Upload folder using huggingface_hub
Browse files- instruct/128_128_e3_3e-5/adapter_config.json +39 -0
- instruct/128_128_e3_3e-5/adapter_model.safetensors +3 -0
- instruct/128_128_e3_3e-5/added_tokens.json +9 -0
- instruct/128_128_e3_3e-5/all_results.json +9 -0
- instruct/128_128_e3_3e-5/chat_template.jinja +62 -0
- instruct/128_128_e3_3e-5/config.json +32 -0
- instruct/128_128_e3_3e-5/merges.txt +0 -0
- instruct/128_128_e3_3e-5/special_tokens_map.json +33 -0
- instruct/128_128_e3_3e-5/tokenizer.json +0 -0
- instruct/128_128_e3_3e-5/tokenizer_config.json +234 -0
- instruct/128_128_e3_3e-5/train_results.json +9 -0
- instruct/128_128_e3_3e-5/trainer_state.json +3382 -0
- instruct/128_128_e3_3e-5/training_args.bin +3 -0
- instruct/128_128_e3_3e-5/vocab.json +0 -0
instruct/128_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 |
+
"q_proj",
|
| 28 |
+
"up_proj",
|
| 29 |
+
"v_proj",
|
| 30 |
+
"gate_proj",
|
| 31 |
+
"down_proj",
|
| 32 |
+
"k_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/128_128_e3_3e-5/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc33beb13b32eb1667de54f15e4d2c9453e718ce8de8afd708c63ff7adf7b7c9
|
| 3 |
+
size 791751704
|
instruct/128_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/128_128_e3_3e-5/all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 2.994644650003792e+18,
|
| 4 |
+
"train_loss": 0.3442072710973933,
|
| 5 |
+
"train_runtime": 1455.861,
|
| 6 |
+
"train_samples": 25450,
|
| 7 |
+
"train_samples_per_second": 52.443,
|
| 8 |
+
"train_steps_per_second": 1.64
|
| 9 |
+
}
|
instruct/128_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/128_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/128_128_e3_3e-5/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
instruct/128_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/128_128_e3_3e-5/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
instruct/128_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/128_128_e3_3e-5/train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 2.994644650003792e+18,
|
| 4 |
+
"train_loss": 0.3442072710973933,
|
| 5 |
+
"train_runtime": 1455.861,
|
| 6 |
+
"train_samples": 25450,
|
| 7 |
+
"train_samples_per_second": 52.443,
|
| 8 |
+
"train_steps_per_second": 1.64
|
| 9 |
+
}
|
instruct/128_128_e3_3e-5/trainer_state.json
ADDED
|
@@ -0,0 +1,3382 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 2388,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.006285355122564425,
|
| 14 |
+
"grad_norm": 2.761408805847168,
|
| 15 |
+
"learning_rate": 1e-06,
|
| 16 |
+
"loss": 1.6576,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.01257071024512885,
|
| 21 |
+
"grad_norm": 2.2180190086364746,
|
| 22 |
+
"learning_rate": 2.25e-06,
|
| 23 |
+
"loss": 1.5784,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.018856065367693273,
|
| 28 |
+
"grad_norm": 1.619667887687683,
|
| 29 |
+
"learning_rate": 3.5e-06,
|
| 30 |
+
"loss": 1.5388,
|
| 31 |
+
"step": 15
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.0251414204902577,
|
| 35 |
+
"grad_norm": 1.3265295028686523,
|
| 36 |
+
"learning_rate": 4.75e-06,
|
| 37 |
+
"loss": 1.546,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.03142677561282212,
|
| 42 |
+
"grad_norm": 0.7975988984107971,
|
| 43 |
+
"learning_rate": 6e-06,
|
| 44 |
+
"loss": 1.4751,
|
| 45 |
+
"step": 25
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.03771213073538655,
|
| 49 |
+
"grad_norm": 0.5942533016204834,
|
| 50 |
+
"learning_rate": 7.25e-06,
|
| 51 |
+
"loss": 1.4272,
|
| 52 |
+
"step": 30
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.04399748585795098,
|
| 56 |
+
"grad_norm": 0.4847055673599243,
|
| 57 |
+
"learning_rate": 8.5e-06,
|
| 58 |
+
"loss": 1.4348,
|
| 59 |
+
"step": 35
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.0502828409805154,
|
| 63 |
+
"grad_norm": 0.4672721028327942,
|
| 64 |
+
"learning_rate": 9.75e-06,
|
| 65 |
+
"loss": 1.4208,
|
| 66 |
+
"step": 40
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.056568196103079824,
|
| 70 |
+
"grad_norm": 0.5222629308700562,
|
| 71 |
+
"learning_rate": 1.1e-05,
|
| 72 |
+
"loss": 1.4245,
|
| 73 |
+
"step": 45
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.06285355122564425,
|
| 77 |
+
"grad_norm": 0.4598546028137207,
|
| 78 |
+
"learning_rate": 1.225e-05,
|
| 79 |
+
"loss": 1.4368,
|
| 80 |
+
"step": 50
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.06913890634820867,
|
| 84 |
+
"grad_norm": 0.47465452551841736,
|
| 85 |
+
"learning_rate": 1.3500000000000001e-05,
|
| 86 |
+
"loss": 1.3988,
|
| 87 |
+
"step": 55
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.0754242614707731,
|
| 91 |
+
"grad_norm": 0.541188657283783,
|
| 92 |
+
"learning_rate": 1.475e-05,
|
| 93 |
+
"loss": 1.3994,
|
| 94 |
+
"step": 60
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.08170961659333752,
|
| 98 |
+
"grad_norm": 2.766167163848877,
|
| 99 |
+
"learning_rate": 1.6e-05,
|
| 100 |
+
"loss": 1.3572,
|
| 101 |
+
"step": 65
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.08799497171590195,
|
| 105 |
+
"grad_norm": 0.4344269633293152,
|
| 106 |
+
"learning_rate": 1.725e-05,
|
| 107 |
+
"loss": 1.3965,
|
| 108 |
+
"step": 70
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.09428032683846638,
|
| 112 |
+
"grad_norm": 0.42142146825790405,
|
| 113 |
+
"learning_rate": 1.8500000000000002e-05,
|
| 114 |
+
"loss": 1.3444,
|
| 115 |
+
"step": 75
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.1005656819610308,
|
| 119 |
+
"grad_norm": 0.462269127368927,
|
| 120 |
+
"learning_rate": 1.975e-05,
|
| 121 |
+
"loss": 1.3657,
|
| 122 |
+
"step": 80
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.10685103708359522,
|
| 126 |
+
"grad_norm": 0.44445449113845825,
|
| 127 |
+
"learning_rate": 2.1e-05,
|
| 128 |
+
"loss": 1.3089,
|
| 129 |
+
"step": 85
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.11313639220615965,
|
| 133 |
+
"grad_norm": 0.4413028955459595,
|
| 134 |
+
"learning_rate": 2.2250000000000002e-05,
|
| 135 |
+
"loss": 1.317,
|
| 136 |
+
"step": 90
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.11942174732872407,
|
| 140 |
+
"grad_norm": 0.4518461227416992,
|
| 141 |
+
"learning_rate": 2.3500000000000002e-05,
|
| 142 |
+
"loss": 1.2978,
|
| 143 |
+
"step": 95
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.1257071024512885,
|
| 147 |
+
"grad_norm": 0.9033398628234863,
|
| 148 |
+
"learning_rate": 2.475e-05,
|
| 149 |
+
"loss": 1.3219,
|
| 150 |
+
"step": 100
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.13199245757385292,
|
| 154 |
+
"grad_norm": 1.5538249015808105,
|
| 155 |
+
"learning_rate": 2.6000000000000002e-05,
|
| 156 |
+
"loss": 1.3206,
|
| 157 |
+
"step": 105
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.13827781269641734,
|
| 161 |
+
"grad_norm": 0.46547821164131165,
|
| 162 |
+
"learning_rate": 2.725e-05,
|
| 163 |
+
"loss": 1.2525,
|
| 164 |
+
"step": 110
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.14456316781898176,
|
| 168 |
+
"grad_norm": 0.5106672644615173,
|
| 169 |
+
"learning_rate": 2.8499999999999998e-05,
|
| 170 |
+
"loss": 1.2506,
|
| 171 |
+
"step": 115
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.1508485229415462,
|
| 175 |
+
"grad_norm": 0.5095160007476807,
|
| 176 |
+
"learning_rate": 2.975e-05,
|
| 177 |
+
"loss": 1.2081,
|
| 178 |
+
"step": 120
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.1571338780641106,
|
| 182 |
+
"grad_norm": 0.6342917680740356,
|
| 183 |
+
"learning_rate": 2.999976975310621e-05,
|
| 184 |
+
"loss": 1.223,
|
| 185 |
+
"step": 125
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.16341923318667503,
|
| 189 |
+
"grad_norm": 0.6309908628463745,
|
| 190 |
+
"learning_rate": 2.999883438721462e-05,
|
| 191 |
+
"loss": 1.1732,
|
| 192 |
+
"step": 130
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.16970458830923948,
|
| 196 |
+
"grad_norm": 0.5935143232345581,
|
| 197 |
+
"learning_rate": 2.999717955672752e-05,
|
| 198 |
+
"loss": 1.1456,
|
| 199 |
+
"step": 135
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.1759899434318039,
|
| 203 |
+
"grad_norm": 0.5954174995422363,
|
| 204 |
+
"learning_rate": 2.9994805341023874e-05,
|
| 205 |
+
"loss": 1.1745,
|
| 206 |
+
"step": 140
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.18227529855436833,
|
| 210 |
+
"grad_norm": 0.6493895649909973,
|
| 211 |
+
"learning_rate": 2.9991711853990137e-05,
|
| 212 |
+
"loss": 1.1607,
|
| 213 |
+
"step": 145
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.18856065367693275,
|
| 217 |
+
"grad_norm": 0.6415303349494934,
|
| 218 |
+
"learning_rate": 2.9987899244014802e-05,
|
| 219 |
+
"loss": 1.1503,
|
| 220 |
+
"step": 150
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.19484600879949718,
|
| 224 |
+
"grad_norm": 0.6455085277557373,
|
| 225 |
+
"learning_rate": 2.998336769398127e-05,
|
| 226 |
+
"loss": 1.1152,
|
| 227 |
+
"step": 155
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.2011313639220616,
|
| 231 |
+
"grad_norm": 0.6694583892822266,
|
| 232 |
+
"learning_rate": 2.9978117421259094e-05,
|
| 233 |
+
"loss": 1.1063,
|
| 234 |
+
"step": 160
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.20741671904462602,
|
| 238 |
+
"grad_norm": 0.7554137110710144,
|
| 239 |
+
"learning_rate": 2.9972148677693526e-05,
|
| 240 |
+
"loss": 1.1455,
|
| 241 |
+
"step": 165
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.21370207416719045,
|
| 245 |
+
"grad_norm": 0.7370375394821167,
|
| 246 |
+
"learning_rate": 2.9965461749593465e-05,
|
| 247 |
+
"loss": 1.113,
|
| 248 |
+
"step": 170
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.21998742928975487,
|
| 252 |
+
"grad_norm": 0.6840000152587891,
|
| 253 |
+
"learning_rate": 2.99580569577177e-05,
|
| 254 |
+
"loss": 1.0093,
|
| 255 |
+
"step": 175
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.2262727844123193,
|
| 259 |
+
"grad_norm": 0.7379521131515503,
|
| 260 |
+
"learning_rate": 2.9949934657259548e-05,
|
| 261 |
+
"loss": 1.1237,
|
| 262 |
+
"step": 180
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.23255813953488372,
|
| 266 |
+
"grad_norm": 0.6838027834892273,
|
| 267 |
+
"learning_rate": 2.9941095237829775e-05,
|
| 268 |
+
"loss": 1.069,
|
| 269 |
+
"step": 185
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.23884349465744814,
|
| 273 |
+
"grad_norm": 0.6910735964775085,
|
| 274 |
+
"learning_rate": 2.993153912343797e-05,
|
| 275 |
+
"loss": 1.1396,
|
| 276 |
+
"step": 190
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.24512884978001256,
|
| 280 |
+
"grad_norm": 0.7946160435676575,
|
| 281 |
+
"learning_rate": 2.9921266772472135e-05,
|
| 282 |
+
"loss": 0.981,
|
| 283 |
+
"step": 195
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.251414204902577,
|
| 287 |
+
"grad_norm": 0.8434353470802307,
|
| 288 |
+
"learning_rate": 2.991027867767676e-05,
|
| 289 |
+
"loss": 1.0855,
|
| 290 |
+
"step": 200
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.25769956002514144,
|
| 294 |
+
"grad_norm": 0.8489897847175598,
|
| 295 |
+
"learning_rate": 2.9898575366129145e-05,
|
| 296 |
+
"loss": 1.0477,
|
| 297 |
+
"step": 205
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.26398491514770583,
|
| 301 |
+
"grad_norm": 0.8660523891448975,
|
| 302 |
+
"learning_rate": 2.9886157399214137e-05,
|
| 303 |
+
"loss": 0.9853,
|
| 304 |
+
"step": 210
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.2702702702702703,
|
| 308 |
+
"grad_norm": 0.8215709924697876,
|
| 309 |
+
"learning_rate": 2.9873025372597185e-05,
|
| 310 |
+
"loss": 0.9644,
|
| 311 |
+
"step": 215
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.2765556253928347,
|
| 315 |
+
"grad_norm": 0.8182950019836426,
|
| 316 |
+
"learning_rate": 2.9859179916195792e-05,
|
| 317 |
+
"loss": 1.0023,
|
| 318 |
+
"step": 220
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.28284098051539913,
|
| 322 |
+
"grad_norm": 0.7971950173377991,
|
| 323 |
+
"learning_rate": 2.984462169414928e-05,
|
| 324 |
+
"loss": 0.9995,
|
| 325 |
+
"step": 225
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.2891263356379635,
|
| 329 |
+
"grad_norm": 0.8991819024085999,
|
| 330 |
+
"learning_rate": 2.9829351404786934e-05,
|
| 331 |
+
"loss": 0.9362,
|
| 332 |
+
"step": 230
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.295411690760528,
|
| 336 |
+
"grad_norm": 0.8519879579544067,
|
| 337 |
+
"learning_rate": 2.9813369780594512e-05,
|
| 338 |
+
"loss": 0.9038,
|
| 339 |
+
"step": 235
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.3016970458830924,
|
| 343 |
+
"grad_norm": 0.882102906703949,
|
| 344 |
+
"learning_rate": 2.979667758817911e-05,
|
| 345 |
+
"loss": 0.9471,
|
| 346 |
+
"step": 240
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.3079824010056568,
|
| 350 |
+
"grad_norm": 0.8495810031890869,
|
| 351 |
+
"learning_rate": 2.977927562823237e-05,
|
| 352 |
+
"loss": 0.9795,
|
| 353 |
+
"step": 245
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.3142677561282212,
|
| 357 |
+
"grad_norm": 0.9390241503715515,
|
| 358 |
+
"learning_rate": 2.97611647354921e-05,
|
| 359 |
+
"loss": 0.9781,
|
| 360 |
+
"step": 250
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.32055311125078567,
|
| 364 |
+
"grad_norm": 0.8496411442756653,
|
| 365 |
+
"learning_rate": 2.9742345778702215e-05,
|
| 366 |
+
"loss": 0.9071,
|
| 367 |
+
"step": 255
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.32683846637335007,
|
| 371 |
+
"grad_norm": 0.8532080054283142,
|
| 372 |
+
"learning_rate": 2.9722819660571066e-05,
|
| 373 |
+
"loss": 0.9195,
|
| 374 |
+
"step": 260
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.3331238214959145,
|
| 378 |
+
"grad_norm": 0.9096272587776184,
|
| 379 |
+
"learning_rate": 2.9702587317728157e-05,
|
| 380 |
+
"loss": 0.9016,
|
| 381 |
+
"step": 265
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.33940917661847897,
|
| 385 |
+
