"grad_norm": 1.2035683393478394,
|
| 498 |
+
"learning_rate": 2.5890875358904622e-05,
|
| 499 |
+
"loss": 0.4607,
|
| 500 |
+
"step": 350
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.8533653846153846,
|
| 504 |
+
"grad_norm": 1.1913330554962158,
|
| 505 |
+
"learning_rate": 2.575319703490007e-05,
|
| 506 |
+
"loss": 0.4745,
|
| 507 |
+
"step": 355
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.8653846153846154,
|
| 511 |
+
"grad_norm": 1.0664615631103516,
|
| 512 |
+
"learning_rate": 2.5613629265707572e-05,
|
| 513 |
+
"loss": 0.3978,
|
| 514 |
+
"step": 360
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.8774038461538461,
|
| 518 |
+
"grad_norm": 1.1914716958999634,
|
| 519 |
+
"learning_rate": 2.547219657479202e-05,
|
| 520 |
+
"loss": 0.4582,
|
| 521 |
+
"step": 365
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.8894230769230769,
|
| 525 |
+
"grad_norm": 1.073660969734192,
|
| 526 |
+
"learning_rate": 2.532892381330386e-05,
|
| 527 |
+
"loss": 0.4198,
|
| 528 |
+
"step": 370
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.9014423076923077,
|
| 532 |
+
"grad_norm": 1.0263564586639404,
|
| 533 |
+
"learning_rate": 2.5183836155712492e-05,
|
| 534 |
+
"loss": 0.4085,
|
| 535 |
+
"step": 375
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.9134615384615384,
|
| 539 |
+
"grad_norm": 1.0695228576660156,
|
| 540 |
+
"learning_rate": 2.5036959095382875e-05,
|
| 541 |
+
"loss": 0.4111,
|
| 542 |
+
"step": 380
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.9254807692307693,
|
| 546 |
+
"grad_norm": 1.3179558515548706,
|
| 547 |
+
"learning_rate": 2.4888318440096076e-05,
|
| 548 |
+
"loss": 0.4187,
|
| 549 |
+
"step": 385
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.9375,
|
| 553 |
+
"grad_norm": 1.3367719650268555,
|
| 554 |
+
"learning_rate": 2.4737940307514592e-05,
|
| 555 |
+
"loss": 0.4006,
|
| 556 |
+
"step": 390
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.9495192307692307,
|
| 560 |
+
"grad_norm": 1.1475625038146973,
|
| 561 |
+
"learning_rate": 2.4585851120593196e-05,
|
| 562 |
+
"loss": 0.4034,
|
| 563 |
+
"step": 395
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.9615384615384616,
|
| 567 |
+
"grad_norm": 1.4168444871902466,
|
| 568 |
+
"learning_rate": 2.443207760293617e-05,
|
| 569 |
+
"loss": 0.3877,
|
| 570 |
+
"step": 400
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.9735576923076923,
|
| 574 |
+
"grad_norm": 1.1740849018096924,
|
| 575 |
+
"learning_rate": 2.427664677410171e-05,
|
| 576 |
+
"loss": 0.3948,
|
| 577 |
+
"step": 405
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.9855769230769231,
|
| 581 |
+
"grad_norm": 1.054010033607483,
|
| 582 |
+
"learning_rate": 2.411958594485429e-05,
|
| 583 |
+
"loss": 0.3513,
|
| 584 |
+
"step": 410
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.9975961538461539,
|
| 588 |
+
"grad_norm": 1.3729983568191528,
|
| 589 |
+
"learning_rate": 2.3960922712365893e-05,
|
| 590 |
+
"loss": 0.3834,
|
| 591 |
+
"step": 415
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.0096153846153846,
|
| 595 |
+
"grad_norm": 1.0171478986740112,
|
| 596 |
+
"learning_rate": 2.380068495536694e-05,
|
| 597 |
+
"loss": 0.338,
|
| 598 |
+
"step": 420
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.0216346153846154,
|
| 602 |
+
"grad_norm": 1.0823450088500977,
|
| 603 |
+
"learning_rate": 2.3638900829247666e-05,
|
| 604 |
+
"loss": 0.3162,
|
| 605 |
+
"step": 425
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.0336538461538463,
|
| 609 |
+
"grad_norm": 1.0885355472564697,
|
| 610 |
+
"learning_rate": 2.3475598761110962e-05,
|
| 611 |
+
"loss": 0.3427,
|
| 612 |
+
"step": 430
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.0456730769230769,
|
| 616 |
+
"grad_norm": 1.2596081495285034,
|
| 617 |
+
"learning_rate": 2.3310807444777458e-05,
|
| 618 |
+
"loss": 0.2851,
|
| 619 |
+
"step": 435
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.0576923076923077,
|
| 623 |
+
"grad_norm": 1.2260217666625977,
|
| 624 |
+
"learning_rate": 2.31445558357437e-05,
|
| 625 |
+
"loss": 0.2948,
|
| 626 |
+
"step": 440
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.0697115384615385,
|
| 630 |
+
"grad_norm": 1.1115962266921997,
|
| 631 |
+
"learning_rate": 2.2976873146094403e-05,
|
| 632 |
+
"loss": 0.3097,
|
| 633 |
+
"step": 445
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.0817307692307692,
|
| 637 |
+
"grad_norm": 1.4730960130691528,
|
| 638 |
+
"learning_rate": 2.2807788839369572e-05,
|
| 639 |
+
"loss": 0.3288,
|
| 640 |
+
"step": 450
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.09375,
|
| 644 |
+
"grad_norm": 1.1630613803863525,
|
| 645 |
+
"learning_rate": 2.263733262538747e-05,
|
| 646 |
+
"loss": 0.3072,
|
| 647 |
+
"step": 455
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.1057692307692308,
|
| 651 |
+
"grad_norm": 1.302695393562317,
|
| 652 |
+
"learning_rate": 2.2465534455024314e-05,
|
| 653 |
+
"loss": 0.3117,
|
| 654 |
+
"step": 460
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.1177884615384615,
|
| 658 |
+
"grad_norm": 1.1780915260314941,
|
| 659 |
+
"learning_rate": 2.229242451495159e-05,
|
| 660 |
+
"loss": 0.293,
|
| 661 |
+
"step": 465
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.1298076923076923,
|
| 665 |
+
"grad_norm": 1.5236937999725342,
|
| 666 |
+
"learning_rate": 2.2118033222331943e-05,
|
| 667 |
+
"loss": 0.2804,
|
| 668 |
+
"step": 470
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.1418269230769231,
|
| 672 |
+
"grad_norm": 0.9936278462409973,
|
| 673 |
+
"learning_rate": 2.19423912194746e-05,
|
| 674 |
+
"loss": 0.3384,
|
| 675 |
+
"step": 475
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.1538461538461537,
|
| 679 |
+
"grad_norm": 1.1205698251724243,
|
| 680 |
+
"learning_rate": 2.1765529368451183e-05,
|
| 681 |
+
"loss": 0.2982,
|
| 682 |
+
"step": 480
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.1658653846153846,
|
| 686 |
+
"grad_norm": 1.2928378582000732,
|
| 687 |
+
"learning_rate": 2.1587478745672946e-05,
|
| 688 |
+
