Upload folder using huggingface_hub
Browse files- 135_128_e3_3e-5/adapter_config.json +39 -0
- 135_128_e3_3e-5/adapter_model.safetensors +3 -0
- 135_128_e3_3e-5/added_tokens.json +9 -0
- 135_128_e3_3e-5/all_results.json +9 -0
- 135_128_e3_3e-5/chat_template.jinja +62 -0
- 135_128_e3_3e-5/config.json +32 -0
- 135_128_e3_3e-5/merges.txt +0 -0
- 135_128_e3_3e-5/special_tokens_map.json +33 -0
- 135_128_e3_3e-5/tokenizer.json +0 -0
- 135_128_e3_3e-5/tokenizer_config.json +234 -0
- 135_128_e3_3e-5/train_results.json +9 -0
- 135_128_e3_3e-5/trainer_state.json +1674 -0
- 135_128_e3_3e-5/training_args.bin +3 -0
- 135_128_e3_3e-5/vocab.json +0 -0
135_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-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": 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 |
+
"o_proj",
|
| 29 |
+
"v_proj",
|
| 30 |
+
"gate_proj",
|
| 31 |
+
"q_proj",
|
| 32 |
+
"k_proj",
|
| 33 |
+
"down_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
+
"use_dora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
135_128_e3_3e-5/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0a761012f22152eeedc352e3c5ec40ad26ed091a93ef7e48885553c61388d07
|
| 3 |
+
size 791751704
|
135_128_e3_3e-5/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 |
+
}
|
135_128_e3_3e-5/all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 1.460258687019909e+18,
|
| 4 |
+
"train_loss": 0.37291577482642324,
|
| 5 |
+
"train_runtime": 701.2954,
|
| 6 |
+
"train_samples": 12433,
|
| 7 |
+
"train_samples_per_second": 53.186,
|
| 8 |
+
"train_steps_per_second": 1.664
|
| 9 |
+
}
|
135_128_e3_3e-5/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 %}
|
135_128_e3_3e-5/config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"GraniteForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 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 |
+
}
|
135_128_e3_3e-5/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
135_128_e3_3e-5/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 |
+
}
|
135_128_e3_3e-5/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
135_128_e3_3e-5/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 |
+
}
|
135_128_e3_3e-5/train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 1.460258687019909e+18,
|
| 4 |
+
"train_loss": 0.37291577482642324,
|
| 5 |
+
"train_runtime": 701.2954,
|
| 6 |
+
"train_samples": 12433,
|
| 7 |
+
"train_samples_per_second": 53.186,
|
| 8 |
+
"train_steps_per_second": 1.664
|
| 9 |
+
}
|
135_128_e3_3e-5/trainer_state.json
ADDED
|
@@ -0,0 +1,1674 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 1167,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.012853470437017995,
|
| 14 |
+
"grad_norm": 2.3323185443878174,
|
| 15 |
+
"learning_rate": 2.033898305084746e-06,
|
| 16 |
+
"loss": 1.6004,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.02570694087403599,
|
| 21 |
+
"grad_norm": 1.6483618021011353,
|
| 22 |
+
"learning_rate": 4.576271186440678e-06,
|
| 23 |
+
"loss": 1.5485,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.038560411311053984,
|
| 28 |
+
"grad_norm": 0.9693793654441833,
|
| 29 |
+
"learning_rate": 7.1186440677966106e-06,
|
| 30 |
+
"loss": 1.5286,
|
| 31 |
+
"step": 15
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.05141388174807198,
|
| 35 |
+
"grad_norm": 0.6269199252128601,
|
| 36 |
+
"learning_rate": 9.661016949152542e-06,
|
| 37 |
+
"loss": 1.4503,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.06426735218508997,
|
| 42 |
+
"grad_norm": 0.6316661238670349,
|
| 43 |
+
"learning_rate": 1.2203389830508475e-05,
|
| 44 |
+
"loss": 1.4181,
|
| 45 |
+
"step": 25
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.07712082262210797,
|
| 49 |
+
"grad_norm": 0.44627124071121216,
|
| 50 |
+
"learning_rate": 1.4745762711864408e-05,
|
| 51 |
+
"loss": 1.4054,
|
| 52 |
+
"step": 30
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.08997429305912596,
|
| 56 |
+
"grad_norm": 0.42011284828186035,
|
| 57 |
+
"learning_rate": 1.728813559322034e-05,
|
| 58 |
+
"loss": 1.4507,
|
| 59 |
+
"step": 35
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.10282776349614396,
|
| 63 |
+
"grad_norm": 0.4015228748321533,
|
| 64 |
+
"learning_rate": 1.983050847457627e-05,
|
| 65 |
+
"loss": 1.4252,
|
| 66 |
+
"step": 40
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.11568123393316196,
|
| 70 |
+
"grad_norm": 0.39050647616386414,
|
| 71 |
+
"learning_rate": 2.2372881355932205e-05,
|
| 72 |
+
"loss": 1.3619,
|
| 73 |
+
"step": 45
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.12853470437017994,
|
| 77 |
+
"grad_norm": 0.3995406925678253,
|
| 78 |
+
"learning_rate": 2.4915254237288138e-05,
|
| 79 |
+
"loss": 1.3539,
|
| 80 |
+
"step": 50
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.14138817480719795,
|
| 84 |
+
"grad_norm": 0.3981720805168152,
|
| 85 |
+
"learning_rate": 2.7457627118644068e-05,
|
| 86 |
+
"loss": 1.2961,
|
| 87 |
+
"step": 55
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.15424164524421594,
|
| 91 |
+
"grad_norm": 0.43246394395828247,
|
| 92 |
+
"learning_rate": 3e-05,
|
| 93 |
+
"loss": 1.2913,
|
| 94 |
+
"step": 60
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.16709511568123395,
|
| 98 |
+
"grad_norm": 0.4783930778503418,
|
| 99 |
+
"learning_rate": 2.9998492649592036e-05,
|
| 100 |
+
"loss": 1.2855,
|
| 101 |
+
"step": 65
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.17994858611825193,
|
| 105 |
+
"grad_norm": 0.5165207386016846,
|
| 106 |
+
"learning_rate": 2.9993970901315514e-05,
|
| 107 |
+
"loss": 1.2594,
|
| 108 |
+
"step": 70
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.1928020565552699,
|
| 112 |
+
"grad_norm": 0.46765437722206116,
|
| 113 |
+
"learning_rate": 2.9986435663951645e-05,
|
| 114 |
+
"loss": 1.2574,
|
| 115 |
+
"step": 75
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.20565552699228792,
|
| 119 |
+
"grad_norm": 0.5255847573280334,
|
| 120 |
+
"learning_rate": 2.997588845193284e-05,
|
| 121 |
+
"loss": 1.2262,
|
| 122 |
+
"step": 80
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.2185089974293059,
|
| 126 |
+
"grad_norm": 0.529129147529602,
|
| 127 |
+
"learning_rate": 2.9962331385038356e-05,
|
| 128 |
+
"loss": 1.1962,
|
| 129 |
+
"step": 85
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.23136246786632392,
|
| 133 |
+
"grad_norm": 0.497693806886673,
|
| 134 |
+
"learning_rate": 2.9945767187968226e-05,
|
| 135 |
+
"loss": 1.1405,
|
| 136 |
+
"step": 90
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.2442159383033419,
|
| 140 |
+
"grad_norm": 0.5641687512397766,
|
| 141 |
+
"learning_rate": 2.9926199189795684e-05,
|
| 142 |
+
"loss": 1.1629,
|
| 143 |
+
"step": 95
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.2570694087403599,
|
| 147 |
+
"grad_norm": 0.6152422428131104,
|
| 148 |
+
"learning_rate": 2.990363132329806e-05,
|
| 149 |
+
"loss": 1.1686,
|
| 150 |
+
"step": 100
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.2699228791773779,
