Upload folder using huggingface_hub
Browse files- instruct/122_128_e3_3e-5/adapter_config.json +39 -0
- instruct/122_128_e3_3e-5/adapter_model.safetensors +3 -0
- instruct/122_128_e3_3e-5/added_tokens.json +9 -0
- instruct/122_128_e3_3e-5/all_results.json +9 -0
- instruct/122_128_e3_3e-5/chat_template.jinja +62 -0
- instruct/122_128_e3_3e-5/config.json +32 -0
- instruct/122_128_e3_3e-5/merges.txt +0 -0
- instruct/122_128_e3_3e-5/special_tokens_map.json +33 -0
- instruct/122_128_e3_3e-5/tokenizer.json +0 -0
- instruct/122_128_e3_3e-5/tokenizer_config.json +234 -0
- instruct/122_128_e3_3e-5/train_results.json +9 -0
- instruct/122_128_e3_3e-5/trainer_state.json +2507 -0
- instruct/122_128_e3_3e-5/training_args.bin +3 -0
- instruct/122_128_e3_3e-5/vocab.json +0 -0
instruct/122_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 |
+
"v_proj",
|
| 29 |
+
"q_proj",
|
| 30 |
+
"up_proj",
|
| 31 |
+
"k_proj",
|
| 32 |
+
"gate_proj",
|
| 33 |
+
"o_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
+
"use_dora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
instruct/122_128_e3_3e-5/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:590041793ce0cb3bb8d84bc6dfdc2ac52d075a0a0e57c4457eed6ccf1eaaf1bc
|
| 3 |
+
size 791751704
|
instruct/122_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/122_128_e3_3e-5/all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 2.1874027065392497e+18,
|
| 4 |
+
"train_loss": 0.3763406072520587,
|
| 5 |
+
"train_runtime": 1082.1068,
|
| 6 |
+
"train_samples": 18774,
|
| 7 |
+
"train_samples_per_second": 52.048,
|
| 8 |
+
"train_steps_per_second": 1.627
|
| 9 |
+
}
|
instruct/122_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/122_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/122_128_e3_3e-5/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
instruct/122_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/122_128_e3_3e-5/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
instruct/122_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/122_128_e3_3e-5/train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 2.1874027065392497e+18,
|
| 4 |
+
"train_loss": 0.3763406072520587,
|
| 5 |
+
"train_runtime": 1082.1068,
|
| 6 |
+
"train_samples": 18774,
|
| 7 |
+
"train_samples_per_second": 52.048,
|
| 8 |
+
"train_steps_per_second": 1.627
|
| 9 |
+
}
|
instruct/122_128_e3_3e-5/trainer_state.json
ADDED
|
@@ -0,0 +1,2507 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 1761,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.008517887563884156,
|
| 14 |
+
"grad_norm": 2.5716965198516846,
|
| 15 |
+
"learning_rate": 1.348314606741573e-06,
|
| 16 |
+
"loss": 1.6266,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.017035775127768313,
|
| 21 |
+
"grad_norm": 2.067826509475708,
|
| 22 |
+
"learning_rate": 3.033707865168539e-06,
|
| 23 |
+
"loss": 1.6501,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.02555366269165247,
|
| 28 |
+
"grad_norm": 1.3793977499008179,
|
| 29 |
+
"learning_rate": 4.719101123595506e-06,
|
| 30 |
+
"loss": 1.5666,
|
| 31 |
+
"step": 15
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.034071550255536626,
|
| 35 |
+
"grad_norm": 0.7923021912574768,
|
| 36 |
+
"learning_rate": 6.404494382022472e-06,
|
| 37 |
+
"loss": 1.5227,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.04258943781942078,
|
| 42 |
+
"grad_norm": 0.5614107847213745,
|
| 43 |
+
"learning_rate": 8.089887640449438e-06,
|
| 44 |
+
"loss": 1.4989,
|
| 45 |
+
"step": 25
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.05110732538330494,
|
| 49 |
+
"grad_norm": 0.4602738916873932,
|
| 50 |
+
"learning_rate": 9.775280898876405e-06,
|
| 51 |
+
"loss": 1.4666,
|
| 52 |
+
"step": 30
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.059625212947189095,
|
| 56 |
+
"grad_norm": 1.9673638343811035,
|
| 57 |
+
"learning_rate": 1.146067415730337e-05,
|
| 58 |
+
"loss": 1.4752,
|
| 59 |
+
"step": 35
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.06814310051107325,
|
| 63 |
+
"grad_norm": 0.4384709596633911,
|
| 64 |
+
"learning_rate": 1.3146067415730338e-05,
|
| 65 |
+
"loss": 1.4352,
|
| 66 |
+
"step": 40
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.07666098807495741,
|
| 70 |
+
"grad_norm": 0.4366346597671509,
|
| 71 |
+
"learning_rate": 1.4831460674157303e-05,
|
| 72 |
+
"loss": 1.4782,
|
| 73 |
+
"step": 45
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.08517887563884156,
|
| 77 |
+
"grad_norm": 0.38269561529159546,
|
| 78 |
+
"learning_rate": 1.651685393258427e-05,
|
| 79 |
+
"loss": 1.378,
|
| 80 |
+
"step": 50
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.09369676320272573,
|
| 84 |
+
"grad_norm": 0.41208064556121826,
|
| 85 |
+
"learning_rate": 1.8202247191011237e-05,
|
| 86 |
+
"loss": 1.3733,
|
| 87 |
+
"step": 55
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.10221465076660988,
|
| 91 |
+
"grad_norm": 0.43251052498817444,
|
| 92 |
+
"learning_rate": 1.98876404494382e-05,
|
| 93 |
+
"loss": 1.3889,
|
| 94 |
+
"step": 60
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.11073253833049404,
|
| 98 |
+
"grad_norm": 0.4335126578807831,
|
| 99 |
+
"learning_rate": 2.1573033707865168e-05,
|
| 100 |
+
"loss": 1.3934,
|
| 101 |
+
"step": 65
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.11925042589437819,
|
| 105 |
+
"grad_norm": 0.41279542446136475,
|
| 106 |
+
"learning_rate": 2.3258426966292135e-05,
|
| 107 |
+
"loss": 1.3515,
|
| 108 |
+
"step": 70
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.12776831345826234,
|
| 112 |
+
"grad_norm": 0.44880396127700806,
|
| 113 |
+
"learning_rate": 2.4943820224719103e-05,
|
| 114 |
+
"loss": 1.3285,
|
| 115 |
+
"step": 75
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.1362862010221465,
|
| 119 |
+
"grad_norm": 0.5295153260231018,
|
| 120 |
+
"learning_rate": 2.6629213483146066e-05,
|
| 121 |
+
"loss": 1.3686,
|
| 122 |
+
"step": 80
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.14480408858603067,
|
| 126 |
+
"grad_norm": 0.4765026867389679,
|
| 127 |
+
"learning_rate": 2.8314606741573034e-05,
|
| 128 |
+
"loss": 1.3386,
|
| 129 |
+
"step": 85
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.15332197614991483,
|
| 133 |
+
"grad_norm": 0.47458839416503906,
|
| 134 |
+
"learning_rate": 3e-05,
|
| 135 |
+
"loss": 1.3094,
|
| 136 |
+
"step": 90
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.16183986371379896,
|
| 140 |
+
"grad_norm": 0.5297031402587891,
|
| 141 |
+
"learning_rate": 2.9999338049862092e-05,
|
| 142 |
+
"loss": 1.2885,
|
| 143 |
+
"step": 95
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.17035775127768313,
|
| 147 |
+
"grad_norm": 0.5081350207328796,
|
| 148 |
+
"learning_rate": 2.9997352257872093e-05,
|
| 149 |
+
"loss": 1.2637,
|
| 150 |
+
"step": 100
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.1788756388415673,
|
| 154 |
+
"grad_norm": 0.5122872591018677,
|
| 155 |
+
"learning_rate": 2.999404279929604e-05,
|
| 156 |
+
"loss": 1.211,
|
| 157 |
+
"step": 105
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.18739352640545145,
|
| 161 |
+
"grad_norm": 0.5396663546562195,
|
| 162 |
+
"learning_rate": 2.998940996622681e-05,
|
| 163 |
+
"loss": 1.2455,
|
| 164 |
+
"step": 110
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.19591141396933562,
|
| 168 |
+
"grad_norm": 0.5753917098045349,
|
| 169 |
+
"learning_rate": 2.9983454167558336e-05,
|
| 170 |
+
"loss": 1.2128,
|
| 171 |
+
"step": 115
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.20442930153321975,
|
| 175 |
+
"grad_norm": 0.6351743340492249,
|
| 176 |
+
"learning_rate": 2.9976175928949518e-05,
|
| 177 |
+
"loss": 1.2659,
|
| 178 |
+
"step": 120
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.21294718909710392,
|
| 182 |
+
"grad_norm": 0.5563240647315979,
|
| 183 |
+
"learning_rate": 2.9967575892777828e-05,
|
| 184 |
+
"loss": 1.1233,
|
| 185 |
+
"step": 125
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.22146507666098808,
|
| 189 |
+
"grad_norm": 0.6018843054771423,
|
| 190 |
+
"learning_rate": 2.9957654818082615e-05,
|
| 191 |
+
"loss": 1.1588,
|
| 192 |
+
"step": 130
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.22998296422487224,
|
| 196 |
+
"grad_norm": 0.6488460898399353,
|
| 197 |
+
"learning_rate": 2.9946413580498117e-05,
|
| 198 |
+
"loss": 1.1039,
|
| 199 |
+
"step": 135
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.23850085178875638,
|
| 203 |
+
"grad_norm": 0.6414260268211365,
|
| 204 |
+
"learning_rate": 2.993385317217617e-05,
|
| 205 |
+
"loss": 1.1149,
|
| 206 |
+
"step": 140
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.24701873935264054,
|
| 210 |
+
"grad_norm": 0.6578723788261414,
|
| 211 |
+
"learning_rate": 2.9919974701698638e-05,
|
| 212 |
+
"loss": 1.1449,
|
| 213 |
+
"step": 145
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.2555366269165247,
|
| 217 |
+
"grad_norm": 0.6642760634422302,
|
| 218 |
+
"learning_rate": 2.990477939397959e-05,
|
| 219 |
+
"loss": 1.1263,
|
| 220 |
+
"step": 150
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.26405451448040884,
|
| 224 |
+
"grad_norm": 0.7432608604431152,
|
| 225 |
+
"learning_rate": 2.9888268590157154e-05,
|
| 226 |
+
"loss": 1.1365,
|
| 227 |
+
"step": 155
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.272572402044293,
|
| 231 |
+
"grad_norm": 0.7459192872047424,
|
| 232 |
+
"learning_rate": 2.987044374747519e-05,
|
| 233 |
+
"loss": 1.0926,
|
| 234 |
+
"step": 160
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.28109028960817717,
|
| 238 |
+
"grad_norm": 0.7195029854774475,
|
| 239 |
+
"learning_rate": 2.9851306439154636e-05,
|
| 240 |
+
"loss": 1.0152,
|
| 241 |
+
"step": 165
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.28960817717206133,
|
| 245 |
+
"grad_norm": 0.7255988121032715,
|
| 246 |
+
"learning_rate": 2.9830858354254672e-05,
|
| 247 |
+
"loss": 1.0374,
|
| 248 |
+
"step": 170
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.2981260647359455,
|
| 252 |
+
"grad_norm": 0.8572341799736023,
|
| 253 |
+
"learning_rate": 2.980910129752365e-05,
|
| 254 |
+
"loss": 1.084,
|
| 255 |
+
"step": 175
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.30664395229982966,
|
| 259 |
+
"grad_norm": 0.816211998462677,
|
| 260 |
+
"learning_rate": 2.97860371892398e-05,
|
| 261 |
+
"loss": 1.0212,
|
| 262 |
+
"step": 180