"loss": 0.3118,
|
| 689 |
+
"step": 485
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.1778846153846154,
|
| 693 |
+
"grad_norm": 1.1839667558670044,
|
| 694 |
+
"learning_rate": 2.140827063643034e-05,
|
| 695 |
+
"loss": 0.2741,
|
| 696 |
+
"step": 490
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.1899038461538463,
|
| 700 |
+
"grad_norm": 1.1333720684051514,
|
| 701 |
+
"learning_rate": 2.1227936529395842e-05,
|
| 702 |
+
"loss": 0.3029,
|
| 703 |
+
"step": 495
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.2019230769230769,
|
| 707 |
+
"grad_norm": 1.0409576892852783,
|
| 708 |
+
"learning_rate": 2.1046508111091116e-05,
|
| 709 |
+
"loss": 0.2937,
|
| 710 |
+
"step": 500
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.2139423076923077,
|
| 714 |
+
"grad_norm": 1.1262787580490112,
|
| 715 |
+
"learning_rate": 2.0864017260319356e-05,
|
| 716 |
+
"loss": 0.2771,
|
| 717 |
+
"step": 505
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.2259615384615385,
|
| 721 |
+
"grad_norm": 1.2130638360977173,
|
| 722 |
+
"learning_rate": 2.068049604256384e-05,
|
| 723 |
+
"loss": 0.2715,
|
| 724 |
+
"step": 510
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.2379807692307692,
|
| 728 |
+
"grad_norm": 1.0754139423370361,
|
| 729 |
+
"learning_rate": 2.0495976704353747e-05,
|
| 730 |
+
"loss": 0.2508,
|
| 731 |
+
"step": 515
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.25,
|
| 735 |
+
"grad_norm": 1.1324025392532349,
|
| 736 |
+
"learning_rate": 2.0310491667598054e-05,
|
| 737 |
+
"loss": 0.2458,
|
| 738 |
+
"step": 520
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.2620192307692308,
|
| 742 |
+
"grad_norm": 1.1243354082107544,
|
| 743 |
+
"learning_rate": 2.0124073523888738e-05,
|
| 744 |
+
"loss": 0.2414,
|
| 745 |
+
"step": 525
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.2740384615384617,
|
| 749 |
+
"grad_norm": 1.2003353834152222,
|
| 750 |
+
"learning_rate": 1.9936755028774077e-05,
|
| 751 |
+
"loss": 0.2709,
|
| 752 |
+
"step": 530
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.2860576923076923,
|
| 756 |
+
"grad_norm": 1.124956488609314,
|
| 757 |
+
"learning_rate": 1.9748569096003166e-05,
|
| 758 |
+
"loss": 0.2755,
|
| 759 |
+
"step": 535
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.2980769230769231,
|
| 763 |
+
"grad_norm": 1.1734342575073242,
|
| 764 |
+
"learning_rate": 1.9559548791742647e-05,
|
| 765 |
+
"loss": 0.2455,
|
| 766 |
+
"step": 540
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.3100961538461537,
|
| 770 |
+
"grad_norm": 1.18361496925354,
|
| 771 |
+
"learning_rate": 1.9369727328766652e-05,
|
| 772 |
+
"loss": 0.2735,
|
| 773 |
+
"step": 545
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.3221153846153846,
|
| 777 |
+
"grad_norm": 1.1195272207260132,
|
| 778 |
+
"learning_rate": 1.917913806062098e-05,
|
| 779 |
+
"loss": 0.2547,
|
| 780 |
+
"step": 550
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.3341346153846154,
|
| 784 |
+
"grad_norm": 1.090206265449524,
|
| 785 |
+
"learning_rate": 1.8987814475762543e-05,
|
| 786 |
+
"loss": 0.2507,
|
| 787 |
+
"step": 555
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.3461538461538463,
|
| 791 |
+
"grad_norm": 1.1639816761016846,
|
| 792 |
+
"learning_rate": 1.8795790191675113e-05,
|
| 793 |
+
"loss": 0.2599,
|
| 794 |
+
"step": 560
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.3581730769230769,
|
| 798 |
+
"grad_norm": 1.1676899194717407,
|
| 799 |
+
"learning_rate": 1.8603098948962367e-05,
|
| 800 |
+
"loss": 0.1926,
|
| 801 |
+
"step": 565
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.3701923076923077,
|
| 805 |
+
"grad_norm": 1.2414155006408691,
|
| 806 |
+
"learning_rate": 1.8409774605419357e-05,
|
| 807 |
+
"loss": 0.2148,
|
| 808 |
+
"step": 570
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.3822115384615383,
|
| 812 |
+
"grad_norm": 1.0530052185058594,
|
| 813 |
+
"learning_rate": 1.821585113008333e-05,
|
| 814 |
+
"loss": 0.2494,
|
| 815 |
+
"step": 575
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.3942307692307692,
|
| 819 |
+
"grad_norm": 1.2354861497879028,
|
| 820 |
+
"learning_rate": 1.8021362597265038e-05,
|
| 821 |
+
"loss": 0.2665,
|
| 822 |
+
"step": 580
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.40625,
|
| 826 |
+
"grad_norm": 1.236233115196228,
|
| 827 |
+
"learning_rate": 1.782634318056153e-05,
|
| 828 |
+
"loss": 0.2383,
|
| 829 |
+
"step": 585
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.4182692307692308,
|
| 833 |
+
"grad_norm": 1.0393859148025513,
|
| 834 |
+
"learning_rate": 1.7630827146851496e-05,
|
| 835 |
+
"loss": 0.2522,
|
| 836 |
+
"step": 590
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.4302884615384617,
|
| 840 |
+
"grad_norm": 1.117124319076538,
|
| 841 |
+
"learning_rate": 1.7434848850274267e-05,
|
| 842 |
+
"loss": 0.2497,
|
| 843 |
+
"step": 595
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.4423076923076923,
|
| 847 |
+
"grad_norm": 0.9746337532997131,
|
| 848 |
+
"learning_rate": 1.72384427261934e-05,
|
| 849 |
+
"loss": 0.2437,
|
| 850 |
+
"step": 600
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.4543269230769231,
|
| 854 |
+
"grad_norm": 1.3971160650253296,
|
| 855 |
+
"learning_rate": 1.7041643285146077e-05,
|
| 856 |
+
"loss": 0.2032,
|
| 857 |
+
"step": 605
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.4663461538461537,
|
| 861 |
+
"grad_norm": 1.4052479267120361,
|
| 862 |
+
"learning_rate": 1.6844485106779233e-05,
|
| 863 |
+
"loss": 0.2294,
|
| 864 |
+
"step": 610
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.4783653846153846,
|
| 868 |
+
"grad_norm": 1.1875889301300049,
|
| 869 |
+
"learning_rate": 1.6647002833773565e-05,
|
| 870 |
+
"loss": 0.2181,
|
| 871 |
+
"step": 615
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.4903846153846154,
|
| 875 |
+
"grad_norm": 1.1940609216690063,
|
| 876 |
+
"learning_rate": 1.6449231165756467e-05,
|
| 877 |
+
"loss": 0.2062,
|
| 878 |
+
"step": 620
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.5024038461538463,
