Upload folder using huggingface_hub
Browse files- instruct/142_128_e3_3e-5/adapter_config.json +39 -0
- instruct/142_128_e3_3e-5/adapter_model.safetensors +3 -0
- instruct/142_128_e3_3e-5/added_tokens.json +9 -0
- instruct/142_128_e3_3e-5/all_results.json +9 -0
- instruct/142_128_e3_3e-5/chat_template.jinja +62 -0
- instruct/142_128_e3_3e-5/config.json +32 -0
- instruct/142_128_e3_3e-5/merges.txt +0 -0
- instruct/142_128_e3_3e-5/special_tokens_map.json +33 -0
- instruct/142_128_e3_3e-5/tokenizer.json +0 -0
- instruct/142_128_e3_3e-5/tokenizer_config.json +234 -0
- instruct/142_128_e3_3e-5/train_results.json +9 -0
- instruct/142_128_e3_3e-5/trainer_state.json +1807 -0
- instruct/142_128_e3_3e-5/training_args.bin +3 -0
- instruct/142_128_e3_3e-5/vocab.json +0 -0
instruct/142_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 |
+
"down_proj",
|
| 28 |
+
"q_proj",
|
| 29 |
+
"k_proj",
|
| 30 |
+
"v_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 |
+
}
|
instruct/142_128_e3_3e-5/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4f4ae065b3636093a7a0462f1532d3ec3179a0e36cbac760eb4e2ecdfa5bc824
|
| 3 |
+
size 791751704
|
instruct/142_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 |
+
}
|
instruct/142_128_e3_3e-5/all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 1.6060508203804262e+18,
|
| 4 |
+
"train_loss": 0.3766768909635998,
|
| 5 |
+
"train_runtime": 786.8652,
|
| 6 |
+
"train_samples": 13419,
|
| 7 |
+
"train_samples_per_second": 51.161,
|
| 8 |
+
"train_steps_per_second": 1.601
|
| 9 |
+
}
|
instruct/142_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 %}
|
instruct/142_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 |
+
}
|
instruct/142_128_e3_3e-5/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
instruct/142_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 |
+
}
|
instruct/142_128_e3_3e-5/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
instruct/142_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 |
+
}
|
instruct/142_128_e3_3e-5/train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 1.6060508203804262e+18,
|
| 4 |
+
"train_loss": 0.3766768909635998,
|
| 5 |
+
"train_runtime": 786.8652,
|
| 6 |
+
"train_samples": 13419,
|
| 7 |
+
"train_samples_per_second": 51.161,
|
| 8 |
+
"train_steps_per_second": 1.601
|
| 9 |
+
}
|
instruct/142_128_e3_3e-5/trainer_state.json
ADDED
|
@@ -0,0 +1,1807 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 1260,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.011918951132300357,
|
| 14 |
+
"grad_norm": 2.262829542160034,
|
| 15 |
+
"learning_rate": 1.9047619047619047e-06,
|
| 16 |
+
"loss": 1.61,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.023837902264600714,
|
| 21 |
+
"grad_norm": 1.9369862079620361,
|
| 22 |
+
"learning_rate": 4.2857142857142855e-06,
|
| 23 |
+
"loss": 1.5976,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.03575685339690107,
|
| 28 |
+
"grad_norm": 0.8963153958320618,
|
| 29 |
+
"learning_rate": 6.666666666666667e-06,
|
| 30 |
+
"loss": 1.5312,
|
| 31 |
+
"step": 15
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.04767580452920143,
|
| 35 |
+
"grad_norm": 0.5530104041099548,
|
| 36 |
+
"learning_rate": 9.047619047619047e-06,
|
| 37 |
+
"loss": 1.4826,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.05959475566150179,
|
| 42 |
+
"grad_norm": 0.45540815591812134,
|
| 43 |
+
"learning_rate": 1.1428571428571429e-05,
|
| 44 |
+
"loss": 1.429,
|
| 45 |
+
"step": 25
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.07151370679380215,
|
| 49 |
+
"grad_norm": 0.5416069030761719,
|
| 50 |
+
"learning_rate": 1.380952380952381e-05,
|
| 51 |
+
"loss": 1.4362,
|
| 52 |
+
"step": 30
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.08343265792610251,
|
| 56 |
+
"grad_norm": 0.4352725148200989,
|
| 57 |
+
"learning_rate": 1.619047619047619e-05,
|
| 58 |
+
"loss": 1.4108,
|
| 59 |
+
"step": 35
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.09535160905840286,
|
| 63 |
+
"grad_norm": 0.47551846504211426,
|
| 64 |
+
"learning_rate": 1.8571428571428572e-05,
|
| 65 |
+
"loss": 1.372,
|
| 66 |
+
"step": 40
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.10727056019070322,
|
| 70 |
+
"grad_norm": 0.3884429931640625,
|
| 71 |
+
"learning_rate": 2.095238095238095e-05,
|
| 72 |
+
"loss": 1.3941,
|
| 73 |
+
"step": 45
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.11918951132300358,
|
| 77 |
+
"grad_norm": 0.449757844209671,
|
| 78 |
+
"learning_rate": 2.3333333333333336e-05,
|
| 79 |
+
"loss": 1.3654,
|
| 80 |
+
"step": 50
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.13110846245530394,
|
| 84 |
+
"grad_norm": 0.48552206158638,
|
| 85 |
+
"learning_rate": 2.5714285714285714e-05,
|
| 86 |
+
"loss": 1.3678,
|
| 87 |
+
"step": 55
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.1430274135876043,
|
| 91 |
+
"grad_norm": 0.4075373411178589,
|
| 92 |
+
"learning_rate": 2.8095238095238096e-05,
|
| 93 |
+
"loss": 1.3344,
|
| 94 |
+
"step": 60
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.15494636471990464,
|
| 98 |
+
"grad_norm": 0.49731016159057617,
|
| 99 |
+
"learning_rate": 2.999994833785207e-05,
|
| 100 |
+
"loss": 1.3004,
|
| 101 |
+
"step": 65
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.16686531585220502,
|
| 105 |
+
"grad_norm": 0.4355427920818329,
|
| 106 |
+
"learning_rate": 2.9998140200039827e-05,
|
| 107 |
+
"loss": 1.2597,
|
| 108 |
+
"step": 70
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.17878426698450536,
|
| 112 |
+
"grad_norm": 0.4720499515533447,
|
| 113 |
+
"learning_rate": 2.9993749310683582e-05,
|
| 114 |
+
"loss": 1.2848,
|
| 115 |
+
"step": 75
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.1907032181168057,
|
| 119 |
+
"grad_norm": 0.4637933373451233,
|
| 120 |
+
"learning_rate": 2.9986776425915508e-05,
|
| 121 |
+
"loss": 1.2072,
|
| 122 |
+
"step": 80
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.2026221692491061,
|
| 126 |
+
"grad_norm": 0.5206542611122131,
|
| 127 |
+
"learning_rate": 2.997722274649974e-05,
|
| 128 |
+
"loss": 1.2183,
|
| 129 |
+
"step": 85
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.21454112038140644,
|
| 133 |
+
"grad_norm": 0.5006417632102966,
|
| 134 |
+
"learning_rate": 2.9965089917625624e-05,
|
| 135 |
+
"loss": 1.1818,
|
| 136 |
+
"step": 90
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.22646007151370678,
|
| 140 |
+
"grad_norm": 0.6354581117630005,
|
| 141 |
+
"learning_rate": 2.9950380028624356e-05,
|
| 142 |
+
"loss": 1.1769,
|
| 143 |
+
"step": 95
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.23837902264600716,
|
| 147 |
+
"grad_norm": 0.5311831831932068,
|
| 148 |
+
"learning_rate": 2.9933095612609253e-05,
|
| 149 |
+
"loss": 1.2033,
|
| 150 |
+
"step": 100
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.25029797377830754,
|
| 154 |
+
"grad_norm": 0.5797717571258545,
|
| 155 |
+
"learning_rate": 2.9913239646039503e-05,
|
| 156 |
+
"loss": 1.1114,
|
| 157 |
+
"step": 105
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.2622169249106079,
|
| 161 |
+
"grad_norm": 0.618526041507721,
|
| 162 |
+
"learning_rate": 2.98908155482076e-05,
|
| 163 |
+
"loss": 1.1299,
|
| 164 |
+
"step": 110
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.27413587604290823,
|
| 168 |
+
"grad_norm": 0.7171409130096436,
|
| 169 |
+
"learning_rate": 2.986582718065055e-05,
|
| 170 |
+
"loss": 1.0934,
|
| 171 |
+
"step": 115
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.2860548271752086,
|
| 175 |