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.3151618398637138,
|
| 266 |
+
"grad_norm": 0.7273570895195007,
|
| 267 |
+
"learning_rate": 2.976166806504174e-05,
|
| 268 |
+
"loss": 0.9874,
|
| 269 |
+
"step": 185
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.32367972742759793,
|
| 273 |
+
"grad_norm": 0.8952082395553589,
|
| 274 |
+
"learning_rate": 2.9735996075748825e-05,
|
| 275 |
+
"loss": 1.0065,
|
| 276 |
+
"step": 190
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.3321976149914821,
|
| 280 |
+
"grad_norm": 0.9264750480651855,
|
| 281 |
+
"learning_rate": 2.9709023487171294e-05,
|
| 282 |
+
"loss": 1.0485,
|
| 283 |
+
"step": 195
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.34071550255536626,
|
| 287 |
+
"grad_norm": 0.8489630222320557,
|
| 288 |
+
"learning_rate": 2.968075267991032e-05,
|
| 289 |
+
"loss": 0.9244,
|
| 290 |
+
"step": 200
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.3492333901192504,
|
| 294 |
+
"grad_norm": 0.9751719236373901,
|
| 295 |
+
"learning_rate": 2.9651186149147862e-05,
|
| 296 |
+
"loss": 0.9519,
|
| 297 |
+
"step": 205
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.3577512776831346,
|
| 301 |
+
"grad_norm": 0.9077705144882202,
|
| 302 |
+
"learning_rate": 2.9620326504426476e-05,
|
| 303 |
+
"loss": 0.9786,
|
| 304 |
+
"step": 210
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.36626916524701875,
|
| 308 |
+
"grad_norm": 0.83640456199646,
|
| 309 |
+
"learning_rate": 2.9588176469418968e-05,
|
| 310 |
+
"loss": 0.9166,
|
| 311 |
+
"step": 215
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.3747870528109029,
|
| 315 |
+
"grad_norm": 0.9151703119277954,
|
| 316 |
+
"learning_rate": 2.955473888168802e-05,
|
| 317 |
+
"loss": 0.94,
|
| 318 |
+
"step": 220
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.3833049403747871,
|
| 322 |
+
"grad_norm": 0.864013135433197,
|
| 323 |
+
"learning_rate": 2.9520016692435745e-05,
|
| 324 |
+
"loss": 0.8711,
|
| 325 |
+
"step": 225
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.39182282793867124,
|
| 329 |
+
"grad_norm": 0.9450227618217468,
|
| 330 |
+
"learning_rate": 2.9484012966243196e-05,
|
| 331 |
+
"loss": 0.8764,
|
| 332 |
+
"step": 230
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.40034071550255534,
|
| 336 |
+
"grad_norm": 0.9630789160728455,
|
| 337 |
+
"learning_rate": 2.9446730880799918e-05,
|
| 338 |
+
"loss": 0.8813,
|
| 339 |
+
"step": 235
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.4088586030664395,
|
| 343 |
+
"grad_norm": 0.928720235824585,
|
| 344 |
+
"learning_rate": 2.9408173726623453e-05,
|
| 345 |
+
"loss": 0.8965,
|
| 346 |
+
"step": 240
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.41737649063032367,
|
| 350 |
+
"grad_norm": 1.0673857927322388,
|
| 351 |
+
"learning_rate": 2.9368344906768935e-05,
|
| 352 |
+
"loss": 0.8654,
|
| 353 |
+
"step": 245
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.42589437819420783,
|
| 357 |
+
"grad_norm": 0.942517101764679,
|
| 358 |
+
"learning_rate": 2.9327247936528742e-05,
|
| 359 |
+
"loss": 0.8513,
|
| 360 |
+
"step": 250
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.434412265758092,
|
| 364 |
+
"grad_norm": 1.0638647079467773,
|
| 365 |
+
"learning_rate": 2.928488644312222e-05,
|
| 366 |
+
"loss": 0.7952,
|
| 367 |
+
"step": 255
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.44293015332197616,
|
| 371 |
+
"grad_norm": 0.9732940793037415,
|
| 372 |
+
"learning_rate": 2.9241264165375555e-05,
|
| 373 |
+
"loss": 0.8494,
|
| 374 |
+
"step": 260
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.4514480408858603,
|
| 378 |
+
"grad_norm": 1.1443026065826416,
|
| 379 |
+
"learning_rate": 2.9196384953391785e-05,
|
| 380 |
+
"loss": 0.8343,
|
| 381 |
+
"step": 265
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.4599659284497445,
|
| 385 |
+
"grad_norm": 0.995349109172821,
|
| 386 |
+
"learning_rate": 2.9150252768210988e-05,
|
| 387 |
+
"loss": 0.8069,
|
| 388 |
+
"step": 270
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.4684838160136286,
|
| 392 |
+
"grad_norm": 0.9946545958518982,
|
| 393 |
+
"learning_rate": 2.9102871681460672e-05,
|
| 394 |
+
"loss": 0.8171,
|
| 395 |
+
"step": 275
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.47700170357751276,
|
| 399 |
+
"grad_norm": 1.086196780204773,
|
| 400 |
+
"learning_rate": 2.905424587499643e-05,
|
| 401 |
+
"loss": 0.8015,
|
| 402 |
+
"step": 280
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.4855195911413969,
|
| 406 |
+
"grad_norm": 1.0003418922424316,
|
| 407 |
+
"learning_rate": 2.9004379640532822e-05,
|
| 408 |
+
"loss": 0.7678,
|
| 409 |
+
"step": 285
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.4940374787052811,
|
| 413 |
+
"grad_norm": 1.0537084341049194,
|
| 414 |
+
"learning_rate": 2.8953277379264633e-05,
|
| 415 |
+
"loss": 0.7088,
|
| 416 |
+
"step": 290
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.5025553662691652,
|
| 420 |
+
"grad_norm": 1.0518896579742432,
|
| 421 |
+
"learning_rate": 2.8900943601478374e-05,
|
| 422 |
+
"loss": 0.7828,
|
| 423 |
+
"step": 295
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.5110732538330494,
|
| 427 |
+
"grad_norm": 1.1696645021438599,
|
| 428 |
+
"learning_rate": 2.884738292615424e-05,
|
| 429 |
+
"loss": 0.754,
|
| 430 |
+
"step": 300
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.5195911413969335,
|
| 434 |
+
"grad_norm": 0.9354255199432373,
|
| 435 |
+
"learning_rate": 2.8792600080558416e-05,
|
| 436 |
+
"loss": 0.7213,
|
| 437 |
+
"step": 305
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.5281090289608177,
|
| 441 |
+
"grad_norm": 0.9859469532966614,
|
| 442 |
+
"learning_rate": 2.873659989982586e-05,
|
| 443 |
+
"loss": 0.7927,
|
| 444 |
+
"step": 310
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.5366269165247018,
|
| 448 |
+
"grad_norm": 1.1230337619781494,
|
| 449 |
+
"learning_rate": 2.867938732653356e-05,
|
| 450 |
+
"loss": 0.7591,
|
| 451 |
+
"step": 315
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.545144804088586,
|
| 455 |
+
"grad_norm": 1.0584527254104614,
|
| 456 |
+
"learning_rate": 2.8620967410264283e-05,
|
| 457 |
+
"loss": 0.698,
|
| 458 |
+
"step": 320
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.5536626916524702,
|
| 462 |
+
"grad_norm": 1.1889570951461792,
|
| 463 |
+
"learning_rate": 2.856134530716091e-05,
|
| 464 |
+
"loss": 0.7146,
|
| 465 |
+
"step": 325
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.5621805792163543,
|
| 469 |
+
"grad_norm": 1.2046887874603271,
|
| 470 |
+
"learning_rate": 2.8500526279471362e-05,
|
| 471 |
+
"loss": 0.6747,
|
| 472 |
+
"step": 330
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.5706984667802385,
|
| 476 |
+
"grad_norm": 1.1777886152267456,
|
| 477 |
+
"learning_rate": 2.843851569508414e-05,
|
| 478 |
+
"loss": 0.7156,
|
| 479 |
+
"step": 335
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.5792163543441227,
|
| 483 |
+
"grad_norm": 1.1542694568634033,
|
| 484 |
+
"learning_rate": 2.837531902705456e-05,
|
| 485 |
+
"loss": 0.7352,
|
| 486 |
+
"step": 340
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.5877342419080068,
|
| 490 |
+
"grad_norm": 1.3923040628433228,
|
| 491 |
+
"learning_rate": 2.8310941853121707e-05,
|
| 492 |
+
"loss": 0.7221,
|
| 493 |
+
"step": 345
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.596252129471891,
|
| 497 |
+
"grad_norm": 1.110425591468811,
|
| 498 |
+
"learning_rate": 2.8245389855216138e-05,
|
| 499 |
+
"loss": 0.7382,
|
| 500 |
+
"step": 350
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.6047700170357752,
|
| 504 |
+
"grad_norm": 1.224516749382019,
|
| 505 |
+
"learning_rate": 2.817866881895839e-05,
|
| 506 |
+
"loss": 0.6995,
|
| 507 |
+
"step": 355
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.6132879045996593,
|
| 511 |
+
"grad_norm": 1.3371371030807495,
|
| 512 |
+
"learning_rate": 2.811078463314835e-05,
|
| 513 |
+
"loss": 0.6471,
|
| 514 |
+
"step": 360
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.6218057921635435,
|
| 518 |
+
"grad_norm": 1.164310097694397,
|
| 519 |
+
"learning_rate": 2.8041743289245503e-05,
|
| 520 |
+
"loss": 0.6075,
|
| 521 |
+
"step": 365
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.6303236797274276,
|
| 525 |
+
"grad_norm": 1.2550768852233887,
|
| 526 |
+
"learning_rate": 2.7971550880840138e-05,
|
| 527 |
+
"loss": 0.5859,
|
| 528 |
+
"step": 370
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.6388415672913118,
|
| 532 |
+
"grad_norm": 1.1263628005981445,
|
| 533 |
+
"learning_rate": 2.790021360311551e-05,
|
| 534 |
+
"loss": 0.6236,
|
| 535 |
+
"step": 375
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.6473594548551959,
|
| 539 |
+
"grad_norm": 1.1764050722122192,
|
| 540 |
+
"learning_rate": 2.7827737752301056e-05,
|
| 541 |
+
"loss": 0.6422,
|
| 542 |
+
"step": 380
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.65587734241908,
|
| 546 |
+
"grad_norm": 1.2301489114761353,
|
| 547 |
+
"learning_rate": 2.7754129725116715e-05,
|
| 548 |
+
"loss": 0.5974,
|
| 549 |
+
"step": 385
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.6643952299829642,
|
| 553 |
+
"grad_norm": 1.197425365447998,
|
| 554 |
+
"learning_rate": 2.7679396018208302e-05,
|
| 555 |
+
"loss": 0.5994,
|
| 556 |
+
"step": 390
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.6729131175468483,
|
| 560 |
+
"grad_norm": 1.1501034498214722,
|
| 561 |
+
"learning_rate": 2.760354322757418e-05,
|
| 562 |
+
"loss": 0.6343,
|
| 563 |
+
"step": 395
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.6814310051107325,
|
| 567 |
+
"grad_norm": 1.3084397315979004,
|
| 568 |
+
"learning_rate": 2.7526578047983032e-05,
|
| 569 |
+
"loss": 0.6478,
|
| 570 |
+
"step": 400
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.6899488926746167,
|
| 574 |
+
"grad_norm": 1.1720685958862305,
|
| 575 |
+
"learning_rate": 2.7448507272383033e-05,
|
| 576 |
+
"loss": 0.57,
|
| 577 |
+
"step": 405
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.6984667802385008,
|
| 581 |
+
"grad_norm": 1.1148557662963867,
|
| 582 |
+
"learning_rate": 2.7369337791302272e-05,
|
| 583 |
+
"loss": 0.5782,
|
| 584 |
+
"step": 410
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.706984667802385,
|
| 588 |
+
"grad_norm": 1.18994140625,
|
| 589 |
+
"learning_rate": 2.7289076592240602e-05,
|
| 590 |
+
"loss": 0.5649,
|
| 591 |