|
| 882 |
+
"grad_norm": 1.250762701034546,
|
| 883 |
+
"learning_rate": 1.6251204853204963e-05,
|
| 884 |
+
"loss": 0.2177,
|
| 885 |
+
"step": 625
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.5144230769230769,
|
| 889 |
+
"grad_norm": 1.129923701286316,
|
| 890 |
+
"learning_rate": 1.6052958691339684e-05,
|
| 891 |
+
"loss": 0.1962,
|
| 892 |
+
"step": 630
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 1.5264423076923077,
|
| 896 |
+
"grad_norm": 1.3019468784332275,
|
| 897 |
+
"learning_rate": 1.5854527514011003e-05,
|
| 898 |
+
"loss": 0.207,
|
| 899 |
+
"step": 635
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 1.5384615384615383,
|
| 903 |
+
"grad_norm": 1.054835557937622,
|
| 904 |
+
"learning_rate": 1.565594618757838e-05,
|
| 905 |
+
"loss": 0.1919,
|
| 906 |
+
"step": 640
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.5504807692307692,
|
| 910 |
+
"grad_norm": 1.2226996421813965,
|
| 911 |
+
"learning_rate": 1.5457249604783987e-05,
|
| 912 |
+
"loss": 0.1945,
|
| 913 |
+
"step": 645
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.5625,
|
| 917 |
+
"grad_norm": 1.1076081991195679,
|
| 918 |
+
"learning_rate": 1.5258472678621689e-05,
|
| 919 |
+
"loss": 0.2006,
|
| 920 |
+
"step": 650
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.5745192307692308,
|
| 924 |
+
"grad_norm": 1.3228180408477783,
|
| 925 |
+
"learning_rate": 1.5059650336202514e-05,
|
| 926 |
+
"loss": 0.2046,
|
| 927 |
+
"step": 655
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.5865384615384617,
|
| 931 |
+
"grad_norm": 1.0375016927719116,
|
| 932 |
+
"learning_rate": 1.4860817512617563e-05,
|
| 933 |
+
"loss": 0.1667,
|
| 934 |
+
"step": 660
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.5985576923076923,
|
| 938 |
+
"grad_norm": 1.1839097738265991,
|
| 939 |
+
"learning_rate": 1.4662009144799606e-05,
|
| 940 |
+
"loss": 0.2037,
|
| 941 |
+
"step": 665
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.6105769230769231,
|
| 945 |
+
"grad_norm": 1.3273729085922241,
|
| 946 |
+
"learning_rate": 1.446326016538426e-05,
|
| 947 |
+
"loss": 0.2081,
|
| 948 |
+
"step": 670
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 1.6225961538461537,
|
| 952 |
+
"grad_norm": 1.073245644569397,
|
| 953 |
+
"learning_rate": 1.426460549657202e-05,
|
| 954 |
+
"loss": 0.1884,
|
| 955 |
+
"step": 675
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.6346153846153846,
|
| 959 |
+
"grad_norm": 0.9736878871917725,
|
| 960 |
+
"learning_rate": 1.406608004399206e-05,
|
| 961 |
+
"loss": 0.1974,
|
| 962 |
+
"step": 680
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.6466346153846154,
|
| 966 |
+
"grad_norm": 1.1511292457580566,
|
| 967 |
+
"learning_rate": 1.3867718690568935e-05,
|
| 968 |
+
"loss": 0.1933,
|
| 969 |
+
"step": 685
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.6586538461538463,
|
| 973 |
+
"grad_norm": 1.19102942943573,
|
| 974 |
+
"learning_rate": 1.3669556290393355e-05,
|
| 975 |
+
"loss": 0.1947,
|
| 976 |
+
"step": 690
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.6706730769230769,
|
| 980 |
+
"grad_norm": 1.0989696979522705,
|
| 981 |
+
"learning_rate": 1.3471627662597905e-05,
|
| 982 |
+
"loss": 0.1903,
|
| 983 |
+
"step": 695
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.6826923076923077,
|
| 987 |
+
"grad_norm": 1.0407869815826416,
|
| 988 |
+
"learning_rate": 1.3273967585239034e-05,
|
| 989 |
+
"loss": 0.1905,
|
| 990 |
+
"step": 700
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.6947115384615383,
|
| 994 |
+
"grad_norm": 1.0488600730895996,
|
| 995 |
+
"learning_rate": 1.3076610789186147e-05,
|
| 996 |
+
"loss": 0.1659,
|
| 997 |
+
"step": 705
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 1.7067307692307692,
|
| 1001 |
+
"grad_norm": 1.110643982887268,
|
| 1002 |
+
"learning_rate": 1.2879591952019086e-05,
|
| 1003 |
+
"loss": 0.1579,
|
| 1004 |
+
"step": 710
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.71875,
|
| 1008 |
+
"grad_norm": 1.141809344291687,
|
| 1009 |
+
"learning_rate": 1.2682945691934882e-05,
|
| 1010 |
+
"loss": 0.1531,
|
| 1011 |
+
"step": 715
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 1.7307692307692308,
|
| 1015 |
+
"grad_norm": 1.0936837196350098,
|
| 1016 |
+
"learning_rate": 1.2486706561665043e-05,
|
| 1017 |
+
"loss": 0.1678,
|
| 1018 |
+
"step": 720
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.7427884615384617,
|
| 1022 |
+
"grad_norm": 1.1208605766296387,
|
| 1023 |
+
"learning_rate": 1.2290909042404234e-05,
|
| 1024 |
+
"loss": 0.1659,
|
| 1025 |
+
"step": 725
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 1.7548076923076923,
|
| 1029 |
+
"grad_norm": 1.1449054479599,
|
| 1030 |
+
"learning_rate": 1.209558753775163e-05,
|
| 1031 |
+
"loss": 0.1384,
|
| 1032 |
+
"step": 730
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 1.7668269230769231,
|
| 1036 |
+
"grad_norm": 1.1121894121170044,
|
| 1037 |
+
"learning_rate": 1.1900776367665839e-05,
|
| 1038 |
+
"loss": 0.165,
|
| 1039 |
+
"step": 735
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 1.7788461538461537,
|
| 1043 |
+
"grad_norm": 1.1895214319229126,
|
| 1044 |
+
"learning_rate": 1.1706509762434517e-05,
|
| 1045 |
+
"loss": 0.1651,
|
| 1046 |
+
"step": 740
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.7908653846153846,
|
| 1050 |
+
"grad_norm": 1.1474723815917969,
|
| 1051 |
+
"learning_rate": 1.1512821856659805e-05,
|
| 1052 |
+
"loss": 0.1648,
|
| 1053 |
+
"step": 745
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 1.8028846153846154,
|
| 1057 |
+
"grad_norm": 1.071448802947998,
|
| 1058 |
+
"learning_rate": 1.1319746683260498e-05,
|
| 1059 |
+
"loss": 0.1641,
|
| 1060 |
+
"step": 750
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 1.8149038461538463,
|
| 1064 |
+
"grad_norm": 1.2289284467697144,
|
| 1065 |
+
"learning_rate": 1.1127318167492146e-05,
|
| 1066 |
+
"loss": 0.1367,
|
| 1067 |
+
"step": 755
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 1.8269230769230769,
|
| 1071 |
+