"grad_norm": 0.8771380186080933,
|
| 386 |
+
"learning_rate": 2.9681649720679194e-05,
|
| 387 |
+
"loss": 0.8987,
|
| 388 |
+
"step": 270
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.34569453174104336,
|
| 392 |
+
"grad_norm": 0.9231809377670288,
|
| 393 |
+
"learning_rate": 2.9660007873759537e-05,
|
| 394 |
+
"loss": 0.8486,
|
| 395 |
+
"step": 275
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.3519798868636078,
|
| 399 |
+
"grad_norm": 0.9215781092643738,
|
| 400 |
+
"learning_rate": 2.9637662815086028e-05,
|
| 401 |
+
"loss": 0.9295,
|
| 402 |
+
"step": 280
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.3582652419861722,
|
| 406 |
+
"grad_norm": 1.1387286186218262,
|
| 407 |
+
"learning_rate": 2.9614615616507202e-05,
|
| 408 |
+
"loss": 0.9184,
|
| 409 |
+
"step": 285
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.36455059710873666,
|
| 413 |
+
"grad_norm": 0.9523952603340149,
|
| 414 |
+
"learning_rate": 2.959086738355186e-05,
|
| 415 |
+
"loss": 0.8409,
|
| 416 |
+
"step": 290
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.37083595223130106,
|
| 420 |
+
"grad_norm": 1.0988142490386963,
|
| 421 |
+
"learning_rate": 2.956641925537605e-05,
|
| 422 |
+
"loss": 0.903,
|
| 423 |
+
"step": 295
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.3771213073538655,
|
| 427 |
+
"grad_norm": 1.0601834058761597,
|
| 428 |
+
"learning_rate": 2.9541272404708403e-05,
|
| 429 |
+
"loss": 0.8389,
|
| 430 |
+
"step": 300
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.3834066624764299,
|
| 434 |
+
"grad_norm": 0.8795098662376404,
|
| 435 |
+
"learning_rate": 2.9515428037793904e-05,
|
| 436 |
+
"loss": 0.8924,
|
| 437 |
+
"step": 305
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.38969201759899436,
|
| 441 |
+
"grad_norm": 1.014522671699524,
|
| 442 |
+
"learning_rate": 2.9488887394336025e-05,
|
| 443 |
+
"loss": 0.8903,
|
| 444 |
+
"step": 310
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.39597737272155875,
|
| 448 |
+
"grad_norm": 1.0858501195907593,
|
| 449 |
+
"learning_rate": 2.9461651747437247e-05,
|
| 450 |
+
"loss": 0.8573,
|
| 451 |
+
"step": 315
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.4022627278441232,
|
| 455 |
+
"grad_norm": 0.8751233220100403,
|
| 456 |
+
"learning_rate": 2.9433722403537998e-05,
|
| 457 |
+
"loss": 0.775,
|
| 458 |
+
"step": 320
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.4085480829666876,
|
| 462 |
+
"grad_norm": 0.9622077345848083,
|
| 463 |
+
"learning_rate": 2.9405100702353998e-05,
|
| 464 |
+
"loss": 0.7896,
|
| 465 |
+
"step": 325
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.41483343808925205,
|
| 469 |
+
"grad_norm": 1.0280210971832275,
|
| 470 |
+
"learning_rate": 2.9375788016811972e-05,
|
| 471 |
+
"loss": 0.7568,
|
| 472 |
+
"step": 330
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.42111879321181644,
|
| 476 |
+
"grad_norm": 1.0586369037628174,
|
| 477 |
+
"learning_rate": 2.934578575298382e-05,
|
| 478 |
+
"loss": 0.8497,
|
| 479 |
+
"step": 335
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.4274041483343809,
|
| 483 |
+
"grad_norm": 1.0849709510803223,
|
| 484 |
+
"learning_rate": 2.9315095350019143e-05,
|
| 485 |
+
"loss": 0.8156,
|
| 486 |
+
"step": 340
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.4336895034569453,
|
| 490 |
+
"grad_norm": 0.9962833523750305,
|
| 491 |
+
"learning_rate": 2.928371828007623e-05,
|
| 492 |
+
"loss": 0.7275,
|
| 493 |
+
"step": 345
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.43997485857950974,
|
| 497 |
+
"grad_norm": 1.1352893114089966,
|
| 498 |
+
"learning_rate": 2.9251656048251435e-05,
|
| 499 |
+
"loss": 0.7516,
|
| 500 |
+
"step": 350
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.4462602137020742,
|
| 504 |
+
"grad_norm": 1.0239955186843872,
|
| 505 |
+
"learning_rate": 2.9218910192506977e-05,
|
| 506 |
+
"loss": 0.7435,
|
| 507 |
+
"step": 355
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.4525455688246386,
|
| 511 |
+
"grad_norm": 1.1110831499099731,
|
| 512 |
+
"learning_rate": 2.9185482283597176e-05,
|
| 513 |
+
"loss": 0.7461,
|
| 514 |
+
"step": 360
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.45883092394720304,
|
| 518 |
+
"grad_norm": 1.0096551179885864,
|
| 519 |
+
"learning_rate": 2.9151373924993094e-05,
|
| 520 |
+
"loss": 0.7602,
|
| 521 |
+
"step": 365
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.46511627906976744,
|
| 525 |
+
"grad_norm": 0.9863064885139465,
|
| 526 |
+
"learning_rate": 2.9116586752805634e-05,
|
| 527 |
+
"loss": 0.7405,
|
| 528 |
+
"step": 370
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.4714016341923319,
|
| 532 |
+
"grad_norm": 1.0303754806518555,
|
| 533 |
+
"learning_rate": 2.908112243570705e-05,
|
| 534 |
+
"loss": 0.7796,
|
| 535 |
+
"step": 375
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.4776869893148963,
|
| 539 |
+
"grad_norm": 1.0935781002044678,
|
| 540 |
+
"learning_rate": 2.9044982674850896e-05,
|
| 541 |
+
"loss": 0.7466,
|
| 542 |
+
"step": 380
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.48397234443746073,
|
| 546 |
+
"grad_norm": 1.0478512048721313,
|
| 547 |
+
"learning_rate": 2.9008169203790455e-05,
|
| 548 |
+
"loss": 0.742,
|
| 549 |
+
"step": 385
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.49025769956002513,
|
| 553 |
+
"grad_norm": 1.0247925519943237,
|
| 554 |
+
"learning_rate": 2.8970683788395547e-05,
|
| 555 |
+
"loss": 0.7269,
|
| 556 |
+
"step": 390
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.4965430546825896,
|
| 560 |
+
"grad_norm": 1.0711115598678589,
|
| 561 |
+
"learning_rate": 2.893252822676785e-05,
|
| 562 |
+
"loss": 0.7022,
|
| 563 |
+
"step": 395
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.502828409805154,
|
| 567 |
+
"grad_norm": 1.0501431226730347,
|
| 568 |
+
"learning_rate": 2.889370434915463e-05,
|
| 569 |
+
"loss": 0.8008,
|
| 570 |
+
"step": 400
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.5091137649277184,
|
| 574 |
+
"grad_norm": 1.1197237968444824,
|
| 575 |
+
"learning_rate": 2.885421401786097e-05,
|
| 576 |
+
"loss": 0.7148,
|
| 577 |
+
"step": 405
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.5153991200502829,
|
| 581 |
+
"grad_norm": 1.1785345077514648,
|
| 582 |
+
"learning_rate": 2.881405912716041e-05,
|
| 583 |
+
"loss": 0.6744,
|
| 584 |
+
"step": 410
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.5216844751728472,
|
| 588 |
+
"grad_norm": 1.0534093379974365,
|
| 589 |
+
"learning_rate": 2.877324160320411e-05,
|
| 590 |
+
"loss": 0.7075,
|
| 591 |
+
"step": 415
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.5279698302954117,
|
| 595 |
+
"grad_norm": 1.0276355743408203,
|
| 596 |
+
"learning_rate": 2.873176340392844e-05,
|
| 597 |
+
"loss": 0.6805,
|
| 598 |
+
"step": 420
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.5342551854179761,
|
| 602 |
+
"grad_norm": 1.1763999462127686,
|
| 603 |
+
"learning_rate": 2.868962651896107e-05,
|
| 604 |
+
"loss": 0.6774,
|
| 605 |
+
"step": 425
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.5405405405405406,
|
| 609 |
+
"grad_norm": 1.0350736379623413,
|
| 610 |
+
"learning_rate": 2.8646832969525518e-05,
|
| 611 |
+
"loss": 0.6417,
|
| 612 |
+
"step": 430
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.5468258956631049,
|
| 616 |
+
"grad_norm": 1.1017727851867676,
|
| 617 |
+
"learning_rate": 2.8603384808344217e-05,
|
| 618 |
+
"loss": 0.6793,
|
| 619 |
+
"step": 435
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.5531112507856694,
|
| 623 |
+
"grad_norm": 0.9999217987060547,
|
| 624 |
+
"learning_rate": 2.8559284119540028e-05,
|
| 625 |
+
"loss": 0.6502,
|
| 626 |
+
"step": 440
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.5593966059082338,
|
| 630 |
+
"grad_norm": 1.2499898672103882,
|
| 631 |
+
"learning_rate": 2.8514533018536286e-05,
|
| 632 |
+
"loss": 0.6118,
|
| 633 |
+
"step": 445
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.5656819610307983,
|
| 637 |
+
"grad_norm": 1.2199169397354126,
|
| 638 |
+
"learning_rate": 2.8469133651955322e-05,
|
| 639 |
+
"loss": 0.6433,
|
| 640 |
+
"step": 450
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.5719673161533627,
|
| 644 |
+
"grad_norm": 1.2673394680023193,
|
| 645 |
+
"learning_rate": 2.8423088197515486e-05,
|
| 646 |
+
"loss": 0.6588,
|
| 647 |
+
"step": 455
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.578252671275927,
|
| 651 |
+
"grad_norm": 0.9634625315666199,
|
| 652 |
+
"learning_rate": 2.8376398863926694e-05,
|
| 653 |
+
"loss": 0.6601,
|
| 654 |
+
"step": 460
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.5845380263984915,
|
| 658 |
+
"grad_norm": 1.3017187118530273,
|
| 659 |
+
"learning_rate": 2.8329067890784482e-05,
|
| 660 |
+
"loss": 0.6692,
|
| 661 |
+
"step": 465
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.590823381521056,
|
| 665 |
+
"grad_norm": 1.0561813116073608,
|
| 666 |
+
"learning_rate": 2.8281097548462572e-05,
|
| 667 |
+
"loss": 0.5724,
|
| 668 |
+
"step": 470
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.5971087366436204,
|
| 672 |
+
"grad_norm": 1.4166231155395508,
|
| 673 |
+
"learning_rate": 2.823249013800396e-05,
|
| 674 |
+
"loss": 0.6185,
|
| 675 |
+
"step": 475
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.6033940917661847,
|
| 679 |
+
"grad_norm": 1.1313611268997192,
|
| 680 |
+
"learning_rate": 2.8183247991010568e-05,
|
| 681 |
+
"loss": 0.616,
|
| 682 |
+
"step": 480
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.6096794468887492,
|
| 686 |
+
"grad_norm": 1.2021806240081787,
|
| 687 |
+
"learning_rate": 2.8133373469531362e-05,
|
| 688 |
+
"loss": 0.6485,
|
| 689 |
+
"step": 485
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.6159648020113137,
|
| 693 |
+
"grad_norm": 1.1013792753219604,
|
| 694 |
+
"learning_rate": 2.8082868965949083e-05,
|
| 695 |
+
"loss": 0.5616,
|
| 696 |
+
"step": 490
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.6222501571338781,
|
| 700 |
+
"grad_norm": 1.1561661958694458,
|
| 701 |
+
"learning_rate": 2.8031736902865456e-05,
|
| 702 |
+
"loss": 0.5722,
|
| 703 |
+
"step": 495
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.6285355122564424,
|
| 707 |
+
"grad_norm": 1.064666986465454,
|
| 708 |
+
"learning_rate": 2.7979979732985025e-05,
|
| 709 |
+
"loss": 0.6041,
|
| 710 |
+
"step": 500
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.6348208673790069,
|
| 714 |
+
"grad_norm": 1.0838035345077515,
|
| 715 |
+
"learning_rate": 2.792759993899746e-05,
|
| 716 |
+
"loss": 0.5715,
|
| 717 |
+
"step": 505
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.6411062225015713,
|
| 721 |
+
"grad_norm": 1.1847580671310425,
|
| 722 |
+
"learning_rate": 2.7874600033458495e-05,
|
| 723 |
+
"loss": 0.5643,
|
| 724 |
+
"step": 510
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.6473915776241358,
|
| 728 |
+
"grad_norm": 1.133327603340149,
|
| 729 |
+
"learning_rate": 2.7820982558669394e-05,
|
| 730 |
+
"loss": 0.5965,
|
| 731 |
+
"step": 515
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.6536769327467001,
|
| 735 |
+
"grad_norm": 1.0827841758728027,
|
| 736 |
+
"learning_rate": 2.7766750086554997e-05,
|
| 737 |
+
"loss": 0.5501,
|
| 738 |
+
"step": 520
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.6599622878692646,
|
| 742 |
+
"grad_norm": 1.0360702276229858,
|
| 743 |
+
"learning_rate": 2.7711905218540367e-05,
|
| 744 |
+
"loss": 0.6193,
|
| 745 |
+
"step": 525
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.666247642991829,
|
| 749 |
+
"grad_norm": 1.2351385354995728,
|
| 750 |
+
"learning_rate": 2.7656450585425983e-05,
|
| 751 |
+
"loss": 0.4863,
|
| 752 |
+
"step": 530
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.6725329981143935,
|
| 756 |
+
"grad_norm": 1.2169417142868042,
|
| 757 |
+
"learning_rate": 2.7600388847261576e-05,
|
| 758 |
+
"loss": 0.5427,
|
| 759 |
+
"step": 535
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.6788183532369579,
|
| 763 |
+
"grad_norm": 1.07058846950531,
|
| 764 |
+
"learning_rate": 2.754372269321848e-05,
|
| 765 |
+
"loss": 0.5881,
|
| 766 |
+
"step": 540
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.6851037083595223,
|
| 770 |
+
"grad_norm": 1.132266640663147,
|
| 771 |
+
"learning_rate": 2.7486454841460706e-05,
|
| 772 |
+
"loss": 0.5586,
|
| 773 |
+
"step": 545
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.6913890634820867,
|
| 777 |
+
"grad_norm": 1.1541614532470703,
|
| 778 |
+
"learning_rate": 2.74285880390145e-05,
|
| 779 |
+
"loss": 0.589,
|
| 780 |
+
"step": 550
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.6976744186046512,
|
| 784 |
+
"grad_norm": 1.2179677486419678,
|
| 785 |
+
"learning_rate": 2.7370125061636605e-05,
|
| 786 |
+
"loss": 0.5686,
|
| 787 |
+
"step": 555
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.7039597737272156,
|
| 791 |
+
"grad_norm": 1.0758997201919556,
|
| 792 |
+
"learning_rate": 2.7311068713681087e-05,
|
| 793 |
+
"loss": 0.5152,
|
| 794 |
+
"step": 560
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.71024512884978,
|
| 798 |
+
"grad_norm": 1.1887001991271973,
|
| 799 |
+
"learning_rate": 2.7251421827964852e-05,
|
| 800 |
+
"loss": 0.4797,
|
| 801 |
+
"step": 565
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.7165304839723444,
|
| 805 |
+
"grad_norm": 1.213713526725769,
|
| 806 |
+
"learning_rate": 2.719118726563173e-05,
|
| 807 |
+
"loss": 0.5055,
|
| 808 |
+
"step": 570
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.7228158390949089,
|
| 812 |
+
"grad_norm": 1.059728980064392,
|
| 813 |
+
"learning_rate": 2.713036791601525e-05,
|
| 814 |
+
"loss": 0.4876,
|
| 815 |
+
"step": 575
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.7291011942174733,
|
| 819 |
+
"grad_norm": 1.1815284490585327,
|
| 820 |
+
"learning_rate": 2.7068966696500025e-05,
|
| 821 |
+
"loss": 0.55,
|
| 822 |
+
"step": 580