+
"step": 415
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.7155025553662692,
|
| 595 |
+
"grad_norm": 1.3601725101470947,
|
| 596 |
+
"learning_rate": 2.7207730759052925e-05,
|
| 597 |
+
"loss": 0.5736,
|
| 598 |
+
"step": 420
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.7240204429301533,
|
| 602 |
+
"grad_norm": 1.1529043912887573,
|
| 603 |
+
"learning_rate": 2.712530747132398e-05,
|
| 604 |
+
"loss": 0.5636,
|
| 605 |
+
"step": 425
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.7325383304940375,
|
| 609 |
+
"grad_norm": 1.1896905899047852,
|
| 610 |
+
"learning_rate": 2.7041814003734654e-05,
|
| 611 |
+
"loss": 0.5281,
|
| 612 |
+
"step": 430
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.7410562180579217,
|
| 616 |
+
"grad_norm": 1.222347378730774,
|
| 617 |
+
"learning_rate": 2.6957257725419934e-05,
|
| 618 |
+
"loss": 0.5214,
|
| 619 |
+
"step": 435
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.7495741056218058,
|
| 623 |
+
"grad_norm": 1.1348633766174316,
|
| 624 |
+
"learning_rate": 2.6871646099318497e-05,
|
| 625 |
+
"loss": 0.5504,
|
| 626 |
+
"step": 440
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.75809199318569,
|
| 630 |
+
"grad_norm": 1.2366816997528076,
|
| 631 |
+
"learning_rate": 2.678498668151404e-05,
|
| 632 |
+
"loss": 0.5136,
|
| 633 |
+
"step": 445
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.7666098807495741,
|
| 637 |
+
"grad_norm": 1.1904083490371704,
|
| 638 |
+
"learning_rate": 2.6697287120568364e-05,
|
| 639 |
+
"loss": 0.5324,
|
| 640 |
+
"step": 450
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.7751277683134583,
|
| 644 |
+
"grad_norm": 1.2197129726409912,
|
| 645 |
+
"learning_rate": 2.6608555156846343e-05,
|
| 646 |
+
"loss": 0.5192,
|
| 647 |
+
"step": 455
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.7836456558773425,
|
| 651 |
+
"grad_norm": 1.3645553588867188,
|
| 652 |
+
"learning_rate": 2.6518798621832716e-05,
|
| 653 |
+
"loss": 0.5412,
|
| 654 |
+
"step": 460
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.7921635434412265,
|
| 658 |
+
"grad_norm": 1.1919114589691162,
|
| 659 |
+
"learning_rate": 2.6428025437440923e-05,
|
| 660 |
+
"loss": 0.4974,
|
| 661 |
+
"step": 465
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.8006814310051107,
|
| 665 |
+
"grad_norm": 1.244622826576233,
|
| 666 |
+
"learning_rate": 2.6336243615313876e-05,
|
| 667 |
+
"loss": 0.4904,
|
| 668 |
+
"step": 470
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.8091993185689949,
|
| 672 |
+
"grad_norm": 1.2408119440078735,
|
| 673 |
+
"learning_rate": 2.6243461256116892e-05,
|
| 674 |
+
"loss": 0.5103,
|
| 675 |
+
"step": 475
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.817717206132879,
|
| 679 |
+
"grad_norm": 1.499105453491211,
|
| 680 |
+
"learning_rate": 2.61496865488227e-05,
|
| 681 |
+
"loss": 0.5079,
|
| 682 |
+
"step": 480
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.8262350936967632,
|
| 686 |
+
"grad_norm": 1.3035911321640015,
|
| 687 |
+
"learning_rate": 2.6054927769988684e-05,
|
| 688 |
+
"loss": 0.4738,
|
| 689 |
+
"step": 485
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.8347529812606473,
|
| 693 |
+
"grad_norm": 1.5184330940246582,
|
| 694 |
+
"learning_rate": 2.595919328302641e-05,
|
| 695 |
+
"loss": 0.5343,
|
| 696 |
+
"step": 490
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.8432708688245315,
|
| 700 |
+
"grad_norm": 1.3481537103652954,
|
| 701 |
+
"learning_rate": 2.5862491537463463e-05,
|
| 702 |
+
"loss": 0.4876,
|
| 703 |
+
"step": 495
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.8517887563884157,
|
| 707 |
+
"grad_norm": 1.4336282014846802,
|
| 708 |
+
"learning_rate": 2.5764831068197674e-05,
|
| 709 |
+
"loss": 0.4184,
|
| 710 |
+
"step": 500
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.8603066439522998,
|
| 714 |
+
"grad_norm": 1.2017250061035156,
|
| 715 |
+
"learning_rate": 2.5666220494743867e-05,
|
| 716 |
+
"loss": 0.4596,
|
| 717 |
+
"step": 505
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.868824531516184,
|
| 721 |
+
"grad_norm": 1.247363567352295,
|
| 722 |
+
"learning_rate": 2.5566668520473058e-05,
|
| 723 |
+
"loss": 0.4765,
|
| 724 |
+
"step": 510
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.8773424190800682,
|
| 728 |
+
"grad_norm": 1.3750962018966675,
|
| 729 |
+
"learning_rate": 2.5466183931844337e-05,
|
| 730 |
+
"loss": 0.4974,
|
| 731 |
+
"step": 515
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.8858603066439523,
|
| 735 |
+
"grad_norm": 1.361673355102539,
|
| 736 |
+
"learning_rate": 2.5364775597629334e-05,
|
| 737 |
+
"loss": 0.4865,
|
| 738 |
+
"step": 520
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.8943781942078365,
|
| 742 |
+
"grad_norm": 1.2031968832015991,
|
| 743 |
+
"learning_rate": 2.5262452468129495e-05,
|
| 744 |
+
"loss": 0.4738,
|
| 745 |
+
"step": 525
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.9028960817717206,
|
| 749 |
+
"grad_norm": 1.2770336866378784,
|
| 750 |
+
"learning_rate": 2.5159223574386117e-05,
|
| 751 |
+
"loss": 0.4644,
|
| 752 |
+
"step": 530
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.9114139693356048,
|
| 756 |
+
"grad_norm": 1.3006300926208496,
|
| 757 |
+
"learning_rate": 2.505509802738325e-05,
|
| 758 |
+
"loss": 0.4539,
|
| 759 |
+
"step": 535
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.919931856899489,
|
| 763 |
+
"grad_norm": 1.2540030479431152,
|
| 764 |
+
"learning_rate": 2.4950085017243598e-05,
|
| 765 |
+
"loss": 0.4378,
|
| 766 |
+
"step": 540
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.9284497444633731,
|
| 770 |
+
"grad_norm": 1.3631476163864136,
|
| 771 |
+
"learning_rate": 2.484419381241736e-05,
|
| 772 |
+
"loss": 0.4199,
|
| 773 |
+
"step": 545
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.9369676320272572,
|
| 777 |
+
"grad_norm": 1.1703877449035645,
|
| 778 |
+
"learning_rate": 2.4737433758864226e-05,
|
| 779 |
+
"loss": 0.4057,
|
| 780 |
+
"step": 550
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.9454855195911414,
|
| 784 |
+
"grad_norm": 1.308478593826294,
|
| 785 |
+
"learning_rate": 2.4629814279228474e-05,
|
| 786 |
+
"loss": 0.4343,
|
| 787 |
+
"step": 555
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.9540034071550255,
|
| 791 |
+
"grad_norm": 1.2152435779571533,
|
| 792 |
+
"learning_rate": 2.452134487200737e-05,
|
| 793 |
+
"loss": 0.4317,
|
| 794 |
+
"step": 560
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.9625212947189097,
|
| 798 |
+
"grad_norm": 1.2530341148376465,
|
| 799 |
+
"learning_rate": 2.441203511071278e-05,
|
| 800 |
+
"loss": 0.4096,
|
| 801 |
+
"step": 565
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.9710391822827938,
|
| 805 |
+
"grad_norm": 1.1599371433258057,
|
| 806 |
+
"learning_rate": 2.430189464302625e-05,
|
| 807 |
+
"loss": 0.4103,
|
| 808 |
+
"step": 570
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.979557069846678,
|
| 812 |
+
"grad_norm": 1.1663986444473267,
|
| 813 |
+
"learning_rate": 2.4190933189947483e-05,
|
| 814 |
+
"loss": 0.4135,
|
| 815 |
+
"step": 575
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.9880749574105622,
|
| 819 |
+
"grad_norm": 1.3156894445419312,
|
| 820 |
+
"learning_rate": 2.4079160544936372e-05,
|
| 821 |
+
"loss": 0.4311,
|
| 822 |
+
"step": 580
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.9965928449744463,
|
| 826 |
+
"grad_norm": 1.1847128868103027,
|
| 827 |
+
"learning_rate": 2.396658657304861e-05,
|
| 828 |
+
"loss": 0.3886,
|
| 829 |
+
"step": 585
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.0051107325383304,
|
| 833 |
+
"grad_norm": 1.202667474746704,
|
| 834 |
+
"learning_rate": 2.385322121006504e-05,
|
| 835 |
+
"loss": 0.3208,
|
| 836 |
+
"step": 590
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.0136286201022147,
|
| 840 |
+
"grad_norm": 1.5622453689575195,
|
| 841 |
+
"learning_rate": 2.373907446161467e-05,
|
| 842 |
+
"loss": 0.329,
|
| 843 |
+
"step": 595
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.0221465076660987,
|
| 847 |
+
"grad_norm": 1.4166574478149414,
|
| 848 |
+
"learning_rate": 2.3624156402291627e-05,
|
| 849 |
+
"loss": 0.3125,
|
| 850 |
+
"step": 600
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.030664395229983,
|
| 854 |
+
"grad_norm": 1.160851001739502,
|
| 855 |
+
"learning_rate": 2.3508477174765937e-05,
|
| 856 |
+
"loss": 0.333,
|
| 857 |
+
"step": 605
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.039182282793867,
|
| 861 |
+
"grad_norm": 1.4737623929977417,
|
| 862 |
+
"learning_rate": 2.3392046988888345e-05,
|
| 863 |
+
"loss": 0.3013,
|
| 864 |
+
"step": 610
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.0477001703577513,
|
| 868 |
+
"grad_norm": 1.235217809677124,
|
| 869 |
+
"learning_rate": 2.32748761207892e-05,
|
| 870 |
+
"loss": 0.3152,
|
| 871 |
+
"step": 615
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.0562180579216354,
|
| 875 |
+
"grad_norm": 1.286151647567749,
|
| 876 |
+
"learning_rate": 2.315697491197148e-05,
|
| 877 |
+
"loss": 0.2973,
|
| 878 |
+
"step": 620
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.0647359454855196,
|
| 882 |
+
"grad_norm": 1.0681358575820923,
|
| 883 |
+
"learning_rate": 2.3038353768398035e-05,
|
| 884 |
+
"loss": 0.3014,
|
| 885 |
+
"step": 625
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.0732538330494037,
|
| 889 |
+
"grad_norm": 1.111215591430664,
|
| 890 |
+
"learning_rate": 2.291902315957318e-05,
|
| 891 |
+
"loss": 0.3249,
|
| 892 |
+
"step": 630
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 1.081771720613288,
|
| 896 |
+
"grad_norm": 1.1295338869094849,
|
| 897 |
+
"learning_rate": 2.2798993617618648e-05,
|
| 898 |
+
"loss": 0.3272,
|
| 899 |
+
"step": 635
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 1.090289608177172,
|
| 903 |
+
"grad_norm": 1.3621184825897217,
|
| 904 |
+
"learning_rate": 2.2678275736344014e-05,
|
| 905 |
+
"loss": 0.3252,
|
| 906 |
+
"step": 640
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.0988074957410563,
|
| 910 |
+
"grad_norm": 1.0505887269973755,
|
| 911 |
+
"learning_rate": 2.2556880170311705e-05,
|
| 912 |
+
"loss": 0.3058,
|
| 913 |
+
"step": 645
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.1073253833049403,
|
| 917 |
+
"grad_norm": 1.3699302673339844,
|
| 918 |
+
"learning_rate": 2.243481763389661e-05,