"grad_norm": 1.0453468561172485,
|
| 1072 |
+
"learning_rate": 1.0935570120986009e-05,
|
| 1073 |
+
"loss": 0.1656,
|
| 1074 |
+
"step": 760
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.8389423076923077,
|
| 1078 |
+
"grad_norm": 1.0767699480056763,
|
| 1079 |
+
"learning_rate": 1.074453623580806e-05,
|
| 1080 |
+
"loss": 0.1152,
|
| 1081 |
+
"step": 765
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 1.8509615384615383,
|
| 1085 |
+
"grad_norm": 1.0895256996154785,
|
| 1086 |
+
"learning_rate": 1.055425007853889e-05,
|
| 1087 |
+
"loss": 0.1559,
|
| 1088 |
+
"step": 770
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 1.8629807692307692,
|
| 1092 |
+
"grad_norm": 1.0803401470184326,
|
| 1093 |
+
"learning_rate": 1.036474508437579e-05,
|
| 1094 |
+
"loss": 0.1514,
|
| 1095 |
+
"step": 775
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 1.875,
|
| 1099 |
+
"grad_norm": 1.0541728734970093,
|
| 1100 |
+
"learning_rate": 1.0176054551257783e-05,
|
| 1101 |
+
"loss": 0.1536,
|
| 1102 |
+
"step": 780
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 1.8870192307692308,
|
| 1106 |
+
"grad_norm": 1.0652881860733032,
|
| 1107 |
+
"learning_rate": 9.988211634014898e-06,
|
| 1108 |
+
"loss": 0.1193,
|
| 1109 |
+
"step": 785
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 1.8990384615384617,
|
| 1113 |
+
"grad_norm": 1.1308025121688843,
|
| 1114 |
+
"learning_rate": 9.801249338542477e-06,
|
| 1115 |
+
"loss": 0.1465,
|
| 1116 |
+
"step": 790
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 1.9110576923076923,
|
| 1120 |
+
"grad_norm": 0.9933103322982788,
|
| 1121 |
+
"learning_rate": 9.615200516001759e-06,
|
| 1122 |
+
"loss": 0.1493,
|
| 1123 |
+
"step": 795
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 1.9230769230769231,
|
| 1127 |
+
"grad_norm": 1.1899884939193726,
|
| 1128 |
+
"learning_rate": 9.430097857047551e-06,
|
| 1129 |
+
"loss": 0.1314,
|
| 1130 |
+
"step": 800
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 1.9350961538461537,
|
| 1134 |
+
"grad_norm": 1.2951399087905884,
|
| 1135 |
+
"learning_rate": 9.245973886084196e-06,
|
| 1136 |
+
"loss": 0.1423,
|
| 1137 |
+
"step": 805
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 1.9471153846153846,
|
| 1141 |
+
"grad_norm": 1.0231060981750488,
|
| 1142 |
+
"learning_rate": 9.062860955550673e-06,
|
| 1143 |
+
"loss": 0.1287,
|
| 1144 |
+
"step": 810
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 1.9591346153846154,
|
| 1148 |
+
"grad_norm": 1.068280577659607,
|
| 1149 |
+
"learning_rate": 8.880791240235956e-06,
|
| 1150 |
+
"loss": 0.1293,
|
| 1151 |
+
"step": 815
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.9711538461538463,
|
| 1155 |
+
"grad_norm": 1.1946337223052979,
|
| 1156 |
+
"learning_rate": 8.699796731625593e-06,
|
| 1157 |
+
"loss": 0.1304,
|
| 1158 |
+
"step": 820
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 1.9831730769230769,
|
| 1162 |
+
"grad_norm": 1.1802127361297607,
|
| 1163 |
+
"learning_rate": 8.519909232280457e-06,
|
| 1164 |
+
"loss": 0.1302,
|
| 1165 |
+
"step": 825
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 1.9951923076923077,
|
| 1169 |
+
"grad_norm": 1.2763161659240723,
|
| 1170 |
+
"learning_rate": 8.34116035024874e-06,
|
| 1171 |
+
"loss": 0.124,
|
| 1172 |
+
"step": 830
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 2.0072115384615383,
|
| 1176 |
+
"grad_norm": 0.8236063122749329,
|
| 1177 |
+
"learning_rate": 8.163581493512065e-06,
|
| 1178 |
+
"loss": 0.1243,
|
| 1179 |
+
"step": 835
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 2.019230769230769,
|
| 1183 |
+
"grad_norm": 1.3003407716751099,
|
| 1184 |
+
"learning_rate": 7.987203864466837e-06,
|
| 1185 |
+
"loss": 0.089,
|
| 1186 |
+
"step": 840
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 2.03125,
|
| 1190 |
+
"grad_norm": 0.911975085735321,
|
| 1191 |
+
"learning_rate": 7.81205845444161e-06,
|
| 1192 |
+
"loss": 0.1007,
|
| 1193 |
+
"step": 845
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 2.043269230769231,
|
| 1197 |
+
"grad_norm": 1.0726350545883179,
|
| 1198 |
+
"learning_rate": 7.63817603825165e-06,
|
| 1199 |
+
"loss": 0.1297,
|
| 1200 |
+
"step": 850
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 2.0552884615384617,
|
| 1204 |
+
"grad_norm": 0.9304943084716797,
|
| 1205 |
+
"learning_rate": 7.465587168791451e-06,
|
| 1206 |
+
"loss": 0.1065,
|
| 1207 |
+
"step": 855
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 2.0673076923076925,
|
| 1211 |
+
"grad_norm": 0.858324408531189,
|
| 1212 |
+
"learning_rate": 7.294322171666301e-06,
|
| 1213 |
+
"loss": 0.0915,
|
| 1214 |
+
"step": 860
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 2.079326923076923,
|
| 1218 |
+
"grad_norm": 0.7753244042396545,
|
| 1219 |
+
"learning_rate": 7.124411139863774e-06,
|
| 1220 |
+
"loss": 0.0915,
|
| 1221 |
+
"step": 865
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 2.0913461538461537,
|
| 1225 |
+
"grad_norm": 0.9631093740463257,
|
| 1226 |
+
"learning_rate": 6.955883928466074e-06,
|
| 1227 |
+
"loss": 0.0922,
|
| 1228 |
+
"step": 870
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 2.1033653846153846,
|
| 1232 |
+
"grad_norm": 1.0768178701400757,
|
| 1233 |
+
"learning_rate": 6.788770149404197e-06,
|
| 1234 |
+
"loss": 0.0965,
|
| 1235 |
+
"step": 875
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 2.1153846153846154,
|
| 1239 |
+
"grad_norm": 0.8874614238739014,
|
| 1240 |
+
"learning_rate": 6.623099166254816e-06,
|
| 1241 |
+
"loss": 0.1077,
|
| 1242 |
+
"step": 880
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 2.1274038461538463,
|
| 1246 |
+
"grad_norm": 1.0433396100997925,
|
| 1247 |
+
"learning_rate": 6.458900089080827e-06,
|
| 1248 |
+
"loss": 0.113,
|
| 1249 |
+
"step": 885
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 2.139423076923077,
|
| 1253 |
+
"grad_norm": 0.9960035085678101,
|
| 1254 |
+
"learning_rate": 6.296201769316374e-06,
|
| 1255 |
+
"loss": 0.086,
|
| 1256 |
+
"step": 890
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 2.1514423076923075,