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.7353865493400377,
|
| 826 |
+
"grad_norm": 1.1927337646484375,
|
| 827 |
+
"learning_rate": 2.700698655238184e-05,
|
| 828 |
+
"loss": 0.4745,
|
| 829 |
+
"step": 585
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.7416719044626021,
|
| 833 |
+
"grad_norm": 1.2041906118392944,
|
| 834 |
+
"learning_rate": 2.6944430456726336e-05,
|
| 835 |
+
"loss": 0.5094,
|
| 836 |
+
"step": 590
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.7479572595851666,
|
| 840 |
+
"grad_norm": 1.0723963975906372,
|
| 841 |
+
"learning_rate": 2.6881301410226434e-05,
|
| 842 |
+
"loss": 0.5256,
|
| 843 |
+
"step": 595
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.754242614707731,
|
| 847 |
+
"grad_norm": 1.2735044956207275,
|
| 848 |
+
"learning_rate": 2.681760244105837e-05,
|
| 849 |
+
"loss": 0.4944,
|
| 850 |
+
"step": 600
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.7605279698302954,
|
| 854 |
+
"grad_norm": 1.129440188407898,
|
| 855 |
+
"learning_rate": 2.6753336604736457e-05,
|
| 856 |
+
"loss": 0.5351,
|
| 857 |
+
"step": 605
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.7668133249528598,
|
| 861 |
+
"grad_norm": 1.135921597480774,
|
| 862 |
+
"learning_rate": 2.6688506983966496e-05,
|
| 863 |
+
"loss": 0.4379,
|
| 864 |
+
"step": 610
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.7730986800754243,
|
| 868 |
+
"grad_norm": 1.0958871841430664,
|
| 869 |
+
"learning_rate": 2.6623116688497944e-05,
|
| 870 |
+
"loss": 0.5325,
|
| 871 |
+
"step": 615
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.7793840351979887,
|
| 875 |
+
"grad_norm": 1.1030149459838867,
|
| 876 |
+
"learning_rate": 2.6557168854974697e-05,
|
| 877 |
+
"loss": 0.4492,
|
| 878 |
+
"step": 620
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.7856693903205532,
|
| 882 |
+
"grad_norm": 1.3361397981643677,
|
| 883 |
+
"learning_rate": 2.649066664678467e-05,
|
| 884 |
+
"loss": 0.4288,
|
| 885 |
+
"step": 625
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.7919547454431175,
|
| 889 |
+
"grad_norm": 1.2488876581192017,
|
| 890 |
+
"learning_rate": 2.6423613253908037e-05,
|
| 891 |
+
"loss": 0.507,
|
| 892 |
+
"step": 630
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.798240100565682,
|
| 896 |
+
"grad_norm": 1.19242525100708,
|
| 897 |
+
"learning_rate": 2.6356011892764212e-05,
|
| 898 |
+
"loss": 0.4365,
|
| 899 |
+
"step": 635
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.8045254556882464,
|
| 903 |
+
"grad_norm": 1.2375750541687012,
|
| 904 |
+
"learning_rate": 2.628786580605758e-05,
|
| 905 |
+
"loss": 0.4741,
|
| 906 |
+
"step": 640
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.8108108108108109,
|
| 910 |
+
"grad_norm": 1.4009876251220703,
|
| 911 |
+
"learning_rate": 2.6219178262621933e-05,
|
| 912 |
+
"loss": 0.4255,
|
| 913 |
+
"step": 645
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.8170961659333752,
|
| 917 |
+
"grad_norm": 1.1205885410308838,
|
| 918 |
+
"learning_rate": 2.614995255726367e-05,
|
| 919 |
+
"loss": 0.4667,
|
| 920 |
+
"step": 650
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.8233815210559396,
|
| 924 |
+
"grad_norm": 1.3346655368804932,
|
| 925 |
+
"learning_rate": 2.6080192010603785e-05,
|
| 926 |
+
"loss": 0.4073,
|
| 927 |
+
"step": 655
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.8296668761785041,
|
| 931 |
+
"grad_norm": 1.2312875986099243,
|
| 932 |
+
"learning_rate": 2.600989996891853e-05,
|
| 933 |
+
"loss": 0.4446,
|
| 934 |
+
"step": 660
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.8359522313010685,
|
| 938 |
+
"grad_norm": 1.2087233066558838,
|
| 939 |
+
"learning_rate": 2.5939079803978943e-05,
|
| 940 |
+
"loss": 0.4324,
|
| 941 |
+
"step": 665
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.8422375864236329,
|
| 945 |
+
"grad_norm": 1.1934200525283813,
|
| 946 |
+
"learning_rate": 2.586773491288909e-05,
|
| 947 |
+
"loss": 0.483,
|
| 948 |
+
"step": 670
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.8485229415461973,
|
| 952 |
+
"grad_norm": 1.2474349737167358,
|
| 953 |
+
"learning_rate": 2.5795868717923128e-05,
|
| 954 |
+
"loss": 0.4203,
|
| 955 |
+
"step": 675
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.8548082966687618,
|
| 959 |
+
"grad_norm": 1.4342896938323975,
|
| 960 |
+
"learning_rate": 2.5723484666361116e-05,
|
| 961 |
+
"loss": 0.4106,
|
| 962 |
+
"step": 680
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.8610936517913262,
|
| 966 |
+
"grad_norm": 1.1344951391220093,
|
| 967 |
+
"learning_rate": 2.5650586230323705e-05,
|
| 968 |
+
"loss": 0.4249,
|
| 969 |
+
"step": 685
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.8673790069138906,
|
| 973 |
+
"grad_norm": 1.3197280168533325,
|
| 974 |
+
"learning_rate": 2.5577176906605534e-05,
|
| 975 |
+
"loss": 0.405,
|
| 976 |
+
"step": 690
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.873664362036455,
|
| 980 |
+
"grad_norm": 1.1772801876068115,
|
| 981 |
+
"learning_rate": 2.5503260216507528e-05,
|
| 982 |
+
"loss": 0.4642,
|
| 983 |
+
"step": 695
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.8799497171590195,
|
| 987 |
+
"grad_norm": 1.3981150388717651,
|
| 988 |
+
"learning_rate": 2.5428839705667983e-05,
|
| 989 |
+
"loss": 0.4125,
|
| 990 |
+
"step": 700
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.8862350722815839,
|
| 994 |
+
"grad_norm": 1.2730729579925537,
|
| 995 |
+
"learning_rate": 2.5353918943892473e-05,
|
| 996 |
+
"loss": 0.4177,
|
| 997 |
+
"step": 705
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.8925204274041484,
|
| 1001 |
+
"grad_norm": 1.2144984006881714,
|
| 1002 |
+
"learning_rate": 2.527850152498264e-05,
|
| 1003 |
+
"loss": 0.4273,
|
| 1004 |
+
"step": 710
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.8988057825267127,
|
| 1008 |
+
"grad_norm": 1.2719829082489014,
|
| 1009 |
+
"learning_rate": 2.520259106656379e-05,
|
| 1010 |
+
"loss": 0.4004,
|
| 1011 |
+
"step": 715
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.9050911376492772,
|
| 1015 |
+
"grad_norm": 0.9871245622634888,
|
| 1016 |
+
"learning_rate": 2.5126191209911358e-05,
|
| 1017 |
+
"loss": 0.4118,
|
| 1018 |
+
"step": 720
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.9113764927718416,
|
| 1022 |
+
"grad_norm": 1.2270817756652832,
|
| 1023 |
+
"learning_rate": 2.5049305619776255e-05,
|
| 1024 |
+
"loss": 0.4077,
|
| 1025 |
+
"step": 725
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.9176618478944061,
|
| 1029 |
+
"grad_norm": 1.0903793573379517,
|
| 1030 |
+
"learning_rate": 2.4971937984209064e-05,
|
| 1031 |
+
"loss": 0.3726,
|
| 1032 |
+
"step": 730
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.9239472030169704,
|
| 1036 |
+
"grad_norm": 1.257041096687317,
|
| 1037 |
+
"learning_rate": 2.489409201438316e-05,
|
| 1038 |
+
"loss": 0.3828,
|
| 1039 |
+
"step": 735
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.9302325581395349,
|
| 1043 |
+
"grad_norm": 1.1131738424301147,
|
| 1044 |
+
"learning_rate": 2.4815771444416647e-05,
|
| 1045 |
+
"loss": 0.3798,
|
| 1046 |
+
"step": 740
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.9365179132620993,
|
| 1050 |
+
"grad_norm": 1.2549203634262085,
|
| 1051 |
+
"learning_rate": 2.4736980031193278e-05,
|
| 1052 |
+
"loss": 0.3659,
|
| 1053 |
+
"step": 745
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.9428032683846638,
|
| 1057 |
+
"grad_norm": 1.0018150806427002,
|
| 1058 |
+
"learning_rate": 2.4657721554182233e-05,
|
| 1059 |
+
"loss": 0.3886,
|
| 1060 |
+
"step": 750
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.9490886235072281,
|
| 1064 |
+
"grad_norm": 1.1696054935455322,
|
| 1065 |
+
"learning_rate": 2.4577999815256816e-05,
|
| 1066 |
+
"loss": 0.368,
|
| 1067 |
+
"step": 755
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.9553739786297926,
|
| 1071 |
+
"grad_norm": 1.2519277334213257,
|
| 1072 |
+
"learning_rate": 2.4497818638512098e-05,
|
| 1073 |
+
"loss": 0.3593,
|
| 1074 |
+
"step": 760
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.961659333752357,
|
| 1078 |
+
"grad_norm": 1.091099500656128,
|
| 1079 |
+
"learning_rate": 2.441718187008148e-05,
|
| 1080 |
+
"loss": 0.3965,
|
| 1081 |
+
"step": 765
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.9679446888749215,
|
| 1085 |
+
"grad_norm": 1.1574701070785522,
|
| 1086 |
+
"learning_rate": 2.4336093377952196e-05,
|
| 1087 |
+
"loss": 0.3365,
|
| 1088 |
+
"step": 770
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.9742300439974858,
|
| 1092 |
+
"grad_norm": 1.0723313093185425,
|
| 1093 |
+
"learning_rate": 2.425455705177979e-05,
|
| 1094 |
+
"loss": 0.3808,
|
| 1095 |
+
"step": 775
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.9805153991200503,
|
| 1099 |
+
"grad_norm": 1.3618332147598267,
|
| 1100 |
+
"learning_rate": 2.4172576802701503e-05,
|
| 1101 |
+
"loss": 0.3326,
|
| 1102 |
+
"step": 780
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.9868007542426147,
|
| 1106 |
+
"grad_norm": 1.2843025922775269,
|
| 1107 |
+
"learning_rate": 2.409015656314871e-05,
|
| 1108 |
+
"loss": 0.3294,
|
| 1109 |
+
"step": 785
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.9930861093651792,
|
| 1113 |
+
"grad_norm": 1.2292474508285522,
|
| 1114 |
+
"learning_rate": 2.400730028665824e-05,
|
| 1115 |
+
"loss": 0.3533,
|
| 1116 |
+
"step": 790
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.9993714644877436,
|
| 1120 |
+
"grad_norm": 1.1691044569015503,
|
| 1121 |
+
"learning_rate": 2.3924011947682772e-05,
|
| 1122 |
+
"loss": 0.3296,
|
| 1123 |
+
"step": 795
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 1.0050282840980516,
|
| 1127 |
+
"grad_norm": 1.1004573106765747,
|
| 1128 |
+
"learning_rate": 2.3840295541400172e-05,
|
| 1129 |
+
"loss": 0.2928,
|
| 1130 |
+
"step": 800
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 1.011313639220616,
|
| 1134 |
+
"grad_norm": 1.136668086051941,
|
| 1135 |
+
"learning_rate": 2.375615508352185e-05,
|
| 1136 |
+
"loss": 0.2747,
|
| 1137 |
+
"step": 805
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 1.0175989943431805,
|
| 1141 |
+
"grad_norm": 1.6121195554733276,
|
| 1142 |
+
"learning_rate": 2.3671594610100128e-05,
|
| 1143 |
+
"loss": 0.3122,
|
| 1144 |
+
"step": 810
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 1.0238843494657448,
|
| 1148 |
+
"grad_norm": 1.2607626914978027,
|
| 1149 |
+
"learning_rate": 2.358661817733467e-05,
|
| 1150 |
+
"loss": 0.3033,
|
| 1151 |
+
"step": 815
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.0301697045883091,
|
| 1155 |
+
"grad_norm": 1.118066668510437,
|
| 1156 |
+
"learning_rate": 2.350122986137787e-05,
|
| 1157 |
+
"loss": 0.2996,
|
| 1158 |
+
"step": 820
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 1.0364550597108737,
|
| 1162 |
+
"grad_norm": 1.293691873550415,
|
| 1163 |
+
"learning_rate": 2.3415433758139363e-05,
|
| 1164 |
+
"loss": 0.2756,
|
| 1165 |
+
"step": 825
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 1.042740414833438,
|
| 1169 |
+
"grad_norm": 1.1096911430358887,
|
| 1170 |
+
"learning_rate": 2.3329233983089526e-05,
|
| 1171 |
+
"loss": 0.2791,
|
| 1172 |
+
"step": 830
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 1.0490257699560026,
|
| 1176 |
+
"grad_norm": 1.244630217552185,
|
| 1177 |
+
"learning_rate": 2.324263467106209e-05,
|
| 1178 |
+
"loss": 0.3114,
|
| 1179 |
+
"step": 835
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 1.055311125078567,
|
| 1183 |
+
"grad_norm": 1.142496109008789,
|
| 1184 |
+
"learning_rate": 2.315563997605579e-05,
|
| 1185 |
+
"loss": 0.309,
|
| 1186 |
+
"step": 840
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 1.0615964802011313,
|
| 1190 |
+
"grad_norm": 1.1298565864562988,
|
| 1191 |
+
"learning_rate": 2.3068254071035088e-05,
|
| 1192 |
+
"loss": 0.3075,
|
| 1193 |
+
"step": 845
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 1.0678818353236958,
|
| 1197 |
+
"grad_norm": 1.133744478225708,
|
| 1198 |
+
"learning_rate": 2.298048114773005e-05,
|
| 1199 |
+
"loss": 0.2683,
|
| 1200 |
+
"step": 850
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 1.0741671904462602,
|
| 1204 |
+
"grad_norm": 1.1544510126113892,
|
| 1205 |
+
"learning_rate": 2.289232541643522e-05,
|
| 1206 |
+
"loss": 0.2964,
|
| 1207 |
+
"step": 855
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 1.0804525455688245,
|
| 1211 |
+
"grad_norm": 1.2098685503005981,
|
| 1212 |
+
"learning_rate": 2.2803791105807702e-05,
|
| 1213 |
+
"loss": 0.2771,
|
| 1214 |
+
"step": 860
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 1.086737900691389,
|
| 1218 |
+
"grad_norm": 1.1151440143585205,
|
| 1219 |
+
"learning_rate": 2.2714882462664306e-05,
|
| 1220 |
+
"loss": 0.2517,
|
| 1221 |
+
"step": 865
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 1.0930232558139534,
|
| 1225 |
+
"grad_norm": 1.1082156896591187,
|
| 1226 |
+
"learning_rate": 2.262560375177783e-05,
|
| 1227 |
+
"loss": 0.2758,
|
| 1228 |
+
"step": 870
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 1.099308610936518,
|
| 1232 |
+
"grad_norm": 1.3181571960449219,
|
| 1233 |
+
"learning_rate": 2.2535959255672515e-05,
|
| 1234 |
+
"loss": 0.2911,
|
| 1235 |
+
"step": 875
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 1.1055939660590823,
|
| 1239 |
+
"grad_norm": 1.2665706872940063,
|
| 1240 |
+
"learning_rate": 2.244595327441857e-05,
|
| 1241 |
+
"loss": 0.2829,
|
| 1242 |
+
"step": 880
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 1.1118793211816467,
|
| 1246 |
+
"grad_norm": 1.1373525857925415,
|
| 1247 |
+
"learning_rate": 2.235559012542595e-05,
|
| 1248 |
+
"loss": 0.2325,
|
| 1249 |
+
"step": 885
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 1.1181646763042112,
|
| 1253 |
+
"grad_norm": 1.3746609687805176,
|
| 1254 |
+
"learning_rate": 2.2264874143237252e-05,
|
| 1255 |
+