|
| 154 |
+
"grad_norm": 0.6150014996528625,
|
| 155 |
+
"learning_rate": 2.9878068124166394e-05,
|
| 156 |
+
"loss": 1.1254,
|
| 157 |
+
"step": 105
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.2827763496143959,
|
| 161 |
+
"grad_norm": 0.7687254548072815,
|
| 162 |
+
"learning_rate": 2.9849514730093843e-05,
|
| 163 |
+
"loss": 1.0541,
|
| 164 |
+
"step": 110
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.29562982005141386,
|
| 168 |
+
"grad_norm": 0.6652163863182068,
|
| 169 |
+
"learning_rate": 2.9817976879743092e-05,
|
| 170 |
+
"loss": 1.0482,
|
| 171 |
+
"step": 115
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.30848329048843187,
|
| 175 |
+
"grad_norm": 0.6970682144165039,
|
| 176 |
+
"learning_rate": 2.9783460911593024e-05,
|
| 177 |
+
"loss": 1.0637,
|
| 178 |
+
"step": 120
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.3213367609254499,
|
| 182 |
+
"grad_norm": 0.741788923740387,
|
| 183 |
+
"learning_rate": 2.97459737626648e-05,
|
| 184 |
+
"loss": 1.0185,
|
| 185 |
+
"step": 125
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.3341902313624679,
|
| 189 |
+
"grad_norm": 0.6817389130592346,
|
| 190 |
+
"learning_rate": 2.970552296712764e-05,
|
| 191 |
+
"loss": 0.986,
|
| 192 |
+
"step": 130
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.34704370179948585,
|
| 196 |
+
"grad_norm": 0.7854952812194824,
|
| 197 |
+
"learning_rate": 2.966211665478464e-05,
|
| 198 |
+
"loss": 1.0042,
|
| 199 |
+
"step": 135
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.35989717223650386,
|
| 203 |
+
"grad_norm": 0.7330520749092102,
|
| 204 |
+
"learning_rate": 2.961576354943881e-05,
|
| 205 |
+
"loss": 0.9638,
|
| 206 |
+
"step": 140
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.37275064267352187,
|
| 210 |
+
"grad_norm": 0.7493976950645447,
|
| 211 |
+
"learning_rate": 2.9566472967139796e-05,
|
| 212 |
+
"loss": 0.9517,
|
| 213 |
+
"step": 145
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.3856041131105398,
|
| 217 |
+
"grad_norm": 0.8060358166694641,
|
| 218 |
+
"learning_rate": 2.9514254814311492e-05,
|
| 219 |
+
"loss": 0.896,
|
| 220 |
+
"step": 150
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.39845758354755784,
|
| 224 |
+
"grad_norm": 0.8042199611663818,
|
| 225 |
+
"learning_rate": 2.9459119585761107e-05,
|
| 226 |
+
"loss": 0.912,
|
| 227 |
+
"step": 155
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.41131105398457585,
|
| 231 |
+
"grad_norm": 1.0758025646209717,
|
| 232 |
+
"learning_rate": 2.9401078362569866e-05,
|
| 233 |
+
"loss": 0.866,
|
| 234 |
+
"step": 160
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.4241645244215938,
|
| 238 |
+
"grad_norm": 0.959560751914978,
|
| 239 |
+
"learning_rate": 2.9340142809865967e-05,
|
| 240 |
+
"loss": 0.8542,
|
| 241 |
+
"step": 165
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.4370179948586118,
|
| 245 |
+
"grad_norm": 1.0657316446304321,
|
| 246 |
+
"learning_rate": 2.9276325174480108e-05,
|
| 247 |
+
"loss": 0.8501,
|
| 248 |
+
"step": 170
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.4498714652956298,
|
| 252 |
+
"grad_norm": 0.9416517615318298,
|
| 253 |
+
"learning_rate": 2.9209638282484122e-05,
|
| 254 |
+
"loss": 0.8489,
|
| 255 |
+
"step": 175
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.46272493573264784,
|
| 259 |
+
"grad_norm": 0.9036505222320557,
|
| 260 |
+
"learning_rate": 2.9140095536613182e-05,
|
| 261 |
+
"loss": 0.8095,
|
| 262 |
+
"step": 180
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.4755784061696658,
|
| 266 |
+
"grad_norm": 0.980981707572937,
|
| 267 |
+
"learning_rate": 2.9067710913572146e-05,
|
| 268 |
+
"loss": 0.7938,
|
| 269 |
+
"step": 185
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.4884318766066838,
|
| 273 |
+
"grad_norm": 0.9042716026306152,
|
| 274 |
+
"learning_rate": 2.8992498961226482e-05,
|
| 275 |
+
"loss": 0.7594,
|
| 276 |
+
"step": 190
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.5012853470437018,
|
| 280 |
+
"grad_norm": 1.0132904052734375,
|
| 281 |
+
"learning_rate": 2.8914474795678462e-05,
|
| 282 |
+
"loss": 0.7831,
|
| 283 |
+
"step": 195
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.5141388174807198,
|
| 287 |
+
"grad_norm": 0.9460030794143677,
|
| 288 |
+
"learning_rate": 2.8833654098229132e-05,
|
| 289 |
+
"loss": 0.7418,
|
| 290 |
+
"step": 200
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.5269922879177378,
|
| 294 |
+
"grad_norm": 1.1338616609573364,
|
| 295 |
+
"learning_rate": 2.8750053112226654e-05,
|
| 296 |
+
"loss": 0.7465,
|
| 297 |
+
"step": 205
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.5398457583547558,
|
| 301 |
+
"grad_norm": 1.0191024541854858,
|
| 302 |
+
"learning_rate": 2.8663688639801748e-05,
|
| 303 |
+
"loss": 0.7693,
|
| 304 |
+
"step": 210
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.5526992287917738,
|
| 308 |
+
"grad_norm": 1.0968343019485474,
|
| 309 |
+
"learning_rate": 2.8574578038490772e-05,
|
| 310 |
+
"loss": 0.7213,
|
| 311 |
+
"step": 215
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.5655526992287918,
|
| 315 |
+
"grad_norm": 1.0838876962661743,
|
| 316 |
+
"learning_rate": 2.8482739217747228e-05,
|
| 317 |
+
"loss": 0.7238,
|
| 318 |
+
"step": 220
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.5784061696658098,
|
| 322 |
+
"grad_norm": 1.0779169797897339,
|
| 323 |
+
"learning_rate": 2.838819063534231e-05,
|
| 324 |
+
"loss": 0.6921,
|
| 325 |
+
"step": 225
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.5912596401028277,
|
| 329 |
+
"grad_norm": 1.0446289777755737,
|
| 330 |
+
"learning_rate": 2.8290951293655244e-05,
|
| 331 |
+
"loss": 0.6534,
|
| 332 |
+
"step": 230
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.6041131105398457,
|
| 336 |
+
"grad_norm": 1.2199687957763672,
|
| 337 |
+
"learning_rate": 2.819104073585422e-05,
|
| 338 |
+
"loss": 0.6783,
|
| 339 |
+
"step": 235
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.6169665809768637,
|
| 343 |
+
"grad_norm": 1.1266030073165894,
|
| 344 |
+
"learning_rate": 2.808847904196857e-05,
|
| 345 |
+
"loss": 0.64,
|
| 346 |
+
"step": 240
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.6298200514138818,
|
| 350 |
+
"grad_norm": 1.0706994533538818,
|
| 351 |
+
"learning_rate": 2.798328682485312e-05,
|
| 352 |
+
"loss": 0.6141,
|
| 353 |
+
"step": 245
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.6426735218508998,
|
| 357 |
+
"grad_norm": 1.1383925676345825,
|
| 358 |
+
"learning_rate": 2.7875485226045385e-05,
|
| 359 |
+
"loss": 0.5933,
|
| 360 |
+
"step": 250
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.6555269922879178,
|
| 364 |
+
"grad_norm": 1.1288636922836304,
|
| 365 |
+
"learning_rate": 2.7765095911516548e-05,
|
| 366 |
+
"loss": 0.6092,
|
| 367 |
+
"step": 255
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.6683804627249358,
|
| 371 |
+
"grad_norm": 1.401145577430725,
|
| 372 |
+
"learning_rate": 2.765214106731706e-05,
|
| 373 |
+