|
| 919 |
+
"loss": 0.2829,
|
| 920 |
+
"step": 650
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.1158432708688246,
|
| 924 |
+
"grad_norm": 1.297153115272522,
|
| 925 |
+
"learning_rate": 2.2312098900340428e-05,
|
| 926 |
+
"loss": 0.2982,
|
| 927 |
+
"step": 655
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.1243611584327087,
|
| 931 |
+
"grad_norm": 1.2881468534469604,
|
| 932 |
+
"learning_rate": 2.2188734800800855e-05,
|
| 933 |
+
"loss": 0.3097,
|
| 934 |
+
"step": 660
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.1328790459965927,
|
| 938 |
+
"grad_norm": 1.150026798248291,
|
| 939 |
+
"learning_rate": 2.206473622339557e-05,
|
| 940 |
+
"loss": 0.2931,
|
| 941 |
+
"step": 665
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.141396933560477,
|
| 945 |
+
"grad_norm": 1.172498345375061,
|
| 946 |
+
"learning_rate": 2.194011411224131e-05,
|
| 947 |
+
"loss": 0.3111,
|
| 948 |
+
"step": 670
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 1.1499148211243613,
|
| 952 |
+
"grad_norm": 1.2184269428253174,
|
| 953 |
+
"learning_rate": 2.1814879466487877e-05,
|
| 954 |
+
"loss": 0.3387,
|
| 955 |
+
"step": 675
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.1584327086882453,
|
| 959 |
+
"grad_norm": 1.4021327495574951,
|
| 960 |
+
"learning_rate": 2.1689043339347426e-05,
|
| 961 |
+
"loss": 0.2959,
|
| 962 |
+
"step": 680
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.1669505962521294,
|
| 966 |
+
"grad_norm": 1.077187418937683,
|
| 967 |
+
"learning_rate": 2.1562616837118843e-05,
|
| 968 |
+
"loss": 0.2831,
|
| 969 |
+
"step": 685
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.1754684838160137,
|
| 973 |
+
"grad_norm": 1.226365566253662,
|
| 974 |
+
"learning_rate": 2.1435611118207546e-05,
|
| 975 |
+
"loss": 0.3204,
|
| 976 |
+
"step": 690
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.1839863713798977,
|
| 980 |
+
"grad_norm": 1.1422818899154663,
|
| 981 |
+
"learning_rate": 2.1308037392140613e-05,
|
| 982 |
+
"loss": 0.3058,
|
| 983 |
+
"step": 695
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.192504258943782,
|
| 987 |
+
"grad_norm": 1.2097809314727783,
|
| 988 |
+
"learning_rate": 2.1179906918577463e-05,
|
| 989 |
+
"loss": 0.2878,
|
| 990 |
+
"step": 700
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.201022146507666,
|
| 994 |
+
"grad_norm": 1.4937372207641602,
|
| 995 |
+
"learning_rate": 2.1051231006316037e-05,
|
| 996 |
+
"loss": 0.2657,
|
| 997 |
+
"step": 705
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 1.2095400340715503,
|
| 1001 |
+
"grad_norm": 1.1077746152877808,
|
| 1002 |
+
"learning_rate": 2.092202101229473e-05,
|
| 1003 |
+
"loss": 0.2667,
|
| 1004 |
+
"step": 710
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.2180579216354344,
|
| 1008 |
+
"grad_norm": 1.5927270650863647,
|
| 1009 |
+
"learning_rate": 2.0792288340589974e-05,
|
| 1010 |
+
"loss": 0.2647,
|
| 1011 |
+
"step": 715
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 1.2265758091993186,
|
| 1015 |
+
"grad_norm": 1.5449562072753906,
|
| 1016 |
+
"learning_rate": 2.0662044441409774e-05,
|
| 1017 |
+
"loss": 0.283,
|
| 1018 |
+
"step": 720
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.2350936967632027,
|
| 1022 |
+
"grad_norm": 1.19553804397583,
|
| 1023 |
+
"learning_rate": 2.053130081008306e-05,
|
| 1024 |
+
"loss": 0.2423,
|
| 1025 |
+
"step": 725
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 1.243611584327087,
|
| 1029 |
+
"grad_norm": 1.327296495437622,
|
| 1030 |
+
"learning_rate": 2.0400068986045142e-05,
|
| 1031 |
+
"loss": 0.2493,
|
| 1032 |
+
"step": 730
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 1.252129471890971,
|
| 1036 |
+
"grad_norm": 1.0173994302749634,
|
| 1037 |
+
"learning_rate": 2.026836055181922e-05,
|
| 1038 |
+
"loss": 0.2375,
|
| 1039 |
+
"step": 735
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 1.2606473594548553,
|
| 1043 |
+
"grad_norm": 1.0237390995025635,
|
| 1044 |
+
"learning_rate": 2.0136187131994113e-05,
|
| 1045 |
+
"loss": 0.25,
|
| 1046 |
+
"step": 740
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.2691652470187393,
|
| 1050 |
+
"grad_norm": 1.4696601629257202,
|
| 1051 |
+
"learning_rate": 2.0003560392198294e-05,
|
| 1052 |
+
"loss": 0.2606,
|
| 1053 |
+
"step": 745
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 1.2776831345826234,
|
| 1057 |
+
"grad_norm": 1.1605949401855469,
|
| 1058 |
+
"learning_rate": 1.9870492038070255e-05,
|
| 1059 |
+
"loss": 0.2315,
|
| 1060 |
+
"step": 750
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 1.2862010221465077,
|
| 1064 |
+
"grad_norm": 1.0390037298202515,
|
| 1065 |
+
"learning_rate": 1.9736993814225374e-05,
|
| 1066 |
+
"loss": 0.2364,
|
| 1067 |
+
"step": 755
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 1.294718909710392,
|
| 1071 |
+
"grad_norm": 1.2867923974990845,
|
| 1072 |
+
"learning_rate": 1.960307750321935e-05,
|
| 1073 |
+
"loss": 0.2437,
|
| 1074 |
+
"step": 760
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.303236797274276,
|
| 1078 |
+
"grad_norm": 1.2633079290390015,
|
| 1079 |
+
"learning_rate": 1.946875492450825e-05,
|
| 1080 |
+
"loss": 0.2778,
|
| 1081 |
+
"step": 765
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 1.31175468483816,
|
| 1085 |
+
"grad_norm": 1.2951111793518066,
|
| 1086 |
+
"learning_rate": 1.9334037933405337e-05,
|
| 1087 |
+
"loss": 0.2534,
|
| 1088 |
+
"step": 770
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 1.3202725724020443,
|
| 1092 |
+
"grad_norm": 1.274283766746521,
|
| 1093 |
+
"learning_rate": 1.9198938420034732e-05,
|
| 1094 |
+
"loss": 0.2633,
|
| 1095 |
+
"step": 775
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 1.3287904599659284,
|
| 1099 |
+
"grad_norm": 1.2139161825180054,
|
| 1100 |
+
"learning_rate": 1.9063468308281958e-05,
|
| 1101 |
+
"loss": 0.2682,
|
| 1102 |
+
"step": 780
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 1.3373083475298126,
|
| 1106 |
+
"grad_norm": 1.1931724548339844,
|
| 1107 |
+
"learning_rate": 1.892763955474158e-05,
|
| 1108 |
+
"loss": 0.2207,
|
| 1109 |
+
"step": 785
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 1.3458262350936967,
|
| 1113 |
+
"grad_norm": 1.2369731664657593,
|
| 1114 |
+
"learning_rate": 1.8791464147661878e-05,
|
| 1115 |
+
"loss": 0.2259,
|
| 1116 |
+
"step": 790
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 1.354344122657581,
|
| 1120 |
+
"grad_norm": 1.1618366241455078,
|
| 1121 |
+
"learning_rate": 1.8654954105886787e-05,
|
| 1122 |
+
"loss": 0.2015,
|
| 1123 |
+
"step": 795
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 1.362862010221465,
|
| 1127 |
+
"grad_norm": 1.3816810846328735,
|
| 1128 |
+
"learning_rate": 1.8518121477795103e-05,
|
| 1129 |
+
"loss": 0.2623,
|
| 1130 |
+
"step": 800
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 1.3713798977853493,
|
| 1134 |
+
"grad_norm": 1.2025938034057617,
|
| 1135 |
+
"learning_rate": 1.8380978340237094e-05,
|
| 1136 |
+
"loss": 0.2279,
|
| 1137 |
+
"step": 805
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 1.3798977853492334,
|
| 1141 |
+
"grad_norm": 1.1096776723861694,
|
| 1142 |
+
"learning_rate": 1.824353679746861e-05,
|
| 1143 |
+
"loss": 0.2324,
|
| 1144 |
+
"step": 810
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 1.3884156729131176,
|
| 1148 |
+
"grad_norm": 1.2480747699737549,
|
| 1149 |
+
"learning_rate": 1.810580898008274e-05,
|
| 1150 |
+
"loss": 0.27,
|
| 1151 |
+
"step": 815
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.3969335604770017,
|
| 1155 |
+
"grad_norm": 1.2055765390396118,
|
| 1156 |
+
"learning_rate": 1.7967807043939177e-05,
|
| 1157 |
+
"loss": 0.2309,
|
| 1158 |
+
"step": 820
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 1.405451448040886,
|
| 1162 |
+
"grad_norm": 1.372480869293213,
|
| 1163 |
+
"learning_rate": 1.782954316909134e-05,
|
| 1164 |
+
"loss": 0.2273,
|
| 1165 |
+
"step": 825
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 1.41396933560477,
|
| 1169 |
+
"grad_norm": 1.2389492988586426,
|
| 1170 |
+
"learning_rate": 1.7691029558711375e-05,
|
| 1171 |
+
"loss": 0.2132,
|
| 1172 |
+
"step": 830
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 1.422487223168654,
|
| 1176 |
+
"grad_norm": 1.1238925457000732,
|
| 1177 |
+
"learning_rate": 1.7552278438013068e-05,
|
| 1178 |
+
"loss": 0.2146,
|
| 1179 |
+
"step": 835
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 1.4310051107325383,
|
| 1183 |
+
"grad_norm": 1.5139601230621338,
|
| 1184 |
+
"learning_rate": 1.7413302053172897e-05,
|
| 1185 |
+
"loss": 0.2125,
|
| 1186 |
+
"step": 840
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 1.4395229982964226,
|
| 1190 |
+
"grad_norm": 1.0129921436309814,
|
| 1191 |
+
"learning_rate": 1.7274112670249135e-05,
|
| 1192 |
+
"loss": 0.2513,
|
| 1193 |
+
"step": 845
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 1.4480408858603067,
|
| 1197 |
+
"grad_norm": 1.4059174060821533,
|
| 1198 |
+
"learning_rate": 1.713472257409928e-05,
|
| 1199 |
+
"loss": 0.2104,
|
| 1200 |
+
"step": 850
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 1.4565587734241907,
|
| 1204 |
+
"grad_norm": 1.568130612373352,
|
| 1205 |
+
"learning_rate": 1.699514406729578e-05,
|
| 1206 |
+
"loss": 0.2045,
|
| 1207 |
+
"step": 855
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 1.465076660988075,
|
| 1211 |
+
"grad_norm": 1.2132091522216797,
|
| 1212 |
+
"learning_rate": 1.6855389469040217e-05,
|
| 1213 |
+
"loss": 0.2005,
|
| 1214 |
+
"step": 860
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 1.473594548551959,
|
| 1218 |
+
"grad_norm": 1.153464913368225,
|
| 1219 |
+
"learning_rate": 1.6715471114075995e-05,
|
| 1220 |
+
"loss": 0.2058,
|
| 1221 |
+
"step": 865
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 1.4821124361158433,
|
| 1225 |
+
"grad_norm": 1.1657319068908691,
|
| 1226 |
+
"learning_rate": 1.6575401351599707e-05,
|
| 1227 |
+
"loss": 0.2048,
|
| 1228 |
+
"step": 870
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 1.4906303236797274,
|
| 1232 |
+
"grad_norm": 1.1234029531478882,
|
| 1233 |
+
"learning_rate": 1.643519254417115e-05,
|
| 1234 |
+
"loss": 0.2023,
|
| 1235 |
+
"step": 875
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 1.4991482112436116,
|
| 1239 |
+
"grad_norm": 1.013460397720337,
|
| 1240 |
+
"learning_rate": 1.6294857066622263e-05,