+
"grad_norm": 0.6281618475914001,
|
| 176 |
+
"learning_rate": 2.9838278846484868e-05,
|
| 177 |
+
"loss": 1.1083,
|
| 178 |
+
"step": 120
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.29797377830750893,
|
| 182 |
+
"grad_norm": 0.6588351726531982,
|
| 183 |
+
"learning_rate": 2.9808175289665588e-05,
|
| 184 |
+
"loss": 1.0419,
|
| 185 |
+
"step": 125
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.3098927294398093,
|
| 189 |
+
"grad_norm": 0.6377130746841431,
|
| 190 |
+
"learning_rate": 2.9775521694169305e-05,
|
| 191 |
+
"loss": 1.0501,
|
| 192 |
+
"step": 130
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.3218116805721097,
|
| 196 |
+
"grad_norm": 0.7825397849082947,
|
| 197 |
+
"learning_rate": 2.974032368310149e-05,
|
| 198 |
+
"loss": 1.0072,
|
| 199 |
+
"step": 135
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.33373063170441003,
|
| 203 |
+
"grad_norm": 0.6922541260719299,
|
| 204 |
+
"learning_rate": 2.9702587317728157e-05,
|
| 205 |
+
"loss": 0.9956,
|
| 206 |
+
"step": 140
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.3456495828367104,
|
| 210 |
+
"grad_norm": 0.720664918422699,
|
| 211 |
+
"learning_rate": 2.966231909643208e-05,
|
| 212 |
+
"loss": 1.0259,
|
| 213 |
+
"step": 145
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.3575685339690107,
|
| 217 |
+
"grad_norm": 0.776907742023468,
|
| 218 |
+
"learning_rate": 2.961952595359374e-05,
|
| 219 |
+
"loss": 0.9403,
|
| 220 |
+
"step": 150
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.3694874851013111,
|
| 224 |
+
"grad_norm": 0.7776645421981812,
|
| 225 |
+
"learning_rate": 2.957421525839721e-05,
|
| 226 |
+
"loss": 0.9646,
|
| 227 |
+
"step": 155
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.3814064362336114,
|
| 231 |
+
"grad_norm": 0.8240993022918701,
|
| 232 |
+
"learning_rate": 2.952639481356111e-05,
|
| 233 |
+
"loss": 0.9902,
|
| 234 |
+
"step": 160
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.3933253873659118,
|
| 238 |
+
"grad_norm": 0.8797292113304138,
|
| 239 |
+
"learning_rate": 2.9476072853994983e-05,
|
| 240 |
+
"loss": 0.9434,
|
| 241 |
+
"step": 165
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.4052443384982122,
|
| 245 |
+
"grad_norm": 0.8732948303222656,
|
| 246 |
+
"learning_rate": 2.942325804538117e-05,
|
| 247 |
+
"loss": 0.8379,
|
| 248 |
+
"step": 170
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.4171632896305125,
|
| 252 |
+
"grad_norm": 0.8640727996826172,
|
| 253 |
+
"learning_rate": 2.9367959482682564e-05,
|
| 254 |
+
"loss": 0.8333,
|
| 255 |
+
"step": 175
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.42908224076281287,
|
| 259 |
+
"grad_norm": 1.0544800758361816,
|
| 260 |
+
"learning_rate": 2.931018668857639e-05,
|
| 261 |
+
"loss": 0.8182,
|
| 262 |
+
"step": 180
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.4410011918951132,
|
| 266 |
+
"grad_norm": 0.8845022320747375,
|
| 267 |
+
"learning_rate": 2.9249949611814378e-05,
|
| 268 |
+
"loss": 0.8368,
|
| 269 |
+
"step": 185
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.45292014302741357,
|
| 273 |
+
"grad_norm": 0.8514461517333984,
|
| 274 |
+
"learning_rate": 2.9187258625509518e-05,
|
| 275 |
+
"loss": 0.8377,
|
| 276 |
+
"step": 190
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.464839094159714,
|
| 280 |
+
"grad_norm": 0.9174619913101196,
|
| 281 |
+
"learning_rate": 2.9122124525349782e-05,
|
| 282 |
+
"loss": 0.8931,
|
| 283 |
+
"step": 195
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.4767580452920143,
|
| 287 |
+
"grad_norm": 1.1025309562683105,
|
| 288 |
+
"learning_rate": 2.9054558527739036e-05,
|
| 289 |
+
"loss": 0.7824,
|
| 290 |
+
"step": 200
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.48867699642431467,
|
| 294 |
+
"grad_norm": 1.1116083860397339,
|
| 295 |
+
"learning_rate": 2.8984572267865527e-05,
|
| 296 |
+
"loss": 0.8803,
|
| 297 |
+
"step": 205
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.5005959475566151,
|
| 301 |
+
"grad_norm": 1.0345054864883423,
|
| 302 |
+
"learning_rate": 2.8912177797698263e-05,
|
| 303 |
+
"loss": 0.7496,
|
| 304 |
+
"step": 210
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.5125148986889154,
|
| 308 |
+
"grad_norm": 1.0969973802566528,
|
| 309 |
+
"learning_rate": 2.8837387583911582e-05,
|
| 310 |
+
"loss": 0.7376,
|
| 311 |
+
"step": 215
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.5244338498212158,
|
| 315 |
+
"grad_norm": 1.1282289028167725,
|
| 316 |
+
"learning_rate": 2.8760214505738336e-05,
|
| 317 |
+
"loss": 0.7933,
|
| 318 |
+
"step": 220
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.5363528009535161,
|
| 322 |
+
"grad_norm": 1.0125519037246704,
|
| 323 |
+
"learning_rate": 2.8680671852752058e-05,
|
| 324 |
+
"loss": 0.7147,
|
| 325 |
+
"step": 225
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.5482717520858165,
|
| 329 |
+
"grad_norm": 1.1023448705673218,
|
| 330 |
+
"learning_rate": 2.859877332257838e-05,
|
| 331 |
+
"loss": 0.7011,
|
| 332 |
+
"step": 230
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.5601907032181168,
|
| 336 |
+
"grad_norm": 1.1131722927093506,
|
| 337 |
+
"learning_rate": 2.8514533018536286e-05,
|
| 338 |
+
"loss": 0.6894,
|
| 339 |
+
"step": 235
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.5721096543504172,
|
| 343 |
+
"grad_norm": 1.1107255220413208,
|
| 344 |
+
"learning_rate": 2.8427965447209415e-05,
|
| 345 |
+
"loss": 0.732,
|
| 346 |
+
"step": 240
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.5840286054827175,
|
| 350 |
+
"grad_norm": 1.033869743347168,
|
| 351 |
+
"learning_rate": 2.833908551594798e-05,
|
| 352 |
+
"loss": 0.6823,
|
| 353 |
+
"step": 245
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.5959475566150179,
|
| 357 |
+
"grad_norm": 0.9664804935455322,
|
| 358 |
+
"learning_rate": 2.8247908530301646e-05,
|
| 359 |
+
"loss": 0.7001,
|
| 360 |
+
"step": 250
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.6078665077473182,
|
| 364 |
+
"grad_norm": 1.3919854164123535,
|
| 365 |
+
"learning_rate": 2.8154450191383834e-05,
|
| 366 |
+
"loss": 0.652,
|
| 367 |
+
"step": 255
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.6197854588796186,
|
| 371 |
+
"grad_norm": 1.0857477188110352,
|
| 372 |
+
"learning_rate": 2.8058726593167938e-05,
|
| 373 |
+
"loss": 0.6552,
|
| 374 |
+
"step": 260
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.6317044100119189,
|
| 378 |
+
"grad_norm": 1.2335199117660522,
|
| 379 |
+
"learning_rate": 2.796075421971582e-05,
|
| 380 |
+
"loss": 0.6621,
|
| 381 |
+
"step": 265
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.6436233611442194,
|
| 385 |
+
"grad_norm": 1.0945508480072021,
|
| 386 |
+
"learning_rate": 2.7860549942339224e-05,
|
| 387 |
+
"loss": 0.6384,
|
| 388 |
+
"step": 270
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.6555423122765197,
|
| 392 |
+
"grad_norm": 1.1837527751922607,
|
| 393 |
+
"learning_rate": 2.775813101669443e-05,
|
| 394 |
+
"loss": 0.6248,
|
| 395 |
+
"step": 275
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.6674612634088201,
|
| 399 |
+
"grad_norm": 1.3278813362121582,
|
| 400 |
+
"learning_rate": 2.7653515079810744e-05,
|
| 401 |
+
"loss": 0.6212,
|
| 402 |
+
"step": 280
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.6793802145411204,
|
| 406 |
+
"grad_norm": 1.209497094154358,
|
| 407 |
+
"learning_rate": 2.7546720147053336e-05,
|
| 408 |
+
"loss": 0.6081,
|
| 409 |
+
"step": 285
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.6912991656734208,