"loss": 0.5973,
|
| 374 |
+
"step": 260
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.6812339331619537,
|
| 378 |
+
"grad_norm": 1.13032066822052,
|
| 379 |
+
"learning_rate": 2.7536643395117645e-05,
|
| 380 |
+
"loss": 0.5815,
|
| 381 |
+
"step": 265
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.6940874035989717,
|
| 385 |
+
"grad_norm": 1.3153561353683472,
|
| 386 |
+
"learning_rate": 2.7418626107646747e-05,
|
| 387 |
+
"loss": 0.5604,
|
| 388 |
+
"step": 270
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.7069408740359897,
|
| 392 |
+
"grad_norm": 1.2068425416946411,
|
| 393 |
+
"learning_rate": 2.729811292402522e-05,
|
| 394 |
+
"loss": 0.5718,
|
| 395 |
+
"step": 275
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.7197943444730077,
|
| 399 |
+
"grad_norm": 1.1330766677856445,
|
| 400 |
+
"learning_rate": 2.7175128064999272e-05,
|
| 401 |
+
"loss": 0.5647,
|
| 402 |
+
"step": 280
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.7326478149100257,
|
| 406 |
+
"grad_norm": 1.2667220830917358,
|
| 407 |
+
"learning_rate": 2.704969624807254e-05,
|
| 408 |
+
"loss": 0.5918,
|
| 409 |
+
"step": 285
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.7455012853470437,
|
| 413 |
+
"grad_norm": 1.143860101699829,
|
| 414 |
+
"learning_rate": 2.6921842682538436e-05,
|
| 415 |
+
"loss": 0.5884,
|
| 416 |
+
"step": 290
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.7583547557840618,
|
| 420 |
+
"grad_norm": 1.218053936958313,
|
| 421 |
+
"learning_rate": 2.6791593064413498e-05,
|
| 422 |
+
"loss": 0.5392,
|
| 423 |
+
"step": 295
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.7712082262210797,
|
| 427 |
+
"grad_norm": 1.2691618204116821,
|
| 428 |
+
"learning_rate": 2.6658973571273077e-05,
|
| 429 |
+
"loss": 0.5445,
|
| 430 |
+
"step": 300
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.7840616966580977,
|
| 434 |
+
"grad_norm": 1.179202914237976,
|
| 435 |
+
"learning_rate": 2.65240108569901e-05,
|
| 436 |
+
"loss": 0.506,
|
| 437 |
+
"step": 305
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.7969151670951157,
|
| 441 |
+
"grad_norm": 1.2560627460479736,
|
| 442 |
+
"learning_rate": 2.6386732046378242e-05,
|
| 443 |
+
"loss": 0.4967,
|
| 444 |
+
"step": 310
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.8097686375321337,
|
| 448 |
+
"grad_norm": 1.2643569707870483,
|
| 449 |
+
"learning_rate": 2.6247164729740317e-05,
|
| 450 |
+
"loss": 0.5018,
|
| 451 |
+
"step": 315
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.8226221079691517,
|
| 455 |
+
"grad_norm": 1.3074184656143188,
|
| 456 |
+
"learning_rate": 2.6105336957323214e-05,
|
| 457 |
+
"loss": 0.4611,
|
| 458 |
+
"step": 320
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.8354755784061697,
|
| 462 |
+
"grad_norm": 1.1067798137664795,
|
| 463 |
+
"learning_rate": 2.5961277233680356e-05,
|
| 464 |
+
"loss": 0.5118,
|
| 465 |
+
"step": 325
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.8483290488431876,
|
| 469 |
+
"grad_norm": 1.1286767721176147,
|
| 470 |
+
"learning_rate": 2.5815014511942828e-05,
|
| 471 |
+
"loss": 0.4866,
|
| 472 |
+
"step": 330
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.8611825192802056,
|
| 476 |
+
"grad_norm": 1.2853611707687378,
|
| 477 |
+
"learning_rate": 2.566657818800041e-05,
|
| 478 |
+
"loss": 0.4548,
|
| 479 |
+
"step": 335
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.8740359897172236,
|
| 483 |
+
"grad_norm": 1.2642810344696045,
|
| 484 |
+
"learning_rate": 2.5515998094593555e-05,
|
| 485 |
+
"loss": 0.4832,
|
| 486 |
+
"step": 340
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.8868894601542416,
|
| 490 |
+
"grad_norm": 1.1365891695022583,
|
| 491 |
+
"learning_rate": 2.5363304495317633e-05,
|
| 492 |
+
"loss": 0.4666,
|
| 493 |
+
"step": 345
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.8997429305912596,
|
| 497 |
+
"grad_norm": 1.476871371269226,
|
| 498 |
+
"learning_rate": 2.5208528078540524e-05,
|
| 499 |
+
"loss": 0.4648,
|
| 500 |
+
"step": 350
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.9125964010282777,
|
| 504 |
+
"grad_norm": 1.249257206916809,
|
| 505 |
+
"learning_rate": 2.50516999512349e-05,
|
| 506 |
+
"loss": 0.4819,
|
| 507 |
+
"step": 355
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.9254498714652957,
|
| 511 |
+
"grad_norm": 1.2145664691925049,
|
| 512 |
+
"learning_rate": 2.4892851632726306e-05,
|
| 513 |
+
"loss": 0.4098,
|
| 514 |
+
"step": 360
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.9383033419023136,
|
| 518 |
+
"grad_norm": 1.2550289630889893,
|
| 519 |
+
"learning_rate": 2.4732015048358447e-05,
|
| 520 |
+
"loss": 0.3978,
|
| 521 |
+
"step": 365
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.9511568123393316,
|
| 525 |
+
"grad_norm": 1.3079956769943237,
|
| 526 |
+
"learning_rate": 2.4569222523076796e-05,
|
| 527 |
+
"loss": 0.4076,
|
| 528 |
+
"step": 370
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.9640102827763496,
|
| 532 |
+
"grad_norm": 1.1965786218643188,
|
| 533 |
+
"learning_rate": 2.440450677493194e-05,
|
| 534 |
+
"loss": 0.3964,
|
| 535 |
+
"step": 375
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.9768637532133676,
|
| 539 |
+
"grad_norm": 1.2370487451553345,
|
| 540 |
+
"learning_rate": 2.4237900908503894e-05,
|
| 541 |
+
"loss": 0.43,
|
| 542 |
+
"step": 380
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.9897172236503856,
|
| 546 |
+
"grad_norm": 1.3813867568969727,
|
| 547 |
+
"learning_rate": 2.406943840824876e-05,
|
| 548 |
+
"loss": 0.3799,
|
| 549 |
+
"step": 385
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.0025706940874035,
|
| 553 |
+
"grad_norm": 1.2741672992706299,
|
| 554 |
+
"learning_rate": 2.3899153131769004e-05,
|
| 555 |
+
"loss": 0.4122,
|
| 556 |
+
"step": 390
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.0154241645244215,
|
| 560 |
+
"grad_norm": 1.5492188930511475,
|
| 561 |
+
"learning_rate": 2.3727079303008752e-05,
|
| 562 |
+
"loss": 0.3185,
|
| 563 |
+
"step": 395
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.0282776349614395,
|
| 567 |
+
"grad_norm": 1.4042234420776367,
|
| 568 |
+
"learning_rate": 2.355325150537548e-05,
|
| 569 |
+
"loss": 0.2957,
|
| 570 |
+
"step": 400
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.0411311053984575,
|
| 574 |
+
"grad_norm": 1.152010202407837,
|
| 575 |
+
"learning_rate": 2.337770467478939e-05,
|
| 576 |
+
"loss": 0.299,
|
| 577 |
+
"step": 405
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.0539845758354756,
|
| 581 |
+
"grad_norm": 1.321955680847168,
|
| 582 |
+
"learning_rate": 2.320047409266206e-05,
|
| 583 |
+
"loss": 0.3078,
|
| 584 |
+
"step": 410
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.0668380462724936,
|
| 588 |
+
"grad_norm": 1.1702276468276978,
|
| 589 |
+
"learning_rate": 2.3021595378805517e-05,
|
| 590 |
+
"loss": 0.3069,
|
| 591 |
+
"step": 415
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.0796915167095116,
|
| 595 |
+