|
| 1260 |
+
"grad_norm": 1.2471390962600708,
|
| 1261 |
+
"learning_rate": 6.135032794697411e-06,
|
| 1262 |
+
"loss": 0.0883,
|
| 1263 |
+
"step": 895
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 2.1634615384615383,
|
| 1267 |
+
"grad_norm": 0.9632691740989685,
|
| 1268 |
+
"learning_rate": 5.975421484238501e-06,
|
| 1269 |
+
"loss": 0.0991,
|
| 1270 |
+
"step": 900
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 2.175480769230769,
|
| 1274 |
+
"grad_norm": 0.935407817363739,
|
| 1275 |
+
"learning_rate": 5.817395883256922e-06,
|
| 1276 |
+
"loss": 0.1097,
|
| 1277 |
+
"step": 905
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 2.1875,
|
| 1281 |
+
"grad_norm": 0.9011824131011963,
|
| 1282 |
+
"learning_rate": 5.660983758444781e-06,
|
| 1283 |
+
"loss": 0.0999,
|
| 1284 |
+
"step": 910
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 2.199519230769231,
|
| 1288 |
+
"grad_norm": 1.3069969415664673,
|
| 1289 |
+
"learning_rate": 5.506212592990162e-06,
|
| 1290 |
+
"loss": 0.0924,
|
| 1291 |
+
"step": 915
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 2.2115384615384617,
|
| 1295 |
+
"grad_norm": 0.9187776446342468,
|
| 1296 |
+
"learning_rate": 5.353109581748032e-06,
|
| 1297 |
+
"loss": 0.0905,
|
| 1298 |
+
"step": 920
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 2.2235576923076925,
|
| 1302 |
+
"grad_norm": 0.8160563111305237,
|
| 1303 |
+
"learning_rate": 5.201701626461843e-06,
|
| 1304 |
+
"loss": 0.0917,
|
| 1305 |
+
"step": 925
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 2.235576923076923,
|
| 1309 |
+
"grad_norm": 1.1737111806869507,
|
| 1310 |
+
"learning_rate": 5.0520153310366e-06,
|
| 1311 |
+
"loss": 0.0896,
|
| 1312 |
+
"step": 930
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 2.2475961538461537,
|
| 1316 |
+
"grad_norm": 1.0108404159545898,
|
| 1317 |
+
"learning_rate": 4.904076996864324e-06,
|
| 1318 |
+
"loss": 0.0902,
|
| 1319 |
+
"step": 935
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 2.2596153846153846,
|
| 1323 |
+
"grad_norm": 0.8107301592826843,
|
| 1324 |
+
"learning_rate": 4.757912618202593e-06,
|
| 1325 |
+
"loss": 0.0915,
|
| 1326 |
+
"step": 940
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 2.2716346153846154,
|
| 1330 |
+
"grad_norm": 2.5428028106689453,
|
| 1331 |
+
"learning_rate": 4.613547877607125e-06,
|
| 1332 |
+
"loss": 0.084,
|
| 1333 |
+
"step": 945
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 2.2836538461538463,
|
| 1337 |
+
"grad_norm": 0.781078040599823,
|
| 1338 |
+
"learning_rate": 4.471008141419066e-06,
|
| 1339 |
+
"loss": 0.0797,
|
| 1340 |
+
"step": 950
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 2.295673076923077,
|
| 1344 |
+
"grad_norm": 0.9500632882118225,
|
| 1345 |
+
"learning_rate": 4.3303184553078766e-06,
|
| 1346 |
+
"loss": 0.0913,
|
| 1347 |
+
"step": 955
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 2.3076923076923075,
|
| 1351 |
+
"grad_norm": 0.7812657356262207,
|
| 1352 |
+
"learning_rate": 4.191503539870567e-06,
|
| 1353 |
+
"loss": 0.0675,
|
| 1354 |
+
"step": 960
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 2.3197115384615383,
|
| 1358 |
+
"grad_norm": 0.7566204071044922,
|
| 1359 |
+
"learning_rate": 4.0545877862880205e-06,
|
| 1360 |
+
"loss": 0.0839,
|
| 1361 |
+
"step": 965
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 2.331730769230769,
|
| 1365 |
+
"grad_norm": 0.8071829080581665,
|
| 1366 |
+
"learning_rate": 3.919595252039238e-06,
|
| 1367 |
+
"loss": 0.0716,
|
| 1368 |
+
"step": 970
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 2.34375,
|
| 1372 |
+
"grad_norm": 0.8333010673522949,
|
| 1373 |
+
"learning_rate": 3.7865496566741605e-06,
|
| 1374 |
+
"loss": 0.088,
|
| 1375 |
+
"step": 975
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 2.355769230769231,
|
| 1379 |
+
"grad_norm": 0.7376113533973694,
|
| 1380 |
+
"learning_rate": 3.6554743776459538e-06,
|
| 1381 |
+
"loss": 0.0832,
|
| 1382 |
+
"step": 980
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 2.3677884615384617,
|
| 1386 |
+
"grad_norm": 0.8682145476341248,
|
| 1387 |
+
"learning_rate": 3.5263924462033075e-06,
|
| 1388 |
+
"loss": 0.0883,
|
| 1389 |
+
"step": 985
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 2.3798076923076925,
|
| 1393 |
+
"grad_norm": 0.7741600871086121,
|
| 1394 |
+
"learning_rate": 3.3993265433436506e-06,
|
| 1395 |
+
"loss": 0.0764,
|
| 1396 |
+
"step": 990
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 2.391826923076923,
|
| 1400 |
+
"grad_norm": 0.7913270592689514,
|
| 1401 |
+
"learning_rate": 3.2742989958278375e-06,
|
| 1402 |
+
"loss": 0.0637,
|
| 1403 |
+
"step": 995
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 2.4038461538461537,
|
| 1407 |
+
"grad_norm": 0.7780194282531738,
|
| 1408 |
+
"learning_rate": 3.1513317722571468e-06,
|
| 1409 |
+
"loss": 0.0803,
|
| 1410 |
+
"step": 1000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 2.4158653846153846,
|
| 1414 |
+
"grad_norm": 1.0683140754699707,
|
| 1415 |
+
"learning_rate": 3.0304464792131338e-06,
|
| 1416 |
+
"loss": 0.0798,
|
| 1417 |
+
"step": 1005
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 2.4278846153846154,
|
| 1421 |
+
"grad_norm": 0.8349136114120483,
|
| 1422 |
+
"learning_rate": 2.9116643574611783e-06,
|
| 1423 |
+
"loss": 0.0758,
|
| 1424 |
+
"step": 1010
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 2.4399038461538463,
|
| 1428 |
+
"grad_norm": 0.8111016154289246,
|
| 1429 |
+
"learning_rate": 2.7950062782182474e-06,
|
| 1430 |
+
"loss": 0.0982,
|
| 1431 |
+
"step": 1015
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 2.451923076923077,
|
| 1435 |
+
"grad_norm": 0.6899818778038025,
|
| 1436 |
+
"learning_rate": 2.6804927394856015e-06,
|
| 1437 |
+
"loss": 0.0818,
|
| 1438 |
+
"step": 1020
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 2.4639423076923075,
|
| 1442 |
+
"grad_norm": 0.7170876860618591,
|
| 1443 |
+
"learning_rate": 2.568143862447117e-06,
|
| 1444 |
+
"loss": 0.0845,
|
| 1445 |
+
"step": 1025
