Upload folder using huggingface_hub
Browse files- 119_128_e3_3e-5/adapter_config.json +39 -0
- 119_128_e3_3e-5/adapter_model.safetensors +3 -0
- 119_128_e3_3e-5/added_tokens.json +9 -0
- 119_128_e3_3e-5/all_results.json +9 -0
- 119_128_e3_3e-5/chat_template.jinja +62 -0
- 119_128_e3_3e-5/config.json +32 -0
- 119_128_e3_3e-5/merges.txt +0 -0
- 119_128_e3_3e-5/special_tokens_map.json +33 -0
- 119_128_e3_3e-5/tokenizer.json +0 -0
- 119_128_e3_3e-5/tokenizer_config.json +234 -0
- 119_128_e3_3e-5/train_results.json +9 -0
- 119_128_e3_3e-5/trainer_state.json +1618 -0
- 119_128_e3_3e-5/training_args.bin +3 -0
- 119_128_e3_3e-5/vocab.json +0 -0
119_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 |
+
"o_proj",
|
| 28 |
+
"k_proj",
|
| 29 |
+
"q_proj",
|
| 30 |
+
"v_proj",
|
| 31 |
+
"up_proj",
|
| 32 |
+
"gate_proj",
|
| 33 |
+
"down_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
+
"use_dora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
119_128_e3_3e-5/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:715f291337ef76f4e4573c7dbb0dc71141861a0f6d6cc9722ecd6de10708745c
|
| 3 |
+
size 791751704
|
119_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 |
+
}
|
119_128_e3_3e-5/all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 1.5976229698011136e+18,
|
| 4 |
+
"train_loss": 0.5715485998789469,
|
| 5 |
+
"train_runtime": 747.2338,
|
| 6 |
+
"train_samples": 12000,
|
| 7 |
+
"train_samples_per_second": 48.178,
|
| 8 |
+
"train_steps_per_second": 1.506
|
| 9 |
+
}
|
119_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 %}
|
119_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 |
+
}
|
119_128_e3_3e-5/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
119_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 |
+
}
|
119_128_e3_3e-5/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
119_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 |
+
}
|
119_128_e3_3e-5/train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 1.5976229698011136e+18,
|
| 4 |
+
"train_loss": 0.5715485998789469,
|
| 5 |
+
"train_runtime": 747.2338,
|
| 6 |
+
"train_samples": 12000,
|
| 7 |
+
"train_samples_per_second": 48.178,
|
| 8 |
+
"train_steps_per_second": 1.506
|
| 9 |
+
}
|
119_128_e3_3e-5/trainer_state.json
ADDED
|
@@ -0,0 +1,1618 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 1125,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.013333333333333334,
|
| 14 |
+
"grad_norm": 3.255089282989502,
|
| 15 |
+
"learning_rate": 2.1052631578947366e-06,
|
| 16 |
+
"loss": 1.6481,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.02666666666666667,
|
| 21 |
+
"grad_norm": 2.281451940536499,
|
| 22 |
+
"learning_rate": 4.736842105263158e-06,
|
| 23 |
+
"loss": 1.568,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.04,
|
| 28 |
+
"grad_norm": 0.8792422413825989,
|
| 29 |
+
"learning_rate": 7.3684210526315784e-06,
|
| 30 |
+
"loss": 1.4206,
|
| 31 |
+
"step": 15
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.05333333333333334,
|
| 35 |
+
"grad_norm": 0.5659372210502625,
|
| 36 |
+
"learning_rate": 9.999999999999999e-06,
|
| 37 |
+
"loss": 1.3994,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.06666666666666667,
|
| 42 |
+
"grad_norm": 0.49395468831062317,
|
| 43 |
+
"learning_rate": 1.263157894736842e-05,
|
| 44 |
+
"loss": 1.3987,
|
| 45 |
+
"step": 25
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.08,
|
| 49 |
+
"grad_norm": 0.37605854868888855,
|
| 50 |
+
"learning_rate": 1.5263157894736842e-05,
|
| 51 |
+
"loss": 1.3026,
|
| 52 |
+
"step": 30
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.09333333333333334,
|
| 56 |
+
"grad_norm": 0.5765936970710754,
|
| 57 |
+
"learning_rate": 1.7894736842105264e-05,
|
| 58 |
+
"loss": 1.3841,
|
| 59 |
+
"step": 35
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.10666666666666667,
|
| 63 |
+
"grad_norm": 0.3517501652240753,
|
| 64 |
+
"learning_rate": 2.0526315789473685e-05,
|
| 65 |
+
"loss": 1.3613,
|
| 66 |
+
"step": 40
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.12,
|
| 70 |
+
"grad_norm": 0.3450149893760681,
|
| 71 |
+
"learning_rate": 2.3157894736842103e-05,
|
| 72 |
+
"loss": 1.3156,
|
| 73 |
+
"step": 45
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.13333333333333333,
|
| 77 |
+
"grad_norm": 0.3605840802192688,
|
| 78 |
+