|
| 1241 |
+
"loss": 0.1784,
|
| 1242 |
+
"step": 880
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 1.5076660988074957,
|
| 1246 |
+
"grad_norm": 1.248849868774414,
|
| 1247 |
+
"learning_rate": 1.615440730496486e-05,
|
| 1248 |
+
"loss": 0.1835,
|
| 1249 |
+
"step": 885
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 1.51618398637138,
|
| 1253 |
+
"grad_norm": 1.3258328437805176,
|
| 1254 |
+
"learning_rate": 1.6013855655297498e-05,
|
| 1255 |
+
"loss": 0.1874,
|
| 1256 |
+
"step": 890
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 1.524701873935264,
|
| 1260 |
+
"grad_norm": 1.1744338274002075,
|
| 1261 |
+
"learning_rate": 1.587321452271135e-05,
|
| 1262 |
+
"loss": 0.1901,
|
| 1263 |
+
"step": 895
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 1.533219761499148,
|
| 1267 |
+
"grad_norm": 1.1411858797073364,
|
| 1268 |
+
"learning_rate": 1.5732496320195376e-05,
|
| 1269 |
+
"loss": 0.1865,
|
| 1270 |
+
"step": 900
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 1.5417376490630323,
|
| 1274 |
+
"grad_norm": 1.1237488985061646,
|
| 1275 |
+
"learning_rate": 1.5591713467540714e-05,
|
| 1276 |
+
"loss": 0.2037,
|
| 1277 |
+
"step": 905
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 1.5502555366269166,
|
| 1281 |
+
"grad_norm": 1.3481311798095703,
|
| 1282 |
+
"learning_rate": 1.5450878390244523e-05,
|
| 1283 |
+
"loss": 0.1887,
|
| 1284 |
+
"step": 910
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 1.5587734241908007,
|
| 1288 |
+
"grad_norm": 1.194317102432251,
|
| 1289 |
+
"learning_rate": 1.5310003518413318e-05,
|
| 1290 |
+
"loss": 0.1843,
|
| 1291 |
+
"step": 915
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 1.5672913117546847,
|
| 1295 |
+
"grad_norm": 1.321331262588501,
|
| 1296 |
+
"learning_rate": 1.5169101285665876e-05,
|
| 1297 |
+
"loss": 0.2035,
|
| 1298 |
+
"step": 920
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 1.575809199318569,
|
| 1302 |
+
"grad_norm": 1.1920100450515747,
|
| 1303 |
+
"learning_rate": 1.5028184128035856e-05,
|
| 1304 |
+
"loss": 0.1687,
|
| 1305 |
+
"step": 925
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 1.5843270868824533,
|
| 1309 |
+
"grad_norm": 1.3775837421417236,
|
| 1310 |
+
"learning_rate": 1.4887264482874173e-05,
|
| 1311 |
+
"loss": 0.1828,
|
| 1312 |
+
"step": 930
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 1.5928449744463373,
|
| 1316 |
+
"grad_norm": 1.2679349184036255,
|
| 1317 |
+
"learning_rate": 1.4746354787751304e-05,
|
| 1318 |
+
"loss": 0.1687,
|
| 1319 |
+
"step": 935
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 1.6013628620102214,
|
| 1323 |
+
"grad_norm": 1.063085675239563,
|
| 1324 |
+
"learning_rate": 1.4605467479359539e-05,
|
| 1325 |
+
"loss": 0.1662,
|
| 1326 |
+
"step": 940
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 1.6098807495741057,
|
| 1330 |
+
"grad_norm": 1.0780327320098877,
|
| 1331 |
+
"learning_rate": 1.4464614992415294e-05,
|
| 1332 |
+
"loss": 0.1559,
|
| 1333 |
+
"step": 945
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 1.61839863713799,
|
| 1337 |
+
"grad_norm": 1.0649099349975586,
|
| 1338 |
+
"learning_rate": 1.4323809758561665e-05,
|
| 1339 |
+
"loss": 0.1742,
|
| 1340 |
+
"step": 950
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 1.626916524701874,
|
| 1344 |
+
"grad_norm": 1.2298070192337036,
|
| 1345 |
+
"learning_rate": 1.4183064205271177e-05,
|
| 1346 |
+
"loss": 0.1791,
|
| 1347 |
+
"step": 955
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 1.635434412265758,
|
| 1351 |
+
"grad_norm": 1.206802487373352,
|
| 1352 |
+
"learning_rate": 1.4042390754748959e-05,
|
| 1353 |
+
"loss": 0.179,
|
| 1354 |
+
"step": 960
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 1.643952299829642,
|
| 1358 |
+
"grad_norm": 1.3613325357437134,
|
| 1359 |
+
"learning_rate": 1.3901801822836332e-05,
|
| 1360 |
+
"loss": 0.1812,
|
| 1361 |
+
"step": 965
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 1.6524701873935264,
|
| 1365 |
+
"grad_norm": 1.1871285438537598,
|
| 1366 |
+
"learning_rate": 1.3761309817915017e-05,
|
| 1367 |
+
"loss": 0.1636,
|
| 1368 |
+
"step": 970
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 1.6609880749574106,
|
| 1372 |
+
"grad_norm": 1.1290268898010254,
|
| 1373 |
+
"learning_rate": 1.362092713981195e-05,
|
| 1374 |
+
"loss": 0.1509,
|
| 1375 |
+
"step": 975
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 1.6695059625212947,
|
| 1379 |
+
"grad_norm": 1.176270842552185,
|
| 1380 |
+
"learning_rate": 1.3480666178704878e-05,
|
| 1381 |
+
"loss": 0.1765,
|
| 1382 |
+
"step": 980
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 1.6780238500851787,
|
| 1386 |
+
"grad_norm": 1.0180604457855225,
|
| 1387 |
+
"learning_rate": 1.3340539314028812e-05,
|
| 1388 |
+
"loss": 0.1597,
|
| 1389 |
+
"step": 985
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 1.686541737649063,
|
| 1393 |
+
"grad_norm": 1.0694501399993896,
|
| 1394 |
+
"learning_rate": 1.3200558913383407e-05,
|
| 1395 |
+
"loss": 0.1512,
|
| 1396 |
+
"step": 990
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 1.6950596252129473,
|
| 1400 |
+
"grad_norm": 1.1029022932052612,
|
| 1401 |
+
"learning_rate": 1.3060737331441397e-05,
|
| 1402 |
+
"loss": 0.1632,
|
| 1403 |
+
"step": 995
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 1.7035775127768313,
|
| 1407 |
+
"grad_norm": 0.9396603107452393,
|
| 1408 |
+
"learning_rate": 1.2921086908858166e-05,
|
| 1409 |
+
"loss": 0.1645,
|
| 1410 |
+
"step": 1000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 1.7120954003407154,
|
| 1414 |
+
"grad_norm": 1.2016267776489258,
|
| 1415 |
+
"learning_rate": 1.278161997118259e-05,
|
| 1416 |
+
"loss": 0.1508,
|
| 1417 |
+
"step": 1005
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 1.7206132879045997,
|
| 1421 |
+
"grad_norm": 1.1595627069473267,
|
| 1422 |
+
"learning_rate": 1.2642348827769152e-05,
|
| 1423 |
+
"loss": 0.1685,
|
| 1424 |
+
"step": 1010
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 1.729131175468484,
|
| 1428 |
+
"grad_norm": 1.232333779335022,
|
| 1429 |
+
"learning_rate": 1.2503285770691525e-05,
|
| 1430 |
+
"loss": 0.1521,
|
| 1431 |
+
"step": 1015
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 1.737649063032368,
|
| 1435 |
+
"grad_norm": 1.2201088666915894,
|
| 1436 |
+
"learning_rate": 1.2364443073657683e-05,
|
| 1437 |
+
"loss": 0.1554,
|
| 1438 |
+
"step": 1020
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 1.746166950596252,
|
| 1442 |
+
"grad_norm": 0.9584128260612488,
|
| 1443 |
+
"learning_rate": 1.2225832990926625e-05,
|
| 1444 |
+
"loss": 0.13,
|
| 1445 |
+
"step": 1025
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 1.7546848381601363,
|
| 1449 |
+
"grad_norm": 0.9535162448883057,
|
| 1450 |
+
"learning_rate": 1.2087467756226803e-05,
|
| 1451 |
+
"loss": 0.1585,
|
| 1452 |
+
"step": 1030
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 1.7632027257240206,
|
| 1456 |
+
"grad_norm": 1.0932948589324951,
|
| 1457 |
+
"learning_rate": 1.194935958167637e-05,
|
| 1458 |
+
"loss": 0.1536,
|
| 1459 |
+
"step": 1035
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 1.7717206132879046,
|
| 1463 |
+
"grad_norm": 1.0091915130615234,
|
| 1464 |
+
"learning_rate": 1.181152065670535e-05,
|
| 1465 |
+
"loss": 0.1659,
|
| 1466 |
+
"step": 1040
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 1.7802385008517887,
|
| 1470 |
+
"grad_norm": 1.1463590860366821,
|
| 1471 |
+
"learning_rate": 1.16739631469798e-05,
|
| 1472 |
+
"loss": 0.1516,
|
| 1473 |
+
"step": 1045
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 1.7887563884156727,
|
| 1477 |
+
"grad_norm": 1.1547257900238037,
|
| 1478 |
+
"learning_rate": 1.1536699193328063e-05,
|
| 1479 |
+
"loss": 0.1521,
|
| 1480 |
+
"step": 1050
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 1.797274275979557,
|
| 1484 |
+
"grad_norm": 0.9791980385780334,
|
| 1485 |
+
"learning_rate": 1.1399740910669204e-05,
|
| 1486 |
+
"loss": 0.1273,
|
| 1487 |
+
"step": 1055
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 1.8057921635434413,
|
| 1491 |
+
"grad_norm": 1.335015892982483,
|
| 1492 |
+
"learning_rate": 1.1263100386943768e-05,
|
| 1493 |
+
"loss": 0.1366,
|
| 1494 |
+
"step": 1060
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 1.8143100511073254,
|
| 1498 |
+
"grad_norm": 0.9781949520111084,
|
| 1499 |
+
"learning_rate": 1.1126789682046894e-05,
|
| 1500 |
+
"loss": 0.1458,
|
| 1501 |
+
"step": 1065
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 1.8228279386712094,
|
| 1505 |
+
"grad_norm": 1.001914143562317,
|
| 1506 |
+
"learning_rate": 1.0990820826763907e-05,
|
| 1507 |
+
"loss": 0.1347,
|
| 1508 |
+
"step": 1070
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 1.8313458262350937,
|
| 1512 |
+
"grad_norm": 1.1571121215820312,
|
| 1513 |
+
"learning_rate": 1.085520582170847e-05,
|
| 1514 |
+
"loss": 0.1431,
|
| 1515 |
+
"step": 1075
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 1.839863713798978,
|
| 1519 |
+
"grad_norm": 1.0157941579818726,
|
| 1520 |
+
"learning_rate": 1.0719956636263424e-05,
|
| 1521 |
+
"loss": 0.1168,
|
| 1522 |
+
"step": 1080
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 1.848381601362862,
|
| 1526 |
+
"grad_norm": 1.1341521739959717,
|
| 1527 |
+
"learning_rate": 1.0585085207524356e-05,
|
| 1528 |
+
"loss": 0.1342,
|
| 1529 |
+
"step": 1085
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 1.856899488926746,
|
| 1533 |
+
"grad_norm": 1.3904448747634888,
|
| 1534 |
+
"learning_rate": 1.0450603439246063e-05,
|
| 1535 |
+
"loss": 0.1476,
|
| 1536 |
+
"step": 1090
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 1.8654173764906303,
|
| 1540 |
+
"grad_norm": 0.9600460529327393,
|
| 1541 |
+
"learning_rate": 1.0316523200791874e-05,
|
| 1542 |
+
"loss": 0.1477,
|
| 1543 |
+
"step": 1095
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 1.8739352640545146,
|
| 1547 |
+
"grad_norm": 0.8376882672309875,
|
| 1548 |
+
"learning_rate": 1.0182856326086102e-05,
|
| 1549 |
+
"loss": 0.118,
|
| 1550 |
+
"step": 1100
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 1.8824531516183987,
|
| 1554 |
+
"grad_norm": 1.1173150539398193,
|
| 1555 |
+
"learning_rate": 1.0049614612569565e-05,
|
| 1556 |
+
"loss": 0.126,
|
| 1557 |
+
"step": 1105
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 1.8909710391822827,