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 2.4759615384615383,
|
| 1449 |
+
"grad_norm": 0.8445954322814941,
|
| 1450 |
+
"learning_rate": 2.457979387933759e-06,
|
| 1451 |
+
"loss": 0.0788,
|
| 1452 |
+
"step": 1030
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 2.487980769230769,
|
| 1456 |
+
"grad_norm": 0.8173021674156189,
|
| 1457 |
+
"learning_rate": 2.3500186729549482e-06,
|
| 1458 |
+
"loss": 0.0795,
|
| 1459 |
+
"step": 1035
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 2.5,
|
| 1463 |
+
"grad_norm": 0.6942948698997498,
|
| 1464 |
+
"learning_rate": 2.2442806872973177e-06,
|
| 1465 |
+
"loss": 0.0789,
|
| 1466 |
+
"step": 1040
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 2.512019230769231,
|
| 1470 |
+
"grad_norm": 0.7162089943885803,
|
| 1471 |
+
"learning_rate": 2.1407840101915456e-06,
|
| 1472 |
+
"loss": 0.0596,
|
| 1473 |
+
"step": 1045
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 2.5240384615384617,
|
| 1477 |
+
"grad_norm": 0.7772409319877625,
|
| 1478 |
+
"learning_rate": 2.0395468270477763e-06,
|
| 1479 |
+
"loss": 0.0663,
|
| 1480 |
+
"step": 1050
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 2.5360576923076925,
|
| 1484 |
+
"grad_norm": 0.8099181652069092,
|
| 1485 |
+
"learning_rate": 1.9405869262602842e-06,
|
| 1486 |
+
"loss": 0.0718,
|
| 1487 |
+
"step": 1055
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 2.5480769230769234,
|
| 1491 |
+
"grad_norm": 0.8204342722892761,
|
| 1492 |
+
"learning_rate": 1.8439216960818623e-06,
|
| 1493 |
+
"loss": 0.0682,
|
| 1494 |
+
"step": 1060
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 2.5600961538461537,
|
| 1498 |
+
"grad_norm": 0.7497991323471069,
|
| 1499 |
+
"learning_rate": 1.7495681215685232e-06,
|
| 1500 |
+
"loss": 0.0745,
|
| 1501 |
+
"step": 1065
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 2.5721153846153846,
|
| 1505 |
+
"grad_norm": 0.8546372056007385,
|
| 1506 |
+
"learning_rate": 1.6575427815950672e-06,
|
| 1507 |
+
"loss": 0.071,
|
| 1508 |
+
"step": 1070
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 2.5841346153846154,
|
| 1512 |
+
"grad_norm": 0.8411610126495361,
|
| 1513 |
+
"learning_rate": 1.5678618459420036e-06,
|
| 1514 |
+
"loss": 0.0885,
|
| 1515 |
+
"step": 1075
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 2.5961538461538463,
|
| 1519 |
+
"grad_norm": 0.7687364816665649,
|
| 1520 |
+
"learning_rate": 1.4805410724543427e-06,
|
| 1521 |
+
"loss": 0.0743,
|
| 1522 |
+
"step": 1080
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 2.6081730769230766,
|
| 1526 |
+
"grad_norm": 0.8551532626152039,
|
| 1527 |
+
"learning_rate": 1.3955958042728078e-06,
|
| 1528 |
+
"loss": 0.0753,
|
| 1529 |
+
"step": 1085
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 2.6201923076923075,
|
| 1533 |
+
"grad_norm": 0.8031885027885437,
|
| 1534 |
+
"learning_rate": 1.3130409671378724e-06,
|
| 1535 |
+
"loss": 0.0772,
|
| 1536 |
+
"step": 1090
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 2.6322115384615383,
|
| 1540 |
+
"grad_norm": 0.8098322153091431,
|
| 1541 |
+
"learning_rate": 1.2328910667671568e-06,
|
| 1542 |
+
"loss": 0.077,
|
| 1543 |
+
"step": 1095
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 2.644230769230769,
|
| 1547 |
+
"grad_norm": 0.7140254974365234,
|
| 1548 |
+
"learning_rate": 1.1551601863066452e-06,
|
| 1549 |
+
"loss": 0.0722,
|
| 1550 |
+
"step": 1100
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 2.65625,
|
| 1554 |
+
"grad_norm": 0.8040745258331299,
|
| 1555 |
+
"learning_rate": 1.0798619838561109e-06,
|
| 1556 |
+
"loss": 0.0739,
|
| 1557 |
+
"step": 1105
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 2.668269230769231,
|
| 1561 |
+
"grad_norm": 0.6164737343788147,
|
| 1562 |
+
"learning_rate": 1.0070096900692694e-06,
|
| 1563 |
+
"loss": 0.0752,
|
| 1564 |
+
"step": 1110
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 2.6802884615384617,
|
| 1568 |
+
"grad_norm": 0.7043773531913757,
|
| 1569 |
+
"learning_rate": 9.366161058290113e-07,
|
| 1570 |
+
"loss": 0.0689,
|
| 1571 |
+
"step": 1115
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 2.6923076923076925,
|
| 1575 |
+
"grad_norm": 0.6824246048927307,
|
| 1576 |
+
"learning_rate": 8.686935999981588e-07,
|
| 1577 |
+
"loss": 0.0791,
|
| 1578 |
+
"step": 1120
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 2.7043269230769234,
|
| 1582 |
+
"grad_norm": 0.7310678958892822,
|
| 1583 |
+
"learning_rate": 8.032541072461231e-07,
|
| 1584 |
+
"loss": 0.0675,
|
| 1585 |
+
"step": 1125
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 2.7163461538461537,
|
| 1589 |
+
"grad_norm": 0.7166014909744263,
|
| 1590 |
+
"learning_rate": 7.403091259518829e-07,
|
| 1591 |
+
"loss": 0.0754,
|
| 1592 |
+
"step": 1130
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 2.7283653846153846,
|
| 1596 |
+
"grad_norm": 0.7140399217605591,
|
| 1597 |
+
"learning_rate": 6.798697161835815e-07,
|
| 1598 |
+
"loss": 0.0688,
|
| 1599 |
+
"step": 1135
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 2.7403846153846154,
|
| 1603 |
+
"grad_norm": 0.698891818523407,
|
| 1604 |
+
"learning_rate": 6.21946497755182e-07,
|
| 1605 |
+
"loss": 0.0743,
|
| 1606 |
+
"step": 1140
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 2.7524038461538463,
|
| 1610 |
+
"grad_norm": 0.5776200294494629,
|
| 1611 |
+
"learning_rate": 5.665496483604338e-07,
|
| 1612 |
+
"loss": 0.0739,
|
| 1613 |
+
"step": 1145
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 2.7644230769230766,
|
| 1617 |
+
"grad_norm": 0.7660831809043884,
|
| 1618 |
+
"learning_rate": 5.136889017845764e-07,
|
| 1619 |
+
"loss": 0.0819,
|
| 1620 |
+
"step": 1150
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 2.7764423076923075,
|
| 1624 |
+
"grad_norm": 0.8342573046684265,
|
| 1625 |
+
"learning_rate": 4.633735461939925e-07,
|
| 1626 |
+
"loss": 0.0768,
|
| 1627 |
+
"step": 1155
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 2.7884615384615383,
|
| 1631 |
+
"grad_norm": 0.7281113266944885,
|
| 1632 |
+