"loss": 0.2622,
|
| 1256 |
+
"step": 890
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 1.1244500314267756,
|
| 1260 |
+
"grad_norm": 1.2727433443069458,
|
| 1261 |
+
"learning_rate": 2.2173809679319776e-05,
|
| 1262 |
+
"loss": 0.2862,
|
| 1263 |
+
"step": 895
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 1.1307353865493401,
|
| 1267 |
+
"grad_norm": 1.1987885236740112,
|
| 1268 |
+
"learning_rate": 2.2082401101856806e-05,
|
| 1269 |
+
"loss": 0.2342,
|
| 1270 |
+
"step": 900
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 1.1370207416719045,
|
| 1274 |
+
"grad_norm": 1.2422605752944946,
|
| 1275 |
+
"learning_rate": 2.1990652795538085e-05,
|
| 1276 |
+
"loss": 0.3043,
|
| 1277 |
+
"step": 905
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 1.1433060967944688,
|
| 1281 |
+
"grad_norm": 1.1664384603500366,
|
| 1282 |
+
"learning_rate": 2.1898569161349472e-05,
|
| 1283 |
+
"loss": 0.2763,
|
| 1284 |
+
"step": 910
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 1.1495914519170334,
|
| 1288 |
+
"grad_norm": 1.1260954141616821,
|
| 1289 |
+
"learning_rate": 2.1806154616361846e-05,
|
| 1290 |
+
"loss": 0.2661,
|
| 1291 |
+
"step": 915
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 1.1558768070395977,
|
| 1295 |
+
"grad_norm": 1.3076298236846924,
|
| 1296 |
+
"learning_rate": 2.1713413593519235e-05,
|
| 1297 |
+
"loss": 0.227,
|
| 1298 |
+
"step": 920
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 1.1621621621621623,
|
| 1302 |
+
"grad_norm": 1.2505238056182861,
|
| 1303 |
+
"learning_rate": 2.162035054142616e-05,
|
| 1304 |
+
"loss": 0.2334,
|
| 1305 |
+
"step": 925
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 1.1684475172847266,
|
| 1309 |
+
"grad_norm": 0.9663398265838623,
|
| 1310 |
+
"learning_rate": 2.152696992413425e-05,
|
| 1311 |
+
"loss": 0.2436,
|
| 1312 |
+
"step": 930
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 1.174732872407291,
|
| 1316 |
+
"grad_norm": 1.2054481506347656,
|
| 1317 |
+
"learning_rate": 2.143327622092812e-05,
|
| 1318 |
+
"loss": 0.2467,
|
| 1319 |
+
"step": 935
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 1.1810182275298555,
|
| 1323 |
+
"grad_norm": 0.9899621605873108,
|
| 1324 |
+
"learning_rate": 2.1339273926110493e-05,
|
| 1325 |
+
"loss": 0.2669,
|
| 1326 |
+
"step": 940
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 1.1873035826524199,
|
| 1330 |
+
"grad_norm": 1.119245171546936,
|
| 1331 |
+
"learning_rate": 2.124496754878663e-05,
|
| 1332 |
+
"loss": 0.2249,
|
| 1333 |
+
"step": 945
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 1.1935889377749842,
|
| 1337 |
+
"grad_norm": 1.1755388975143433,
|
| 1338 |
+
"learning_rate": 2.1150361612648028e-05,
|
| 1339 |
+
"loss": 0.2645,
|
| 1340 |
+
"step": 950
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 1.1998742928975488,
|
| 1344 |
+
"grad_norm": 1.0573670864105225,
|
| 1345 |
+
"learning_rate": 2.1055460655755434e-05,
|
| 1346 |
+
"loss": 0.2522,
|
| 1347 |
+
"step": 955
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 1.206159648020113,
|
| 1351 |
+
"grad_norm": 1.0916844606399536,
|
| 1352 |
+
"learning_rate": 2.0960269230321162e-05,
|
| 1353 |
+
"loss": 0.2075,
|
| 1354 |
+
"step": 960
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 1.2124450031426774,
|
| 1358 |
+
"grad_norm": 1.0620564222335815,
|
| 1359 |
+
"learning_rate": 2.086479190249073e-05,
|
| 1360 |
+
"loss": 0.2159,
|
| 1361 |
+
"step": 965
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 1.218730358265242,
|
| 1365 |
+
"grad_norm": 1.1370034217834473,
|
| 1366 |
+
"learning_rate": 2.076903325212383e-05,
|
| 1367 |
+
"loss": 0.2264,
|
| 1368 |
+
"step": 970
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 1.2250157133878063,
|
| 1372 |
+
"grad_norm": 1.1833701133728027,
|
| 1373 |
+
"learning_rate": 2.0672997872574638e-05,
|
| 1374 |
+
"loss": 0.1951,
|
| 1375 |
+
"step": 975
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 1.231301068510371,
|
| 1379 |
+
"grad_norm": 1.1464062929153442,
|
| 1380 |
+
"learning_rate": 2.0576690370471498e-05,
|
| 1381 |
+
"loss": 0.2292,
|
| 1382 |
+
"step": 980
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 1.2375864236329353,
|
| 1386 |
+
"grad_norm": 1.0714120864868164,
|
| 1387 |
+
"learning_rate": 2.0480115365495928e-05,
|
| 1388 |
+
"loss": 0.2429,
|
| 1389 |
+
"step": 985
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 1.2438717787554996,
|
| 1393 |
+
"grad_norm": 1.0614490509033203,
|
| 1394 |
+
"learning_rate": 2.0383277490161028e-05,
|
| 1395 |
+
"loss": 0.2153,
|
| 1396 |
+
"step": 990
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 1.2501571338780642,
|
| 1400 |
+
"grad_norm": 1.2731209993362427,
|
| 1401 |
+
"learning_rate": 2.0286181389589298e-05,
|
| 1402 |
+
"loss": 0.2167,
|
| 1403 |
+
"step": 995
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 1.2564424890006285,
|
| 1407 |
+
"grad_norm": 1.0006394386291504,
|
| 1408 |
+
"learning_rate": 2.0188831721289755e-05,
|
| 1409 |
+
"loss": 0.209,
|
| 1410 |
+
"step": 1000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 1.262727844123193,
|
| 1414 |
+
"grad_norm": 0.9272480010986328,
|
| 1415 |
+
"learning_rate": 2.00912331549346e-05,
|
| 1416 |
+
"loss": 0.2494,
|
| 1417 |
+
"step": 1005
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 1.2690131992457574,
|
| 1421 |
+
"grad_norm": 1.223780870437622,
|
| 1422 |
+
"learning_rate": 1.9993390372135147e-05,
|
| 1423 |
+
"loss": 0.2501,
|
| 1424 |
+
"step": 1010
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 1.2752985543683217,
|
| 1428 |
+
"grad_norm": 1.251940369606018,
|
| 1429 |
+
"learning_rate": 1.9895308066217337e-05,
|
| 1430 |
+
"loss": 0.2089,
|
| 1431 |
+
"step": 1015
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 1.2815839094908863,
|
| 1435 |
+
"grad_norm": 1.0528546571731567,
|
| 1436 |
+
"learning_rate": 1.979699094199652e-05,
|
| 1437 |
+
"loss": 0.2217,
|
| 1438 |
+
"step": 1020
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 1.2878692646134506,
|
| 1442 |
+
"grad_norm": 0.9511886239051819,
|
| 1443 |
+
"learning_rate": 1.969844371555185e-05,
|
| 1444 |
+
"loss": 0.2092,
|
| 1445 |
+
"step": 1025
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 1.2941546197360152,
|
| 1449 |
+
"grad_norm": 1.1945406198501587,
|
| 1450 |
+
"learning_rate": 1.9599671114000015e-05,
|
| 1451 |
+
"loss": 0.2357,
|
| 1452 |
+
"step": 1030
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 1.3004399748585795,
|
| 1456 |
+
"grad_norm": 1.2407405376434326,
|
| 1457 |
+
"learning_rate": 1.950067787526851e-05,
|
| 1458 |
+
"loss": 0.185,
|
| 1459 |
+
"step": 1035
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 1.3067253299811439,
|
| 1463 |
+
"grad_norm": 1.1109362840652466,
|
| 1464 |
+
"learning_rate": 1.9401468747868367e-05,
|
| 1465 |
+
"loss": 0.1922,
|
| 1466 |
+
"step": 1040
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 1.3130106851037084,
|
| 1470 |
+
"grad_norm": 0.983195960521698,
|
| 1471 |
+
"learning_rate": 1.9302048490666356e-05,
|
| 1472 |
+
"loss": 0.1859,
|
| 1473 |
+
"step": 1045
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 1.3192960402262728,
|
| 1477 |
+
"grad_norm": 1.2260570526123047,
|
| 1478 |
+
"learning_rate": 1.9202421872656743e-05,
|
| 1479 |
+
"loss": 0.2126,
|
| 1480 |
+
"step": 1050
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 1.3255813953488373,
|
| 1484 |
+
"grad_norm": 1.0699470043182373,
|
| 1485 |
+
"learning_rate": 1.9102593672732516e-05,
|
| 1486 |
+
"loss": 0.1961,
|
| 1487 |
+
"step": 1055
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 1.3318667504714017,
|
| 1491 |
+
"grad_norm": 1.1135671138763428,
|
| 1492 |
+
"learning_rate": 1.9002568679456145e-05,
|
| 1493 |
+
"loss": 0.2306,
|
| 1494 |
+
"step": 1060
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 1.338152105593966,
|
| 1498 |
+
"grad_norm": 1.08716881275177,
|
| 1499 |
+
"learning_rate": 1.8902351690829897e-05,
|
| 1500 |
+
"loss": 0.2106,
|
| 1501 |
+
"step": 1065
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 1.3444374607165304,
|
| 1505 |
+
"grad_norm": 1.2198331356048584,
|
| 1506 |
+
"learning_rate": 1.8801947514065667e-05,
|
| 1507 |
+
"loss": 0.217,
|
| 1508 |
+
"step": 1070
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 1.350722815839095,
|
| 1512 |
+
"grad_norm": 1.0800694227218628,
|
| 1513 |
+
"learning_rate": 1.87013609653544e-05,
|
| 1514 |
+
"loss": 0.2222,
|
| 1515 |
+
"step": 1075
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 1.3570081709616593,
|
| 1519 |
+
"grad_norm": 1.2261335849761963,
|
| 1520 |
+
"learning_rate": 1.860059686963509e-05,
|
| 1521 |
+
"loss": 0.2137,
|
| 1522 |
+
"step": 1080
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 1.3632935260842238,
|
| 1526 |
+
"grad_norm": 0.9979224801063538,
|
| 1527 |
+
"learning_rate": 1.849966006036327e-05,
|
| 1528 |
+
"loss": 0.2219,
|
| 1529 |
+
"step": 1085
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 1.3695788812067882,
|
| 1533 |
+
"grad_norm": 1.1516265869140625,
|
| 1534 |
+
"learning_rate": 1.8398555379279233e-05,
|
| 1535 |
+
"loss": 0.2128,
|
| 1536 |
+
"step": 1090
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 1.3758642363293525,
|
| 1540 |
+
"grad_norm": 1.0832141637802124,
|
| 1541 |
+
"learning_rate": 1.8297287676175742e-05,
|
| 1542 |
+
"loss": 0.2097,
|
| 1543 |
+
"step": 1095
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 1.382149591451917,
|
| 1547 |
+
"grad_norm": 1.0212297439575195,
|
| 1548 |
+
"learning_rate": 1.8195861808665404e-05,
|
| 1549 |
+
"loss": 0.1978,
|
| 1550 |
+
"step": 1100
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 1.3884349465744814,
|
| 1554 |
+
"grad_norm": 1.1129353046417236,
|
| 1555 |
+
"learning_rate": 1.8094282641947664e-05,
|
| 1556 |
+
"loss": 0.1682,
|
| 1557 |
+
"step": 1105
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 1.394720301697046,
|
| 1561 |
+
"grad_norm": 1.1344804763793945,
|
| 1562 |
+
"learning_rate": 1.799255504857543e-05,
|
| 1563 |
+
"loss": 0.1794,
|
| 1564 |
+
"step": 1110
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 1.4010056568196103,
|
| 1568 |
+
"grad_norm": 1.0280684232711792,
|
| 1569 |
+
"learning_rate": 1.789068390822135e-05,
|
| 1570 |
+
"loss": 0.1879,
|
| 1571 |
+
"step": 1115
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 1.4072910119421747,
|
| 1575 |
+
"grad_norm": 1.0350013971328735,
|
| 1576 |
+
"learning_rate": 1.778867410744372e-05,
|
| 1577 |
+
"loss": 0.1791,
|
| 1578 |
+
"step": 1120
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 1.4135763670647392,
|
| 1582 |
+
"grad_norm": 1.1130858659744263,
|
| 1583 |
+
"learning_rate": 1.768653053945213e-05,
|
| 1584 |
+
"loss": 0.1724,
|
| 1585 |
+
"step": 1125
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 1.4198617221873036,
|
| 1589 |
+
"grad_norm": 1.1738640069961548,
|
| 1590 |
+
"learning_rate": 1.758425810387269e-05,
|
| 1591 |
+
"loss": 0.1813,
|
| 1592 |
+
"step": 1130
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 1.4261470773098681,
|
| 1596 |
+
"grad_norm": 1.099075198173523,
|
| 1597 |
+
"learning_rate": 1.7481861706513067e-05,
|
| 1598 |
+
"loss": 0.1931,
|
| 1599 |
+
"step": 1135
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 1.4324324324324325,
|
| 1603 |
+
"grad_norm": 1.0371235609054565,
|
| 1604 |
+
"learning_rate": 1.737934625912711e-05,
|
| 1605 |
+
"loss": 0.1658,
|
| 1606 |
+
"step": 1140
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 1.4387177875549968,
|
| 1610 |
+
"grad_norm": 1.024571180343628,
|
| 1611 |
+
"learning_rate": 1.7276716679179268e-05,
|
| 1612 |
+
"loss": 0.1722,
|
| 1613 |
+
"step": 1145
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 1.4450031426775614,
|
| 1617 |
+
"grad_norm": 1.1209981441497803,
|
| 1618 |
+
"learning_rate": 1.7173977889608698e-05,
|
| 1619 |
+
"loss": 0.1877,
|
| 1620 |
+
"step": 1150
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 1.4512884978001257,
|
| 1624 |
+
"grad_norm": 1.1291701793670654,
|
| 1625 |
+
"learning_rate": 1.707113481859315e-05,
|
| 1626 |
+
"loss": 0.1824,
|
| 1627 |
+
"step": 1155
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 1.4575738529226903,
|
| 1631 |
+
"grad_norm": 1.0689659118652344,
|
| 1632 |
+
"learning_rate": 1.6968192399312527e-05,
|
| 1633 |
+
"loss": 0.1817,
|
| 1634 |
+
"step": 1160
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 1.4638592080452546,
|
| 1638 |
+
"grad_norm": 1.0945924520492554,
|
| 1639 |
+
"learning_rate": 1.686515556971228e-05,
|
| 1640 |
+
"loss": 0.1644,
|
| 1641 |
+
"step": 1165
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 1.470144563167819,
|
| 1645 |
+
"grad_norm": 1.1064441204071045,
|
| 1646 |
+
"learning_rate": 1.6762029272266536e-05,
|
| 1647 |
+
"loss": 0.1893,
|
| 1648 |
+
"step": 1170
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 1.4764299182903833,
|
| 1652 |
+
"grad_norm": 1.2518751621246338,
|
| 1653 |
+
"learning_rate": 1.6658818453741028e-05,
|
| 1654 |
+
"loss": 0.1877,
|
| 1655 |
+
"step": 1175
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 1.4827152734129478,
|
| 1659 |
+
"grad_norm": 1.0318760871887207,
|
| 1660 |
+
"learning_rate": 1.6555528064955793e-05,
|
| 1661 |
+
"loss": 0.17,
|
| 1662 |
+
"step": 1180
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 1.4890006285355122,
|
| 1666 |
+
"grad_norm": 1.0516771078109741,
|
| 1667 |
+
"learning_rate": 1.6452163060547687e-05,
|
| 1668 |
+
"loss": 0.1809,
|
| 1669 |
+
"step": 1185
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 1.4952859836580767,
|
| 1673 |
+
"grad_norm": 1.2100393772125244,
|
| 1674 |
+
"learning_rate": 1.634872839873275e-05,
|
| 1675 |
+
"loss": 0.1724,
|
| 1676 |
+
"step": 1190
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 1.501571338780641,
|
| 1680 |
+
"grad_norm": 0.9679239988327026,
|
| 1681 |
+
"learning_rate": 1.624522904106833e-05,