|
| 1561 |
+
"grad_norm": 1.0346934795379639,
|
| 1562 |
+
"learning_rate": 9.916809820158356e-06,
|
| 1563 |
+
"loss": 0.1281,
|
| 1564 |
+
"step": 1110
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 1.899488926746167,
|
| 1568 |
+
"grad_norm": 1.1980435848236084,
|
| 1569 |
+
"learning_rate": 9.784453670205887e-06,
|
| 1570 |
+
"loss": 0.1379,
|
| 1571 |
+
"step": 1115
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 1.9080068143100513,
|
| 1575 |
+
"grad_norm": 0.6915777921676636,
|
| 1576 |
+
"learning_rate": 9.652557844468388e-06,
|
| 1577 |
+
"loss": 0.12,
|
| 1578 |
+
"step": 1120
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 1.9165247018739353,
|
| 1582 |
+
"grad_norm": 1.1642189025878906,
|
| 1583 |
+
"learning_rate": 9.521133984073865e-06,
|
| 1584 |
+
"loss": 0.1236,
|
| 1585 |
+
"step": 1125
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 1.9250425894378194,
|
| 1589 |
+
"grad_norm": 1.0226366519927979,
|
| 1590 |
+
"learning_rate": 9.390193688494657e-06,
|
| 1591 |
+
"loss": 0.1221,
|
| 1592 |
+
"step": 1130
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 1.9335604770017034,
|
| 1596 |
+
"grad_norm": 0.9829905033111572,
|
| 1597 |
+
"learning_rate": 9.259748514523654e-06,
|
| 1598 |
+
"loss": 0.1195,
|
| 1599 |
+
"step": 1135
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 1.9420783645655877,
|
| 1603 |
+
"grad_norm": 1.1167612075805664,
|
| 1604 |
+
"learning_rate": 9.129809975254311e-06,
|
| 1605 |
+
"loss": 0.1306,
|
| 1606 |
+
"step": 1140
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 1.950596252129472,
|
| 1610 |
+
"grad_norm": 0.9897305369377136,
|
| 1611 |
+
"learning_rate": 9.000389539064496e-06,
|
| 1612 |
+
"loss": 0.12,
|
| 1613 |
+
"step": 1145
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 1.959114139693356,
|
| 1617 |
+
"grad_norm": 0.8389292359352112,
|
| 1618 |
+
"learning_rate": 8.87149862860428e-06,
|
| 1619 |
+
"loss": 0.1028,
|
| 1620 |
+
"step": 1150
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 1.96763202725724,
|
| 1624 |
+
"grad_norm": 1.0902999639511108,
|
| 1625 |
+
"learning_rate": 8.743148619787796e-06,
|
| 1626 |
+
"loss": 0.1047,
|
| 1627 |
+
"step": 1155
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 1.9761499148211243,
|
| 1631 |
+
"grad_norm": 1.032793402671814,
|
| 1632 |
+
"learning_rate": 8.615350840789182e-06,
|
| 1633 |
+
"loss": 0.1226,
|
| 1634 |
+
"step": 1160
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 1.9846678023850086,
|
| 1638 |
+
"grad_norm": 1.1826974153518677,
|
| 1639 |
+
"learning_rate": 8.48811657104276e-06,
|
| 1640 |
+
"loss": 0.1268,
|
| 1641 |
+
"step": 1165
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 1.9931856899488927,
|
| 1645 |
+
"grad_norm": 0.8397160172462463,
|
| 1646 |
+
"learning_rate": 8.361457040247518e-06,
|
| 1647 |
+
"loss": 0.1079,
|
| 1648 |
+
"step": 1170
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 2.0017035775127767,
|
| 1652 |
+
"grad_norm": 0.7468289136886597,
|
| 1653 |
+
"learning_rate": 8.235383427375975e-06,
|
| 1654 |
+
"loss": 0.1015,
|
| 1655 |
+
"step": 1175
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 2.0102214650766608,
|
| 1659 |
+
"grad_norm": 0.9834156632423401,
|
| 1660 |
+
"learning_rate": 8.10990685968752e-06,
|
| 1661 |
+
"loss": 0.097,
|
| 1662 |
+
"step": 1180
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 2.0187393526405453,
|
| 1666 |
+
"grad_norm": 0.9269552230834961,
|
| 1667 |
+
"learning_rate": 7.985038411746324e-06,
|
| 1668 |
+
"loss": 0.09,
|
| 1669 |
+
"step": 1185
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 2.0272572402044293,
|
| 1673 |
+
"grad_norm": 0.713595449924469,
|
| 1674 |
+
"learning_rate": 7.860789104443897e-06,
|
| 1675 |
+
"loss": 0.0917,
|
| 1676 |
+
"step": 1190
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 2.0357751277683134,
|
| 1680 |
+
"grad_norm": 1.085956335067749,
|
| 1681 |
+
"learning_rate": 7.737169904026389e-06,
|
| 1682 |
+
"loss": 0.1032,
|
| 1683 |
+
"step": 1195
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 2.0442930153321974,
|
| 1687 |
+
"grad_norm": 0.8596060872077942,
|
| 1688 |
+
"learning_rate": 7.614191721126702e-06,
|
| 1689 |
+
"loss": 0.1014,
|
| 1690 |
+
"step": 1200
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 2.052810902896082,
|
| 1694 |
+
"grad_norm": 0.8330885171890259,
|
| 1695 |
+
"learning_rate": 7.491865409801518e-06,
|
| 1696 |
+
"loss": 0.0892,
|
| 1697 |
+
"step": 1205
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 2.061328790459966,
|
| 1701 |
+
"grad_norm": 0.7561232447624207,
|
| 1702 |
+
"learning_rate": 7.370201766573325e-06,
|
| 1703 |
+
"loss": 0.0839,
|
| 1704 |
+
"step": 1210
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 2.06984667802385,
|
| 1708 |
+
"grad_norm": 0.9073164463043213,
|
| 1709 |
+
"learning_rate": 7.249211529477512e-06,
|
| 1710 |
+
"loss": 0.1027,
|
| 1711 |
+
"step": 1215
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 2.078364565587734,
|
| 1715 |
+
"grad_norm": 0.9696881175041199,
|
| 1716 |
+
"learning_rate": 7.128905377114629e-06,
|
| 1717 |
+
"loss": 0.0874,
|
| 1718 |
+
"step": 1220
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 2.0868824531516186,
|
| 1722 |
+
"grad_norm": 0.9521986246109009,
|
| 1723 |
+
"learning_rate": 7.0092939277078956e-06,
|
| 1724 |
+
"loss": 0.086,
|
| 1725 |
+
"step": 1225
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 2.0954003407155026,
|
| 1729 |
+
"grad_norm": 0.8560494184494019,
|
| 1730 |
+
"learning_rate": 6.890387738166042e-06,
|
| 1731 |
+
"loss": 0.0937,
|
| 1732 |
+
"step": 1230
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 2.1039182282793867,
|
| 1736 |
+
"grad_norm": 0.9920060634613037,
|
| 1737 |
+
"learning_rate": 6.772197303151526e-06,
|
| 1738 |
+
"loss": 0.0933,
|
| 1739 |
+
"step": 1235
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 2.1124361158432707,
|
| 1743 |
+
"grad_norm": 0.8045631051063538,
|
| 1744 |
+
"learning_rate": 6.6547330541543335e-06,
|
| 1745 |
+
"loss": 0.0922,
|
| 1746 |
+
"step": 1240
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 2.1209540034071552,
|
| 1750 |
+
"grad_norm": 0.8037899732589722,
|
| 1751 |
+
"learning_rate": 6.538005358571235e-06,
|
| 1752 |
+
"loss": 0.0898,
|
| 1753 |
+
"step": 1245
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 2.1294718909710393,
|
| 1757 |
+
"grad_norm": 0.8837285041809082,
|
| 1758 |
+
"learning_rate": 6.4220245187907915e-06,
|
| 1759 |
+
"loss": 0.0801,
|
| 1760 |
+
"step": 1250
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 2.1379897785349233,
|
| 1764 |
+
"grad_norm": 0.7099907398223877,
|
| 1765 |
+
"learning_rate": 6.306800771284044e-06,
|
| 1766 |
+
"loss": 0.0907,
|
| 1767 |
+
"step": 1255
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 2.1465076660988074,
|
| 1771 |
+
"grad_norm": 0.7926245927810669,
|
| 1772 |
+
"learning_rate": 6.192344285701078e-06,
|
| 1773 |
+
"loss": 0.0854,
|
| 1774 |
+
"step": 1260
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 2.155025553662692,
|
| 1778 |
+
"grad_norm": 0.8906794786453247,
|
| 1779 |
+
"learning_rate": 6.078665163973412e-06,
|
| 1780 |
+
"loss": 0.0741,
|
| 1781 |
+
"step": 1265
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 2.163543441226576,
|
| 1785 |
+
"grad_norm": 0.6445258855819702,
|
| 1786 |
+
"learning_rate": 5.965773439422424e-06,
|
| 1787 |
+
"loss": 0.08,
|
| 1788 |
+
"step": 1270
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 2.17206132879046,
|
| 1792 |
+
"grad_norm": 0.759277880191803,
|
| 1793 |
+
"learning_rate": 5.853679075873785e-06,
|
| 1794 |
+
"loss": 0.0843,
|
| 1795 |
+
"step": 1275
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 2.180579216354344,
|
| 1799 |
+
"grad_norm": 1.0248292684555054,
|
| 1800 |
+
"learning_rate": 5.742391966778096e-06,
|
| 1801 |
+
"loss": 0.0925,
|
| 1802 |
+
"step": 1280
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 2.189097103918228,
|
| 1806 |
+
"grad_norm": 0.7602913975715637,
|
| 1807 |
+
"learning_rate": 5.63192193433765e-06,
|
| 1808 |
+
"loss": 0.0782,
|
| 1809 |
+
"step": 1285
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 2.1976149914821126,
|
| 1813 |
+
"grad_norm": 0.6932392120361328,
|
| 1814 |
+
"learning_rate": 5.522278728639544e-06,
|
| 1815 |
+
"loss": 0.0895,
|
| 1816 |
+
"step": 1290
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 2.2061328790459966,
|
| 1820 |
+
"grad_norm": 0.690974771976471,
|
| 1821 |
+
"learning_rate": 5.413472026795116e-06,
|
| 1822 |
+
"loss": 0.092,
|
| 1823 |
+
"step": 1295
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 2.2146507666098807,
|
| 1827 |
+
"grad_norm": 0.8959670662879944,
|
| 1828 |
+
"learning_rate": 5.305511432085885e-06,
|
| 1829 |
+
"loss": 0.0931,
|
| 1830 |
+
"step": 1300
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 2.2231686541737647,
|
| 1834 |
+
"grad_norm": 0.6588398218154907,
|
| 1835 |
+
"learning_rate": 5.198406473115922e-06,
|
| 1836 |
+
"loss": 0.076,
|
| 1837 |
+
"step": 1305
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 2.2316865417376492,
|
| 1841 |
+
"grad_norm": 0.7627379298210144,
|
| 1842 |
+
"learning_rate": 5.092166602970878e-06,
|
| 1843 |
+
"loss": 0.0898,
|
| 1844 |
+
"step": 1310
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 2.2402044293015333,
|
| 1848 |
+
"grad_norm": 0.849267303943634,
|
| 1849 |
+
"learning_rate": 4.986801198383636e-06,
|
| 1850 |
+
"loss": 0.0858,
|
| 1851 |
+
"step": 1315
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 2.2487223168654173,
|
| 1855 |
+
"grad_norm": 0.7844652533531189,
|
| 1856 |
+
"learning_rate": 4.8823195589067435e-06,
|
| 1857 |
+
"loss": 0.0849,
|
| 1858 |
+
"step": 1320
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 2.2572402044293014,
|
| 1862 |
+
"grad_norm": 0.7158147096633911,
|
| 1863 |
+
"learning_rate": 4.778730906091633e-06,
|
| 1864 |
+
"loss": 0.0828,
|
| 1865 |
+
"step": 1325
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 2.2657580919931855,
|
| 1869 |
+
"grad_norm": 0.8349435329437256,
|
| 1870 |
+
"learning_rate": 4.676044382674702e-06,
|
| 1871 |
+
"loss": 0.0775,
|
| 1872 |
+
"step": 1330
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 2.27427597955707,
|
| 1876 |
+
"grad_norm": 0.7931089401245117,
|
| 1877 |
+
"learning_rate": 4.574269051770391e-06,
|