"grad_norm": 1.3890055418014526,
|
| 596 |
+
"learning_rate": 2.284110448427341e-05,
|
| 597 |
+
"loss": 0.3153,
|
| 598 |
+
"step": 420
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.0925449871465296,
|
| 602 |
+
"grad_norm": 1.246214747428894,
|
| 603 |
+
"learning_rate": 2.2659037684135527e-05,
|
| 604 |
+
"loss": 0.3105,
|
| 605 |
+
"step": 425
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.1053984575835476,
|
| 609 |
+
"grad_norm": 1.230148434638977,
|
| 610 |
+
"learning_rate": 2.2475431570187282e-05,
|
| 611 |
+
"loss": 0.283,
|
| 612 |
+
"step": 430
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.1182519280205656,
|
| 616 |
+
"grad_norm": 1.3062918186187744,
|
| 617 |
+
"learning_rate": 2.2290323043595433e-05,
|
| 618 |
+
"loss": 0.2822,
|
| 619 |
+
"step": 435
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.1311053984575836,
|
| 623 |
+
"grad_norm": 1.241830587387085,
|
| 624 |
+
"learning_rate": 2.210374930748172e-05,
|
| 625 |
+
"loss": 0.2683,
|
| 626 |
+
"step": 440
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.1439588688946016,
|
| 630 |
+
"grad_norm": 1.3768752813339233,
|
| 631 |
+
"learning_rate": 2.1915747859445784e-05,
|
| 632 |
+
"loss": 0.3283,
|
| 633 |
+
"step": 445
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.1568123393316196,
|
| 637 |
+
"grad_norm": 1.3402104377746582,
|
| 638 |
+
"learning_rate": 2.1726356484028865e-05,
|
| 639 |
+
"loss": 0.2971,
|
| 640 |
+
"step": 450
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.1696658097686377,
|
| 644 |
+
"grad_norm": 1.3632996082305908,
|
| 645 |
+
"learning_rate": 2.1535613245119913e-05,
|
| 646 |
+
"loss": 0.2512,
|
| 647 |
+
"step": 455
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.1825192802056554,
|
| 651 |
+
"grad_norm": 1.2795768976211548,
|
| 652 |
+
"learning_rate": 2.1343556478305444e-05,
|
| 653 |
+
"loss": 0.2825,
|
| 654 |
+
"step": 460
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.1953727506426735,
|
| 658 |
+
"grad_norm": 1.1815543174743652,
|
| 659 |
+
"learning_rate": 2.1150224783164913e-05,
|
| 660 |
+
"loss": 0.2772,
|
| 661 |
+
"step": 465
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.2082262210796915,
|
| 665 |
+
"grad_norm": 1.161288857460022,
|
| 666 |
+
"learning_rate": 2.0955657015512916e-05,
|
| 667 |
+
"loss": 0.2899,
|
| 668 |
+
"step": 470
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.2210796915167095,
|
| 672 |
+
"grad_norm": 1.379600167274475,
|
| 673 |
+
"learning_rate": 2.0759892279589983e-05,
|
| 674 |
+
"loss": 0.2496,
|
| 675 |
+
"step": 475
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.2339331619537275,
|
| 679 |
+
"grad_norm": 1.3972254991531372,
|
| 680 |
+
"learning_rate": 2.056296992020339e-05,
|
| 681 |
+
"loss": 0.2715,
|
| 682 |
+
"step": 480
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.2467866323907455,
|
| 686 |
+
"grad_norm": 1.3368836641311646,
|
| 687 |
+
"learning_rate": 2.036492951481963e-05,
|
| 688 |
+
"loss": 0.2619,
|
| 689 |
+
"step": 485
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.2596401028277635,
|
| 693 |
+
"grad_norm": 1.4315762519836426,
|
| 694 |
+
"learning_rate": 2.016581086561016e-05,
|
| 695 |
+
"loss": 0.2528,
|
| 696 |
+
"step": 490
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.2724935732647815,
|
| 700 |
+
"grad_norm": 1.2277283668518066,
|
| 701 |
+
"learning_rate": 1.996565399145192e-05,
|
| 702 |
+
"loss": 0.2608,
|
| 703 |
+
"step": 495
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.2853470437017995,
|
| 707 |
+
"grad_norm": 1.2831872701644897,
|
| 708 |
+
"learning_rate": 1.976449911988438e-05,
|
| 709 |
+
"loss": 0.2432,
|
| 710 |
+
"step": 500
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.2982005141388175,
|
| 714 |
+
"grad_norm": 1.300130009651184,
|
| 715 |
+
"learning_rate": 1.956238667902455e-05,
|
| 716 |
+
"loss": 0.2344,
|
| 717 |
+
"step": 505
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.3110539845758356,
|
| 721 |
+
"grad_norm": 1.1015888452529907,
|
| 722 |
+
"learning_rate": 1.93593572894418e-05,
|
| 723 |
+
"loss": 0.2497,
|
| 724 |
+
"step": 510
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.3239074550128533,
|
| 728 |
+
"grad_norm": 1.233827829360962,
|
| 729 |
+
"learning_rate": 1.9155451755993896e-05,
|
| 730 |
+
"loss": 0.2281,
|
| 731 |
+
"step": 515
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.3367609254498714,
|
| 735 |
+
"grad_norm": 1.7423725128173828,
|
| 736 |
+
"learning_rate": 1.8950711059626032e-05,
|
| 737 |
+
"loss": 0.2327,
|
| 738 |
+
"step": 520
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.3496143958868894,
|
| 742 |
+
"grad_norm": 1.1446610689163208,
|
| 743 |
+
"learning_rate": 1.8745176349134498e-05,
|
| 744 |
+
"loss": 0.2124,
|
| 745 |
+
"step": 525
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.3624678663239074,
|
| 749 |
+
"grad_norm": 1.0682686567306519,
|
| 750 |
+
"learning_rate": 1.853888893289661e-05,
|
| 751 |
+
"loss": 0.2363,
|
| 752 |
+
"step": 530
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.3753213367609254,
|
| 756 |
+
"grad_norm": 1.2087314128875732,
|
| 757 |
+
"learning_rate": 1.833189027056848e-05,
|
| 758 |
+
"loss": 0.2228,
|
| 759 |
+
"step": 535
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.3881748071979434,
|
| 763 |
+
"grad_norm": 1.2801451683044434,
|
| 764 |
+
"learning_rate": 1.8124221964752535e-05,
|
| 765 |
+
"loss": 0.2306,
|
| 766 |
+
"step": 540
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.4010282776349614,
|
| 770 |
+
"grad_norm": 1.213588833808899,
|
| 771 |
+
"learning_rate": 1.7915925752636164e-05,
|
| 772 |
+
"loss": 0.2254,
|
| 773 |
+
"step": 545
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.4138817480719794,
|
| 777 |
+
"grad_norm": 1.1860700845718384,
|
| 778 |
+
"learning_rate": 1.7707043497603426e-05,
|
| 779 |
+
"loss": 0.1983,
|
| 780 |
+
"step": 550
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.4267352185089974,
|
| 784 |
+
"grad_norm": 1.1246360540390015,
|
| 785 |
+
"learning_rate": 1.7497617180821287e-05,
|
| 786 |
+
"loss": 0.2089,
|
| 787 |
+
"step": 555
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.4395886889460154,
|
| 791 |
+
"grad_norm": 1.2236223220825195,
|
| 792 |
+
"learning_rate": 1.728768889280229e-05,
|
| 793 |
+
"loss": 0.2077,
|
| 794 |
+
"step": 560
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.4524421593830334,
|
| 798 |
+
"grad_norm": 1.3709501028060913,
|
| 799 |
+
"learning_rate": 1.7077300824945174e-05,
|
| 800 |
+
"loss": 0.1933,
|
| 801 |
+
"step": 565
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.4652956298200515,
|
| 805 |
+
"grad_norm": 1.0942673683166504,
|
| 806 |
+
"learning_rate": 1.6866495261055265e-05,
|
| 807 |
+
"loss": 0.1825,
|
| 808 |
+
"step": 570
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.4781491002570695,
|
| 812 |
+
"grad_norm": 1.1473671197891235,
|
| 813 |
+
"learning_rate": 1.6655314568846265e-05,
|
| 814 |
+
"loss": 0.2058,
|
| 815 |