|
| 1682 |
+
"loss": 0.1462,
|
| 1683 |
+
"step": 1195
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 1.5078566939032054,
|
| 1687 |
+
"grad_norm": 1.087494969367981,
|
| 1688 |
+
"learning_rate": 1.6141669952215127e-05,
|
| 1689 |
+
"loss": 0.1568,
|
| 1690 |
+
"step": 1200
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 1.51414204902577,
|
| 1694 |
+
"grad_norm": 1.005810022354126,
|
| 1695 |
+
"learning_rate": 1.6038056099699015e-05,
|
| 1696 |
+
"loss": 0.1714,
|
| 1697 |
+
"step": 1205
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 1.5204274041483343,
|
| 1701 |
+
"grad_norm": 0.929412305355072,
|
| 1702 |
+
"learning_rate": 1.5934392453672784e-05,
|
| 1703 |
+
"loss": 0.1426,
|
| 1704 |
+
"step": 1210
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 1.526712759270899,
|
| 1708 |
+
"grad_norm": 0.9758539795875549,
|
| 1709 |
+
"learning_rate": 1.583068398667771e-05,
|
| 1710 |
+
"loss": 0.1863,
|
| 1711 |
+
"step": 1215
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 1.5329981143934632,
|
| 1715 |
+
"grad_norm": 1.0374505519866943,
|
| 1716 |
+
"learning_rate": 1.5726935673405046e-05,
|
| 1717 |
+
"loss": 0.1721,
|
| 1718 |
+
"step": 1220
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 1.5392834695160276,
|
| 1722 |
+
"grad_norm": 1.1279064416885376,
|
| 1723 |
+
"learning_rate": 1.5623152490457405e-05,
|
| 1724 |
+
"loss": 0.1453,
|
| 1725 |
+
"step": 1225
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 1.5455688246385921,
|
| 1729 |
+
"grad_norm": 1.0279524326324463,
|
| 1730 |
+
"learning_rate": 1.551933941611e-05,
|
| 1731 |
+
"loss": 0.1624,
|
| 1732 |
+
"step": 1230
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 1.5518541797611565,
|
| 1736 |
+
"grad_norm": 1.1977365016937256,
|
| 1737 |
+
"learning_rate": 1.5415501430071913e-05,
|
| 1738 |
+
"loss": 0.1533,
|
| 1739 |
+
"step": 1235
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 1.558139534883721,
|
| 1743 |
+
"grad_norm": 0.9948567748069763,
|
| 1744 |
+
"learning_rate": 1.5311643513247165e-05,
|
| 1745 |
+
"loss": 0.1494,
|
| 1746 |
+
"step": 1240
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 1.5644248900062854,
|
| 1750 |
+
"grad_norm": 0.9690392017364502,
|
| 1751 |
+
"learning_rate": 1.5207770647495829e-05,
|
| 1752 |
+
"loss": 0.1481,
|
| 1753 |
+
"step": 1245
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 1.5707102451288497,
|
| 1757 |
+
"grad_norm": 1.1922271251678467,
|
| 1758 |
+
"learning_rate": 1.5103887815395037e-05,
|
| 1759 |
+
"loss": 0.1591,
|
| 1760 |
+
"step": 1250
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 1.576995600251414,
|
| 1764 |
+
"grad_norm": 1.1286476850509644,
|
| 1765 |
+
"learning_rate": 1.5e-05,
|
| 1766 |
+
"loss": 0.1546,
|
| 1767 |
+
"step": 1255
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 1.5832809553739786,
|
| 1771 |
+
"grad_norm": 1.0081957578659058,
|
| 1772 |
+
"learning_rate": 1.4896112184604963e-05,
|
| 1773 |
+
"loss": 0.1398,
|
| 1774 |
+
"step": 1260
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 1.5895663104965432,
|
| 1778 |
+
"grad_norm": 0.9740825295448303,
|
| 1779 |
+
"learning_rate": 1.4792229352504179e-05,
|
| 1780 |
+
"loss": 0.1532,
|
| 1781 |
+
"step": 1265
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 1.5958516656191075,
|
| 1785 |
+
"grad_norm": 0.9399315118789673,
|
| 1786 |
+
"learning_rate": 1.4688356486752838e-05,
|
| 1787 |
+
"loss": 0.1466,
|
| 1788 |
+
"step": 1270
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 1.6021370207416719,
|
| 1792 |
+
"grad_norm": 1.1516889333724976,
|
| 1793 |
+
"learning_rate": 1.4584498569928087e-05,
|
| 1794 |
+
"loss": 0.1692,
|
| 1795 |
+
"step": 1275
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 1.6084223758642362,
|
| 1799 |
+
"grad_norm": 1.037536382675171,
|
| 1800 |
+
"learning_rate": 1.4480660583890003e-05,
|
| 1801 |
+
"loss": 0.1424,
|
| 1802 |
+
"step": 1280
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 1.6147077309868008,
|
| 1806 |
+
"grad_norm": 1.1316567659378052,
|
| 1807 |
+
"learning_rate": 1.4376847509542601e-05,
|
| 1808 |
+
"loss": 0.1423,
|
| 1809 |
+
"step": 1285
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 1.6209930861093653,
|
| 1813 |
+
"grad_norm": 0.8720541000366211,
|
| 1814 |
+
"learning_rate": 1.4273064326594958e-05,
|
| 1815 |
+
"loss": 0.144,
|
| 1816 |
+
"step": 1290
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 1.6272784412319297,
|
| 1820 |
+
"grad_norm": 1.1674761772155762,
|
| 1821 |
+
"learning_rate": 1.4169316013322294e-05,
|
| 1822 |
+
"loss": 0.1316,
|
| 1823 |
+
"step": 1295
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 1.633563796354494,
|
| 1827 |
+
"grad_norm": 1.0667779445648193,
|
| 1828 |
+
"learning_rate": 1.4065607546327219e-05,
|
| 1829 |
+
"loss": 0.1549,
|
| 1830 |
+
"step": 1300
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 1.6398491514770583,
|
| 1834 |
+
"grad_norm": 0.8888705372810364,
|
| 1835 |
+
"learning_rate": 1.3961943900300986e-05,
|
| 1836 |
+
"loss": 0.1483,
|
| 1837 |
+
"step": 1305
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 1.646134506599623,
|
| 1841 |
+
"grad_norm": 0.9815040230751038,
|
| 1842 |
+
"learning_rate": 1.3858330047784877e-05,
|
| 1843 |
+
"loss": 0.1373,
|
| 1844 |
+
"step": 1310
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 1.6524198617221875,
|
| 1848 |
+
"grad_norm": 1.058190941810608,
|
| 1849 |
+
"learning_rate": 1.3754770958931672e-05,
|
| 1850 |
+
"loss": 0.1631,
|
| 1851 |
+
"step": 1315
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 1.6587052168447518,
|
| 1855 |
+
"grad_norm": 1.028100609779358,
|
| 1856 |
+
"learning_rate": 1.3651271601267254e-05,
|
| 1857 |
+
"loss": 0.1523,
|
| 1858 |
+
"step": 1320
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 1.6649905719673161,
|
| 1862 |
+
"grad_norm": 0.8832222819328308,
|
| 1863 |
+
"learning_rate": 1.3547836939452315e-05,
|
| 1864 |
+
"loss": 0.143,
|
| 1865 |
+
"step": 1325
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 1.6712759270898805,
|
| 1869 |
+
"grad_norm": 0.948860228061676,
|
| 1870 |
+
"learning_rate": 1.3444471935044211e-05,
|
| 1871 |
+
"loss": 0.1316,
|
| 1872 |
+
"step": 1330
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 1.677561282212445,
|
| 1876 |
+
"grad_norm": 1.1122239828109741,
|
| 1877 |
+
"learning_rate": 1.3341181546258973e-05,
|
| 1878 |
+
"loss": 0.146,
|
| 1879 |
+
"step": 1335
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 1.6838466373350094,
|
| 1883 |
+
"grad_norm": 0.9949674010276794,
|
| 1884 |
+
"learning_rate": 1.3237970727733463e-05,
|
| 1885 |
+
"loss": 0.1369,
|
| 1886 |
+
"step": 1340
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 1.690131992457574,
|
| 1890 |
+
"grad_norm": 1.022530198097229,
|
| 1891 |
+
"learning_rate": 1.3134844430287727e-05,
|
| 1892 |
+
"loss": 0.1227,
|
| 1893 |
+
"step": 1345
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 1.6964173475801383,
|
| 1897 |
+
"grad_norm": 1.1453173160552979,
|
| 1898 |
+
"learning_rate": 1.3031807600687476e-05,
|
| 1899 |
+
"loss": 0.1404,
|
| 1900 |
+
"step": 1350
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 1.7027027027027026,
|
| 1904 |
+
"grad_norm": 1.163140058517456,
|
| 1905 |
+
"learning_rate": 1.2928865181406848e-05,
|
| 1906 |
+
"loss": 0.148,
|
| 1907 |
+
"step": 1355
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 1.708988057825267,
|
| 1911 |
+
"grad_norm": 0.7806092500686646,
|
| 1912 |
+
"learning_rate": 1.2826022110391301e-05,
|
| 1913 |
+
"loss": 0.1222,
|
| 1914 |
+
"step": 1360
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 1.7152734129478315,
|
| 1918 |
+
"grad_norm": 0.9624476432800293,
|
| 1919 |
+
"learning_rate": 1.2723283320820735e-05,
|
| 1920 |
+
"loss": 0.1229,
|
| 1921 |
+
"step": 1365
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 1.721558768070396,
|
| 1925 |
+
"grad_norm": 1.237204909324646,
|
| 1926 |
+
"learning_rate": 1.2620653740872896e-05,
|
| 1927 |
+
"loss": 0.1241,
|
| 1928 |
+
"step": 1370
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 1.7278441231929604,
|
| 1932 |
+
"grad_norm": 1.018872857093811,
|
| 1933 |
+
"learning_rate": 1.2518138293486933e-05,
|
| 1934 |
+
"loss": 0.126,
|
| 1935 |
+
"step": 1375
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 1.7341294783155248,
|
| 1939 |
+
"grad_norm": 1.0383186340332031,
|
| 1940 |
+
"learning_rate": 1.2415741896127306e-05,
|
| 1941 |
+
"loss": 0.1201,
|
| 1942 |
+
"step": 1380
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 1.7404148334380891,
|
| 1946 |
+
"grad_norm": 1.0076663494110107,
|
| 1947 |
+
"learning_rate": 1.2313469460547878e-05,
|
| 1948 |
+
"loss": 0.133,
|
| 1949 |
+
"step": 1385
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 1.7467001885606537,
|
| 1953 |
+
"grad_norm": 1.077681541442871,
|
| 1954 |
+
"learning_rate": 1.2211325892556282e-05,
|
| 1955 |
+
"loss": 0.1167,
|
| 1956 |
+
"step": 1390
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 1.7529855436832182,
|
| 1960 |
+
"grad_norm": 1.1024730205535889,
|
| 1961 |
+
"learning_rate": 1.2109316091778652e-05,
|
| 1962 |
+
"loss": 0.1404,
|
| 1963 |
+
"step": 1395
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 1.7592708988057826,
|
| 1967 |
+
"grad_norm": 0.9659144878387451,
|
| 1968 |
+
"learning_rate": 1.2007444951424572e-05,
|
| 1969 |
+
"loss": 0.1229,
|
| 1970 |
+
"step": 1400
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 1.765556253928347,
|
| 1974 |
+
"grad_norm": 0.9410082697868347,
|
| 1975 |
+
"learning_rate": 1.1905717358052338e-05,
|
| 1976 |
+
"loss": 0.1213,
|
| 1977 |
+
"step": 1405
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 1.7718416090509113,
|
| 1981 |
+
"grad_norm": 0.9698991179466248,
|
| 1982 |
+
"learning_rate": 1.1804138191334604e-05,
|
| 1983 |
+
"loss": 0.1305,
|
| 1984 |
+
"step": 1410
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 1.7781269641734758,
|
| 1988 |
+
"grad_norm": 0.7264032959938049,
|
| 1989 |
+
"learning_rate": 1.1702712323824262e-05,
|
| 1990 |
+
"loss": 0.1147,
|
| 1991 |
+
"step": 1415
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 1.7844123192960404,
|
| 1995 |
+
"grad_norm": 1.186924695968628,
|
| 1996 |
+
"learning_rate": 1.160144462072077e-05,
|
| 1997 |
+
"loss": 0.1217,
|
| 1998 |
+
"step": 1420
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 1.7906976744186047,
|
| 2002 |
+
"grad_norm": 1.0098295211791992,
|
| 2003 |
+
"learning_rate": 1.150033993963673e-05,
|
| 2004 |
+
"loss": 0.1207,
|
| 2005 |
+
"step": 1425
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 1.796983029541169,
|
| 2009 |
+
"grad_norm": 0.8685053586959839,
|
| 2010 |
+
"learning_rate": 1.1399403130364914e-05,
|
| 2011 |
+
"loss": 0.1298,
|
| 2012 |
+
"step": 1430
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 1.8032683846637334,
|
| 2016 |
+
"grad_norm": 1.169630765914917,
|
| 2017 |
+
"learning_rate": 1.1298639034645595e-05,
|
| 2018 |
+
"loss": 0.122,
|
| 2019 |
+
"step": 1435
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 1.809553739786298,
|
| 2023 |
+
"grad_norm": 0.852220892906189,
|
| 2024 |
+
"learning_rate": 1.1198052485934336e-05,
|
| 2025 |
+
"loss": 0.1053,
|
| 2026 |
+
"step": 1440
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 1.8158390949088623,
|
| 2030 |
+
"grad_norm": 0.9320086240768433,
|
| 2031 |
+
"learning_rate": 1.1097648309170109e-05,
|
| 2032 |
+
"loss": 0.1196,
|
| 2033 |
+
"step": 1445
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 1.8221244500314269,
|
| 2037 |
+
"grad_norm": 1.0622563362121582,
|
| 2038 |
+
"learning_rate": 1.0997431320543856e-05,
|
| 2039 |
+
"loss": 0.1211,
|
| 2040 |
+
"step": 1450
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 1.8284098051539912,
|
| 2044 |
+
"grad_norm": 0.8508372902870178,
|
| 2045 |
+
"learning_rate": 1.0897406327267486e-05,
|
| 2046 |
+
"loss": 0.1033,
|
| 2047 |
+
"step": 1455
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 1.8346951602765555,
|
| 2051 |
+
"grad_norm": 0.7957747578620911,
|
| 2052 |
+
"learning_rate": 1.0797578127343258e-05,
|
| 2053 |
+
"loss": 0.1032,
|
| 2054 |
+
"step": 1460
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 1.8409805153991199,
|
| 2058 |
+
"grad_norm": 0.9280251860618591,
|
| 2059 |
+
"learning_rate": 1.069795150933365e-05,
|
| 2060 |
+
"loss": 0.1203,
|
| 2061 |
+
"step": 1465
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 1.8472658705216844,
|
| 2065 |
+
"grad_norm": 0.8382870554924011,
|
| 2066 |
+
"learning_rate": 1.0598531252131639e-05,
|
| 2067 |
+
"loss": 0.1154,
|
| 2068 |
+
"step": 1470
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 1.853551225644249,
|
| 2072 |
+
"grad_norm": 1.2353485822677612,
|
| 2073 |
+
"learning_rate": 1.0499322124731486e-05,
|
| 2074 |
+
"loss": 0.107,
|
| 2075 |
+
"step": 1475
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 1.8598365807668134,
|
| 2079 |
+
"grad_norm": 0.8504846692085266,
|
| 2080 |
+
"learning_rate": 1.0400328885999987e-05,
|
| 2081 |
+
"loss": 0.1029,
|
| 2082 |
+
"step": 1480
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 1.8661219358893777,
|
| 2086 |
+
"grad_norm": 0.818196177482605,
|
| 2087 |
+
"learning_rate": 1.030155628444815e-05,
|
| 2088 |
+
"loss": 0.1047,
|
| 2089 |
+
"step": 1485
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 1.872407291011942,
|
| 2093 |
+
"grad_norm": 0.7848305702209473,
|
| 2094 |
+
"learning_rate": 1.0203009058003483e-05,
|
| 2095 |
+
"loss": 0.1131,
|
| 2096 |
+
"step": 1490
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 1.8786926461345066,
|
| 2100 |
+
"grad_norm": 0.943403422832489,
|
| 2101 |
+
"learning_rate": 1.0104691933782667e-05,
|
| 2102 |
+
"loss": 0.1196,
|
| 2103 |
+
"step": 1495
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 1.8849780012570712,
|
| 2107 |
+
"grad_norm": 0.9196809530258179,