"learning_rate": 4.1561242250419853e-07,
|
| 1633 |
+
"loss": 0.0678,
|
| 1634 |
+
"step": 1160
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 2.800480769230769,
|
| 1638 |
+
"grad_norm": 0.902446448802948,
|
| 1639 |
+
"learning_rate": 3.7041392282640196e-07,
|
| 1640 |
+
"loss": 0.0736,
|
| 1641 |
+
"step": 1165
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 2.8125,
|
| 1645 |
+
"grad_norm": 0.5936735272407532,
|
| 1646 |
+
"learning_rate": 3.277859889929147e-07,
|
| 1647 |
+
"loss": 0.0667,
|
| 1648 |
+
"step": 1170
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 2.824519230769231,
|
| 1652 |
+
"grad_norm": 0.6778994202613831,
|
| 1653 |
+
"learning_rate": 2.877361111617105e-07,
|
| 1654 |
+
"loss": 0.065,
|
| 1655 |
+
"step": 1175
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 2.8365384615384617,
|
| 1659 |
+
"grad_norm": 0.7414957284927368,
|
| 1660 |
+
"learning_rate": 2.502713265003065e-07,
|
| 1661 |
+
"loss": 0.0777,
|
| 1662 |
+
"step": 1180
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 2.8485576923076925,
|
| 1666 |
+
"grad_norm": 0.685934841632843,
|
| 1667 |
+
"learning_rate": 2.1539821794928528e-07,
|
| 1668 |
+
"loss": 0.0692,
|
| 1669 |
+
"step": 1185
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 2.8605769230769234,
|
| 1673 |
+
"grad_norm": 0.6723203659057617,
|
| 1674 |
+
"learning_rate": 1.8312291306558538e-07,
|
| 1675 |
+
"loss": 0.0709,
|
| 1676 |
+
"step": 1190
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 2.8725961538461537,
|
| 1680 |
+
"grad_norm": 0.6801092028617859,
|
| 1681 |
+
"learning_rate": 1.5345108294584077e-07,
|
| 1682 |
+
"loss": 0.0677,
|
| 1683 |
+
"step": 1195
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 2.8846153846153846,
|
| 1687 |
+
"grad_norm": 1.09250009059906,
|
| 1688 |
+
"learning_rate": 1.2638794122990793e-07,
|
| 1689 |
+
"loss": 0.071,
|
| 1690 |
+
"step": 1200
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 2.8966346153846154,
|
| 1694 |
+
"grad_norm": 0.7001774907112122,
|
| 1695 |
+
"learning_rate": 1.019382431847754e-07,
|
| 1696 |
+
"loss": 0.0698,
|
| 1697 |
+
"step": 1205
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 2.9086538461538463,
|
| 1701 |
+
"grad_norm": 0.6066254377365112,
|
| 1702 |
+
"learning_rate": 8.010628486901705e-08,
|
| 1703 |
+
"loss": 0.0738,
|
| 1704 |
+
"step": 1210
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 2.9206730769230766,
|
| 1708 |
+
"grad_norm": 0.6269055604934692,
|
| 1709 |
+
"learning_rate": 6.089590237793097e-08,
|
| 1710 |
+
"loss": 0.0611,
|
| 1711 |
+
"step": 1215
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 2.9326923076923075,
|
| 1715 |
+
"grad_norm": 0.6657592058181763,
|
| 1716 |
+
"learning_rate": 4.4310471169498604e-08,
|
| 1717 |
+
"loss": 0.0745,
|
| 1718 |
+
"step": 1220
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 2.9447115384615383,
|
| 1722 |
+
"grad_norm": 0.6391530632972717,
|
| 1723 |
+
"learning_rate": 3.0352905471280887e-08,
|
| 1724 |
+
"loss": 0.071,
|
| 1725 |
+
"step": 1225
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 2.956730769230769,
|
| 1729 |
+
"grad_norm": 0.7078071236610413,
|
| 1730 |
+
"learning_rate": 1.902565776836618e-08,
|
| 1731 |
+
"loss": 0.0596,
|
| 1732 |
+
"step": 1230
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 2.96875,
|
| 1736 |
+
"grad_norm": 0.5702892541885376,
|
| 1737 |
+
"learning_rate": 1.0330718372433268e-08,
|
| 1738 |
+
"loss": 0.0476,
|
| 1739 |
+
"step": 1235
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 2.980769230769231,
|
| 1743 |
+
"grad_norm": 0.6165497303009033,
|
| 1744 |
+
"learning_rate": 4.2696150720411556e-09,
|
| 1745 |
+
"loss": 0.0646,
|
| 1746 |
+
"step": 1240
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 2.9927884615384617,
|
| 1750 |
+
"grad_norm": 0.5987536907196045,
|
| 1751 |
+
"learning_rate": 8.434128641771066e-10,
|
| 1752 |
+
"loss": 0.0635,
|
| 1753 |
+
"step": 1245
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 3.0,
|
| 1757 |
+
"step": 1248,
|
| 1758 |
+
"total_flos": 2.1835948407453123e+18,
|
| 1759 |
+
"train_loss": 0.35027236877104795,
|
| 1760 |
+
"train_runtime": 993.3547,
|
| 1761 |
+
"train_samples_per_second": 40.179,
|
| 1762 |
+
"train_steps_per_second": 1.256
|
| 1763 |
+
}
|
| 1764 |
+
],
|
| 1765 |
+
"logging_steps": 5,
|
| 1766 |
+
"max_steps": 1248,
|
| 1767 |
+
"num_input_tokens_seen": 0,
|
| 1768 |
+
"num_train_epochs": 3,
|
| 1769 |
+
"save_steps": 2000,
|
| 1770 |
+
"stateful_callbacks": {
|
| 1771 |
+
"TrainerControl": {
|
| 1772 |
+
"args": {
|
| 1773 |
+
"should_epoch_stop": false,
|
| 1774 |
+
"should_evaluate": false,
|
| 1775 |
+
"should_log": false,
|
| 1776 |
+
"should_save": false,
|
| 1777 |
+
"should_training_stop": false
|
| 1778 |
+
},
|
| 1779 |
+
"attributes": {}
|
| 1780 |
+
}
|
| 1781 |
+
},
|
| 1782 |
+
"total_flos": 2.1835948407453123e+18,
|
| 1783 |
+
"train_batch_size": 2,
|
| 1784 |
+
"trial_name": null,
|
| 1785 |
+
"trial_params": null
|
| 1786 |
+
}
|
granite3.3/hotpotqa_test_knowledge_50_base/0_128_e3_3e-5/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:864b3ed6b51af911cf7de0017b4865f1f0ee2b636af8aa1ecc0af5696e6e194e
|
| 3 |
+
size 8273
|
granite3.3/hotpotqa_test_knowledge_50_base/0_128_e3_3e-5/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
granite3.3/hotpotqa_test_knowledge_50_base/1_128_e3_3e-5/README.md
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: ibm-granite/granite-3.3-8b-base
|
| 5 |
+
tags:
|
| 6 |
+
- alignment-handbook
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
datasets:
|
| 9 |
+
- data/hotpotqa/test/processed/knowledge_50
|
| 10 |
+
model-index:
|
| 11 |
+
- name: 1_128_e3_3e-5
|
| 12 |
+
results: []
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 16 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 17 |
+
|
| 18 |
+
# 1_128_e3_3e-5
|
| 19 |
+
|
| 20 |
+
This model is a fine-tuned version of [ibm-granite/granite-3.3-8b-base](https://huggingface.co/ibm-granite/granite-3.3-8b-base) on the data/hotpotqa/test/processed/knowledge_50 dataset.