+
"step": 575
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.4910025706940875,
|
| 819 |
+
"grad_norm": 1.0283526182174683,
|
| 820 |
+
"learning_rate": 1.6443801191425176e-05,
|
| 821 |
+
"loss": 0.1775,
|
| 822 |
+
"step": 580
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.5038560411311055,
|
| 826 |
+
"grad_norm": 1.1558873653411865,
|
| 827 |
+
"learning_rate": 1.6231997638762096e-05,
|
| 828 |
+
"loss": 0.1944,
|
| 829 |
+
"step": 585
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.5167095115681235,
|
| 833 |
+
"grad_norm": 1.2510091066360474,
|
| 834 |
+
"learning_rate": 1.6019946479146567e-05,
|
| 835 |
+
"loss": 0.1802,
|
| 836 |
+
"step": 590
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.5295629820051415,
|
| 840 |
+
"grad_norm": 1.2565644979476929,
|
| 841 |
+
"learning_rate": 1.5807690330632176e-05,
|
| 842 |
+
"loss": 0.2066,
|
| 843 |
+
"step": 595
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.5424164524421595,
|
| 847 |
+
"grad_norm": 1.1275231838226318,
|
| 848 |
+
"learning_rate": 1.5595271852471204e-05,
|
| 849 |
+
"loss": 0.1705,
|
| 850 |
+
"step": 600
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.5552699228791775,
|
| 854 |
+
"grad_norm": 1.159485101699829,
|
| 855 |
+
"learning_rate": 1.5382733736540936e-05,
|
| 856 |
+
"loss": 0.181,
|
| 857 |
+
"step": 605
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.5681233933161953,
|
| 861 |
+
"grad_norm": 1.008790135383606,
|
| 862 |
+
"learning_rate": 1.517011869876348e-05,
|
| 863 |
+
"loss": 0.1735,
|
| 864 |
+
"step": 610
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.5809768637532133,
|
| 868 |
+
"grad_norm": 1.303591251373291,
|
| 869 |
+
"learning_rate": 1.4957469470520697e-05,
|
| 870 |
+
"loss": 0.1879,
|
| 871 |
+
"step": 615
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.5938303341902313,
|
| 875 |
+
"grad_norm": 1.0963256359100342,
|
| 876 |
+
"learning_rate": 1.4744828790066041e-05,
|
| 877 |
+
"loss": 0.1617,
|
| 878 |
+
"step": 620
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.6066838046272494,
|
| 882 |
+
"grad_norm": 1.2369383573532104,
|
| 883 |
+
"learning_rate": 1.4532239393935035e-05,
|
| 884 |
+
"loss": 0.1848,
|
| 885 |
+
"step": 625
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.6195372750642674,
|
| 889 |
+
"grad_norm": 1.1727296113967896,
|
| 890 |
+
"learning_rate": 1.4319744008356085e-05,
|
| 891 |
+
"loss": 0.1599,
|
| 892 |
+
"step": 630
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 1.6323907455012854,
|
| 896 |
+
"grad_norm": 1.148640751838684,
|
| 897 |
+
"learning_rate": 1.4107385340663331e-05,
|
| 898 |
+
"loss": 0.1666,
|
| 899 |
+
"step": 635
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 1.6452442159383034,
|
| 903 |
+
"grad_norm": 1.297433614730835,
|
| 904 |
+
"learning_rate": 1.3895206070713373e-05,
|
| 905 |
+
"loss": 0.1633,
|
| 906 |
+
"step": 640
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.6580976863753212,
|
| 910 |
+
"grad_norm": 1.1180986166000366,
|
| 911 |
+
"learning_rate": 1.3683248842307416e-05,
|
| 912 |
+
"loss": 0.137,
|
| 913 |
+
"step": 645
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.6709511568123392,
|
| 917 |
+
"grad_norm": 1.1784125566482544,
|
| 918 |
+
"learning_rate": 1.3471556254620751e-05,
|
| 919 |
+
"loss": 0.1725,
|
| 920 |
+
"step": 650
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.6838046272493572,
|
| 924 |
+
"grad_norm": 1.003346562385559,
|
| 925 |
+
"learning_rate": 1.3260170853641178e-05,
|
| 926 |
+
"loss": 0.1671,
|
| 927 |
+
"step": 655
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.6966580976863752,
|
| 931 |
+
"grad_norm": 1.0648976564407349,
|
| 932 |
+
"learning_rate": 1.3049135123618073e-05,
|
| 933 |
+
"loss": 0.1508,
|
| 934 |
+
"step": 660
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.7095115681233932,
|
| 938 |
+
"grad_norm": 1.187290072441101,
|
| 939 |
+
"learning_rate": 1.283849147852395e-05,
|
| 940 |
+
"loss": 0.1663,
|
| 941 |
+
"step": 665
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.7223650385604112,
|
| 945 |
+
"grad_norm": 1.042966365814209,
|
| 946 |
+
"learning_rate": 1.2628282253530037e-05,
|
| 947 |
+
"loss": 0.1282,
|
| 948 |
+
"step": 670
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 1.7352185089974292,
|
| 952 |
+
"grad_norm": 1.2114485502243042,
|
| 953 |
+
"learning_rate": 1.2418549696497832e-05,
|
| 954 |
+
"loss": 0.1546,
|
| 955 |
+
"step": 675
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.7480719794344473,
|
| 959 |
+
"grad_norm": 1.1157336235046387,
|
| 960 |
+
"learning_rate": 1.2209335959488037e-05,
|
| 961 |
+
"loss": 0.1354,
|
| 962 |
+
"step": 680
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.7609254498714653,
|
| 966 |
+
"grad_norm": 1.3702713251113892,
|
| 967 |
+
"learning_rate": 1.2000683090288901e-05,
|
| 968 |
+
"loss": 0.1507,
|
| 969 |
+
"step": 685
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.7737789203084833,
|
| 973 |
+
"grad_norm": 0.9793261289596558,
|
| 974 |
+
"learning_rate": 1.1792633023965433e-05,
|
| 975 |
+
"loss": 0.1427,
|
| 976 |
+
"step": 690
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.7866323907455013,
|
| 980 |
+
"grad_norm": 1.054948091506958,
|
| 981 |
+
"learning_rate": 1.1585227574431263e-05,
|
| 982 |
+
"loss": 0.1446,
|
| 983 |
+
"step": 695
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.7994858611825193,
|
| 987 |
+
"grad_norm": 1.0848296880722046,
|
| 988 |
+
"learning_rate": 1.1378508426044943e-05,
|
| 989 |
+
"loss": 0.1429,
|
| 990 |
+
"step": 700
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.8123393316195373,
|
| 994 |
+
"grad_norm": 0.9673031568527222,
|
| 995 |
+
"learning_rate": 1.1172517125232142e-05,
|
| 996 |
+
"loss": 0.1215,
|
| 997 |
+
"step": 705
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 1.8251928020565553,
|
| 1001 |
+
"grad_norm": 1.0165585279464722,
|
| 1002 |
+
"learning_rate": 1.0967295072135706e-05,
|
| 1003 |
+
"loss": 0.1312,
|
| 1004 |
+
"step": 710
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.8380462724935733,
|
| 1008 |
+
"grad_norm": 1.0991692543029785,
|
| 1009 |
+
"learning_rate": 1.0762883512295037e-05,
|
| 1010 |
+
"loss": 0.1245,
|
| 1011 |
+
"step": 715
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 1.8508997429305913,
|
| 1015 |
+
"grad_norm": 1.0551514625549316,
|
| 1016 |
+
"learning_rate": 1.0559323528356542e-05,
|
| 1017 |
+
"loss": 0.1193,
|
| 1018 |
+
"step": 720
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.8637532133676094,
|
| 1022 |
+
"grad_norm": 0.9879056215286255,
|
| 1023 |
+
"learning_rate": 1.0356656031816873e-05,
|
| 1024 |
+
"loss": 0.1297,
|
| 1025 |
+
"step": 725
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 1.8766066838046274,
|
| 1029 |
+
"grad_norm": 1.0206804275512695,
|
| 1030 |
+
"learning_rate": 1.0154921754800501e-05,
|
| 1031 |
+
"loss": 0.1259,
|
| 1032 |
+
"step": 730
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 1.8894601542416454,