|
| 2108 |
+
"learning_rate": 1.000660962786485e-05,
|
| 2109 |
+
"loss": 0.1037,
|
| 2110 |
+
"step": 1500
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"epoch": 1.8912633563796355,
|
| 2114 |
+
"grad_norm": 0.9809285402297974,
|
| 2115 |
+
"learning_rate": 9.90876684506541e-06,
|
| 2116 |
+
"loss": 0.119,
|
| 2117 |
+
"step": 1505
|
| 2118 |
+
},
|
| 2119 |
+
{
|
| 2120 |
+
"epoch": 1.8975487115021998,
|
| 2121 |
+
"grad_norm": 1.1126230955123901,
|
| 2122 |
+
"learning_rate": 9.811168278710244e-06,
|
| 2123 |
+
"loss": 0.1265,
|
| 2124 |
+
"step": 1510
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 1.9038340666247642,
|
| 2128 |
+
"grad_norm": 0.8952428698539734,
|
| 2129 |
+
"learning_rate": 9.713818610410705e-06,
|
| 2130 |
+
"loss": 0.1017,
|
| 2131 |
+
"step": 1515
|
| 2132 |
+
},
|
| 2133 |
+
{
|
| 2134 |
+
"epoch": 1.9101194217473287,
|
| 2135 |
+
"grad_norm": 0.9836751818656921,
|
| 2136 |
+
"learning_rate": 9.616722509838971e-06,
|
| 2137 |
+
"loss": 0.0979,
|
| 2138 |
+
"step": 1520
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 1.9164047768698933,
|
| 2142 |
+
"grad_norm": 0.8075424432754517,
|
| 2143 |
+
"learning_rate": 9.519884634504074e-06,
|
| 2144 |
+
"loss": 0.1144,
|
| 2145 |
+
"step": 1525
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 1.9226901319924576,
|
| 2149 |
+
"grad_norm": 0.773509681224823,
|
| 2150 |
+
"learning_rate": 9.423309629528506e-06,
|
| 2151 |
+
"loss": 0.1015,
|
| 2152 |
+
"step": 1530
|
| 2153 |
+
},
|
| 2154 |
+
{
|
| 2155 |
+
"epoch": 1.928975487115022,
|
| 2156 |
+
"grad_norm": 0.8212863206863403,
|
| 2157 |
+
"learning_rate": 9.327002127425364e-06,
|
| 2158 |
+
"loss": 0.1001,
|
| 2159 |
+
"step": 1535
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 1.9352608422375863,
|
| 2163 |
+
"grad_norm": 0.8783861398696899,
|
| 2164 |
+
"learning_rate": 9.230966747876174e-06,
|
| 2165 |
+
"loss": 0.1065,
|
| 2166 |
+
"step": 1540
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 1.9415461973601509,
|
| 2170 |
+
"grad_norm": 0.8433883190155029,
|
| 2171 |
+
"learning_rate": 9.135208097509273e-06,
|
| 2172 |
+
"loss": 0.1047,
|
| 2173 |
+
"step": 1545
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 1.9478315524827152,
|
| 2177 |
+
"grad_norm": 0.8886436223983765,
|
| 2178 |
+
"learning_rate": 9.03973076967884e-06,
|
| 2179 |
+
"loss": 0.1043,
|
| 2180 |
+
"step": 1550
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 1.9541169076052798,
|
| 2184 |
+
"grad_norm": 0.866792619228363,
|
| 2185 |
+
"learning_rate": 8.944539344244566e-06,
|
| 2186 |
+
"loss": 0.1066,
|
| 2187 |
+
"step": 1555
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 1.9604022627278441,
|
| 2191 |
+
"grad_norm": 1.0139641761779785,
|
| 2192 |
+
"learning_rate": 8.849638387351976e-06,
|
| 2193 |
+
"loss": 0.0956,
|
| 2194 |
+
"step": 1560
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 1.9666876178504085,
|
| 2198 |
+
"grad_norm": 0.9682946801185608,
|
| 2199 |
+
"learning_rate": 8.755032451213371e-06,
|
| 2200 |
+
"loss": 0.0973,
|
| 2201 |
+
"step": 1565
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 1.972972972972973,
|
| 2205 |
+
"grad_norm": 0.8206133246421814,
|
| 2206 |
+
"learning_rate": 8.66072607388951e-06,
|
| 2207 |
+
"loss": 0.1079,
|
| 2208 |
+
"step": 1570
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 1.9792583280955374,
|
| 2212 |
+
"grad_norm": 0.7307332158088684,
|
| 2213 |
+
"learning_rate": 8.56672377907188e-06,
|
| 2214 |
+
"loss": 0.0886,
|
| 2215 |
+
"step": 1575
|
| 2216 |
+
},
|
| 2217 |
+
{
|
| 2218 |
+
"epoch": 1.985543683218102,
|
| 2219 |
+
"grad_norm": 0.7518356442451477,
|
| 2220 |
+
"learning_rate": 8.473030075865748e-06,
|
| 2221 |
+
"loss": 0.0944,
|
| 2222 |
+
"step": 1580
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 1.9918290383406663,
|
| 2226 |
+
"grad_norm": 0.7491641640663147,
|
| 2227 |
+
"learning_rate": 8.37964945857384e-06,
|
| 2228 |
+
"loss": 0.0932,
|
| 2229 |
+
"step": 1585
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 1.9981143934632306,
|
| 2233 |
+
"grad_norm": 0.7968425154685974,
|
| 2234 |
+
"learning_rate": 8.286586406480762e-06,
|
| 2235 |
+
"loss": 0.0979,
|
| 2236 |
+
"step": 1590
|
| 2237 |
+
},
|
| 2238 |
+
{
|
| 2239 |
+
"epoch": 2.003771213073539,
|
| 2240 |
+
"grad_norm": 0.8225958943367004,
|
| 2241 |
+
"learning_rate": 8.193845383638157e-06,
|
| 2242 |
+
"loss": 0.0812,
|
| 2243 |
+
"step": 1595
|
| 2244 |
+
},
|
| 2245 |
+
{
|
| 2246 |
+
"epoch": 2.010056568196103,
|
| 2247 |
+
"grad_norm": 0.807681679725647,
|
| 2248 |
+
"learning_rate": 8.10143083865053e-06,
|
| 2249 |
+
"loss": 0.0786,
|
| 2250 |
+
"step": 1600
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"epoch": 2.0163419233186675,
|
| 2254 |
+
"grad_norm": 0.7337367534637451,
|
| 2255 |
+
"learning_rate": 8.009347204461922e-06,
|
| 2256 |
+
"loss": 0.0761,
|
| 2257 |
+
"step": 1605
|
| 2258 |
+
},
|
| 2259 |
+
{
|
| 2260 |
+
"epoch": 2.022627278441232,
|
| 2261 |
+
"grad_norm": 0.8403814435005188,
|
| 2262 |
+
"learning_rate": 7.917598898143196e-06,
|
| 2263 |
+
"loss": 0.0772,
|
| 2264 |
+
"step": 1610
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 2.028912633563796,
|
| 2268 |
+
"grad_norm": 0.8842039108276367,
|
| 2269 |
+
"learning_rate": 7.826190320680232e-06,
|
| 2270 |
+
"loss": 0.0812,
|
| 2271 |
+
"step": 1615
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 2.035197988686361,
|
| 2275 |
+
"grad_norm": 0.6775525212287903,
|
| 2276 |
+
"learning_rate": 7.735125856762752e-06,
|
| 2277 |
+
"loss": 0.0849,
|
| 2278 |
+
"step": 1620
|
| 2279 |
+
},
|
| 2280 |
+
{
|
| 2281 |
+
"epoch": 2.0414833438089253,
|
| 2282 |
+
"grad_norm": 0.8478943705558777,
|
| 2283 |
+
"learning_rate": 7.64440987457405e-06,
|
| 2284 |
+
"loss": 0.0837,
|
| 2285 |
+
"step": 1625
|
| 2286 |
+
},
|
| 2287 |
+
{
|
| 2288 |
+
"epoch": 2.0477686989314896,
|
| 2289 |
+
"grad_norm": 0.7873494029045105,
|
| 2290 |
+
"learning_rate": 7.554046725581435e-06,
|
| 2291 |
+
"loss": 0.0748,
|
| 2292 |
+
"step": 1630
|
| 2293 |
+
},
|
| 2294 |
+
{
|
| 2295 |
+
"epoch": 2.054054054054054,
|
| 2296 |
+
"grad_norm": 0.7249782681465149,
|
| 2297 |
+
"learning_rate": 7.464040744327488e-06,
|
| 2298 |
+
"loss": 0.0765,
|
| 2299 |
+
"step": 1635
|
| 2300 |
+
},
|
| 2301 |
+
{
|
| 2302 |
+
"epoch": 2.0603394091766183,
|
| 2303 |
+
"grad_norm": 0.7676404714584351,
|
| 2304 |
+
"learning_rate": 7.374396248222172e-06,
|
| 2305 |
+
"loss": 0.0713,
|
| 2306 |
+
"step": 1640
|
| 2307 |
+
},
|
| 2308 |
+
{
|
| 2309 |
+
"epoch": 2.066624764299183,
|
| 2310 |
+
"grad_norm": 0.7369318008422852,
|
| 2311 |
+
"learning_rate": 7.285117537335698e-06,
|
| 2312 |
+
"loss": 0.0766,
|
| 2313 |
+
"step": 1645
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 2.0729101194217474,
|
| 2317 |
+
"grad_norm": 0.7745431065559387,
|
| 2318 |
+
"learning_rate": 7.196208894192306e-06,
|
| 2319 |
+
"loss": 0.0795,
|
| 2320 |
+
"step": 1650
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 2.0791954745443118,
|
| 2324 |
+
"grad_norm": 0.7855203151702881,
|
| 2325 |
+
"learning_rate": 7.107674583564787e-06,
|
| 2326 |
+
"loss": 0.0774,
|
| 2327 |
+
"step": 1655
|
| 2328 |
+
},
|
| 2329 |
+
{
|
| 2330 |
+
"epoch": 2.085480829666876,
|
| 2331 |
+
"grad_norm": 0.7037616968154907,
|
| 2332 |
+
"learning_rate": 7.019518852269953e-06,
|
| 2333 |
+
"loss": 0.0797,
|
| 2334 |
+
"step": 1660
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 2.0917661847894404,
|
| 2338 |
+
"grad_norm": 0.9567010402679443,
|
| 2339 |
+
"learning_rate": 6.9317459289649135e-06,
|
| 2340 |
+
"loss": 0.0785,
|
| 2341 |
+
"step": 1665
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 2.098051539912005,
|
| 2345 |
+
"grad_norm": 0.9554398655891418,
|
| 2346 |
+
"learning_rate": 6.844360023944214e-06,
|
| 2347 |
+
"loss": 0.0871,
|
| 2348 |
+
"step": 1670
|
| 2349 |
+
},
|
| 2350 |
+
{
|
| 2351 |
+
"epoch": 2.1043368950345696,
|
| 2352 |
+
"grad_norm": 0.6803709268569946,
|
| 2353 |
+
"learning_rate": 6.75736532893791e-06,
|
| 2354 |
+
"loss": 0.0816,
|
| 2355 |
+
"step": 1675
|
| 2356 |
+
},
|
| 2357 |
+
{
|
| 2358 |
+
"epoch": 2.110622250157134,
|
| 2359 |
+
"grad_norm": 0.790193498134613,
|
| 2360 |
+
"learning_rate": 6.670766016910479e-06,
|
| 2361 |
+
"loss": 0.0759,
|
| 2362 |
+
"step": 1680
|
| 2363 |
+
},
|
| 2364 |
+
{
|
| 2365 |
+
"epoch": 2.1169076052796982,
|
| 2366 |
+
"grad_norm": 0.7045140266418457,
|
| 2367 |
+
"learning_rate": 6.584566241860641e-06,
|
| 2368 |
+
"loss": 0.069,
|
| 2369 |
+
"step": 1685
|
| 2370 |
+
},
|
| 2371 |
+
{
|
| 2372 |
+
"epoch": 2.1231929604022626,
|
| 2373 |
+
"grad_norm": 0.7257286310195923,
|
| 2374 |
+
"learning_rate": 6.498770138622136e-06,
|
| 2375 |
+
"loss": 0.0776,
|
| 2376 |
+
"step": 1690
|
| 2377 |
+
},
|
| 2378 |
+
{
|
| 2379 |
+
"epoch": 2.1294783155248274,
|
| 2380 |
+
"grad_norm": 0.7143513560295105,
|
| 2381 |
+
"learning_rate": 6.413381822665333e-06,
|
| 2382 |
+
"loss": 0.0781,
|
| 2383 |
+
"step": 1695
|
| 2384 |
+
},
|
| 2385 |
+
{
|
| 2386 |
+
"epoch": 2.1357636706473917,
|
| 2387 |
+
"grad_norm": 0.7233651280403137,
|
| 2388 |
+
"learning_rate": 6.32840538989987e-06,
|
| 2389 |
+
"loss": 0.0753,
|
| 2390 |
+
"step": 1700
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"epoch": 2.142049025769956,
|
| 2394 |
+
"grad_norm": 0.6778560876846313,
|
| 2395 |
+
"learning_rate": 6.243844916478156e-06,
|
| 2396 |
+
"loss": 0.0756,
|
| 2397 |
+
"step": 1705
|
| 2398 |
+
},
|
| 2399 |
+
{
|
| 2400 |
+
"epoch": 2.1483343808925204,
|
| 2401 |
+
"grad_norm": 0.6528449058532715,
|
| 2402 |
+
"learning_rate": 6.1597044585998284e-06,
|
| 2403 |
+
"loss": 0.0738,
|
| 2404 |
+
"step": 1710
|
| 2405 |
+
},
|
| 2406 |
+
{
|
| 2407 |
+
"epoch": 2.1546197360150847,
|
| 2408 |
+
"grad_norm": 0.8201831579208374,
|
| 2409 |
+
"learning_rate": 6.075988052317226e-06,
|
| 2410 |
+
"loss": 0.0791,
|
| 2411 |
+
"step": 1715
|
| 2412 |
+
},
|
| 2413 |
+
{
|
| 2414 |
+
"epoch": 2.160905091137649,
|
| 2415 |
+
"grad_norm": 0.7476294636726379,
|
| 2416 |
+
"learning_rate": 5.992699713341764e-06,
|
| 2417 |
+
"loss": 0.0757,
|
| 2418 |
+
"step": 1720
|
| 2419 |
+
},
|
| 2420 |
+
{
|
| 2421 |
+
"epoch": 2.167190446260214,
|
| 2422 |
+
"grad_norm": 0.6916204690933228,
|
| 2423 |
+
"learning_rate": 5.909843436851293e-06,
|
| 2424 |
+
"loss": 0.074,
|
| 2425 |
+
"step": 1725
|
| 2426 |
+
},
|
| 2427 |
+
{
|
| 2428 |
+
"epoch": 2.173475801382778,
|
| 2429 |
+
"grad_norm": 0.7249442338943481,
|
| 2430 |
+
"learning_rate": 5.827423197298499e-06,
|
| 2431 |
+
"loss": 0.0717,
|
| 2432 |
+
"step": 1730
|
| 2433 |
+
},
|
| 2434 |
+
{
|
| 2435 |
+
"epoch": 2.1797611565053425,
|
| 2436 |
+
"grad_norm": 0.6465781331062317,
|
| 2437 |
+
"learning_rate": 5.745442948220213e-06,
|
| 2438 |
+
"loss": 0.07,
|
| 2439 |
+
"step": 1735
|
| 2440 |
+
},
|
| 2441 |
+
{
|
| 2442 |
+
"epoch": 2.186046511627907,
|
| 2443 |
+
"grad_norm": 0.8122044801712036,
|
| 2444 |
+
"learning_rate": 5.663906622047802e-06,
|
| 2445 |
+
"loss": 0.0815,
|
| 2446 |
+
"step": 1740
|
| 2447 |
+
},
|
| 2448 |
+
{
|
| 2449 |
+
"epoch": 2.192331866750471,
|
| 2450 |
+
"grad_norm": 0.6990500092506409,
|
| 2451 |
+
"learning_rate": 5.582818129918525e-06,
|
| 2452 |
+
"loss": 0.0791,
|
| 2453 |
+
"step": 1745
|
| 2454 |
+
},
|
| 2455 |
+
{
|
| 2456 |
+
"epoch": 2.198617221873036,
|
| 2457 |
+
"grad_norm": 0.6808353066444397,
|
| 2458 |
+
"learning_rate": 5.502181361487905e-06,
|
| 2459 |
+
"loss": 0.0792,
|
| 2460 |
+
"step": 1750
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 2.2049025769956003,
|
| 2464 |
+
"grad_norm": 0.6883416771888733,
|
| 2465 |
+
"learning_rate": 5.422000184743185e-06,
|
| 2466 |
+
"loss": 0.0728,
|
| 2467 |
+
"step": 1755
|
| 2468 |
+
},
|
| 2469 |
+
{
|
| 2470 |
+
"epoch": 2.2111879321181647,
|
| 2471 |
+
"grad_norm": 0.7865710258483887,
|
| 2472 |
+
"learning_rate": 5.342278445817769e-06,
|
| 2473 |
+
"loss": 0.0793,
|
| 2474 |
+
"step": 1760
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 2.217473287240729,
|
| 2478 |
+
"grad_norm": 0.8760117888450623,
|
| 2479 |
+
"learning_rate": 5.263019968806722e-06,
|
| 2480 |
+
"loss": 0.0699,
|
| 2481 |
+
"step": 1765
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"epoch": 2.2237586423632933,
|
| 2485 |
+
"grad_norm": 0.6477676630020142,
|
| 2486 |
+
"learning_rate": 5.1842285555833564e-06,
|
| 2487 |
+
"loss": 0.07,
|
| 2488 |
+
"step": 1770
|
| 2489 |
+
},
|
| 2490 |
+
{
|
| 2491 |
+
"epoch": 2.230043997485858,
|
| 2492 |
+
"grad_norm": 0.5789802074432373,
|
| 2493 |
+
"learning_rate": 5.105907985616841e-06,
|
| 2494 |
+
"loss": 0.0715,
|
| 2495 |
+
"step": 1775
|
| 2496 |
+
},
|
| 2497 |
+
{
|
| 2498 |
+
"epoch": 2.2363293526084225,
|
| 2499 |
+
"grad_norm": 0.7266568541526794,
|
| 2500 |
+
"learning_rate": 5.0280620157909316e-06,
|
| 2501 |
+
"loss": 0.0733,
|
| 2502 |
+
"step": 1780
|
| 2503 |
+
},
|
| 2504 |
+
{
|
| 2505 |
+
"epoch": 2.242614707730987,
|
| 2506 |
+
"grad_norm": 0.7463145852088928,
|
| 2507 |
+
"learning_rate": 4.950694380223748e-06,
|
| 2508 |
+
"loss": 0.0736,
|
| 2509 |
+
"step": 1785
|
| 2510 |
+
},
|
| 2511 |
+
{
|
| 2512 |
+
"epoch": 2.248900062853551,
|
| 2513 |
+
"grad_norm": 0.65718674659729,
|
| 2514 |
+
"learning_rate": 4.873808790088642e-06,
|
| 2515 |
+
"loss": 0.0733,
|
| 2516 |
+
"step": 1790
|
| 2517 |
+
},
|
| 2518 |
+
{
|
| 2519 |
+
"epoch": 2.2551854179761155,
|
| 2520 |
+
"grad_norm": 0.5933600664138794,
|
| 2521 |
+
"learning_rate": 4.797408933436207e-06,
|
| 2522 |
+
"loss": 0.0731,
|
| 2523 |
+
"step": 1795
|
| 2524 |
+
},
|
| 2525 |
+
{
|
| 2526 |
+
"epoch": 2.2614707730986803,
|
| 2527 |
+
"grad_norm": 0.6472100019454956,
|
| 2528 |
+
"learning_rate": 4.721498475017359e-06,
|
| 2529 |
+
"loss": 0.0706,
|
| 2530 |
+
"step": 1800
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"epoch": 2.2677561282212446,
|
| 2534 |
+
"grad_norm": 0.6243506669998169,