|
| 413 |
+
"grad_norm": 1.2211415767669678,
|
| 414 |
+
"learning_rate": 2.7437764609020895e-05,
|
| 415 |
+
"loss": 0.5635,
|
| 416 |
+
"step": 290
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.7032181168057211,
|
| 420 |
+
"grad_norm": 1.19447660446167,
|
| 421 |
+
"learning_rate": 2.7326667228378677e-05,
|
| 422 |
+
"loss": 0.5978,
|
| 423 |
+
"step": 295
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.7151370679380215,
|
| 427 |
+
"grad_norm": 1.109729290008545,
|
| 428 |
+
"learning_rate": 2.72134471366275e-05,
|
| 429 |
+
"loss": 0.5869,
|
| 430 |
+
"step": 300
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.7270560190703218,
|
| 434 |
+
"grad_norm": 1.2329115867614746,
|
| 435 |
+
"learning_rate": 2.7098123830809173e-05,
|
| 436 |
+
"loss": 0.6126,
|
| 437 |
+
"step": 305
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.7389749702026222,
|
| 441 |
+
"grad_norm": 1.4081915616989136,
|
| 442 |
+
"learning_rate": 2.698071717014907e-05,
|
| 443 |
+
"loss": 0.5829,
|
| 444 |
+
"step": 310
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.7508939213349225,
|
| 448 |
+
"grad_norm": 1.174920678138733,
|
| 449 |
+
"learning_rate": 2.6861247372636216e-05,
|
| 450 |
+
"loss": 0.5679,
|
| 451 |
+
"step": 315
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.7628128724672228,
|
| 455 |
+
"grad_norm": 1.2614197731018066,
|
| 456 |
+
"learning_rate": 2.6739735011541688e-05,
|
| 457 |
+
"loss": 0.5179,
|
| 458 |
+
"step": 320
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.7747318235995232,
|
| 462 |
+
"grad_norm": 1.113453984260559,
|
| 463 |
+
"learning_rate": 2.6616201011875792e-05,
|
| 464 |
+
"loss": 0.5501,
|
| 465 |
+
"step": 325
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.7866507747318237,
|
| 469 |
+
"grad_norm": 1.2454824447631836,
|
| 470 |
+
"learning_rate": 2.649066664678467e-05,
|
| 471 |
+
"loss": 0.5603,
|
| 472 |
+
"step": 330
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.798569725864124,
|
| 476 |
+
"grad_norm": 1.2551757097244263,
|
| 477 |
+
"learning_rate": 2.6363153533886974e-05,
|
| 478 |
+
"loss": 0.5208,
|
| 479 |
+
"step": 335
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.8104886769964244,
|
| 483 |
+
"grad_norm": 1.1531585454940796,
|
| 484 |
+
"learning_rate": 2.6233683631551197e-05,
|
| 485 |
+
"loss": 0.5052,
|
| 486 |
+
"step": 340
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.8224076281287247,
|
| 490 |
+
"grad_norm": 1.3409498929977417,
|
| 491 |
+
"learning_rate": 2.6102279235114335e-05,
|
| 492 |
+
"loss": 0.5026,
|
| 493 |
+
"step": 345
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.834326579261025,
|
| 497 |
+
"grad_norm": 1.218204379081726,
|
| 498 |
+
"learning_rate": 2.596896297304254e-05,
|
| 499 |
+
"loss": 0.4684,
|
| 500 |
+
"step": 350
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.8462455303933254,
|
| 504 |
+
"grad_norm": 1.3288019895553589,
|
| 505 |
+
"learning_rate": 2.583375780303437e-05,
|
| 506 |
+
"loss": 0.5465,
|
| 507 |
+
"step": 355
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.8581644815256257,
|
| 511 |
+
"grad_norm": 1.2845507860183716,
|
| 512 |
+
"learning_rate": 2.5696687008067384e-05,
|
| 513 |
+
"loss": 0.5019,
|
| 514 |
+
"step": 360
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.8700834326579261,
|
| 518 |
+
"grad_norm": 1.4997559785842896,
|
| 519 |
+
"learning_rate": 2.5557774192388674e-05,
|
| 520 |
+
"loss": 0.4185,
|
| 521 |
+
"step": 365
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.8820023837902264,
|
| 525 |
+
"grad_norm": 1.267397165298462,
|
| 526 |
+
"learning_rate": 2.541704327745013e-05,
|
| 527 |
+
"loss": 0.4448,
|
| 528 |
+
"step": 370
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.8939213349225268,
|
| 532 |
+
"grad_norm": 1.3329143524169922,
|
| 533 |
+
"learning_rate": 2.5274518497789038e-05,
|
| 534 |
+
"loss": 0.4489,
|
| 535 |
+
"step": 375
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.9058402860548271,
|
| 539 |
+
"grad_norm": 1.2730886936187744,
|
| 540 |
+
"learning_rate": 2.5130224396854768e-05,
|
| 541 |
+
"loss": 0.4283,
|
| 542 |
+
"step": 380
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.9177592371871275,
|
| 546 |
+
"grad_norm": 1.4327051639556885,
|
| 547 |
+
"learning_rate": 2.498418582278229e-05,
|
| 548 |
+
"loss": 0.4622,
|
| 549 |
+
"step": 385
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.929678188319428,
|
| 553 |
+
"grad_norm": 1.4058210849761963,
|
| 554 |
+
"learning_rate": 2.4836427924113202e-05,
|
| 555 |
+
"loss": 0.4669,
|
| 556 |
+
"step": 390
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.9415971394517283,
|
| 560 |
+
"grad_norm": 1.3866819143295288,
|
| 561 |
+
"learning_rate": 2.4686976145465024e-05,
|
| 562 |
+
"loss": 0.4298,
|
| 563 |
+
"step": 395
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.9535160905840286,
|
| 567 |
+
"grad_norm": 1.4005985260009766,
|
| 568 |
+
"learning_rate": 2.4535856223149525e-05,
|
| 569 |
+
"loss": 0.4234,
|
| 570 |
+
"step": 400
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.965435041716329,
|
| 574 |
+
"grad_norm": 1.2366111278533936,
|
| 575 |
+
"learning_rate": 2.438309418074078e-05,
|
| 576 |
+
"loss": 0.3861,
|
| 577 |
+
"step": 405
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.9773539928486293,
|
| 581 |
+
"grad_norm": 1.262812614440918,
|
| 582 |
+
"learning_rate": 2.422871632459383e-05,
|
| 583 |
+
"loss": 0.3816,
|
| 584 |
+
"step": 410
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.9892729439809297,
|
| 588 |
+
"grad_norm": 1.3693567514419556,
|
| 589 |
+
"learning_rate": 2.4072749239314565e-05,
|
| 590 |
+
"loss": 0.3944,
|
| 591 |
+
"step": 415
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.0,
|
| 595 |
+
"grad_norm": 1.490755319595337,
|
| 596 |
+
"learning_rate": 2.391521978318174e-05,
|
| 597 |
+
"loss": 0.3968,
|
| 598 |
+
"step": 420
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.0119189511323003,
|
| 602 |
+
"grad_norm": 1.2292996644973755,
|
| 603 |
+
"learning_rate": 2.375615508352185e-05,
|
| 604 |
+
"loss": 0.3643,
|
| 605 |
+
"step": 425
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.0238379022646007,
|
| 609 |
+
"grad_norm": 1.270226240158081,
|
| 610 |
+
"learning_rate": 2.359558253203768e-05,
|
| 611 |
+
"loss": 0.3468,
|
| 612 |
+
"step": 430
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.035756853396901,
|
| 616 |
+
"grad_norm": 1.405706524848938,
|
| 617 |
+
"learning_rate": 2.3433529780091315e-05,
|
| 618 |
+
"loss": 0.2815,
|
| 619 |
+
"step": 435
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.0476758045292014,
|
| 623 |
+
"grad_norm": 1.1360613107681274,
|
| 624 |
+
"learning_rate": 2.3270024733942443e-05,
|
| 625 |
+
"loss": 0.3268,
|
| 626 |
+
"step": 440
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.0595947556615017,
|
| 630 |
+
"grad_norm": 1.5314515829086304,
|
| 631 |
+
"learning_rate": 2.3105095549942768e-05,
|
| 632 |
+
"loss": 0.3279,
|
| 633 |
+
"step": 445
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.071513706793802,
|
| 637 |
+
"grad_norm": 1.1298781633377075,
|
| 638 |
+
"learning_rate": 2.2938770629687355e-05,
|
| 639 |
+
"loss": 0.2753,
|
| 640 |
+
"step": 450
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.0834326579261024,
|
| 644 |
+
"grad_norm": 1.2938463687896729,
|
| 645 |
+
"learning_rate": 2.2771078615123728e-05,
|
| 646 |
+
"loss": 0.3415,
|
| 647 |
+
"step": 455
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.0953516090584028,