| 1878 |
+
"loss": 0.0736,
|
| 1879 |
+
"step": 1335
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 2.282793867120954,
|
| 1883 |
+
"grad_norm": 0.6381593942642212,
|
| 1884 |
+
"learning_rate": 4.473413896071273e-06,
|
| 1885 |
+
"loss": 0.0859,
|
| 1886 |
+
"step": 1340
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 2.291311754684838,
|
| 1890 |
+
"grad_norm": 0.7761396765708923,
|
| 1891 |
+
"learning_rate": 4.373487817055257e-06,
|
| 1892 |
+
"loss": 0.0874,
|
| 1893 |
+
"step": 1345
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 2.2998296422487225,
|
| 1897 |
+
"grad_norm": 0.6112410426139832,
|
| 1898 |
+
"learning_rate": 4.274499634199912e-06,
|
| 1899 |
+
"loss": 0.0772,
|
| 1900 |
+
"step": 1350
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 2.3083475298126066,
|
| 1904 |
+
"grad_norm": 0.8848159313201904,
|
| 1905 |
+
"learning_rate": 4.17645808420407e-06,
|
| 1906 |
+
"loss": 0.091,
|
| 1907 |
+
"step": 1355
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 2.3168654173764907,
|
| 1911 |
+
"grad_norm": 0.6908820867538452,
|
| 1912 |
+
"learning_rate": 4.079371820216735e-06,
|
| 1913 |
+
"loss": 0.0745,
|
| 1914 |
+
"step": 1360
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 2.3253833049403747,
|
| 1918 |
+
"grad_norm": 0.6497426629066467,
|
| 1919 |
+
"learning_rate": 3.9832494110733615e-06,
|
| 1920 |
+
"loss": 0.0803,
|
| 1921 |
+
"step": 1365
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 2.3339011925042588,
|
| 1925 |
+
"grad_norm": 0.848296582698822,
|
| 1926 |
+
"learning_rate": 3.888099340539548e-06,
|
| 1927 |
+
"loss": 0.0921,
|
| 1928 |
+
"step": 1370
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 2.3424190800681433,
|
| 1932 |
+
"grad_norm": 0.7882264852523804,
|
| 1933 |
+
"learning_rate": 3.7939300065622596e-06,
|
| 1934 |
+
"loss": 0.0733,
|
| 1935 |
+
"step": 1375
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 2.3509369676320273,
|
| 1939 |
+
"grad_norm": 0.8846136927604675,
|
| 1940 |
+
"learning_rate": 3.700749720528651e-06,
|
| 1941 |
+
"loss": 0.0812,
|
| 1942 |
+
"step": 1380
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 2.3594548551959114,
|
| 1946 |
+
"grad_norm": 0.6956538558006287,
|
| 1947 |
+
"learning_rate": 3.6085667065324735e-06,
|
| 1948 |
+
"loss": 0.0768,
|
| 1949 |
+
"step": 1385
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 2.3679727427597954,
|
| 1953 |
+
"grad_norm": 0.7948773503303528,
|
| 1954 |
+
"learning_rate": 3.517389100648254e-06,
|
| 1955 |
+
"loss": 0.0772,
|
| 1956 |
+
"step": 1390
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 2.37649063032368,
|
| 1960 |
+
"grad_norm": 0.6592779159545898,
|
| 1961 |
+
"learning_rate": 3.427224950213149e-06,
|
| 1962 |
+
"loss": 0.0794,
|
| 1963 |
+
"step": 1395
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 2.385008517887564,
|
| 1967 |
+
"grad_norm": 0.7463333606719971,
|
| 1968 |
+
"learning_rate": 3.338082213116738e-06,
|
| 1969 |
+
"loss": 0.0727,
|
| 1970 |
+
"step": 1400
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 2.393526405451448,
|
| 1974 |
+
"grad_norm": 0.6972132325172424,
|
| 1975 |
+
"learning_rate": 3.249968757098639e-06,
|
| 1976 |
+
"loss": 0.0786,
|
| 1977 |
+
"step": 1405
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 2.402044293015332,
|
| 1981 |
+
"grad_norm": 0.7377766370773315,
|
| 1982 |
+
"learning_rate": 3.162892359054098e-06,
|
| 1983 |
+
"loss": 0.0775,
|
| 1984 |
+
"step": 1410
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 2.410562180579216,
|
| 1988 |
+
"grad_norm": 0.671190619468689,
|
| 1989 |
+
"learning_rate": 3.0768607043476082e-06,
|
| 1990 |
+
"loss": 0.075,
|
| 1991 |
+
"step": 1415
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 2.4190800681431006,
|
| 1995 |
+
"grad_norm": 0.6883941292762756,
|
| 1996 |
+
"learning_rate": 2.9918813861345958e-06,
|
| 1997 |
+
"loss": 0.0758,
|
| 1998 |
+
"step": 1420
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 2.4275979557069847,
|
| 2002 |
+
"grad_norm": 0.6671259999275208,
|
| 2003 |
+
"learning_rate": 2.9079619046912486e-06,
|
| 2004 |
+
"loss": 0.0806,
|
| 2005 |
+
"step": 1425
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 2.4361158432708687,
|
| 2009 |
+
"grad_norm": 0.7585006952285767,
|
| 2010 |
+
"learning_rate": 2.8251096667525426e-06,
|
| 2011 |
+
"loss": 0.0837,
|
| 2012 |
+
"step": 1430
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 2.444633730834753,
|
| 2016 |
+
"grad_norm": 0.787529706954956,
|
| 2017 |
+
"learning_rate": 2.743331984858523e-06,
|
| 2018 |
+
"loss": 0.0877,
|
| 2019 |
+
"step": 1435
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 2.4531516183986373,
|
| 2023 |
+
"grad_norm": 0.7176535129547119,
|
| 2024 |
+
"learning_rate": 2.6626360767088943e-06,
|
| 2025 |
+
"loss": 0.0717,
|
| 2026 |
+
"step": 1440
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 2.4616695059625213,
|
| 2030 |
+
"grad_norm": 0.827599287033081,
|
| 2031 |
+
"learning_rate": 2.583029064525996e-06,
|
| 2032 |
+
"loss": 0.0774,
|
| 2033 |
+
"step": 1445
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 2.4701873935264054,
|
| 2037 |
+
"grad_norm": 0.6832327842712402,
|
| 2038 |
+
"learning_rate": 2.5045179744261864e-06,
|
| 2039 |
+
"loss": 0.0667,
|
| 2040 |
+
"step": 1450
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 2.4787052810902894,
|
| 2044 |
+
"grad_norm": 0.6381378173828125,
|
| 2045 |
+
"learning_rate": 2.4271097357997214e-06,
|
| 2046 |
+
"loss": 0.073,
|
| 2047 |
+
"step": 1455
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 2.487223168654174,
|
| 2051 |
+
"grad_norm": 0.6978477239608765,
|
| 2052 |
+
"learning_rate": 2.3508111806991663e-06,
|
| 2053 |
+
"loss": 0.0808,
|
| 2054 |
+
"step": 1460
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 2.495741056218058,
|
| 2058 |
+
"grad_norm": 0.6542275547981262,
|
| 2059 |
+
"learning_rate": 2.2756290432363958e-06,
|
| 2060 |
+
"loss": 0.0834,
|
| 2061 |
+
"step": 1465
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 2.504258943781942,
|
| 2065 |
+
"grad_norm": 0.5989179611206055,
|
| 2066 |
+
"learning_rate": 2.2015699589882447e-06,
|
| 2067 |
+
"loss": 0.0667,
|
| 2068 |
+
"step": 1470
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 2.512776831345826,
|
| 2072 |
+
"grad_norm": 0.9249573945999146,
|
| 2073 |
+
"learning_rate": 2.128640464410853e-06,
|
| 2074 |
+
"loss": 0.0725,
|
| 2075 |
+
"step": 1475
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 2.5212947189097106,
|
| 2079 |
+
"grad_norm": 0.8012790679931641,
|
| 2080 |
+
"learning_rate": 2.056846996262752e-06,
|
| 2081 |
+
"loss": 0.0752,
|
| 2082 |
+
"step": 1480
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 2.5298126064735946,
|
| 2086 |
+
"grad_norm": 0.6632130742073059,
|
| 2087 |
+
"learning_rate": 1.986195891036758e-06,
|
| 2088 |
+
"loss": 0.0669,
|
| 2089 |
+
"step": 1485
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 2.5383304940374787,
|
| 2093 |
+
"grad_norm": 0.6948779821395874,
|
| 2094 |
+
"learning_rate": 1.916693384400722e-06,
|
| 2095 |
+
"loss": 0.0754,
|
| 2096 |
+
"step": 1490
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 2.5468483816013627,
|
| 2100 |
+
"grad_norm": 0.6110554337501526,
|
| 2101 |
+
"learning_rate": 1.8483456106471541e-06,
|
| 2102 |
+
"loss": 0.0682,
|
| 2103 |
+
"step": 1495
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 2.555366269165247,
|
| 2107 |
+
"grad_norm": 0.542285680770874,
|
| 2108 |
+
"learning_rate": 1.7811586021518238e-06,
|
| 2109 |
+
"loss": 0.063,
|
| 2110 |
+
"step": 1500
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"epoch": 2.5638841567291313,
|
| 2114 |
+
"grad_norm": 0.6294452548027039,
|
| 2115 |
+
"learning_rate": 1.7151382888413359e-06,
|
| 2116 |
+
"loss": 0.0763,
|
| 2117 |
+
"step": 1505
|
| 2118 |
+
},
|
| 2119 |
+
{
|
| 2120 |
+
"epoch": 2.5724020442930153,
|
| 2121 |
+
"grad_norm": 0.6262813806533813,
|
| 2122 |
+
"learning_rate": 1.6502904976697575e-06,
|
| 2123 |
+
"loss": 0.0747,
|
| 2124 |
+
"step": 1510
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 2.5809199318568994,
|
| 2128 |
+
"grad_norm": 0.5802568793296814,
|
| 2129 |
+
"learning_rate": 1.5866209521043307e-06,
|
| 2130 |
+
"loss": 0.0652,
|
| 2131 |
+
"step": 1515
|
| 2132 |
+
},
|
| 2133 |
+
{
|
| 2134 |
+
"epoch": 2.589437819420784,
|
| 2135 |
+
"grad_norm": 0.6935997009277344,
|
| 2136 |
+
"learning_rate": 1.5241352716203173e-06,
|
| 2137 |
+
"loss": 0.0777,
|
| 2138 |
+
"step": 1520
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 2.597955706984668,
|
| 2142 |
+
"grad_norm": 0.6129751801490784,
|
| 2143 |
+
"learning_rate": 1.4628389712050256e-06,
|
| 2144 |
+
"loss": 0.0697,
|
| 2145 |
+
"step": 1525
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 2.606473594548552,
|
| 2149 |
+
"grad_norm": 0.6502246856689453,
|
| 2150 |
+
"learning_rate": 1.402737460871057e-06,
|
| 2151 |
+
"loss": 0.067,
|
| 2152 |
+
"step": 1530
|
| 2153 |
+
},
|
| 2154 |
+
{
|
| 2155 |
+
"epoch": 2.614991482112436,
|
| 2156 |
+
"grad_norm": 0.6873260140419006,
|
| 2157 |
+
"learning_rate": 1.343836045178819e-06,
|
| 2158 |
+
"loss": 0.0677,
|
| 2159 |
+
"step": 1535
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 2.62350936967632,
|
| 2163 |
+
"grad_norm": 0.6103435158729553,
|
| 2164 |
+
"learning_rate": 1.2861399227683434e-06,
|
| 2165 |
+
"loss": 0.0699,
|
| 2166 |
+
"step": 1540
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 2.6320272572402046,
|
| 2170 |
+
"grad_norm": 0.6831743717193604,
|
| 2171 |
+
"learning_rate": 1.229654185900455e-06,
|
| 2172 |
+
"loss": 0.0791,
|
| 2173 |
+
"step": 1545
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 2.6405451448040886,
|
| 2177 |
+
"grad_norm": 0.6810699701309204,
|
| 2178 |
+
"learning_rate": 1.1743838200073327e-06,
|
| 2179 |
+
"loss": 0.0948,
|
| 2180 |
+
"step": 1550
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 2.6490630323679727,
|
| 2184 |
+
"grad_norm": 0.7064430713653564,
|
| 2185 |
+
"learning_rate": 1.1203337032524758e-06,
|
| 2186 |
+
"loss": 0.0691,
|
| 2187 |
+
"step": 1555
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 2.6575809199318567,
|
| 2191 |
+
"grad_norm": 0.5780156850814819,
|
| 2192 |
+
"learning_rate": 1.0675086061001932e-06,
|
| 2193 |
+
"loss": 0.0645,
|
| 2194 |
+
"step": 1560
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 2.6660988074957412,