"learning_rate": 2.578947368421053e-05,
|
| 79 |
+
"loss": 1.284,
|
| 80 |
+
"step": 50
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.14666666666666667,
|
| 84 |
+
"grad_norm": 0.3231770992279053,
|
| 85 |
+
"learning_rate": 2.8421052631578946e-05,
|
| 86 |
+
"loss": 1.2127,
|
| 87 |
+
"step": 55
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.16,
|
| 91 |
+
"grad_norm": 0.3648735284805298,
|
| 92 |
+
"learning_rate": 2.9999740416405374e-05,
|
| 93 |
+
"loss": 1.2488,
|
| 94 |
+
"step": 60
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.17333333333333334,
|
| 98 |
+
"grad_norm": 0.38475602865219116,
|
| 99 |
+
"learning_rate": 2.9996820204146065e-05,
|
| 100 |
+
"loss": 1.2473,
|
| 101 |
+
"step": 65
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.18666666666666668,
|
| 105 |
+
"grad_norm": 0.38595470786094666,
|
| 106 |
+
"learning_rate": 2.9990655933929675e-05,
|
| 107 |
+
"loss": 1.2391,
|
| 108 |
+
"step": 70
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.2,
|
| 112 |
+
"grad_norm": 0.4265404939651489,
|
| 113 |
+
"learning_rate": 2.998124893918886e-05,
|
| 114 |
+
"loss": 1.2738,
|
| 115 |
+
"step": 75
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.21333333333333335,
|
| 119 |
+
"grad_norm": 0.37171587347984314,
|
| 120 |
+
"learning_rate": 2.9968601254810732e-05,
|
| 121 |
+
"loss": 1.1536,
|
| 122 |
+
"step": 80
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.22666666666666666,
|
| 126 |
+
"grad_norm": 0.39155617356300354,
|
| 127 |
+
"learning_rate": 2.995271561669667e-05,
|
| 128 |
+
"loss": 1.1563,
|
| 129 |
+
"step": 85
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.24,
|
| 133 |
+
"grad_norm": 0.38927343487739563,
|
| 134 |
+
"learning_rate": 2.993359546117052e-05,
|
| 135 |
+
"loss": 1.1653,
|
| 136 |
+
"step": 90
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.25333333333333335,
|
| 140 |
+
"grad_norm": 0.4522983729839325,
|
| 141 |
+
"learning_rate": 2.9911244924235226e-05,
|
| 142 |
+
"loss": 1.1746,
|
| 143 |
+
"step": 95
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.26666666666666666,
|
| 147 |
+
"grad_norm": 0.4188370704650879,
|
| 148 |
+
"learning_rate": 2.9885668840678184e-05,
|
| 149 |
+
"loss": 1.1528,
|
| 150 |
+
"step": 100
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.28,
|
| 154 |
+
"grad_norm": 0.45815467834472656,
|
| 155 |
+
"learning_rate": 2.985687274302537e-05,
|
| 156 |
+
"loss": 1.1125,
|
| 157 |
+
"step": 105
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.29333333333333333,
|
| 161 |
+
"grad_norm": 0.45355895161628723,
|
| 162 |
+
"learning_rate": 2.982486286034458e-05,
|
| 163 |
+
"loss": 1.1268,
|
| 164 |
+
"step": 110
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.30666666666666664,
|
| 168 |
+
"grad_norm": 0.4581115245819092,
|
| 169 |
+
"learning_rate": 2.9789646116897966e-05,
|
| 170 |
+
"loss": 1.1292,
|
| 171 |
+
"step": 115
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.32,
|
| 175 |
+
"grad_norm": 0.45455339550971985,
|
| 176 |
+
"learning_rate": 2.9751230130644217e-05,
|
| 177 |
+
"loss": 1.1632,
|
| 178 |
+
"step": 120
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.3333333333333333,
|
| 182 |
+
"grad_norm": 0.606829822063446,
|
| 183 |
+
"learning_rate": 2.9709623211590674e-05,
|
| 184 |
+
"loss": 1.0803,
|
| 185 |
+
"step": 125
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.3466666666666667,
|
| 189 |
+
"grad_norm": 0.43838202953338623,
|
| 190 |
+
"learning_rate": 2.966483435999572e-05,
|
| 191 |
+
"loss": 1.04,
|
| 192 |
+
"step": 130
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.36,
|
| 196 |
+
"grad_norm": 0.5282702445983887,
|
| 197 |
+
"learning_rate": 2.9616873264421887e-05,
|
| 198 |
+
"loss": 1.049,
|
| 199 |
+
"step": 135
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.37333333333333335,
|
| 203 |
+
"grad_norm": 0.501373291015625,
|
| 204 |
+
"learning_rate": 2.9565750299640078e-05,
|
| 205 |
+
"loss": 1.0154,
|
| 206 |
+
"step": 140
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.38666666666666666,
|
| 210 |
+
"grad_norm": 0.5567037463188171,
|
| 211 |
+
"learning_rate": 2.95114765243853e-05,
|
| 212 |
+
"loss": 1.0668,
|
| 213 |
+
"step": 145
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.4,
|
| 217 |
+
"grad_norm": 0.555442214012146,
|
| 218 |
+