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 3e-05
|
| 40 |
+
- train_batch_size: 2
|
| 41 |
+
- eval_batch_size: 1
|
| 42 |
+
- seed: 42
|
| 43 |
+
- distributed_type: multi-GPU
|
| 44 |
+
- num_devices: 8
|
| 45 |
+
- gradient_accumulation_steps: 2
|
| 46 |
+
- total_train_batch_size: 32
|
| 47 |
+
- total_eval_batch_size: 8
|
| 48 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 49 |
+
- lr_scheduler_type: cosine
|
| 50 |
+
- lr_scheduler_warmup_ratio: 0.05
|
| 51 |
+
- num_epochs: 3.0
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
|
| 56 |
+
|
| 57 |
+
### Framework versions
|
| 58 |
+
|
| 59 |
+
- PEFT 0.15.2
|
| 60 |
+
- Transformers 4.52.4
|
| 61 |
+
- Pytorch 2.7.0+cu126
|
| 62 |
+
- Datasets 3.6.0
|
| 63 |
+
- Tokenizers 0.21.2
|
granite3.3/hotpotqa_test_knowledge_50_base/1_128_e3_3e-5/adapter_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "ibm-granite/granite-3.3-8b-base",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 256,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.05,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 128,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"up_proj",
|
| 28 |
+
"gate_proj",
|
| 29 |
+
"o_proj",
|
| 30 |
+
"q_proj",
|
| 31 |
+
"k_proj",
|
| 32 |
+
"down_proj",
|
| 33 |
+
"v_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
+
"use_dora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
granite3.3/hotpotqa_test_knowledge_50_base/1_128_e3_3e-5/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e8cdf17e220c1cc22dfa0267d903066cb6ea513e950cbada78bf409eb48804fe
|
| 3 |
+
size 791751704
|
granite3.3/hotpotqa_test_knowledge_50_base/1_128_e3_3e-5/all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 1.9935578760308326e+18,
|
| 4 |
+
"train_loss": 0.3310968009975013,
|
| 5 |
+
"train_runtime": 917.2937,
|
| 6 |
+
"train_samples": 12163,
|
| 7 |
+
"train_samples_per_second": 39.779,
|
| 8 |
+
"train_steps_per_second": 1.246
|
| 9 |
+
}
|
granite3.3/hotpotqa_test_knowledge_50_base/1_128_e3_3e-5/config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"GraniteForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0,
|
| 7 |
+
"attention_multiplier": 0.0078125,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"embedding_multiplier": 12.0,
|
| 10 |
+
"eos_token_id": 0,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 4096,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 12800,
|
| 15 |
+
"logits_scaling": 16.0,
|
| 16 |
+
"max_position_embeddings": 131072,
|
| 17 |
+
"mlp_bias": false,
|
| 18 |
+
"model_type": "granite",
|
| 19 |
+
"num_attention_heads": 32,
|
| 20 |
+
"num_hidden_layers": 40,
|
| 21 |
+
"num_key_value_heads": 8,
|
| 22 |
+
"pad_token_id": 0,
|
| 23 |
+
"residual_multiplier": 0.22,
|
| 24 |
+
"rms_norm_eps": 1e-05,
|
| 25 |
+
"rope_scaling": null,
|
| 26 |
+
"rope_theta": 10000000.0,
|
| 27 |
+
"tie_word_embeddings": true,
|
| 28 |
+
"torch_dtype": "bfloat16",
|
| 29 |
+
"transformers_version": "4.52.4",
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 49152
|
| 32 |
+
}
|
granite3.3/hotpotqa_test_knowledge_50_base/1_128_e3_3e-5/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
granite3.3/hotpotqa_test_knowledge_50_base/1_128_e3_3e-5/special_tokens_map.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|endoftext|>",
|
| 4 |
+
"<fim_prefix>",
|
| 5 |
+
"<fim_middle>",
|
| 6 |
+
"<fim_suffix>",
|
| 7 |
+
"<fim_pad>",
|
| 8 |
+
"<filename>",
|
| 9 |
+
"<gh_stars>",
|
| 10 |
+
"<issue_start>",
|
| 11 |
+
"<issue_comment>",
|
| 12 |
+
"<issue_closed>",
|
| 13 |
+
"<jupyter_start>",
|
| 14 |
+
"<jupyter_text>",
|
| 15 |
+
"<jupyter_code>",
|
| 16 |
+
"<jupyter_output>",
|
| 17 |
+
"<empty_output>",
|
| 18 |
+
"<commit_before>",
|
| 19 |
+
"<commit_msg>",
|
| 20 |
+
"<commit_after>",
|
| 21 |
+
"<reponame>"
|
| 22 |
+
],
|
| 23 |
+
"bos_token": {
|
| 24 |
+
"content": "<|endoftext|>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"eos_token": {
|
| 31 |
+
"content": "<|endoftext|>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"pad_token": "<reponame>",
|
| 38 |
+
"unk_token": {
|
| 39 |
+
"content": "<|endoftext|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false
|
| 44 |
+
}
|
| 45 |
+
}
|