|
| 2198 |
+
"grad_norm": 0.4241485893726349,
|
| 2199 |
+
"learning_rate": 1.0159131908945291e-06,
|
| 2200 |
+
"loss": 0.0573,
|
| 2201 |
+
"step": 1565
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 2.6746166950596253,
|
| 2205 |
+
"grad_norm": 0.7281294465065002,
|
| 2206 |
+
"learning_rate": 9.655520114477772e-07,
|
| 2207 |
+
"loss": 0.071,
|
| 2208 |
+
"step": 1570
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 2.6831345826235093,
|
| 2212 |
+
"grad_norm": 0.5422447919845581,
|
| 2213 |
+
"learning_rate": 9.164295126385564e-07,
|
| 2214 |
+
"loss": 0.0724,
|
| 2215 |
+
"step": 1575
|
| 2216 |
+
},
|
| 2217 |
+
{
|
| 2218 |
+
"epoch": 2.6916524701873934,
|
| 2219 |
+
"grad_norm": 0.5978062152862549,
|
| 2220 |
+
"learning_rate": 8.685500300195232e-07,
|
| 2221 |
+
"loss": 0.0707,
|
| 2222 |
+
"step": 1580
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 2.7001703577512775,
|
| 2226 |
+
"grad_norm": 0.5231629014015198,
|
| 2227 |
+
"learning_rate": 8.219177894346891e-07,
|
| 2228 |
+
"loss": 0.0664,
|
| 2229 |
+
"step": 1585
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 2.708688245315162,
|
| 2233 |
+
"grad_norm": 0.6919968128204346,
|
| 2234 |
+
"learning_rate": 7.7653690664647e-07,
|
| 2235 |
+
"loss": 0.0714,
|
| 2236 |
+
"step": 1590
|
| 2237 |
+
},
|
| 2238 |
+
{
|
| 2239 |
+
"epoch": 2.717206132879046,
|
| 2240 |
+
"grad_norm": 0.5922629833221436,
|
| 2241 |
+
"learning_rate": 7.324113869724069e-07,
|
| 2242 |
+
"loss": 0.069,
|
| 2243 |
+
"step": 1595
|
| 2244 |
+
},
|
| 2245 |
+
{
|
| 2246 |
+
"epoch": 2.72572402044293,
|
| 2247 |
+
"grad_norm": 0.5499913692474365,
|
| 2248 |
+
"learning_rate": 6.895451249316853e-07,
|
| 2249 |
+
"loss": 0.0732,
|
| 2250 |
+
"step": 1600
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"epoch": 2.7342419080068145,
|
| 2254 |
+
"grad_norm": 0.5531365871429443,
|
| 2255 |
+
"learning_rate": 6.479419039013784e-07,
|
| 2256 |
+
"loss": 0.0668,
|
| 2257 |
+
"step": 1605
|
| 2258 |
+
},
|
| 2259 |
+
{
|
| 2260 |
+
"epoch": 2.7427597955706986,
|
| 2261 |
+
"grad_norm": 0.5937036871910095,
|
| 2262 |
+
"learning_rate": 6.076053957825411e-07,
|
| 2263 |
+
"loss": 0.0655,
|
| 2264 |
+
"step": 1610
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 2.7512776831345827,
|
| 2268 |
+
"grad_norm": 0.6592844724655151,
|
| 2269 |
+
"learning_rate": 5.685391606761159e-07,
|
| 2270 |
+
"loss": 0.0745,
|
| 2271 |
+
"step": 1615
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 2.7597955706984667,
|
| 2275 |
+
"grad_norm": 0.5654294490814209,
|
| 2276 |
+
"learning_rate": 5.307466465687389e-07,
|
| 2277 |
+
"loss": 0.0687,
|
| 2278 |
+
"step": 1620
|
| 2279 |
+
},
|
| 2280 |
+
{
|
| 2281 |
+
"epoch": 2.7683134582623508,
|
| 2282 |
+
"grad_norm": 0.7116056680679321,
|
| 2283 |
+
"learning_rate": 4.942311890283968e-07,
|
| 2284 |
+
"loss": 0.0715,
|
| 2285 |
+
"step": 1625
|
| 2286 |
+
},
|
| 2287 |
+
{
|
| 2288 |
+
"epoch": 2.7768313458262353,
|
| 2289 |
+
"grad_norm": 0.6961405873298645,
|
| 2290 |
+
"learning_rate": 4.589960109100444e-07,
|
| 2291 |
+
"loss": 0.0743,
|
| 2292 |
+
"step": 1630
|
| 2293 |
+
},
|
| 2294 |
+
{
|
| 2295 |
+
"epoch": 2.7853492333901193,
|
| 2296 |
+
"grad_norm": 0.6112069487571716,
|
| 2297 |
+
"learning_rate": 4.250442220711498e-07,
|
| 2298 |
+
"loss": 0.0741,
|
| 2299 |
+
"step": 1635
|
| 2300 |
+
},
|
| 2301 |
+
{
|
| 2302 |
+
"epoch": 2.7938671209540034,
|
| 2303 |
+
"grad_norm": 0.5708335041999817,
|
| 2304 |
+
"learning_rate": 3.9237881909721776e-07,
|
| 2305 |
+
"loss": 0.0578,
|
| 2306 |
+
"step": 1640
|
| 2307 |
+
},
|
| 2308 |
+
{
|
| 2309 |
+
"epoch": 2.8023850085178874,
|
| 2310 |
+
"grad_norm": 0.5360596776008606,
|
| 2311 |
+
"learning_rate": 3.610026850373194e-07,
|
| 2312 |
+
"loss": 0.0676,
|
| 2313 |
+
"step": 1645
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 2.810902896081772,
|
| 2317 |
+
"grad_norm": 0.5463550686836243,
|
| 2318 |
+
"learning_rate": 3.3091858914962415e-07,
|
| 2319 |
+
"loss": 0.0604,
|
| 2320 |
+
"step": 1650
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 2.819420783645656,
|
| 2324 |
+
"grad_norm": 0.5183315873146057,
|
| 2325 |
+
"learning_rate": 3.021291866569853e-07,
|
| 2326 |
+
"loss": 0.0681,
|
| 2327 |
+
"step": 1655
|
| 2328 |
+
},
|
| 2329 |
+
{
|
| 2330 |
+
"epoch": 2.82793867120954,
|
| 2331 |
+
"grad_norm": 0.6110967397689819,
|
| 2332 |
+
"learning_rate": 2.74637018512594e-07,
|
| 2333 |
+
"loss": 0.0701,
|
| 2334 |
+
"step": 1660
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 2.836456558773424,
|
| 2338 |
+
"grad_norm": 0.5699721574783325,
|
| 2339 |
+
"learning_rate": 2.484445111757222e-07,
|
| 2340 |
+
"loss": 0.0707,
|
| 2341 |
+
"step": 1665
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 2.844974446337308,
|
| 2345 |
+
"grad_norm": 0.6234309077262878,
|
| 2346 |
+
"learning_rate": 2.235539763975486e-07,
|
| 2347 |
+
"loss": 0.0714,
|
| 2348 |
+
"step": 1670
|
| 2349 |
+
},
|
| 2350 |
+
{
|
| 2351 |
+
"epoch": 2.8534923339011926,
|
| 2352 |
+
"grad_norm": 0.5821977257728577,
|
| 2353 |
+
"learning_rate": 1.9996761101712558e-07,
|
| 2354 |
+
"loss": 0.0656,
|
| 2355 |
+
"step": 1675
|
| 2356 |
+
},
|
| 2357 |
+
{
|
| 2358 |
+
"epoch": 2.8620102214650767,
|
| 2359 |
+
"grad_norm": 0.5511728525161743,
|
| 2360 |
+
"learning_rate": 1.776874967674974e-07,
|
| 2361 |
+
"loss": 0.0674,
|
| 2362 |
+
"step": 1680
|
| 2363 |
+
},
|
| 2364 |
+
{
|
| 2365 |
+
"epoch": 2.8705281090289607,
|
| 2366 |
+
"grad_norm": 0.5235552191734314,
|
| 2367 |
+
"learning_rate": 1.5671560009195894e-07,
|
| 2368 |
+
"loss": 0.0702,
|
| 2369 |
+
"step": 1685
|
| 2370 |
+
},
|
| 2371 |
+
{
|
| 2372 |
+
"epoch": 2.879045996592845,
|
| 2373 |
+
"grad_norm": 0.6012466549873352,
|
| 2374 |
+
"learning_rate": 1.3705377197049617e-07,
|
| 2375 |
+
"loss": 0.0684,
|
| 2376 |
+
"step": 1690
|
| 2377 |
+
},
|
| 2378 |
+
{
|
| 2379 |
+
"epoch": 2.8875638841567293,
|
| 2380 |
+
"grad_norm": 0.5243468880653381,
|
| 2381 |
+
"learning_rate": 1.1870374775641846e-07,
|
| 2382 |
+
"loss": 0.0671,
|
| 2383 |
+
"step": 1695
|
| 2384 |
+
},
|
| 2385 |
+
{
|
| 2386 |
+
"epoch": 2.8960817717206133,
|
| 2387 |
+
"grad_norm": 0.6735599637031555,
|
| 2388 |
+
"learning_rate": 1.0166714702320113e-07,
|
| 2389 |
+
"loss": 0.0647,
|
| 2390 |
+
"step": 1700
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"epoch": 2.9045996592844974,
|
| 2394 |
+
"grad_norm": 0.5573726296424866,
|
| 2395 |
+
"learning_rate": 8.59454734215398e-08,
|
| 2396 |
+
"loss": 0.0769,
|
| 2397 |
+
"step": 1705
|
| 2398 |
+
},
|
| 2399 |
+
{
|
| 2400 |
+
"epoch": 2.9131175468483814,
|
| 2401 |
+
"grad_norm": 0.6575697660446167,
|
| 2402 |
+
"learning_rate": 7.154011454663489e-08,
|
| 2403 |
+
"loss": 0.0655,
|
| 2404 |
+
"step": 1710
|
| 2405 |
+
},
|
| 2406 |
+
{
|
| 2407 |
+
"epoch": 2.921635434412266,
|
| 2408 |
+
"grad_norm": 0.6582594513893127,
|
| 2409 |
+
"learning_rate": 5.845234181572623e-08,
|
| 2410 |
+
"loss": 0.0727,
|
| 2411 |
+
"step": 1715
|
| 2412 |
+
},
|
| 2413 |
+
{
|
| 2414 |
+
"epoch": 2.93015332197615,
|
| 2415 |
+
"grad_norm": 0.6178227066993713,
|
| 2416 |
+
"learning_rate": 4.6683310355874475e-08,
|
| 2417 |
+
"loss": 0.0645,
|
| 2418 |
+
"step": 1720
|
| 2419 |
+
},
|
| 2420 |
+
{
|
| 2421 |
+
"epoch": 2.938671209540034,
|
| 2422 |
+
"grad_norm": 0.5734277367591858,
|
| 2423 |
+
"learning_rate": 3.6234058902011034e-08,
|
| 2424 |
+
"loss": 0.0617,
|
| 2425 |
+
"step": 1725
|
| 2426 |
+
},
|
| 2427 |
+
{
|
| 2428 |
+
"epoch": 2.947189097103918,
|
| 2429 |
+
"grad_norm": 0.6818283200263977,
|
| 2430 |
+
"learning_rate": 2.710550970526471e-08,
|
| 2431 |
+
"loss": 0.0738,
|
| 2432 |
+
"step": 1730
|
| 2433 |
+
},
|
| 2434 |
+
{
|
| 2435 |
+
"epoch": 2.9557069846678026,
|
| 2436 |
+
"grad_norm": 0.7055466771125793,
|
| 2437 |
+
"learning_rate": 1.929846845155514e-08,
|
| 2438 |
+
"loss": 0.0742,
|
| 2439 |
+
"step": 1735
|
| 2440 |
+
},
|
| 2441 |
+
{
|
| 2442 |
+
"epoch": 2.9642248722316866,
|
| 2443 |
+
"grad_norm": 0.7021325826644897,
|
| 2444 |
+
"learning_rate": 1.2813624190484707e-08,
|
| 2445 |
+
"loss": 0.0702,
|
| 2446 |
+
"step": 1740
|
| 2447 |
+
},
|
| 2448 |
+
{
|
| 2449 |
+
"epoch": 2.9727427597955707,
|
| 2450 |
+
"grad_norm": 0.6380594968795776,
|
| 2451 |
+
"learning_rate": 7.651549274528824e-09,
|
| 2452 |
+
"loss": 0.0705,
|
| 2453 |
+
"step": 1745
|
| 2454 |
+
},
|
| 2455 |
+
{
|
| 2456 |
+
"epoch": 2.9812606473594547,
|
| 2457 |
+
"grad_norm": 0.6334229111671448,
|
| 2458 |
+
"learning_rate": 3.812699308513024e-09,
|
| 2459 |
+
"loss": 0.0619,
|
| 2460 |
+
"step": 1750
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 2.989778534923339,
|
| 2464 |
+
"grad_norm": 0.6881961226463318,
|
| 2465 |
+
"learning_rate": 1.2974131094084519e-09,
|
| 2466 |
+
"loss": 0.0688,
|
| 2467 |
+
"step": 1755
|
| 2468 |
+
},
|
| 2469 |
+
{
|
| 2470 |
+
"epoch": 2.9982964224872233,
|
| 2471 |
+
"grad_norm": 0.5323131084442139,
|
| 2472 |
+
"learning_rate": 1.0591267641912871e-10,
|
| 2473 |
+
"loss": 0.0653,
|
| 2474 |
+
"step": 1760
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 3.0,
|
| 2478 |
+
"step": 1761,
|
| 2479 |
+
"total_flos": 2.1874027065392497e+18,
|
| 2480 |
+
"train_loss": 0.3763406072520587,
|
| 2481 |
+
"train_runtime": 1082.1068,
|
| 2482 |
+
"train_samples_per_second": 52.048,
|
| 2483 |
+
"train_steps_per_second": 1.627
|
| 2484 |
+
}
|
| 2485 |
+
],
|
| 2486 |
+
"logging_steps": 5,
|
| 2487 |
+
"max_steps": 1761,
|
| 2488 |
+
"num_input_tokens_seen": 0,
|
| 2489 |
+
"num_train_epochs": 3,
|
| 2490 |
+
"save_steps": 20000,
|
| 2491 |
+
"stateful_callbacks": {
|
| 2492 |
+
"TrainerControl": {
|
| 2493 |
+
"args": {
|
| 2494 |
+
"should_epoch_stop": false,
|
| 2495 |
+
"should_evaluate": false,
|
| 2496 |
+
"should_log": false,
|
| 2497 |
+
"should_save": false,
|
| 2498 |
+
"should_training_stop": false
|
| 2499 |
+
},
|
| 2500 |
+
"attributes": {}
|
| 2501 |
+
}
|
| 2502 |
+
},
|
| 2503 |
+
"total_flos": 2.1874027065392497e+18,
|
| 2504 |
+
"train_batch_size": 2,
|
| 2505 |
+
"trial_name": null,
|
| 2506 |
+
"trial_params": null
|
| 2507 |
+
}
|
instruct/122_128_e3_3e-5/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f9e8a8ef4e5033d043cbbffe8224180f33b157202fd5ed519bc88cf2e11caea
|
| 3 |
+
size 8273
|
instruct/122_128_e3_3e-5/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|