|
| 651 |
+
"grad_norm": 1.2140966653823853,
|
| 652 |
+
"learning_rate": 2.26020483836196e-05,
|
| 653 |
+
"loss": 0.3398,
|
| 654 |
+
"step": 460
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.1072705601907031,
|
| 658 |
+
"grad_norm": 1.2675073146820068,
|
| 659 |
+
"learning_rate": 2.243170904299004e-05,
|
| 660 |
+
"loss": 0.3252,
|
| 661 |
+
"step": 465
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.1191895113230035,
|
| 665 |
+
"grad_norm": 1.3465524911880493,
|
| 666 |
+
"learning_rate": 2.2260089926484987e-05,
|
| 667 |
+
"loss": 0.3151,
|
| 668 |
+
"step": 470
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.131108462455304,
|
| 672 |
+
"grad_norm": 1.4649810791015625,
|
| 673 |
+
"learning_rate": 2.2087220587737896e-05,
|
| 674 |
+
"loss": 0.3118,
|
| 675 |
+
"step": 475
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.1430274135876042,
|
| 679 |
+
"grad_norm": 1.2737265825271606,
|
| 680 |
+
"learning_rate": 2.1913130795676497e-05,
|
| 681 |
+
"loss": 0.2894,
|
| 682 |
+
"step": 480
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.1549463647199048,
|
| 686 |
+
"grad_norm": 1.4684540033340454,
|
| 687 |
+
"learning_rate": 2.1737850529396413e-05,
|
| 688 |
+
"loss": 0.288,
|
| 689 |
+
"step": 485
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.166865315852205,
|
| 693 |
+
"grad_norm": 1.2002910375595093,
|
| 694 |
+
"learning_rate": 2.1561409972998623e-05,
|
| 695 |
+
"loss": 0.276,
|
| 696 |
+
"step": 490
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.1787842669845054,
|
| 700 |
+
"grad_norm": 1.3152066469192505,
|
| 701 |
+
"learning_rate": 2.1383839510391632e-05,
|
| 702 |
+
"loss": 0.2716,
|
| 703 |
+
"step": 495
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.1907032181168058,
|
| 707 |
+
"grad_norm": 1.2566128969192505,
|
| 708 |
+
"learning_rate": 2.1205169720059185e-05,
|
| 709 |
+
"loss": 0.2603,
|
| 710 |
+
"step": 500
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.2026221692491061,
|
| 714 |
+
"grad_norm": 1.1125105619430542,
|
| 715 |
+
"learning_rate": 2.1025431369794546e-05,
|
| 716 |
+
"loss": 0.2846,
|
| 717 |
+
"step": 505
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.2145411203814065,
|
| 721 |
+
"grad_norm": 1.2085881233215332,
|
| 722 |
+
"learning_rate": 2.0844655411402094e-05,
|
| 723 |
+
"loss": 0.2887,
|
| 724 |
+
"step": 510
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.2264600715137068,
|
| 728 |
+
"grad_norm": 1.2564611434936523,
|
| 729 |
+
"learning_rate": 2.0662872975367304e-05,
|
| 730 |
+
"loss": 0.247,
|
| 731 |
+
"step": 515
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.2383790226460072,
|
| 735 |
+
"grad_norm": 1.231830358505249,
|
| 736 |
+
"learning_rate": 2.0480115365495928e-05,
|
| 737 |
+
"loss": 0.2383,
|
| 738 |
+
"step": 520
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.2502979737783075,
|
| 742 |
+
"grad_norm": 1.2739923000335693,
|
| 743 |
+
"learning_rate": 2.0296414053523307e-05,
|
| 744 |
+
"loss": 0.2673,
|
| 745 |
+
"step": 525
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.2622169249106079,
|
| 749 |
+
"grad_norm": 1.2181757688522339,
|
| 750 |
+
"learning_rate": 2.011180067369481e-05,
|
| 751 |
+
"loss": 0.253,
|
| 752 |
+
"step": 530
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.2741358760429082,
|
| 756 |
+
"grad_norm": 1.1742464303970337,
|
| 757 |
+
"learning_rate": 1.992630701731825e-05,
|
| 758 |
+
"loss": 0.2569,
|
| 759 |
+
"step": 535
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.2860548271752086,
|
| 763 |
+
"grad_norm": 1.4240808486938477,
|
| 764 |
+
"learning_rate": 1.973996502728929e-05,
|
| 765 |
+
"loss": 0.2603,
|
| 766 |
+
"step": 540
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.297973778307509,
|
| 770 |
+
"grad_norm": 1.179705262184143,
|
| 771 |
+
"learning_rate": 1.9552806792590694e-05,
|
| 772 |
+
"loss": 0.2731,
|
| 773 |
+
"step": 545
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.3098927294398093,
|
| 777 |
+
"grad_norm": 1.3327654600143433,
|
| 778 |
+
"learning_rate": 1.936486454276647e-05,
|
| 779 |
+
"loss": 0.241,
|
| 780 |
+
"step": 550
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.3218116805721096,
|
| 784 |
+
"grad_norm": 1.326736330986023,
|
| 785 |
+
"learning_rate": 1.9176170642371785e-05,
|
| 786 |
+
"loss": 0.2465,
|
| 787 |
+
"step": 555
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.33373063170441,
|
| 791 |
+
"grad_norm": 1.084389328956604,
|
| 792 |
+
"learning_rate": 1.898675758539964e-05,
|
| 793 |
+
"loss": 0.2362,
|
| 794 |
+
"step": 560
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.3456495828367103,
|
| 798 |
+
"grad_norm": 1.2351628541946411,
|
| 799 |
+
"learning_rate": 1.879665798968523e-05,
|
| 800 |
+
"loss": 0.2489,
|
| 801 |
+
"step": 565
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.3575685339690107,
|
| 805 |
+
"grad_norm": 1.1064057350158691,
|
| 806 |
+
"learning_rate": 1.8605904591289013e-05,
|
| 807 |
+
"loss": 0.2403,
|
| 808 |
+
"step": 570
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.369487485101311,
|
| 812 |
+
"grad_norm": 1.3226569890975952,
|
| 813 |
+
"learning_rate": 1.8414530238859405e-05,
|
| 814 |
+
"loss": 0.1922,
|
| 815 |
+
"step": 575
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.3814064362336114,
|
| 819 |
+
"grad_norm": 1.1118088960647583,
|
| 820 |
+
"learning_rate": 1.822256788797606e-05,
|
| 821 |
+
"loss": 0.1898,
|
| 822 |
+
"step": 580
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.3933253873659117,
|
| 826 |
+
"grad_norm": 1.2494362592697144,
|
| 827 |
+
"learning_rate": 1.8030050595474803e-05,
|
| 828 |
+
"loss": 0.2315,
|
| 829 |
+
"step": 585
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.4052443384982123,
|
| 833 |
+
"grad_norm": 1.0067795515060425,
|
| 834 |
+
"learning_rate": 1.7837011513755053e-05,
|
| 835 |
+
"loss": 0.2264,
|
| 836 |
+
"step": 590
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.4171632896305124,
|
| 840 |
+
"grad_norm": 1.1102453470230103,
|
| 841 |
+
"learning_rate": 1.7643483885070827e-05,
|
| 842 |
+
"loss": 0.2113,
|
| 843 |
+
"step": 595
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.429082240762813,
|
| 847 |
+
"grad_norm": 1.0318585634231567,
|
| 848 |
+
"learning_rate": 1.7449501035806277e-05,
|
| 849 |
+
"loss": 0.2065,
|
| 850 |
+
"step": 600
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.441001191895113,
|
| 854 |
+
"grad_norm": 1.202604055404663,
|
| 855 |
+
"learning_rate": 1.72550963707367e-05,
|
| 856 |
+
"loss": 0.2121,
|
| 857 |
+
"step": 605
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.4529201430274137,
|
| 861 |
+
"grad_norm": 1.3912785053253174,
|
| 862 |
+
"learning_rate": 1.7060303367276123e-05,
|
| 863 |
+
"loss": 0.2221,
|
| 864 |
+
"step": 610
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.464839094159714,
|
| 868 |
+
"grad_norm": 1.1870397329330444,
|
| 869 |
+
"learning_rate": 1.686515556971228e-05,
|
| 870 |
+
"loss": 0.1888,
|
| 871 |
+
"step": 615
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.4767580452920144,
|
| 875 |
+
"grad_norm": 1.201088309288025,
|
| 876 |
+
"learning_rate": 1.6669686583430154e-05,
|
| 877 |
+
"loss": 0.2001,
|
| 878 |
+
"step": 620
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.4886769964243147,
|
| 882 |
+
"grad_norm": 1.282814621925354,
|
| 883 |
+
"learning_rate": 1.647393006912496e-05,
|
| 884 |
+
"loss": 0.2095,
|
| 885 |
+
"step": 625