|
| 2535 |
+
"learning_rate": 4.646081056107528e-06,
|
| 2536 |
+
"loss": 0.0728,
|
| 2537 |
+
"step": 1805
|
| 2538 |
+
},
|
| 2539 |
+
{
|
| 2540 |
+
"epoch": 2.274041483343809,
|
| 2541 |
+
"grad_norm": 0.7099791169166565,
|
| 2542 |
+
"learning_rate": 4.571160294332022e-06,
|
| 2543 |
+
"loss": 0.0744,
|
| 2544 |
+
"step": 1810
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 2.2803268384663733,
|
| 2548 |
+
"grad_norm": 0.8072351813316345,
|
| 2549 |
+
"learning_rate": 4.496739783492473e-06,
|
| 2550 |
+
"loss": 0.0641,
|
| 2551 |
+
"step": 1815
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 2.2866121935889376,
|
| 2555 |
+
"grad_norm": 0.604190468788147,
|
| 2556 |
+
"learning_rate": 4.422823093394465e-06,
|
| 2557 |
+
"loss": 0.0676,
|
| 2558 |
+
"step": 1820
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 2.292897548711502,
|
| 2562 |
+
"grad_norm": 0.6109089255332947,
|
| 2563 |
+
"learning_rate": 4.349413769676296e-06,
|
| 2564 |
+
"loss": 0.0687,
|
| 2565 |
+
"step": 1825
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 2.2991829038340668,
|
| 2569 |
+
"grad_norm": 0.7936350107192993,
|
| 2570 |
+
"learning_rate": 4.276515333638881e-06,
|
| 2571 |
+
"loss": 0.0646,
|
| 2572 |
+
"step": 1830
|
| 2573 |
+
},
|
| 2574 |
+
{
|
| 2575 |
+
"epoch": 2.305468258956631,
|
| 2576 |
+
"grad_norm": 0.7822954654693604,
|
| 2577 |
+
"learning_rate": 4.204131282076878e-06,
|
| 2578 |
+
"loss": 0.0732,
|
| 2579 |
+
"step": 1835
|
| 2580 |
+
},
|
| 2581 |
+
{
|
| 2582 |
+
"epoch": 2.3117536140791954,
|
| 2583 |
+
"grad_norm": 0.569732129573822,
|
| 2584 |
+
"learning_rate": 4.13226508711091e-06,
|
| 2585 |
+
"loss": 0.0714,
|
| 2586 |
+
"step": 1840
|
| 2587 |
+
},
|
| 2588 |
+
{
|
| 2589 |
+
"epoch": 2.31803896920176,
|
| 2590 |
+
"grad_norm": 0.6624398827552795,
|
| 2591 |
+
"learning_rate": 4.060920196021061e-06,
|
| 2592 |
+
"loss": 0.0718,
|
| 2593 |
+
"step": 1845
|
| 2594 |
+
},
|
| 2595 |
+
{
|
| 2596 |
+
"epoch": 2.3243243243243246,
|
| 2597 |
+
"grad_norm": 0.6570225954055786,
|
| 2598 |
+
"learning_rate": 3.990100031081472e-06,
|
| 2599 |
+
"loss": 0.0657,
|
| 2600 |
+
"step": 1850
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"epoch": 2.330609679446889,
|
| 2604 |
+
"grad_norm": 0.7752540707588196,
|
| 2605 |
+
"learning_rate": 3.919807989396219e-06,
|
| 2606 |
+
"loss": 0.0659,
|
| 2607 |
+
"step": 1855
|
| 2608 |
+
},
|
| 2609 |
+
{
|
| 2610 |
+
"epoch": 2.3368950345694532,
|
| 2611 |
+
"grad_norm": 0.5954207181930542,
|
| 2612 |
+
"learning_rate": 3.85004744273633e-06,
|
| 2613 |
+
"loss": 0.066,
|
| 2614 |
+
"step": 1860
|
| 2615 |
+
},
|
| 2616 |
+
{
|
| 2617 |
+
"epoch": 2.3431803896920176,
|
| 2618 |
+
"grad_norm": 0.7840206623077393,
|
| 2619 |
+
"learning_rate": 3.7808217373780713e-06,
|
| 2620 |
+
"loss": 0.081,
|
| 2621 |
+
"step": 1865
|
| 2622 |
+
},
|
| 2623 |
+
{
|
| 2624 |
+
"epoch": 2.349465744814582,
|
| 2625 |
+
"grad_norm": 0.6711516976356506,
|
| 2626 |
+
"learning_rate": 3.712134193942424e-06,
|
| 2627 |
+
"loss": 0.0579,
|
| 2628 |
+
"step": 1870
|
| 2629 |
+
},
|
| 2630 |
+
{
|
| 2631 |
+
"epoch": 2.3557510999371463,
|
| 2632 |
+
"grad_norm": 0.6024024486541748,
|
| 2633 |
+
"learning_rate": 3.6439881072357885e-06,
|
| 2634 |
+
"loss": 0.0622,
|
| 2635 |
+
"step": 1875
|
| 2636 |
+
},
|
| 2637 |
+
{
|
| 2638 |
+
"epoch": 2.362036455059711,
|
| 2639 |
+
"grad_norm": 0.7049519419670105,
|
| 2640 |
+
"learning_rate": 3.5763867460919676e-06,
|
| 2641 |
+
"loss": 0.0738,
|
| 2642 |
+
"step": 1880
|
| 2643 |
+
},
|
| 2644 |
+
{
|
| 2645 |
+
"epoch": 2.3683218101822754,
|
| 2646 |
+
"grad_norm": 0.5732219815254211,
|
| 2647 |
+
"learning_rate": 3.5093333532153316e-06,
|
| 2648 |
+
"loss": 0.063,
|
| 2649 |
+
"step": 1885
|
| 2650 |
+
},
|
| 2651 |
+
{
|
| 2652 |
+
"epoch": 2.3746071653048397,
|
| 2653 |
+
"grad_norm": 0.6560583114624023,
|
| 2654 |
+
"learning_rate": 3.442831145025303e-06,
|
| 2655 |
+
"loss": 0.063,
|
| 2656 |
+
"step": 1890
|
| 2657 |
+
},
|
| 2658 |
+
{
|
| 2659 |
+
"epoch": 2.380892520427404,
|
| 2660 |
+
"grad_norm": 0.6651554107666016,
|
| 2661 |
+
"learning_rate": 3.3768833115020605e-06,
|
| 2662 |
+
"loss": 0.0659,
|
| 2663 |
+
"step": 1895
|
| 2664 |
+
},
|
| 2665 |
+
{
|
| 2666 |
+
"epoch": 2.3871778755499684,
|
| 2667 |
+
"grad_norm": 0.5772749185562134,
|
| 2668 |
+
"learning_rate": 3.311493016033503e-06,
|
| 2669 |
+
"loss": 0.0683,
|
| 2670 |
+
"step": 1900
|
| 2671 |
+
},
|
| 2672 |
+
{
|
| 2673 |
+
"epoch": 2.393463230672533,
|
| 2674 |
+
"grad_norm": 0.6334845423698425,
|
| 2675 |
+
"learning_rate": 3.24666339526355e-06,
|
| 2676 |
+
"loss": 0.068,
|
| 2677 |
+
"step": 1905
|
| 2678 |
+
},
|
| 2679 |
+
{
|
| 2680 |
+
"epoch": 2.3997485857950975,
|
| 2681 |
+
"grad_norm": 0.5815230011940002,
|
| 2682 |
+
"learning_rate": 3.1823975589416313e-06,
|
| 2683 |
+
"loss": 0.0669,
|
| 2684 |
+
"step": 1910
|
| 2685 |
+
},
|
| 2686 |
+
{
|
| 2687 |
+
"epoch": 2.406033940917662,
|
| 2688 |
+
"grad_norm": 0.5905975103378296,
|
| 2689 |
+
"learning_rate": 3.118698589773567e-06,
|
| 2690 |
+
"loss": 0.0669,
|
| 2691 |
+
"step": 1915
|
| 2692 |
+
},
|
| 2693 |
+
{
|
| 2694 |
+
"epoch": 2.412319296040226,
|
| 2695 |
+
"grad_norm": 0.6059937477111816,
|
| 2696 |
+
"learning_rate": 3.0555695432736664e-06,
|
| 2697 |
+
"loss": 0.0614,
|
| 2698 |
+
"step": 1920
|
| 2699 |
+
},
|
| 2700 |
+
{
|
| 2701 |
+
"epoch": 2.4186046511627906,
|
| 2702 |
+
"grad_norm": 0.8238071799278259,
|
| 2703 |
+
"learning_rate": 2.9930134476181644e-06,
|
| 2704 |
+
"loss": 0.0599,
|
| 2705 |
+
"step": 1925
|
| 2706 |
+
},
|
| 2707 |
+
{
|
| 2708 |
+
"epoch": 2.424890006285355,
|
| 2709 |
+
"grad_norm": 0.5810702443122864,
|
| 2710 |
+
"learning_rate": 2.931033303499975e-06,
|
| 2711 |
+
"loss": 0.0576,
|
| 2712 |
+
"step": 1930
|
| 2713 |
+
},
|
| 2714 |
+
{
|
| 2715 |
+
"epoch": 2.4311753614079197,
|
| 2716 |
+
"grad_norm": 0.5681622624397278,
|
| 2717 |
+
"learning_rate": 2.869632083984755e-06,
|
| 2718 |
+
"loss": 0.0667,
|
| 2719 |
+
"step": 1935
|
| 2720 |
+
},
|
| 2721 |
+
{
|
| 2722 |
+
"epoch": 2.437460716530484,
|
| 2723 |
+
"grad_norm": 0.7053439021110535,
|
| 2724 |
+
"learning_rate": 2.808812734368271e-06,
|
| 2725 |
+
"loss": 0.0551,
|
| 2726 |
+
"step": 1940
|
| 2727 |
+
},
|
| 2728 |
+
{
|
| 2729 |
+
"epoch": 2.4437460716530484,
|
| 2730 |
+
"grad_norm": 0.7042275667190552,
|
| 2731 |
+
"learning_rate": 2.748578172035152e-06,
|
| 2732 |
+
"loss": 0.0695,
|
| 2733 |
+
"step": 1945
|
| 2734 |
+
},
|
| 2735 |
+
{
|
| 2736 |
+
"epoch": 2.4500314267756127,
|
| 2737 |
+
"grad_norm": 1.0293877124786377,
|
| 2738 |
+
"learning_rate": 2.6889312863189168e-06,
|
| 2739 |
+
"loss": 0.0703,
|
| 2740 |
+
"step": 1950
|
| 2741 |
+
},
|
| 2742 |
+
{
|
| 2743 |
+
"epoch": 2.4563167818981775,
|
| 2744 |
+
"grad_norm": 0.7285968065261841,
|
| 2745 |
+
"learning_rate": 2.6298749383633987e-06,
|
| 2746 |
+
"loss": 0.0639,
|
| 2747 |
+
"step": 1955
|
| 2748 |
+
},
|
| 2749 |
+
{
|
| 2750 |
+
"epoch": 2.462602137020742,
|
| 2751 |
+
"grad_norm": 0.540871798992157,
|
| 2752 |
+
"learning_rate": 2.5714119609855015e-06,
|
| 2753 |
+
"loss": 0.0606,
|
| 2754 |
+
"step": 1960
|
| 2755 |
+
},
|
| 2756 |
+
{
|
| 2757 |
+
"epoch": 2.468887492143306,
|
| 2758 |
+
"grad_norm": 0.5285457968711853,
|
| 2759 |
+
"learning_rate": 2.5135451585392943e-06,
|
| 2760 |
+
"loss": 0.0585,
|
| 2761 |
+
"step": 1965
|
| 2762 |
+
},
|
| 2763 |
+
{
|
| 2764 |
+
"epoch": 2.4751728472658705,
|
| 2765 |
+
"grad_norm": 0.5796512961387634,
|
| 2766 |
+
"learning_rate": 2.4562773067815185e-06,
|
| 2767 |
+
"loss": 0.0641,
|
| 2768 |
+
"step": 1970
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 2.481458202388435,
|
| 2772 |
+
"grad_norm": 0.5129778981208801,
|
| 2773 |
+
"learning_rate": 2.399611152738429e-06,
|
| 2774 |
+
"loss": 0.0672,
|
| 2775 |
+
"step": 1975
|
| 2776 |
+
},
|
| 2777 |
+
{
|
| 2778 |
+
"epoch": 2.487743557510999,
|
| 2779 |
+
"grad_norm": 0.6633635759353638,
|
| 2780 |
+
"learning_rate": 2.343549414574016e-06,
|
| 2781 |
+
"loss": 0.0656,
|
| 2782 |
+
"step": 1980
|
| 2783 |
+
},
|
| 2784 |
+
{
|
| 2785 |
+
"epoch": 2.494028912633564,
|
| 2786 |
+
"grad_norm": 0.6912053823471069,
|
| 2787 |
+
"learning_rate": 2.288094781459637e-06,
|
| 2788 |
+
"loss": 0.0622,
|
| 2789 |
+
"step": 1985
|
| 2790 |
+
},
|
| 2791 |
+
{
|
| 2792 |
+
"epoch": 2.5003142677561283,
|
| 2793 |
+
"grad_norm": 0.6154059767723083,
|
| 2794 |
+
"learning_rate": 2.233249913445004e-06,
|
| 2795 |
+
"loss": 0.0649,
|
| 2796 |
+
"step": 1990
|
| 2797 |
+
},
|
| 2798 |
+
{
|
| 2799 |
+
"epoch": 2.5065996228786926,
|
| 2800 |
+
"grad_norm": 0.6414389610290527,
|
| 2801 |
+
"learning_rate": 2.179017441330608e-06,
|
| 2802 |
+
"loss": 0.0562,
|
| 2803 |
+
"step": 1995
|
| 2804 |
+
},
|
| 2805 |
+
{
|
| 2806 |
+
"epoch": 2.512884978001257,
|
| 2807 |
+
"grad_norm": 0.6235894560813904,
|
| 2808 |
+
"learning_rate": 2.1253999665415074e-06,
|
| 2809 |
+
"loss": 0.0654,
|
| 2810 |
+
"step": 2000
|
| 2811 |
+
},
|
| 2812 |
+
{
|
| 2813 |
+
"epoch": 2.5191703331238218,
|
| 2814 |
+
"grad_norm": 0.43080583214759827,
|
| 2815 |
+
"learning_rate": 2.0724000610025406e-06,
|
| 2816 |
+
"loss": 0.0583,
|
| 2817 |
+
"step": 2005
|
| 2818 |
+
},
|
| 2819 |
+
{
|
| 2820 |
+
"epoch": 2.525455688246386,
|
| 2821 |
+
"grad_norm": 0.51055508852005,
|
| 2822 |
+
"learning_rate": 2.020020267014975e-06,
|
| 2823 |
+
"loss": 0.0545,
|
| 2824 |
+
"step": 2010
|
| 2825 |
+
},
|
| 2826 |
+
{
|
| 2827 |
+
"epoch": 2.5317410433689505,
|
| 2828 |
+
"grad_norm": 0.6152725219726562,
|
| 2829 |
+
"learning_rate": 1.968263097134545e-06,
|
| 2830 |
+
"loss": 0.0633,
|
| 2831 |
+
"step": 2015
|
| 2832 |
+
},
|
| 2833 |
+
{
|
| 2834 |
+
"epoch": 2.538026398491515,
|
| 2835 |
+
"grad_norm": 0.525995671749115,
|
| 2836 |
+
"learning_rate": 1.91713103405092e-06,
|
| 2837 |
+
"loss": 0.0665,
|
| 2838 |
+
"step": 2020
|
| 2839 |
+
},
|
| 2840 |
+
{
|
| 2841 |
+
"epoch": 2.544311753614079,
|
| 2842 |
+
"grad_norm": 0.5495784282684326,
|
| 2843 |
+
"learning_rate": 1.8666265304686387e-06,
|
| 2844 |
+
"loss": 0.0644,
|
| 2845 |
+
"step": 2025
|
| 2846 |
+
},
|
| 2847 |
+
{
|
| 2848 |
+
"epoch": 2.5505971087366435,
|
| 2849 |
+
"grad_norm": 0.6181663870811462,
|
| 2850 |
+
"learning_rate": 1.8167520089894314e-06,
|
| 2851 |
+
"loss": 0.0675,
|
| 2852 |
+
"step": 2030
|
| 2853 |
+
},
|
| 2854 |
+
{
|
| 2855 |
+
"epoch": 2.556882463859208,
|
| 2856 |
+
"grad_norm": 0.5169914364814758,
|
| 2857 |
+
"learning_rate": 1.7675098619960367e-06,
|
| 2858 |
+
"loss": 0.059,
|
| 2859 |
+
"step": 2035
|
| 2860 |
+
},
|
| 2861 |
+
{
|
| 2862 |
+
"epoch": 2.5631678189817726,
|
| 2863 |
+
"grad_norm": 0.5283756852149963,
|
| 2864 |
+
"learning_rate": 1.7189024515374313e-06,
|
| 2865 |
+
"loss": 0.0644,
|
| 2866 |
+
"step": 2040
|
| 2867 |
+
},
|
| 2868 |
+
{
|
| 2869 |
+
"epoch": 2.569453174104337,
|
| 2870 |
+
"grad_norm": 0.5616040825843811,
|
| 2871 |
+
"learning_rate": 1.6709321092155183e-06,
|
| 2872 |
+
"loss": 0.0557,
|
| 2873 |
+
"step": 2045
|
| 2874 |
+
},
|
| 2875 |
+
{
|
| 2876 |
+
"epoch": 2.5757385292269013,
|
| 2877 |
+
"grad_norm": 0.4964756369590759,
|
| 2878 |
+
"learning_rate": 1.6236011360733038e-06,
|
| 2879 |
+
"loss": 0.0635,
|
| 2880 |
+
"step": 2050
|
| 2881 |
+
},
|
| 2882 |
+
{
|
| 2883 |
+
"epoch": 2.5820238843494656,
|
| 2884 |
+
"grad_norm": 0.597533643245697,
|
| 2885 |
+
"learning_rate": 1.5769118024845136e-06,
|
| 2886 |
+
"loss": 0.0664,
|
| 2887 |
+
"step": 2055
|
| 2888 |
+
},
|
| 2889 |
+
{
|
| 2890 |
+
"epoch": 2.5883092394720304,
|
| 2891 |
+
"grad_norm": 0.485101580619812,
|
| 2892 |
+
"learning_rate": 1.5308663480446767e-06,
|
| 2893 |
+
"loss": 0.0663,
|
| 2894 |
+
"step": 2060
|
| 2895 |
+
},
|
| 2896 |
+
{
|
| 2897 |
+
"epoch": 2.5945945945945947,
|
| 2898 |
+
"grad_norm": 0.5150339603424072,
|
| 2899 |
+
"learning_rate": 1.4854669814637145e-06,
|
| 2900 |
+
"loss": 0.0664,
|
| 2901 |
+
"step": 2065
|
| 2902 |
+
},
|
| 2903 |
+
{
|
| 2904 |
+
"epoch": 2.600879949717159,
|
| 2905 |
+
"grad_norm": 0.4801861047744751,
|
| 2906 |
+
"learning_rate": 1.440715880459973e-06,
|
| 2907 |
+
"loss": 0.0531,
|
| 2908 |
+
"step": 2070
|
| 2909 |
+
},
|
| 2910 |
+
{
|
| 2911 |
+
"epoch": 2.6071653048397234,
|
| 2912 |
+
"grad_norm": 0.4918366074562073,
|
| 2913 |
+
"learning_rate": 1.3966151916557867e-06,
|
| 2914 |
+
"loss": 0.0609,
|
| 2915 |
+
"step": 2075
|
| 2916 |
+
},
|
| 2917 |
+
{
|
| 2918 |
+
"epoch": 2.6134506599622878,
|
| 2919 |
+
"grad_norm": 0.6565448045730591,
|
| 2920 |
+
"learning_rate": 1.3531670304744825e-06,
|
| 2921 |
+
"loss": 0.0561,
|
| 2922 |
+
"step": 2080
|
| 2923 |
+
},
|
| 2924 |
+
{
|
| 2925 |
+
"epoch": 2.619736015084852,
|
| 2926 |
+
"grad_norm": 0.6228674054145813,
|
| 2927 |
+
"learning_rate": 1.3103734810389328e-06,
|
| 2928 |
+
"loss": 0.0648,
|
| 2929 |
+
"step": 2085
|
| 2930 |
+
},
|
| 2931 |
+
{
|
| 2932 |
+
"epoch": 2.626021370207417,
|
| 2933 |
+
"grad_norm": 0.5678302645683289,
|
| 2934 |
+
"learning_rate": 1.2682365960715596e-06,
|
| 2935 |
+
"loss": 0.0571,
|
| 2936 |
+
"step": 2090
|
| 2937 |
+
},
|
| 2938 |
+
{
|
| 2939 |
+
"epoch": 2.6323067253299812,
|
| 2940 |
+
"grad_norm": 0.483974426984787,
|
| 2941 |
+
"learning_rate": 1.2267583967958918e-06,
|
| 2942 |
+
"loss": 0.0581,
|
| 2943 |
+
"step": 2095
|
| 2944 |
+
},
|
| 2945 |
+
{
|
| 2946 |
+
"epoch": 2.6385920804525456,
|
| 2947 |
+
"grad_norm": 0.6418463587760925,
|
| 2948 |
+
"learning_rate": 1.1859408728395915e-06,
|
| 2949 |
+
"loss": 0.058,
|
| 2950 |
+
"step": 2100
|
| 2951 |
+
},
|
| 2952 |
+
{
|
| 2953 |
+
"epoch": 2.64487743557511,
|
| 2954 |
+
"grad_norm": 0.5733784437179565,
|
| 2955 |
+
"learning_rate": 1.1457859821390338e-06,
|
| 2956 |
+
"loss": 0.0647,
|
| 2957 |
+
"step": 2105
|
| 2958 |
+
},
|
| 2959 |
+
{
|
| 2960 |
+
"epoch": 2.6511627906976747,
|
| 2961 |
+
"grad_norm": 0.5690593123435974,
|
| 2962 |
+