|
| 1036 |
+
"grad_norm": 0.9569869637489319,
|
| 1037 |
+
"learning_rate": 9.9541612418734e-06,
|
| 1038 |
+
"loss": 0.1255,
|
| 1039 |
+
"step": 735
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 1.9023136246786634,
|
| 1043 |
+
"grad_norm": 1.1746203899383545,
|
| 1044 |
+
"learning_rate": 9.754414841894377e-06,
|
| 1045 |
+
"loss": 0.1171,
|
| 1046 |
+
"step": 740
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.9151670951156814,
|
| 1050 |
+
"grad_norm": 1.0779139995574951,
|
| 1051 |
+
"learning_rate": 9.55572269990576e-06,
|
| 1052 |
+
"loss": 0.1216,
|
| 1053 |
+
"step": 745
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 1.9280205655526992,
|
| 1057 |
+
"grad_norm": 1.1323301792144775,
|
| 1058 |
+
"learning_rate": 9.358124749065068e-06,
|
| 1059 |
+
"loss": 0.12,
|
| 1060 |
+
"step": 750
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 1.9408740359897172,
|
| 1064 |
+
"grad_norm": 1.013806700706482,
|
| 1065 |
+
"learning_rate": 9.161660702619186e-06,
|
| 1066 |
+
"loss": 0.1175,
|
| 1067 |
+
"step": 755
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 1.9537275064267352,
|
| 1071 |
+
"grad_norm": 0.9499263763427734,
|
| 1072 |
+
"learning_rate": 8.966370045922881e-06,
|
| 1073 |
+
"loss": 0.1046,
|
| 1074 |
+
"step": 760
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.9665809768637532,
|
| 1078 |
+
"grad_norm": 1.0747876167297363,
|
| 1079 |
+
"learning_rate": 8.77229202850294e-06,
|
| 1080 |
+
"loss": 0.1212,
|
| 1081 |
+
"step": 765
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 1.9794344473007712,
|
| 1085 |
+
"grad_norm": 1.0890231132507324,
|
| 1086 |
+
"learning_rate": 8.57946565616987e-06,
|
| 1087 |
+
"loss": 0.1095,
|
| 1088 |
+
"step": 770
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 1.9922879177377892,
|
| 1092 |
+
"grad_norm": 0.9841799139976501,
|
| 1093 |
+
"learning_rate": 8.38792968317847e-06,
|
| 1094 |
+
"loss": 0.1169,
|
| 1095 |
+
"step": 775
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 2.005141388174807,
|
| 1099 |
+
"grad_norm": 0.7302473783493042,
|
| 1100 |
+
"learning_rate": 8.19772260443901e-06,
|
| 1101 |
+
"loss": 0.0898,
|
| 1102 |
+
"step": 780
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 2.017994858611825,
|
| 1106 |
+
"grad_norm": 0.8577669262886047,
|
| 1107 |
+
"learning_rate": 8.008882647780518e-06,
|
| 1108 |
+
"loss": 0.095,
|
| 1109 |
+
"step": 785
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 2.030848329048843,
|
| 1113 |
+
"grad_norm": 1.0443934202194214,
|
| 1114 |
+
"learning_rate": 7.821447766267752e-06,
|
| 1115 |
+
"loss": 0.0857,
|
| 1116 |
+
"step": 790
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 2.043701799485861,
|
| 1120 |
+
"grad_norm": 0.8021896481513977,
|
| 1121 |
+
"learning_rate": 7.635455630573408e-06,
|
| 1122 |
+
"loss": 0.0891,
|
| 1123 |
+
"step": 795
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 2.056555269922879,
|
| 1127 |
+
"grad_norm": 0.8770691156387329,
|
| 1128 |
+
"learning_rate": 7.450943621407026e-06,
|
| 1129 |
+
"loss": 0.0883,
|
| 1130 |
+
"step": 800
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 2.069408740359897,
|
| 1134 |
+
"grad_norm": 0.8594703674316406,
|
| 1135 |
+
"learning_rate": 7.267948822002248e-06,
|
| 1136 |
+
"loss": 0.0767,
|
| 1137 |
+
"step": 805
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 2.082262210796915,
|
| 1141 |
+
"grad_norm": 0.9583711624145508,
|
| 1142 |
+
"learning_rate": 7.086508010663808e-06,
|
| 1143 |
+
"loss": 0.0931,
|
| 1144 |
+
"step": 810
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 2.095115681233933,
|
| 1148 |
+
"grad_norm": 1.1105700731277466,
|
| 1149 |
+
"learning_rate": 6.906657653375839e-06,
|
| 1150 |
+
"loss": 0.0883,
|
| 1151 |
+
"step": 815
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 2.107969151670951,
|
| 1155 |
+
"grad_norm": 0.9344552755355835,
|
| 1156 |
+
"learning_rate": 6.7284338964729366e-06,
|
| 1157 |
+
"loss": 0.0792,
|
| 1158 |
+
"step": 820
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 2.120822622107969,
|
| 1162 |
+
"grad_norm": 0.8351441025733948,
|
| 1163 |
+
"learning_rate": 6.5518725593754465e-06,
|
| 1164 |
+
"loss": 0.077,
|
| 1165 |
+
"step": 825
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 2.133676092544987,
|
| 1169 |
+
"grad_norm": 0.991685688495636,
|
| 1170 |
+
"learning_rate": 6.377009127390523e-06,
|
| 1171 |
+
"loss": 0.0872,
|
| 1172 |
+
"step": 830
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 2.146529562982005,
|
| 1176 |
+
"grad_norm": 1.0037211179733276,
|
| 1177 |
+
"learning_rate": 6.203878744580218e-06,
|
| 1178 |
+
"loss": 0.0876,
|
| 1179 |
+
"step": 835
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 2.159383033419023,
|
| 1183 |
+
"grad_norm": 0.8394771218299866,
|
| 1184 |
+
"learning_rate": 6.032516206698289e-06,
|
| 1185 |
+
"loss": 0.0805,
|
| 1186 |
+
"step": 840
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 2.172236503856041,
|
| 1190 |
+
"grad_norm": 0.8647484183311462,
|
| 1191 |
+
"learning_rate": 5.862955954196931e-06,
|
| 1192 |
+
"loss": 0.0848,
|
| 1193 |
+
"step": 845
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 2.185089974293059,
|
| 1197 |
+
"grad_norm": 0.8657212257385254,
|
| 1198 |
+
"learning_rate": 5.69523206530491e-06,
|
| 1199 |
+
"loss": 0.0817,
|
| 1200 |
+
"step": 850
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 2.197943444730077,
|
| 1204 |
+
"grad_norm": 0.6530460119247437,
|
| 1205 |
+
"learning_rate": 5.529378249178538e-06,
|
| 1206 |
+
"loss": 0.0823,
|
| 1207 |
+
"step": 855
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 2.210796915167095,
|
| 1211 |
+
"grad_norm": 0.9633145332336426,
|
| 1212 |
+
"learning_rate": 5.365427839126795e-06,
|
| 1213 |
+
"loss": 0.0852,
|
| 1214 |
+
"step": 860
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 2.223650385604113,
|
| 1218 |
+
"grad_norm": 0.8830084204673767,
|
| 1219 |
+
"learning_rate": 5.203413785912031e-06,
|
| 1220 |
+
"loss": 0.0884,
|
| 1221 |
+
"step": 865
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 2.236503856041131,
|
| 1225 |
+
"grad_norm": 0.8098734617233276,
|
| 1226 |
+
"learning_rate": 5.043368651127455e-06,
|
| 1227 |
+
"loss": 0.0824,
|
| 1228 |
+
"step": 870
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 2.2493573264781492,
|
| 1232 |
+
"grad_norm": 0.815689206123352,
|
| 1233 |
+
"learning_rate": 4.885324600652963e-06,
|
| 1234 |
+
"loss": 0.0809,
|
| 1235 |
+
"step": 875
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 2.2622107969151672,
|
| 1239 |
+
"grad_norm": 0.7369515895843506,
|
| 1240 |
+
"learning_rate": 4.729313398190428e-06,
|
| 1241 |
+
"loss": 0.0703,
|
| 1242 |
+
"step": 880
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 2.2750642673521853,
|
| 1246 |
+
"grad_norm": 0.8131601810455322,
|
| 1247 |
+
"learning_rate": 4.575366398879799e-06,
|
| 1248 |
+
"loss": 0.0739,
|
| 1249 |
+
"step": 885
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 2.2879177377892033,