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.500595947556615,
|
| 889 |
+
"grad_norm": 1.2941447496414185,
|
| 890 |
+
"learning_rate": 1.6277919737005628e-05,
|
| 891 |
+
"loss": 0.2024,
|
| 892 |
+
"step": 630
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 1.5125148986889154,
|
| 896 |
+
"grad_norm": 1.41281259059906,
|
| 897 |
+
"learning_rate": 1.6081689340989717e-05,
|
| 898 |
+
"loss": 0.1856,
|
| 899 |
+
"step": 635
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 1.5244338498212158,
|
| 903 |
+
"grad_norm": 1.1801561117172241,
|
| 904 |
+
"learning_rate": 1.5885272672890842e-05,
|
| 905 |
+
"loss": 0.1826,
|
| 906 |
+
"step": 640
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.5363528009535161,
|
| 910 |
+
"grad_norm": 1.0479340553283691,
|
| 911 |
+
"learning_rate": 1.5688703556599576e-05,
|
| 912 |
+
"loss": 0.1778,
|
| 913 |
+
"step": 645
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.5482717520858165,
|
| 917 |
+
"grad_norm": 1.2576520442962646,
|
| 918 |
+
"learning_rate": 1.5492015842258793e-05,
|
| 919 |
+
"loss": 0.1834,
|
| 920 |
+
"step": 650
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.5601907032181168,
|
| 924 |
+
"grad_norm": 1.0528560876846313,
|
| 925 |
+
"learning_rate": 1.529524340043451e-05,
|
| 926 |
+
"loss": 0.1956,
|
| 927 |
+
"step": 655
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.5721096543504172,
|
| 931 |
+
"grad_norm": 1.1267445087432861,
|
| 932 |
+
"learning_rate": 1.5098420116283238e-05,
|
| 933 |
+
"loss": 0.1951,
|
| 934 |
+
"step": 660
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.5840286054827175,
|
| 938 |
+
"grad_norm": 1.3407487869262695,
|
| 939 |
+
"learning_rate": 1.4901579883716764e-05,
|
| 940 |
+
"loss": 0.1665,
|
| 941 |
+
"step": 665
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.5959475566150179,
|
| 945 |
+
"grad_norm": 1.0433024168014526,
|
| 946 |
+
"learning_rate": 1.4704756599565494e-05,
|
| 947 |
+
"loss": 0.1618,
|
| 948 |
+
"step": 670
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 1.6078665077473182,
|
| 952 |
+
"grad_norm": 1.0858221054077148,
|
| 953 |
+
"learning_rate": 1.450798415774121e-05,
|
| 954 |
+
"loss": 0.17,
|
| 955 |
+
"step": 675
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.6197854588796186,
|
| 959 |
+
"grad_norm": 1.1185094118118286,
|
| 960 |
+
"learning_rate": 1.4311296443400423e-05,
|
| 961 |
+
"loss": 0.1714,
|
| 962 |
+
"step": 680
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.631704410011919,
|
| 966 |
+
"grad_norm": 1.0421684980392456,
|
| 967 |
+
"learning_rate": 1.411472732710916e-05,
|
| 968 |
+
"loss": 0.1696,
|
| 969 |
+
"step": 685
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.6436233611442193,
|
| 973 |
+
"grad_norm": 1.44697105884552,
|
| 974 |
+
"learning_rate": 1.3918310659010289e-05,
|
| 975 |
+
"loss": 0.1632,
|
| 976 |
+
"step": 690
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.6555423122765198,
|
| 980 |
+
"grad_norm": 1.1032581329345703,
|
| 981 |
+
"learning_rate": 1.3722080262994374e-05,
|
| 982 |
+
"loss": 0.1539,
|
| 983 |
+
"step": 695
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.66746126340882,
|
| 987 |
+
"grad_norm": 1.0234063863754272,
|
| 988 |
+
"learning_rate": 1.3526069930875044e-05,
|
| 989 |
+
"loss": 0.1743,
|
| 990 |
+
"step": 700
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.6793802145411205,
|
| 994 |
+
"grad_norm": 1.5381357669830322,
|
| 995 |
+
"learning_rate": 1.333031341656985e-05,
|
| 996 |
+
"loss": 0.1479,
|
| 997 |
+
"step": 705
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 1.6912991656734206,
|
| 1001 |
+
"grad_norm": 0.906078577041626,
|
| 1002 |
+
"learning_rate": 1.3134844430287727e-05,
|
| 1003 |
+
"loss": 0.1504,
|
| 1004 |
+
"step": 710
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.7032181168057212,
|
| 1008 |
+
"grad_norm": 1.192949891090393,
|
| 1009 |
+
"learning_rate": 1.2939696632723877e-05,
|
| 1010 |
+
"loss": 0.147,
|
| 1011 |
+
"step": 715
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 1.7151370679380213,
|
| 1015 |
+
"grad_norm": 0.9891089200973511,
|
| 1016 |
+
"learning_rate": 1.27449036292633e-05,
|
| 1017 |
+
"loss": 0.1419,
|
| 1018 |
+
"step": 720
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.727056019070322,
|
| 1022 |
+
"grad_norm": 1.1722702980041504,
|
| 1023 |
+
"learning_rate": 1.2550498964193727e-05,
|
| 1024 |
+
"loss": 0.1484,
|
| 1025 |
+
"step": 725
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 1.738974970202622,
|
| 1029 |
+
"grad_norm": 1.304612398147583,
|
| 1030 |
+
"learning_rate": 1.2356516114929176e-05,
|
| 1031 |
+
"loss": 0.1576,
|
| 1032 |
+
"step": 730
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 1.7508939213349226,
|
| 1036 |
+
"grad_norm": 1.1706671714782715,
|
| 1037 |
+
"learning_rate": 1.216298848624495e-05,
|
| 1038 |
+
"loss": 0.1479,
|
| 1039 |
+
"step": 735
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 1.7628128724672227,
|
| 1043 |
+
"grad_norm": 1.3275858163833618,
|
| 1044 |
+
"learning_rate": 1.1969949404525202e-05,
|
| 1045 |
+
"loss": 0.1557,
|
| 1046 |
+
"step": 740
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.7747318235995233,
|
| 1050 |
+
"grad_norm": 1.1614046096801758,
|
| 1051 |
+
"learning_rate": 1.1777432112023942e-05,
|
| 1052 |
+
"loss": 0.1474,
|
| 1053 |
+
"step": 745
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 1.7866507747318237,
|
| 1057 |
+
"grad_norm": 1.0814486742019653,
|
| 1058 |
+
"learning_rate": 1.1585469761140604e-05,
|
| 1059 |
+
"loss": 0.1566,
|
| 1060 |
+
"step": 750
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 1.798569725864124,
|
| 1064 |
+
"grad_norm": 0.8434069156646729,
|
| 1065 |
+
"learning_rate": 1.1394095408710988e-05,
|
| 1066 |
+
"loss": 0.1279,
|
| 1067 |
+
"step": 755
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 1.8104886769964244,
|
| 1071 |
+
"grad_norm": 0.9492409825325012,
|
| 1072 |
+
"learning_rate": 1.1203342010314772e-05,
|
| 1073 |
+
"loss": 0.1337,
|
| 1074 |
+
"step": 760
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.8224076281287247,
|
| 1078 |
+
"grad_norm": 0.9821645021438599,
|
| 1079 |
+
"learning_rate": 1.1013242414600359e-05,
|
| 1080 |
+
"loss": 0.1366,
|
| 1081 |
+
"step": 765
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 1.834326579261025,
|
| 1085 |
+
"grad_norm": 1.0048469305038452,
|
| 1086 |
+
"learning_rate": 1.0823829357628217e-05,
|
| 1087 |
+
"loss": 0.1364,
|
| 1088 |
+
"step": 770
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 1.8462455303933254,
|
| 1092 |
+
"grad_norm": 1.3044865131378174,
|
| 1093 |
+
"learning_rate": 1.0635135457233533e-05,
|
| 1094 |
+
"loss": 0.1449,
|
| 1095 |
+
"step": 775
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 1.8581644815256257,
|
| 1099 |
+
"grad_norm": 1.1135051250457764,
|
| 1100 |
+
"learning_rate": 1.0447193207409314e-05,
|
| 1101 |
+
"loss": 0.1374,
|
| 1102 |
+
"step": 780
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 1.870083432657926,
|
| 1106 |
+
"grad_norm": 1.126865267753601,
|
| 1107 |
+
"learning_rate": 1.0260034972710713e-05,
|
| 1108 |
+
"loss": 0.1463,
|
| 1109 |
+
"step": 785
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 1.8820023837902264,
|
| 1113 |
+
"grad_norm": 1.0014011859893799,
|
| 1114 |
+
"learning_rate": 1.0073692982681755e-05,
|
| 1115 |
+
"loss": 0.1328,
|
| 1116 |
+
"step": 790
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 1.8939213349225268,
|
| 1120 |
+
"grad_norm": 1.0643235445022583,
|