"learning_rate": 1.1062956508453702e-06,
|
| 2963 |
+
"loss": 0.0593,
|
| 2964 |
+
"step": 2110
|
| 2965 |
+
},
|
| 2966 |
+
{
|
| 2967 |
+
"epoch": 2.657448145820239,
|
| 2968 |
+
"grad_norm": 0.5174360871315002,
|
| 2969 |
+
"learning_rate": 1.067471773232151e-06,
|
| 2970 |
+
"loss": 0.0664,
|
| 2971 |
+
"step": 2115
|
| 2972 |
+
},
|
| 2973 |
+
{
|
| 2974 |
+
"epoch": 2.6637335009428034,
|
| 2975 |
+
"grad_norm": 0.547347366809845,
|
| 2976 |
+
"learning_rate": 1.029316211604454e-06,
|
| 2977 |
+
"loss": 0.059,
|
| 2978 |
+
"step": 2120
|
| 2979 |
+
},
|
| 2980 |
+
{
|
| 2981 |
+
"epoch": 2.6700188560653677,
|
| 2982 |
+
"grad_norm": 0.5633419156074524,
|
| 2983 |
+
"learning_rate": 9.91830796209547e-07,
|
| 2984 |
+
"loss": 0.0663,
|
| 2985 |
+
"step": 2125
|
| 2986 |
+
},
|
| 2987 |
+
{
|
| 2988 |
+
"epoch": 2.676304211187932,
|
| 2989 |
+
"grad_norm": 0.5521914958953857,
|
| 2990 |
+
"learning_rate": 9.550173251491034e-07,
|
| 2991 |
+
"loss": 0.0653,
|
| 2992 |
+
"step": 2130
|
| 2993 |
+
},
|
| 2994 |
+
{
|
| 2995 |
+
"epoch": 2.6825895663104964,
|
| 2996 |
+
"grad_norm": 0.4898196756839752,
|
| 2997 |
+
"learning_rate": 9.188775642929559e-07,
|
| 2998 |
+
"loss": 0.0595,
|
| 2999 |
+
"step": 2135
|
| 3000 |
+
},
|
| 3001 |
+
{
|
| 3002 |
+
"epoch": 2.6888749214330607,
|
| 3003 |
+
"grad_norm": 0.488537460565567,
|
| 3004 |
+
"learning_rate": 8.834132471943684e-07,
|
| 3005 |
+
"loss": 0.0633,
|
| 3006 |
+
"step": 2140
|
| 3007 |
+
},
|
| 3008 |
+
{
|
| 3009 |
+
"epoch": 2.6951602765556255,
|
| 3010 |
+
"grad_norm": 0.4986497759819031,
|
| 3011 |
+
"learning_rate": 8.486260750069092e-07,
|
| 3012 |
+
"loss": 0.0581,
|
| 3013 |
+
"step": 2145
|
| 3014 |
+
},
|
| 3015 |
+
{
|
| 3016 |
+
"epoch": 2.70144563167819,
|
| 3017 |
+
"grad_norm": 0.5986743569374084,
|
| 3018 |
+
"learning_rate": 8.145177164028267e-07,
|
| 3019 |
+
"loss": 0.066,
|
| 3020 |
+
"step": 2150
|
| 3021 |
+
},
|
| 3022 |
+
{
|
| 3023 |
+
"epoch": 2.707730986800754,
|
| 3024 |
+
"grad_norm": 0.6351923942565918,
|
| 3025 |
+
"learning_rate": 7.810898074930245e-07,
|
| 3026 |
+
"loss": 0.0625,
|
| 3027 |
+
"step": 2155
|
| 3028 |
+
},
|
| 3029 |
+
{
|
| 3030 |
+
"epoch": 2.7140163419233185,
|
| 3031 |
+
"grad_norm": 0.595151960849762,
|
| 3032 |
+
"learning_rate": 7.483439517485685e-07,
|
| 3033 |
+
"loss": 0.0658,
|
| 3034 |
+
"step": 2160
|
| 3035 |
+
},
|
| 3036 |
+
{
|
| 3037 |
+
"epoch": 2.7203016970458833,
|
| 3038 |
+
"grad_norm": 0.6182135343551636,
|
| 3039 |
+
"learning_rate": 7.162817199237703e-07,
|
| 3040 |
+
"loss": 0.0643,
|
| 3041 |
+
"step": 2165
|
| 3042 |
+
},
|
| 3043 |
+
{
|
| 3044 |
+
"epoch": 2.7265870521684477,
|
| 3045 |
+
"grad_norm": 0.49758222699165344,
|
| 3046 |
+
"learning_rate": 6.849046499808575e-07,
|
| 3047 |
+
"loss": 0.0636,
|
| 3048 |
+
"step": 2170
|
| 3049 |
+
},
|
| 3050 |
+
{
|
| 3051 |
+
"epoch": 2.732872407291012,
|
| 3052 |
+
"grad_norm": 0.5210724472999573,
|
| 3053 |
+
"learning_rate": 6.54214247016181e-07,
|
| 3054 |
+
"loss": 0.0572,
|
| 3055 |
+
"step": 2175
|
| 3056 |
+
},
|
| 3057 |
+
{
|
| 3058 |
+
"epoch": 2.7391577624135763,
|
| 3059 |
+
"grad_norm": 0.4450799822807312,
|
| 3060 |
+
"learning_rate": 6.242119831880261e-07,
|
| 3061 |
+
"loss": 0.0636,
|
| 3062 |
+
"step": 2180
|
| 3063 |
+
},
|
| 3064 |
+
{
|
| 3065 |
+
"epoch": 2.7454431175361407,
|
| 3066 |
+
"grad_norm": 0.5843541622161865,
|
| 3067 |
+
"learning_rate": 5.948992976460038e-07,
|
| 3068 |
+
"loss": 0.0587,
|
| 3069 |
+
"step": 2185
|
| 3070 |
+
},
|
| 3071 |
+
{
|
| 3072 |
+
"epoch": 2.751728472658705,
|
| 3073 |
+
"grad_norm": 0.47416433691978455,
|
| 3074 |
+
"learning_rate": 5.662775964620031e-07,
|
| 3075 |
+
"loss": 0.0577,
|
| 3076 |
+
"step": 2190
|
| 3077 |
+
},
|
| 3078 |
+
{
|
| 3079 |
+
"epoch": 2.75801382778127,
|
| 3080 |
+
"grad_norm": 0.5581854581832886,
|
| 3081 |
+
"learning_rate": 5.383482525627547e-07,
|
| 3082 |
+
"loss": 0.0681,
|
| 3083 |
+
"step": 2195
|
| 3084 |
+
},
|
| 3085 |
+
{
|
| 3086 |
+
"epoch": 2.764299182903834,
|
| 3087 |
+
"grad_norm": 0.5519270896911621,
|
| 3088 |
+
"learning_rate": 5.11112605663977e-07,
|
| 3089 |
+
"loss": 0.0549,
|
| 3090 |
+
"step": 2200
|
| 3091 |
+
},
|
| 3092 |
+
{
|
| 3093 |
+
"epoch": 2.7705845380263985,
|
| 3094 |
+
"grad_norm": 0.4837780296802521,
|
| 3095 |
+
"learning_rate": 4.845719622060956e-07,
|
| 3096 |
+
"loss": 0.0523,
|
| 3097 |
+
"step": 2205
|
| 3098 |
+
},
|
| 3099 |
+
{
|
| 3100 |
+
"epoch": 2.776869893148963,
|
| 3101 |
+
"grad_norm": 0.5808846354484558,
|
| 3102 |
+
"learning_rate": 4.587275952915976e-07,
|
| 3103 |
+
"loss": 0.0615,
|
| 3104 |
+
"step": 2210
|
| 3105 |
+
},
|
| 3106 |
+
{
|
| 3107 |
+
"epoch": 2.7831552482715276,
|
| 3108 |
+
"grad_norm": 0.6188280582427979,
|
| 3109 |
+
"learning_rate": 4.335807446239526e-07,
|
| 3110 |
+
"loss": 0.0623,
|
| 3111 |
+
"step": 2215
|
| 3112 |
+
},
|
| 3113 |
+
{
|
| 3114 |
+
"epoch": 2.789440603394092,
|
| 3115 |
+
"grad_norm": 0.6088958382606506,
|
| 3116 |
+
"learning_rate": 4.0913261644813795e-07,
|
| 3117 |
+
"loss": 0.0601,
|
| 3118 |
+
"step": 2220
|
| 3119 |
+
},
|
| 3120 |
+
{
|
| 3121 |
+
"epoch": 2.7957259585166563,
|
| 3122 |
+
"grad_norm": 0.6536898612976074,
|
| 3123 |
+
"learning_rate": 3.8538438349279947e-07,
|
| 3124 |
+
"loss": 0.0643,
|
| 3125 |
+
"step": 2225
|
| 3126 |
+
},
|
| 3127 |
+
{
|
| 3128 |
+
"epoch": 2.8020113136392206,
|
| 3129 |
+
"grad_norm": 0.6247299313545227,
|
| 3130 |
+
"learning_rate": 3.623371849139751e-07,
|
| 3131 |
+
"loss": 0.0663,
|
| 3132 |
+
"step": 2230
|
| 3133 |
+
},
|
| 3134 |
+
{
|
| 3135 |
+
"epoch": 2.808296668761785,
|
| 3136 |
+
"grad_norm": 0.4167831838130951,
|
| 3137 |
+
"learning_rate": 3.399921262404665e-07,
|
| 3138 |
+
"loss": 0.0567,
|
| 3139 |
+
"step": 2235
|
| 3140 |
+
},
|
| 3141 |
+
{
|
| 3142 |
+
"epoch": 2.8145820238843493,
|
| 3143 |
+
"grad_norm": 0.5756027102470398,
|
| 3144 |
+
"learning_rate": 3.1835027932080875e-07,
|
| 3145 |
+
"loss": 0.0645,
|
| 3146 |
+
"step": 2240
|
| 3147 |
+
},
|
| 3148 |
+
{
|
| 3149 |
+
"epoch": 2.8208673790069136,
|
| 3150 |
+
"grad_norm": 0.5272979140281677,
|
| 3151 |
+
"learning_rate": 2.974126822718426e-07,
|
| 3152 |
+
"loss": 0.0581,
|
| 3153 |
+
"step": 2245
|
| 3154 |
+
},
|
| 3155 |
+
{
|
| 3156 |
+
"epoch": 2.8271527341294784,
|
| 3157 |
+
"grad_norm": 0.6276553273200989,
|
| 3158 |
+
"learning_rate": 2.7718033942893294e-07,
|
| 3159 |
+
"loss": 0.0579,
|
| 3160 |
+
"step": 2250
|
| 3161 |
+
},
|
| 3162 |
+
{
|
| 3163 |
+
"epoch": 2.8334380892520428,
|
| 3164 |
+
"grad_norm": 0.5087743401527405,
|
| 3165 |
+
"learning_rate": 2.5765422129778893e-07,
|
| 3166 |
+
"loss": 0.057,
|
| 3167 |
+
"step": 2255
|
| 3168 |
+
},
|
| 3169 |
+
{
|
| 3170 |
+
"epoch": 2.839723444374607,
|
| 3171 |
+
"grad_norm": 0.5915181636810303,
|
| 3172 |
+
"learning_rate": 2.3883526450790283e-07,
|
| 3173 |
+
"loss": 0.0627,
|
| 3174 |
+
"step": 2260
|
| 3175 |
+
},
|
| 3176 |
+
{
|
| 3177 |
+
"epoch": 2.8460087994971714,
|
| 3178 |
+
"grad_norm": 0.5618940591812134,
|
| 3179 |
+
"learning_rate": 2.2072437176763272e-07,
|
| 3180 |
+
"loss": 0.0518,
|
| 3181 |
+
"step": 2265
|
| 3182 |
+
},
|
| 3183 |
+
{
|
| 3184 |
+
"epoch": 2.8522941546197362,
|
| 3185 |
+
"grad_norm": 0.4876648187637329,
|
| 3186 |
+
"learning_rate": 2.0332241182089206e-07,
|
| 3187 |
+
"loss": 0.0582,
|
| 3188 |
+
"step": 2270
|
| 3189 |
+
},
|
| 3190 |
+
{
|
| 3191 |
+
"epoch": 2.8585795097423006,
|
| 3192 |
+
"grad_norm": 0.6045483946800232,
|
| 3193 |
+
"learning_rate": 1.8663021940548475e-07,
|
| 3194 |
+
"loss": 0.0637,
|
| 3195 |
+
"step": 2275
|
| 3196 |
+
},
|
| 3197 |
+
{
|
| 3198 |
+
"epoch": 2.864864864864865,
|
| 3199 |
+
"grad_norm": 0.5718761682510376,
|
| 3200 |
+
"learning_rate": 1.7064859521306542e-07,
|
| 3201 |
+
"loss": 0.0568,
|
| 3202 |
+
"step": 2280
|
| 3203 |
+
},
|
| 3204 |
+
{
|
| 3205 |
+
"epoch": 2.8711502199874293,
|
| 3206 |
+
"grad_norm": 0.5620940327644348,
|
| 3207 |
+
"learning_rate": 1.553783058507202e-07,
|
| 3208 |
+
"loss": 0.0571,
|
| 3209 |
+
"step": 2285
|
| 3210 |
+
},
|
| 3211 |
+
{
|
| 3212 |
+
"epoch": 2.8774355751099936,
|
| 3213 |
+
"grad_norm": 0.5204417705535889,
|
| 3214 |
+
"learning_rate": 1.4082008380420786e-07,
|
| 3215 |
+
"loss": 0.0609,
|
| 3216 |
+
"step": 2290
|
| 3217 |
+
},
|
| 3218 |
+
{
|
| 3219 |
+
"epoch": 2.883720930232558,
|
| 3220 |
+
"grad_norm": 0.3583226203918457,
|
| 3221 |
+
"learning_rate": 1.2697462740281772e-07,
|
| 3222 |
+
"loss": 0.0603,
|
| 3223 |
+
"step": 2295
|
| 3224 |
+
},
|
| 3225 |
+
{
|
| 3226 |
+
"epoch": 2.8900062853551227,
|
| 3227 |
+
"grad_norm": 0.46450498700141907,
|
| 3228 |
+
"learning_rate": 1.1384260078586673e-07,
|
| 3229 |
+
"loss": 0.0545,
|
| 3230 |
+
"step": 2300
|
| 3231 |
+
},
|
| 3232 |
+
{
|
| 3233 |
+
"epoch": 2.896291640477687,
|
| 3234 |
+
"grad_norm": 0.5413293242454529,
|
| 3235 |
+
"learning_rate": 1.0142463387085465e-07,
|
| 3236 |
+
"loss": 0.0625,
|
| 3237 |
+
"step": 2305
|
| 3238 |
+
},
|
| 3239 |
+
{
|
| 3240 |
+
"epoch": 2.9025769956002514,
|
| 3241 |
+
"grad_norm": 0.5951293110847473,
|
| 3242 |
+
"learning_rate": 8.972132232324015e-08,
|
| 3243 |
+
"loss": 0.0618,
|
| 3244 |
+
"step": 2310
|
| 3245 |
+
},
|
| 3246 |
+
{
|
| 3247 |
+
"epoch": 2.9088623507228157,
|
| 3248 |
+
"grad_norm": 0.4853385090827942,
|
| 3249 |
+
"learning_rate": 7.873322752786516e-08,
|
| 3250 |
+
"loss": 0.0509,
|
| 3251 |
+
"step": 2315
|
| 3252 |
+
},
|
| 3253 |
+
{
|
| 3254 |
+
"epoch": 2.9151477058453805,
|
| 3255 |
+
"grad_norm": 0.49007388949394226,
|
| 3256 |
+
"learning_rate": 6.846087656203314e-08,
|
| 3257 |
+
"loss": 0.0609,
|
| 3258 |
+
"step": 2320
|
| 3259 |
+
},
|
| 3260 |
+
{
|
| 3261 |
+
"epoch": 2.921433060967945,
|
| 3262 |
+
"grad_norm": 0.6433708071708679,
|
| 3263 |
+
"learning_rate": 5.8904762170224334e-08,
|
| 3264 |
+
"loss": 0.055,
|
| 3265 |
+
"step": 2325
|
| 3266 |
+
},
|
| 3267 |
+
{
|
| 3268 |
+
"epoch": 2.927718416090509,
|
| 3269 |
+
"grad_norm": 0.4079529345035553,
|
| 3270 |
+
"learning_rate": 5.00653427404546e-08,
|
| 3271 |
+
"loss": 0.051,
|
| 3272 |
+
"step": 2330
|
| 3273 |
+
},
|
| 3274 |
+
{
|
| 3275 |
+
"epoch": 2.9340037712130735,
|
| 3276 |
+
"grad_norm": 0.5446457266807556,
|
| 3277 |
+
"learning_rate": 4.194304228229806e-08,
|
| 3278 |
+
"loss": 0.0626,
|
| 3279 |
+
"step": 2335
|
| 3280 |
+
},
|
| 3281 |
+
{
|
| 3282 |
+
"epoch": 2.940289126335638,
|
| 3283 |
+
"grad_norm": 0.5291525721549988,
|
| 3284 |
+
"learning_rate": 3.453825040653502e-08,
|
| 3285 |
+
"loss": 0.0634,
|
| 3286 |
+
"step": 2340
|
| 3287 |
+
},
|
| 3288 |
+
{
|
| 3289 |
+
"epoch": 2.946574481458202,
|
| 3290 |
+
"grad_norm": 0.6517899036407471,
|
| 3291 |
+
"learning_rate": 2.7851322306473583e-08,
|
| 3292 |
+
"loss": 0.0678,
|
| 3293 |
+
"step": 2345
|
| 3294 |
+
},
|
| 3295 |
+
{
|
| 3296 |
+
"epoch": 2.9528598365807666,
|
| 3297 |
+
"grad_norm": 0.4177451431751251,
|
| 3298 |
+
"learning_rate": 2.1882578740908265e-08,
|
| 3299 |
+
"loss": 0.0525,
|
| 3300 |
+
"step": 2350
|
| 3301 |
+
},
|
| 3302 |
+
{
|
| 3303 |
+
"epoch": 2.9591451917033313,
|
| 3304 |
+
"grad_norm": 0.5371739864349365,
|
| 3305 |
+
"learning_rate": 1.663230601873067e-08,
|
| 3306 |
+
"loss": 0.0588,
|
| 3307 |
+
"step": 2355
|
| 3308 |
+
},
|
| 3309 |
+
{
|
| 3310 |
+
"epoch": 2.9654305468258957,
|
| 3311 |
+
"grad_norm": 0.6102943420410156,
|
| 3312 |
+
"learning_rate": 1.2100755985202105e-08,
|
| 3313 |
+
"loss": 0.0652,
|
| 3314 |
+
"step": 2360
|
| 3315 |
+
},
|
| 3316 |
+
{
|
| 3317 |
+
"epoch": 2.97171590194846,
|
| 3318 |
+
"grad_norm": 0.712878942489624,
|
| 3319 |
+
"learning_rate": 8.288146009866603e-09,
|
| 3320 |
+
"loss": 0.0715,
|
| 3321 |
+
"step": 2365
|
| 3322 |
+
},
|
| 3323 |
+
{
|
| 3324 |
+
"epoch": 2.9780012570710244,
|
| 3325 |
+
"grad_norm": 0.5315341949462891,
|
| 3326 |
+
"learning_rate": 5.1946589761275866e-09,
|
| 3327 |
+
"loss": 0.0662,
|
| 3328 |
+
"step": 2370
|
| 3329 |
+
},
|
| 3330 |
+
{
|
| 3331 |
+
"epoch": 2.984286612193589,
|
| 3332 |
+
"grad_norm": 0.3915427625179291,
|
| 3333 |
+
"learning_rate": 2.8204432724798777e-09,
|
| 3334 |
+
"loss": 0.0556,
|
| 3335 |
+
"step": 2375
|
| 3336 |
+
},
|
| 3337 |
+
{
|
| 3338 |
+
"epoch": 2.9905719673161535,
|
| 3339 |
+
"grad_norm": 0.4266071319580078,
|
| 3340 |
+
"learning_rate": 1.1656127853770793e-09,
|
| 3341 |
+
"loss": 0.0601,
|
| 3342 |
+
"step": 2380
|
| 3343 |
+
},
|
| 3344 |
+
{
|
| 3345 |
+
"epoch": 2.996857322438718,
|
| 3346 |
+
"grad_norm": 0.5269129872322083,
|
| 3347 |
+
"learning_rate": 2.3024689378925435e-10,
|
| 3348 |
+
"loss": 0.0649,
|
| 3349 |
+
"step": 2385
|
| 3350 |
+
},
|
| 3351 |
+
{
|
| 3352 |
+
"epoch": 3.0,
|
| 3353 |
+
"step": 2388,
|
| 3354 |
+
"total_flos": 2.994644650003792e+18,
|
| 3355 |
+
"train_loss": 0.3442072710973933,
|
| 3356 |
+
"train_runtime": 1455.861,
|
| 3357 |
+
"train_samples_per_second": 52.443,
|
| 3358 |
+
"train_steps_per_second": 1.64
|
| 3359 |
+
}
|
| 3360 |
+
],
|
| 3361 |
+
"logging_steps": 5,
|
| 3362 |
+
"max_steps": 2388,
|
| 3363 |
+
"num_input_tokens_seen": 0,
|
| 3364 |
+
"num_train_epochs": 3,
|
| 3365 |
+
"save_steps": 20000,
|
| 3366 |
+
"stateful_callbacks": {
|
| 3367 |
+
"TrainerControl": {
|
| 3368 |
+
"args": {
|
| 3369 |
+
"should_epoch_stop": false,
|
| 3370 |
+
"should_evaluate": false,
|
| 3371 |
+
"should_log": false,
|
| 3372 |
+
"should_save": false,
|
| 3373 |
+
"should_training_stop": false
|
| 3374 |
+
},
|
| 3375 |
+
"attributes": {}
|
| 3376 |
+
}
|
| 3377 |
+
},
|
| 3378 |
+
"total_flos": 2.994644650003792e+18,
|
| 3379 |
+
"train_batch_size": 2,
|
| 3380 |
+
"trial_name": null,
|
| 3381 |
+
"trial_params": null
|
| 3382 |
+
}
|
instruct/128_128_e3_3e-5/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee10aea200d27a4b871f002c6d857f422d93e3ab14d570e5d9267f9bdcec8ee7
|
| 3 |
+
size 8273
|
instruct/128_128_e3_3e-5/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|