|
| 1253 |
+
"grad_norm": 0.7088854908943176,
|
| 1254 |
+
"learning_rate": 4.4235145429973725e-06,
|
| 1255 |
+
"loss": 0.0819,
|
| 1256 |
+
"step": 890
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 2.3007712082262213,
|
| 1260 |
+
"grad_norm": 0.8050107955932617,
|
| 1261 |
+
"learning_rate": 4.273788349737403e-06,
|
| 1262 |
+
"loss": 0.0673,
|
| 1263 |
+
"step": 895
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 2.3136246786632393,
|
| 1267 |
+
"grad_norm": 0.6616095900535583,
|
| 1268 |
+
"learning_rate": 4.126217911078359e-06,
|
| 1269 |
+
"loss": 0.0725,
|
| 1270 |
+
"step": 900
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 2.3264781491002573,
|
| 1274 |
+
"grad_norm": 0.7336181402206421,
|
| 1275 |
+
"learning_rate": 3.980832885735027e-06,
|
| 1276 |
+
"loss": 0.0844,
|
| 1277 |
+
"step": 905
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 2.3393316195372753,
|
| 1281 |
+
"grad_norm": 0.7268707752227783,
|
| 1282 |
+
"learning_rate": 3.837662493197704e-06,
|
| 1283 |
+
"loss": 0.07,
|
| 1284 |
+
"step": 910
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 2.352185089974293,
|
| 1288 |
+
"grad_norm": 0.7554981112480164,
|
| 1289 |
+
"learning_rate": 3.696735507859685e-06,
|
| 1290 |
+
"loss": 0.0772,
|
| 1291 |
+
"step": 915
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 2.365038560411311,
|
| 1295 |
+
"grad_norm": 0.6731789708137512,
|
| 1296 |
+
"learning_rate": 3.5580802532341293e-06,
|
| 1297 |
+
"loss": 0.0701,
|
| 1298 |
+
"step": 920
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 2.377892030848329,
|
| 1302 |
+
"grad_norm": 0.7684122323989868,
|
| 1303 |
+
"learning_rate": 3.42172459626167e-06,
|
| 1304 |
+
"loss": 0.0759,
|
| 1305 |
+
"step": 925
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 2.390745501285347,
|
| 1309 |
+
"grad_norm": 0.8418908715248108,
|
| 1310 |
+
"learning_rate": 3.287695941709655e-06,
|
| 1311 |
+
"loss": 0.072,
|
| 1312 |
+
"step": 930
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 2.403598971722365,
|
| 1316 |
+
"grad_norm": 0.7376586198806763,
|
| 1317 |
+
"learning_rate": 3.156021226664367e-06,
|
| 1318 |
+
"loss": 0.0733,
|
| 1319 |
+
"step": 935
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 2.416452442159383,
|
| 1323 |
+
"grad_norm": 0.6618520021438599,
|
| 1324 |
+
"learning_rate": 3.026726915117201e-06,
|
| 1325 |
+
"loss": 0.0703,
|
| 1326 |
+
"step": 940
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 2.429305912596401,
|
| 1330 |
+
"grad_norm": 0.6464835405349731,
|
| 1331 |
+
"learning_rate": 2.899838992645918e-06,
|
| 1332 |
+
"loss": 0.0665,
|
| 1333 |
+
"step": 945
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 2.442159383033419,
|
| 1337 |
+
"grad_norm": 0.6353692412376404,
|
| 1338 |
+
"learning_rate": 2.7753829611920906e-06,
|
| 1339 |
+
"loss": 0.0702,
|
| 1340 |
+
"step": 950
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 2.455012853470437,
|
| 1344 |
+
"grad_norm": 0.746442973613739,
|
| 1345 |
+
"learning_rate": 2.653383833935675e-06,
|
| 1346 |
+
"loss": 0.0736,
|
| 1347 |
+
"step": 955
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 2.467866323907455,
|
| 1351 |
+
"grad_norm": 0.5870128273963928,
|
| 1352 |
+
"learning_rate": 2.5338661302679146e-06,
|
| 1353 |
+
"loss": 0.0696,
|
| 1354 |
+
"step": 960
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 2.480719794344473,
|
| 1358 |
+
"grad_norm": 0.6124534010887146,
|
| 1359 |
+
"learning_rate": 2.4168538708633924e-06,
|
| 1360 |
+
"loss": 0.0657,
|
| 1361 |
+
"step": 965
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 2.493573264781491,
|
| 1365 |
+
"grad_norm": 0.7286924123764038,
|
| 1366 |
+
"learning_rate": 2.3023705728523635e-06,
|
| 1367 |
+
"loss": 0.0686,
|
| 1368 |
+
"step": 970
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 2.506426735218509,
|
| 1372 |
+
"grad_norm": 0.7239978909492493,
|
| 1373 |
+
"learning_rate": 2.190439245094294e-06,
|
| 1374 |
+
"loss": 0.0759,
|
| 1375 |
+
"step": 975
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 2.519280205655527,
|
| 1379 |
+
"grad_norm": 0.7404186129570007,
|
| 1380 |
+
"learning_rate": 2.081082383553523e-06,
|
| 1381 |
+
"loss": 0.0679,
|
| 1382 |
+
"step": 980
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 2.532133676092545,
|
| 1386 |
+
"grad_norm": 0.6429500579833984,
|
| 1387 |
+
"learning_rate": 1.9743219667780325e-06,
|
| 1388 |
+
"loss": 0.0632,
|
| 1389 |
+
"step": 985
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 2.544987146529563,
|
| 1393 |
+
"grad_norm": 0.8531081080436707,
|
| 1394 |
+
"learning_rate": 1.8701794514821896e-06,
|
| 1395 |
+
"loss": 0.0716,
|
| 1396 |
+
"step": 990
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 2.557840616966581,
|
| 1400 |
+
"grad_norm": 0.8135824799537659,
|
| 1401 |
+
"learning_rate": 1.7686757682343891e-06,
|
| 1402 |
+
"loss": 0.0681,
|
| 1403 |
+
"step": 995
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 2.570694087403599,
|
| 1407 |
+
"grad_norm": 0.7481814622879028,
|
| 1408 |
+
"learning_rate": 1.6698313172504127e-06,
|
| 1409 |
+
"loss": 0.0704,
|
| 1410 |
+
"step": 1000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 2.583547557840617,
|
| 1414 |
+
"grad_norm": 0.7673191428184509,
|
| 1415 |
+
"learning_rate": 1.5736659642933847e-06,
|
| 1416 |
+
"loss": 0.0745,
|
| 1417 |
+
"step": 1005
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 2.596401028277635,
|
| 1421 |
+
"grad_norm": 0.6232099533081055,
|
| 1422 |
+
"learning_rate": 1.4801990366811836e-06,
|
| 1423 |
+
"loss": 0.0662,
|
| 1424 |
+
"step": 1010
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 2.609254498714653,
|
| 1428 |
+
"grad_norm": 0.7070301175117493,
|
| 1429 |
+
"learning_rate": 1.389449319402002e-06,
|
| 1430 |
+
"loss": 0.0642,
|
| 1431 |
+
"step": 1015
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 2.622107969151671,
|
| 1435 |
+
"grad_norm": 0.6255565285682678,
|
| 1436 |
+
"learning_rate": 1.3014350513389556e-06,
|
| 1437 |
+
"loss": 0.0693,
|
| 1438 |
+
"step": 1020
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 2.6349614395886887,
|
| 1442 |
+
"grad_norm": 0.6472063064575195,
|
| 1443 |
+
"learning_rate": 1.2161739216044243e-06,
|
| 1444 |
+
"loss": 0.0683,
|
| 1445 |
+
"step": 1025
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 2.6478149100257067,
|
| 1449 |
+
"grad_norm": 0.6828406453132629,
|
| 1450 |
+
"learning_rate": 1.1336830659849046e-06,
|
| 1451 |
+
"loss": 0.0737,
|
| 1452 |
+
"step": 1030
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 2.6606683804627247,
|
| 1456 |
+
"grad_norm": 0.7397602200508118,
|
| 1457 |
+
"learning_rate": 1.0539790634970459e-06,
|
| 1458 |
+
"loss": 0.0636,
|
| 1459 |
+
"step": 1035
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 2.6735218508997427,
|
| 1463 |
+
"grad_norm": 0.649748682975769,
|
| 1464 |
+
"learning_rate": 9.770779330555978e-07,
|
| 1465 |
+
"loss": 0.0722,
|
| 1466 |
+