| 1121 |
+
"learning_rate": 9.888199326305194e-06,
|
| 1122 |
+
"loss": 0.1108,
|
| 1123 |
+
"step": 795
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 1.9058402860548271,
|
| 1127 |
+
"grad_norm": 1.1338930130004883,
|
| 1128 |
+
"learning_rate": 9.703585946476698e-06,
|
| 1129 |
+
"loss": 0.1054,
|
| 1130 |
+
"step": 800
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 1.9177592371871275,
|
| 1134 |
+
"grad_norm": 0.9489102363586426,
|
| 1135 |
+
"learning_rate": 9.519884634504074e-06,
|
| 1136 |
+
"loss": 0.1175,
|
| 1137 |
+
"step": 805
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 1.929678188319428,
|
| 1141 |
+
"grad_norm": 0.9772794842720032,
|
| 1142 |
+
"learning_rate": 9.3371270246327e-06,
|
| 1143 |
+
"loss": 0.1228,
|
| 1144 |
+
"step": 810
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 1.9415971394517282,
|
| 1148 |
+
"grad_norm": 0.9834482073783875,
|
| 1149 |
+
"learning_rate": 9.15534458859791e-06,
|
| 1150 |
+
"loss": 0.1187,
|
| 1151 |
+
"step": 815
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.9535160905840288,
|
| 1155 |
+
"grad_norm": 1.1202141046524048,
|
| 1156 |
+
"learning_rate": 8.974568630205462e-06,
|
| 1157 |
+
"loss": 0.124,
|
| 1158 |
+
"step": 820
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 1.9654350417163289,
|
| 1162 |
+
"grad_norm": 1.008472204208374,
|
| 1163 |
+
"learning_rate": 8.794830279940816e-06,
|
| 1164 |
+
"loss": 0.1209,
|
| 1165 |
+
"step": 825
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 1.9773539928486294,
|
| 1169 |
+
"grad_norm": 1.0232521295547485,
|
| 1170 |
+
"learning_rate": 8.616160489608375e-06,
|
| 1171 |
+
"loss": 0.1209,
|
| 1172 |
+
"step": 830
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 1.9892729439809296,
|
| 1176 |
+
"grad_norm": 0.8665810227394104,
|
| 1177 |
+
"learning_rate": 8.43859002700138e-06,
|
| 1178 |
+
"loss": 0.095,
|
| 1179 |
+
"step": 835
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 2.0,
|
| 1183 |
+
"grad_norm": 1.3909196853637695,
|
| 1184 |
+
"learning_rate": 8.262149470603593e-06,
|
| 1185 |
+
"loss": 0.1043,
|
| 1186 |
+
"step": 840
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 2.0119189511323006,
|
| 1190 |
+
"grad_norm": 0.8796659708023071,
|
| 1191 |
+
"learning_rate": 8.086869204323506e-06,
|
| 1192 |
+
"loss": 0.092,
|
| 1193 |
+
"step": 845
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 2.0238379022646007,
|
| 1197 |
+
"grad_norm": 0.8742193579673767,
|
| 1198 |
+
"learning_rate": 7.912779412262105e-06,
|
| 1199 |
+
"loss": 0.0895,
|
| 1200 |
+
"step": 850
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 2.0357568533969013,
|
| 1204 |
+
"grad_norm": 0.865256130695343,
|
| 1205 |
+
"learning_rate": 7.739910073515022e-06,
|
| 1206 |
+
"loss": 0.0879,
|
| 1207 |
+
"step": 855
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 2.0476758045292014,
|
| 1211 |
+
"grad_norm": 0.817166268825531,
|
| 1212 |
+
"learning_rate": 7.568290957009961e-06,
|
| 1213 |
+
"loss": 0.0791,
|
| 1214 |
+
"step": 860
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 2.059594755661502,
|
| 1218 |
+
"grad_norm": 0.6754058003425598,
|
| 1219 |
+
"learning_rate": 7.397951616380401e-06,
|
| 1220 |
+
"loss": 0.082,
|
| 1221 |
+
"step": 865
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 2.071513706793802,
|
| 1225 |
+
"grad_norm": 0.8575050830841064,
|
| 1226 |
+
"learning_rate": 7.2289213848762725e-06,
|
| 1227 |
+
"loss": 0.0901,
|
| 1228 |
+
"step": 870
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 2.0834326579261027,
|
| 1232 |
+
"grad_norm": 0.8716583847999573,
|
| 1233 |
+
"learning_rate": 7.061229370312643e-06,
|
| 1234 |
+
"loss": 0.0889,
|
| 1235 |
+
"step": 875
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 2.095351609058403,
|
| 1239 |
+
"grad_norm": 0.7830521464347839,
|
| 1240 |
+
"learning_rate": 6.894904450057234e-06,
|
| 1241 |
+
"loss": 0.087,
|
| 1242 |
+
"step": 880
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 2.1072705601907034,
|
| 1246 |
+
"grad_norm": 0.8635005354881287,
|
| 1247 |
+
"learning_rate": 6.729975266057559e-06,
|
| 1248 |
+
"loss": 0.099,
|
| 1249 |
+
"step": 885
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 2.1191895113230035,
|
| 1253 |
+
"grad_norm": 0.8649510145187378,
|
| 1254 |
+
"learning_rate": 6.56647021990869e-06,
|
| 1255 |
+
"loss": 0.0836,
|
| 1256 |
+
"step": 890
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 2.131108462455304,
|
| 1260 |
+
"grad_norm": 0.8170863389968872,
|
| 1261 |
+
"learning_rate": 6.404417467962322e-06,
|
| 1262 |
+
"loss": 0.0889,
|
| 1263 |
+
"step": 895
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 2.143027413587604,
|
| 1267 |
+
"grad_norm": 0.8242506980895996,
|
| 1268 |
+
"learning_rate": 6.243844916478156e-06,
|
| 1269 |
+
"loss": 0.0947,
|
| 1270 |
+
"step": 900
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 2.1549463647199048,
|
| 1274 |
+
"grad_norm": 0.6230686902999878,
|
| 1275 |
+
"learning_rate": 6.0847802168182635e-06,
|
| 1276 |
+
"loss": 0.082,
|
| 1277 |
+
"step": 905
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 2.166865315852205,
|
| 1281 |
+
"grad_norm": 0.8451269268989563,
|
| 1282 |
+
"learning_rate": 5.927250760685441e-06,
|
| 1283 |
+
"loss": 0.082,
|
| 1284 |
+
"step": 910
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 2.1787842669845054,
|
| 1288 |
+
"grad_norm": 0.9194000363349915,
|
| 1289 |
+
"learning_rate": 5.771283675406175e-06,
|
| 1290 |
+
"loss": 0.0846,
|
| 1291 |
+
"step": 915
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 2.1907032181168056,
|
| 1295 |
+
"grad_norm": 0.9058287143707275,
|
| 1296 |
+
"learning_rate": 5.616905819259226e-06,
|
| 1297 |
+
"loss": 0.0924,
|
| 1298 |
+
"step": 920
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 2.202622169249106,
|
| 1302 |
+
"grad_norm": 0.743598222732544,
|
| 1303 |
+
"learning_rate": 5.464143776850483e-06,
|
| 1304 |
+
"loss": 0.0823,
|
| 1305 |
+
"step": 925
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 2.2145411203814063,
|
| 1309 |
+
"grad_norm": 0.981116533279419,
|
| 1310 |
+
"learning_rate": 5.313023854534977e-06,
|
| 1311 |
+
"loss": 0.0806,
|
| 1312 |
+
"step": 930
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 2.226460071513707,
|
| 1316 |
+
"grad_norm": 0.8838233947753906,
|
| 1317 |
+
"learning_rate": 5.1635720758867965e-06,
|
| 1318 |
+
"loss": 0.0776,
|
| 1319 |
+
"step": 935
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 2.238379022646007,
|
| 1323 |
+
"grad_norm": 0.6472528576850891,
|
| 1324 |
+
"learning_rate": 5.0158141772177124e-06,
|
| 1325 |
+
"loss": 0.0664,
|
| 1326 |
+
"step": 940
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 2.2502979737783075,
|
| 1330 |
+
"grad_norm": 0.8629567623138428,
|
| 1331 |
+
"learning_rate": 4.869775603145234e-06,
|
| 1332 |
+
"loss": 0.0939,
|
| 1333 |
+
"step": 945
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 2.262216924910608,
|
| 1337 |
+
"grad_norm": 0.752636194229126,
|
| 1338 |
+
"learning_rate": 4.725481502210965e-06,
|
| 1339 |
+
"loss": 0.0786,
|
| 1340 |
+
"step": 950
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 2.2741358760429082,
|
| 1344 |
+
"grad_norm": 0.6699836850166321,
|
| 1345 |
+
"learning_rate": 4.5829567225498696e-06,
|
| 1346 |
+
"loss": 0.0888,
|
| 1347 |
+
"step": 955
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 2.2860548271752084,
|
| 1351 |
+
"grad_norm": 0.6923915147781372,
|
| 1352 |
+
"learning_rate": 4.44222580761133e-06,
|
| 1353 |
+
"loss": 0.0792,
|
| 1354 |
+
"step": 960
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 2.297973778307509,
|
| 1358 |
+
"grad_norm": 0.7279108166694641,
|
| 1359 |
+
"learning_rate": 4.303312991932619e-06,
|
| 1360 |
+
"loss": 0.0866,
|
| 1361 |
+
"step": 965
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 2.3098927294398095,
|
| 1365 |
+
"grad_norm": 0.7187250256538391,
|
| 1366 |
+
"learning_rate": 4.166242196965632e-06,
|
| 1367 |
+
"loss": 0.0893,
|
| 1368 |
+
"step": 970
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 2.3218116805721096,
|
| 1372 |
+
"grad_norm": 0.8220258355140686,
|
| 1373 |
+
"learning_rate": 4.031037026957463e-06,
|
| 1374 |
+
"loss": 0.0755,
|
| 1375 |
+
"step": 975
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 2.33373063170441,
|
| 1379 |
+
"grad_norm": 0.5365100502967834,
|
| 1380 |
+
"learning_rate": 3.897720764885668e-06,
|
| 1381 |
+
"loss": 0.0675,
|
| 1382 |
+
"step": 980
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 2.3456495828367103,
|
| 1386 |
+
"grad_norm": 0.9008510708808899,
|
| 1387 |
+
"learning_rate": 3.766316368448805e-06,
|
| 1388 |
+
"loss": 0.0769,
|
| 1389 |
+
"step": 985
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 2.357568533969011,
|
| 1393 |
+
"grad_norm": 0.7067334055900574,
|
| 1394 |
+
"learning_rate": 3.6368464661130283e-06,
|
| 1395 |
+
"loss": 0.0725,
|
| 1396 |
+
"step": 990
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 2.369487485101311,
|
| 1400 |
+
"grad_norm": 0.6769039630889893,
|
| 1401 |
+
"learning_rate": 3.5093333532153316e-06,
|
| 1402 |
+
"loss": 0.0751,
|
| 1403 |
+
"step": 995
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 2.3814064362336116,
|
| 1407 |
+
"grad_norm": 0.7547945976257324,
|
| 1408 |
+
"learning_rate": 3.3837989881242142e-06,
|
| 1409 |
+
"loss": 0.0703,
|
| 1410 |
+
"step": 1000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 2.3933253873659117,
|
| 1414 |
+
"grad_norm": 0.7641868591308594,
|
| 1415 |
+
"learning_rate": 3.260264988458317e-06,
|
| 1416 |
+
"loss": 0.0789,
|
| 1417 |
+
"step": 1005
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 2.4052443384982123,
|
| 1421 |
+
"grad_norm": 0.6552286148071289,
|
| 1422 |
+
"learning_rate": 3.1387526273637872e-06,
|
| 1423 |
+
"loss": 0.0651,
|
| 1424 |
+
"step": 1010
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 2.4171632896305124,
|
| 1428 |
+
"grad_norm": 0.8305537700653076,
|
| 1429 |
+
"learning_rate": 3.01928282985093e-06,
|
| 1430 |
+
"loss": 0.0843,
|
| 1431 |
+
"step": 1015
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 2.429082240762813,
|
| 1435 |
+
"grad_norm": 0.7220068573951721,
|
| 1436 |
+
"learning_rate": 2.9018761691908267e-06,
|
| 1437 |
+
"loss": 0.0644,
|
| 1438 |
+
"step": 1020
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 2.441001191895113,
|
| 1442 |
+
"grad_norm": 0.7012712359428406,
|
| 1443 |
+
"learning_rate": 2.786552863372504e-06,
|
| 1444 |
+
"loss": 0.0782,
|
| 1445 |
+
"step": 1025
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 2.4529201430274137,
|
| 1449 |
+
"grad_norm": 0.7012676000595093,
|
| 1450 |
+
"learning_rate": 2.673332771621324e-06,
|
| 1451 |
+
"loss": 0.0773,
|
| 1452 |
+
"step": 1030
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 2.464839094159714,
|
| 1456 |
+
"grad_norm": 0.678305983543396,
|
| 1457 |
+
"learning_rate": 2.562235390979106e-06,
|
| 1458 |
+
"loss": 0.0789,
|
| 1459 |
+
"step": 1035
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 2.4767580452920144,
|
| 1463 |
+
"grad_norm": 0.7134694457054138,
|
| 1464 |
+
"learning_rate": 2.453279852946668e-06,
|
| 1465 |
+
"loss": 0.0724,
|
| 1466 |
+
"step": 1040
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 2.4886769964243145,
|
| 1470 |
+
"grad_norm": 0.7144925594329834,
|
| 1471 |
+
"learning_rate": 2.3464849201892596e-06,
|
| 1472 |
+
"loss": 0.0778,
|
| 1473 |
+
"step": 1045
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 2.500595947556615,
|
| 1477 |
+
"grad_norm": 0.6859574913978577,
|
| 1478 |
+
"learning_rate": 2.2418689833055776e-06,
|
| 1479 |
+
"loss": 0.0763,
|
| 1480 |
+
"step": 1050
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 2.5125148986889156,
|
| 1484 |
+
"grad_norm": 0.7104150056838989,
|
| 1485 |
+
"learning_rate": 2.13945005766078e-06,
|
| 1486 |
+
"loss": 0.0651,
|
| 1487 |
+
"step": 1055
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 2.5244338498212158,
|
| 1491 |
+
"grad_norm": 0.7983992099761963,
|
| 1492 |
+
"learning_rate": 2.039245780284185e-06,
|
| 1493 |
+
"loss": 0.0724,
|
| 1494 |
+
"step": 1060
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 2.536352800953516,
|
| 1498 |
+
"grad_norm": 0.6972958445549011,
|
| 1499 |
+
"learning_rate": 1.9412734068320653e-06,
|
| 1500 |
+
"loss": 0.0792,
|
| 1501 |
+
"step": 1065
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 2.5482717520858165,
|
| 1505 |
+
"grad_norm": 0.7128235697746277,
|
| 1506 |
+
"learning_rate": 1.8455498086161665e-06,
|
| 1507 |
+
"loss": 0.0792,
|
| 1508 |
+
"step": 1070
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 2.560190703218117,
|
| 1512 |
+
"grad_norm": 0.7885940074920654,
|
| 1513 |
+
"learning_rate": 1.7520914696983558e-06,
|
| 1514 |
+
"loss": 0.0658,
|
| 1515 |
+
"step": 1075
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 2.572109654350417,
|
| 1519 |
+
"grad_norm": 0.6955039501190186,
|
| 1520 |
+
"learning_rate": 1.6609144840520208e-06,
|
| 1521 |
+
"loss": 0.0696,
|
| 1522 |
+
"step": 1080
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 2.5840286054827173,
|
| 1526 |
+
"grad_norm": 0.626193642616272,
|
| 1527 |
+
"learning_rate": 1.5720345527905872e-06,
|
| 1528 |
+
"loss": 0.0663,
|
| 1529 |
+
"step": 1085
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 2.595947556615018,
|
| 1533 |
+
"grad_norm": 0.5947815179824829,
|
| 1534 |
+
"learning_rate": 1.4854669814637145e-06,
|
| 1535 |
+
"loss": 0.0671,
|
| 1536 |
+
"step": 1090
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 2.6078665077473184,
|
| 1540 |
+
"grad_norm": 0.6333017349243164,
|
| 1541 |
+
"learning_rate": 1.4012266774216171e-06,
|
| 1542 |
+
"loss": 0.0647,
|
| 1543 |
+
"step": 1095
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 2.6197854588796186,
|
| 1547 |
+
"grad_norm": 0.6703285574913025,
|
| 1548 |
+
"learning_rate": 1.319328147247944e-06,
|
| 1549 |
+
"loss": 0.0647,
|
| 1550 |
+
"step": 1100
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 2.6317044100119187,
|
| 1554 |
+
"grad_norm": 0.7315057516098022,
|
| 1555 |
+
"learning_rate": 1.2397854942616632e-06,
|
| 1556 |
+
"loss": 0.0666,
|
| 1557 |
+
"step": 1105
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 2.6436233611442193,
|
| 1561 |
+
"grad_norm": 0.7039070129394531,
|
| 1562 |
+
"learning_rate": 1.1626124160884233e-06,
|
| 1563 |
+
"loss": 0.0711,
|
| 1564 |
+
"step": 1110
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 2.65554231227652,
|
| 1568 |
+
"grad_norm": 0.5952197909355164,
|
| 1569 |
+
"learning_rate": 1.0878222023017392e-06,
|
| 1570 |
+
"loss": 0.0709,
|
| 1571 |
+
"step": 1115
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 2.66746126340882,
|
| 1575 |
+
"grad_norm": 0.6911230683326721,
|
| 1576 |
+
"learning_rate": 1.015427732134473e-06,
|
| 1577 |
+
"loss": 0.0664,
|
| 1578 |
+
"step": 1120
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 2.6793802145411205,
|
| 1582 |
+
"grad_norm": 0.6301825642585754,
|
| 1583 |
+
"learning_rate": 9.454414722609655e-07,