"step": 1040
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 2.6863753213367607,
|
| 1470 |
+
"grad_norm": 0.6505516767501831,
|
| 1471 |
+
"learning_rate": 9.029951302539458e-07,
|
| 1472 |
+
"loss": 0.0587,
|
| 1473 |
+
"step": 1045
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 2.6992287917737787,
|
| 1477 |
+
"grad_norm": 0.5604033470153809,
|
| 1478 |
+
"learning_rate": 8.317455442578231e-07,
|
| 1479 |
+
"loss": 0.0606,
|
| 1480 |
+
"step": 1050
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 2.7120822622107967,
|
| 1484 |
+
"grad_norm": 0.5740429759025574,
|
| 1485 |
+
"learning_rate": 7.633434948128992e-07,
|
| 1486 |
+
"loss": 0.0743,
|
| 1487 |
+
"step": 1055
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 2.7249357326478147,
|
| 1491 |
+
"grad_norm": 0.5274402499198914,
|
| 1492 |
+
"learning_rate": 6.978027293667943e-07,
|
| 1493 |
+
"loss": 0.0607,
|
| 1494 |
+
"step": 1060
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 2.7377892030848328,
|
| 1498 |
+
"grad_norm": 0.6690722703933716,
|
| 1499 |
+
"learning_rate": 6.351364203061116e-07,
|
| 1500 |
+
"loss": 0.0675,
|
| 1501 |
+
"step": 1065
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 2.7506426735218508,
|
| 1505 |
+
"grad_norm": 0.5921615362167358,
|
| 1506 |
+
"learning_rate": 5.753571623090531e-07,
|
| 1507 |
+
"loss": 0.0662,
|
| 1508 |
+
"step": 1070
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 2.763496143958869,
|
| 1512 |
+
"grad_norm": 0.6168600916862488,
|
| 1513 |
+
"learning_rate": 5.184769698141445e-07,
|
| 1514 |
+
"loss": 0.0655,
|
| 1515 |
+
"step": 1075
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 2.776349614395887,
|
| 1519 |
+
"grad_norm": 0.616956353187561,
|
| 1520 |
+
"learning_rate": 4.645072746055684e-07,
|
| 1521 |
+
"loss": 0.0687,
|
| 1522 |
+
"step": 1080
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 2.789203084832905,
|
| 1526 |
+
"grad_norm": 0.6258854269981384,
|
| 1527 |
+
"learning_rate": 4.134589235156022e-07,
|
| 1528 |
+
"loss": 0.0742,
|
| 1529 |
+
"step": 1085
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 2.802056555269923,
|
| 1533 |
+
"grad_norm": 0.5645312070846558,
|
| 1534 |
+
"learning_rate": 3.653421762446252e-07,
|
| 1535 |
+
"loss": 0.0674,
|
| 1536 |
+
"step": 1090
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 2.814910025706941,
|
| 1540 |
+
"grad_norm": 0.5652868747711182,
|
| 1541 |
+
"learning_rate": 3.201667032991212e-07,
|
| 1542 |
+
"loss": 0.0714,
|
| 1543 |
+
"step": 1095
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 2.827763496143959,
|
| 1547 |
+
"grad_norm": 0.5738625526428223,
|
| 1548 |
+
"learning_rate": 2.7794158404810034e-07,
|
| 1549 |
+
"loss": 0.0664,
|
| 1550 |
+
"step": 1100
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 2.840616966580977,
|
| 1554 |
+
"grad_norm": 0.6448652744293213,
|
| 1555 |
+
"learning_rate": 2.3867530489832643e-07,
|
| 1556 |
+
"loss": 0.0754,
|
| 1557 |
+
"step": 1105
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 2.853470437017995,
|
| 1561 |
+
"grad_norm": 0.5809450149536133,
|
| 1562 |
+
"learning_rate": 2.0237575758871697e-07,
|
| 1563 |
+
"loss": 0.0605,
|
| 1564 |
+
"step": 1110
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 2.866323907455013,
|
| 1568 |
+
"grad_norm": 0.6396676898002625,
|
| 1569 |
+
"learning_rate": 1.6905023760426797e-07,
|
| 1570 |
+
"loss": 0.0635,
|
| 1571 |
+
"step": 1115
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 2.879177377892031,
|
| 1575 |
+
"grad_norm": 0.5690900683403015,
|
| 1576 |
+
"learning_rate": 1.3870544270979724e-07,
|
| 1577 |
+
"loss": 0.0668,
|
| 1578 |
+
"step": 1120
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 2.892030848329049,
|
| 1582 |
+
"grad_norm": 0.6804177165031433,
|
| 1583 |
+
"learning_rate": 1.1134747160383263e-07,
|
| 1584 |
+
"loss": 0.0632,
|
| 1585 |
+
"step": 1125
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 2.904884318766067,
|
| 1589 |
+
"grad_norm": 0.6354117393493652,
|
| 1590 |
+
"learning_rate": 8.698182269289423e-08,
|
| 1591 |
+
"loss": 0.0632,
|
| 1592 |
+
"step": 1130
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 2.917737789203085,
|
| 1596 |
+
"grad_norm": 0.5695874691009521,
|
| 1597 |
+
"learning_rate": 6.561339298642999e-08,
|
| 1598 |
+
"loss": 0.0646,
|
| 1599 |
+
"step": 1135
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 2.930591259640103,
|
| 1603 |
+
"grad_norm": 0.4649551808834076,
|
| 1604 |
+
"learning_rate": 4.7246477112599665e-08,
|
| 1605 |
+
"loss": 0.0604,
|
| 1606 |
+
"step": 1140
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 2.943444730077121,
|
| 1610 |
+
"grad_norm": 0.7474439740180969,
|
| 1611 |
+
"learning_rate": 3.188476645515692e-08,
|
| 1612 |
+
"loss": 0.0715,
|
| 1613 |
+
"step": 1145
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 2.956298200514139,
|
| 1617 |
+
"grad_norm": 0.5556385517120361,
|
| 1618 |
+
"learning_rate": 1.953134841154447e-08,
|
| 1619 |
+
"loss": 0.0621,
|
| 1620 |
+
"step": 1150
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 2.969151670951157,
|
| 1624 |
+
"grad_norm": 0.5337257981300354,
|
| 1625 |
+
"learning_rate": 1.0188705772393725e-08,
|
| 1626 |
+
"loss": 0.0645,
|
| 1627 |
+
"step": 1155
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 2.982005141388175,
|
| 1631 |
+
"grad_norm": 0.6417534351348877,
|
| 1632 |
+
"learning_rate": 3.858716222530645e-09,
|
| 1633 |
+
"loss": 0.0655,
|
| 1634 |
+
"step": 1160
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 2.994858611825193,
|
| 1638 |
+
"grad_norm": 0.5771808624267578,
|
| 1639 |
+
"learning_rate": 5.426519635975958e-10,
|
| 1640 |
+
"loss": 0.0616,
|
| 1641 |
+
"step": 1165
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 3.0,
|
| 1645 |
+
"step": 1167,
|
| 1646 |
+
"total_flos": 1.460258687019909e+18,
|
| 1647 |
+
"train_loss": 0.37291577482642324,
|
| 1648 |
+
"train_runtime": 701.2954,
|
| 1649 |
+
"train_samples_per_second": 53.186,
|
| 1650 |
+
"train_steps_per_second": 1.664
|
| 1651 |
+
}
|
| 1652 |
+
],
|
| 1653 |
+
"logging_steps": 5,
|
| 1654 |
+
"max_steps": 1167,
|
| 1655 |
+
"num_input_tokens_seen": 0,
|
| 1656 |
+
"num_train_epochs": 3,
|
| 1657 |
+
"save_steps": 20000,
|
| 1658 |
+
"stateful_callbacks": {
|
| 1659 |
+
"TrainerControl": {
|
| 1660 |
+
"args": {
|
| 1661 |
+
"should_epoch_stop": false,
|
| 1662 |
+
"should_evaluate": false,
|
| 1663 |
+
"should_log": false,
|
| 1664 |
+
"should_save": false,
|
| 1665 |
+
"should_training_stop": false
|
| 1666 |
+
},
|
| 1667 |
+
"attributes": {}
|
| 1668 |
+
}
|
| 1669 |
+
},
|
| 1670 |
+
"total_flos": 1.460258687019909e+18,
|
| 1671 |
+
"train_batch_size": 2,
|
| 1672 |
+
"trial_name": null,
|
| 1673 |
+
"trial_params": null
|
| 1674 |
+
}
|
135_128_e3_3e-5/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ca1c86804b8a6e02d8e5283c12e00e77d158089e3d8234353cbdb6f74a9b792
|
| 3 |
+
size 8273
|
135_128_e3_3e-5/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|