|
| 1584 |
+
"loss": 0.0679,
|
| 1585 |
+
"step": 1125
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 2.6912991656734206,
|
| 1589 |
+
"grad_norm": 0.6624135971069336,
|
| 1590 |
+
"learning_rate": 8.778754746502182e-07,
|
| 1591 |
+
"loss": 0.0688,
|
| 1592 |
+
"step": 1130
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 2.703218116805721,
|
| 1596 |
+
"grad_norm": 0.8037999868392944,
|
| 1597 |
+
"learning_rate": 8.127413744904805e-07,
|
| 1598 |
+
"loss": 0.0743,
|
| 1599 |
+
"step": 1135
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 2.7151370679380213,
|
| 1603 |
+
"grad_norm": 0.6843491196632385,
|
| 1604 |
+
"learning_rate": 7.500503881856247e-07,
|
| 1605 |
+
"loss": 0.0662,
|
| 1606 |
+
"step": 1140
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 2.727056019070322,
|
| 1610 |
+
"grad_norm": 0.5409003496170044,
|
| 1611 |
+
"learning_rate": 6.898133114236111e-07,
|
| 1612 |
+
"loss": 0.0605,
|
| 1613 |
+
"step": 1145
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 2.738974970202622,
|
| 1617 |
+
"grad_norm": 0.69977205991745,
|
| 1618 |
+
"learning_rate": 6.320405173174398e-07,
|
| 1619 |
+
"loss": 0.0637,
|
| 1620 |
+
"step": 1150
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 2.7508939213349226,
|
| 1624 |
+
"grad_norm": 0.6292327046394348,
|
| 1625 |
+
"learning_rate": 5.767419546188319e-07,
|
| 1626 |
+
"loss": 0.0702,
|
| 1627 |
+
"step": 1155
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 2.7628128724672227,
|
| 1631 |
+
"grad_norm": 0.6625396609306335,
|
| 1632 |
+
"learning_rate": 5.239271460050188e-07,
|
| 1633 |
+
"loss": 0.0735,
|
| 1634 |
+
"step": 1160
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 2.7747318235995233,
|
| 1638 |
+
"grad_norm": 0.5859070420265198,
|
| 1639 |
+
"learning_rate": 4.7360518643889015e-07,
|
| 1640 |
+
"loss": 0.0529,
|
| 1641 |
+
"step": 1165
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 2.7866507747318234,
|
| 1645 |
+
"grad_norm": 0.634060800075531,
|
| 1646 |
+
"learning_rate": 4.257847416027927e-07,
|
| 1647 |
+
"loss": 0.0682,
|
| 1648 |
+
"step": 1170
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 2.798569725864124,
|
| 1652 |
+
"grad_norm": 0.5606221556663513,
|
| 1653 |
+
"learning_rate": 3.8047404640625895e-07,
|
| 1654 |
+
"loss": 0.0655,
|
| 1655 |
+
"step": 1175
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 2.8104886769964246,
|
| 1659 |
+
"grad_norm": 0.7701541781425476,
|
| 1660 |
+
"learning_rate": 3.376809035679218e-07,
|
| 1661 |
+
"loss": 0.0765,
|
| 1662 |
+
"step": 1180
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 2.8224076281287247,
|
| 1666 |
+
"grad_norm": 0.7097302675247192,
|
| 1667 |
+
"learning_rate": 2.974126822718426e-07,
|
| 1668 |
+
"loss": 0.0613,
|
| 1669 |
+
"step": 1185
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 2.834326579261025,
|
| 1673 |
+
"grad_norm": 0.6394138932228088,
|
| 1674 |
+
"learning_rate": 2.5967631689850945e-07,
|
| 1675 |
+
"loss": 0.0621,
|
| 1676 |
+
"step": 1190
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 2.8462455303933254,
|
| 1680 |
+
"grad_norm": 0.6242662072181702,
|
| 1681 |
+
"learning_rate": 2.244783058306943e-07,
|
| 1682 |
+
"loss": 0.0625,
|
| 1683 |
+
"step": 1195
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 2.858164481525626,
|
| 1687 |
+
"grad_norm": 0.6908314228057861,
|
| 1688 |
+
"learning_rate": 1.9182471033441284e-07,
|
| 1689 |
+
"loss": 0.0595,
|
| 1690 |
+
"step": 1200
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 2.870083432657926,
|
| 1694 |
+
"grad_norm": 0.5384330153465271,
|
| 1695 |
+
"learning_rate": 1.617211535151314e-07,
|
| 1696 |
+
"loss": 0.0615,
|
| 1697 |
+
"step": 1205
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 2.882002383790226,
|
| 1701 |
+
"grad_norm": 0.7861849069595337,
|
| 1702 |
+
"learning_rate": 1.3417281934945125e-07,
|
| 1703 |
+
"loss": 0.0589,
|
| 1704 |
+
"step": 1210
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 2.893921334922527,
|
| 1708 |
+
"grad_norm": 0.6752415895462036,
|
| 1709 |
+
"learning_rate": 1.0918445179239955e-07,
|
| 1710 |
+
"loss": 0.0554,
|
| 1711 |
+
"step": 1215
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 2.9058402860548274,
|
| 1715 |
+
"grad_norm": 0.8001394271850586,
|
| 1716 |
+
"learning_rate": 8.676035396049942e-08,
|
| 1717 |
+
"loss": 0.0747,
|
| 1718 |
+
"step": 1220
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 2.9177592371871275,
|
| 1722 |
+
"grad_norm": 0.5381464958190918,
|
| 1723 |
+
"learning_rate": 6.690438739074767e-08,
|
| 1724 |
+
"loss": 0.0613,
|
| 1725 |
+
"step": 1225
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 2.929678188319428,
|
| 1729 |
+
"grad_norm": 0.5774752497673035,
|
| 1730 |
+
"learning_rate": 4.9619971375645114e-08,
|
| 1731 |
+
"loss": 0.0594,
|
| 1732 |
+
"step": 1230
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 2.941597139451728,
|
| 1736 |
+
"grad_norm": 0.5088766813278198,
|
| 1737 |
+
"learning_rate": 3.491008237438087e-08,
|
| 1738 |
+
"loss": 0.0565,
|
| 1739 |
+
"step": 1235
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 2.9535160905840288,
|
| 1743 |
+
"grad_norm": 0.4922109842300415,
|
| 1744 |
+
"learning_rate": 2.2777253500257388e-08,
|
| 1745 |
+
"loss": 0.0723,
|
| 1746 |
+
"step": 1240
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 2.965435041716329,
|
| 1750 |
+
"grad_norm": 0.6942237615585327,
|
| 1751 |
+
"learning_rate": 1.3223574084492707e-08,
|
| 1752 |
+
"loss": 0.0693,
|
| 1753 |
+
"step": 1245
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 2.9773539928486294,
|
| 1757 |
+
"grad_norm": 0.6327122449874878,
|
| 1758 |
+
"learning_rate": 6.250689316419922e-09,
|
| 1759 |
+
"loss": 0.0658,
|
| 1760 |
+
"step": 1250
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 2.9892729439809296,
|
| 1764 |
+
"grad_norm": 0.5722461342811584,
|
| 1765 |
+
"learning_rate": 1.8597999601771554e-09,
|
| 1766 |
+
"loss": 0.06,
|
| 1767 |
+
"step": 1255
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 3.0,
|
| 1771 |
+
"grad_norm": 0.8972128629684448,
|
| 1772 |
+
"learning_rate": 5.166214793295154e-11,
|
| 1773 |
+
"loss": 0.0677,
|
| 1774 |
+
"step": 1260
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 3.0,
|
| 1778 |
+
"step": 1260,
|
| 1779 |
+
"total_flos": 1.6060508203804262e+18,
|
| 1780 |
+
"train_loss": 0.3766768909635998,
|
| 1781 |
+
"train_runtime": 786.8652,
|
| 1782 |
+
"train_samples_per_second": 51.161,
|
| 1783 |
+
"train_steps_per_second": 1.601
|
| 1784 |
+
}
|
| 1785 |
+
],
|
| 1786 |
+
"logging_steps": 5,
|
| 1787 |
+
"max_steps": 1260,
|
| 1788 |
+
"num_input_tokens_seen": 0,
|
| 1789 |
+
"num_train_epochs": 3,
|
| 1790 |
+
"save_steps": 20000,
|
| 1791 |
+
"stateful_callbacks": {
|
| 1792 |
+
"TrainerControl": {
|
| 1793 |
+
"args": {
|
| 1794 |
+
"should_epoch_stop": false,
|
| 1795 |
+
"should_evaluate": false,
|
| 1796 |
+
"should_log": false,
|
| 1797 |
+
"should_save": false,
|
| 1798 |
+
"should_training_stop": false
|
| 1799 |
+
},
|
| 1800 |
+
"attributes": {}
|
| 1801 |
+
}
|
| 1802 |
+
},
|
| 1803 |
+
"total_flos": 1.6060508203804262e+18,
|
| 1804 |
+
"train_batch_size": 2,
|
| 1805 |
+
"trial_name": null,
|
| 1806 |
+
"trial_params": null
|
| 1807 |
+
}
|
instruct/142_128_e3_3e-5/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b645553bdb7742ef830cf4e26896b11de9dc52448306d7d916dcd4597583899
|
| 3 |
+
size 8273
|
instruct/142_128_e3_3e-5/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|