"learning_rate": 2.9454063678964502e-05,
|
| 219 |
+
"loss": 1.0402,
|
| 220 |
+
"step": 150
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.41333333333333333,
|
| 224 |
+
"grad_norm": 0.5159408450126648,
|
| 225 |
+
"learning_rate": 2.9393524182716958e-05,
|
| 226 |
+
"loss": 1.026,
|
| 227 |
+
"step": 155
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.4266666666666667,
|
| 231 |
+
"grad_norm": 0.6307178735733032,
|
| 232 |
+
"learning_rate": 2.9329871131327735e-05,
|
| 233 |
+
"loss": 0.9848,
|
| 234 |
+
"step": 160
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.44,
|
| 238 |
+
"grad_norm": 0.5444524884223938,
|
| 239 |
+
"learning_rate": 2.9263118293994908e-05,
|
| 240 |
+
"loss": 1.0017,
|
| 241 |
+
"step": 165
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.4533333333333333,
|
| 245 |
+
"grad_norm": 0.5631515979766846,
|
| 246 |
+
"learning_rate": 2.9193280110451042e-05,
|
| 247 |
+
"loss": 0.9546,
|
| 248 |
+
"step": 170
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.4666666666666667,
|
| 252 |
+
"grad_norm": 0.5779924988746643,
|
| 253 |
+
"learning_rate": 2.9120371687839658e-05,
|
| 254 |
+
"loss": 0.9696,
|
| 255 |
+
"step": 175
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.48,
|
| 259 |
+
"grad_norm": 0.6219637393951416,
|
| 260 |
+
"learning_rate": 2.9044408797447277e-05,
|
| 261 |
+
"loss": 0.9619,
|
| 262 |
+
"step": 180
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.49333333333333335,
|
| 266 |
+
"grad_norm": 0.6588303446769714,
|
| 267 |
+
"learning_rate": 2.896540787129187e-05,
|
| 268 |
+
"loss": 1.0218,
|
| 269 |
+
"step": 185
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.5066666666666667,
|
| 273 |
+
"grad_norm": 0.7458450794219971,
|
| 274 |
+
"learning_rate": 2.8883385998568318e-05,
|
| 275 |
+
"loss": 0.9387,
|
| 276 |
+
"step": 190
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.52,
|
| 280 |
+
"grad_norm": 0.6931763291358948,
|
| 281 |
+
"learning_rate": 2.879836092195175e-05,
|
| 282 |
+
"loss": 0.9901,
|
| 283 |
+
"step": 195
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.5333333333333333,
|
| 287 |
+
"grad_norm": 0.6760740280151367,
|
| 288 |
+
"learning_rate": 2.871035103375952e-05,
|
| 289 |
+
"loss": 0.9425,
|
| 290 |
+
"step": 200
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.5466666666666666,
|
| 294 |
+
"grad_norm": 0.7678902745246887,
|
| 295 |
+
"learning_rate": 2.8619375371972615e-05,
|
| 296 |
+
"loss": 0.9348,
|
| 297 |
+
"step": 205
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.56,
|
| 301 |
+
"grad_norm": 0.6632644534111023,
|
| 302 |
+
"learning_rate": 2.852545361611747e-05,
|
| 303 |
+
"loss": 0.9313,
|
| 304 |
+
"step": 210
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.5733333333333334,
|
| 308 |
+
"grad_norm": 0.7125438451766968,
|
| 309 |
+
"learning_rate": 2.8428606083008928e-05,
|
| 310 |
+
"loss": 0.8767,
|
| 311 |
+
"step": 215
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.5866666666666667,
|
| 315 |
+
"grad_norm": 0.7794106602668762,
|
| 316 |
+
"learning_rate": 2.8328853722355404e-05,
|
| 317 |
+
"loss": 0.8573,
|
| 318 |
+
"step": 220
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.6,
|
| 322 |
+
"grad_norm": 0.7575399875640869,
|
| 323 |
+
"learning_rate": 2.8226218112227115e-05,
|
| 324 |
+
"loss": 0.9314,
|
| 325 |
+
"step": 225
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.6133333333333333,
|
| 329 |
+
"grad_norm": 0.820282518863678,
|
| 330 |
+
"learning_rate": 2.8120721454388376e-05,
|
| 331 |
+
"loss": 0.8605,
|
| 332 |
+
"step": 230
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.6266666666666667,
|
| 336 |
+
"grad_norm": 0.7544353008270264,
|
| 337 |
+
"learning_rate": 2.8012386569495007e-05,
|
| 338 |
+
"loss": 0.828,
|
| 339 |
+
"step": 235
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.64,
|
| 343 |
+
"grad_norm": 0.7657877802848816,
|
| 344 |
+
"learning_rate": 2.7901236892157863e-05,
|
| 345 |
+
"loss": 0.8123,
|
| 346 |
+
"step": 240
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.6533333333333333,
|
| 350 |
+
"grad_norm": 0.8684191107749939,
|
| 351 |
+
"learning_rate": 2.77872964658735e-05,
|
| 352 |
+
"loss": 0.8484,
|
| 353 |
+
"step": 245
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.6666666666666666,
|
| 357 |
+
"grad_norm": 0.9245997071266174,
|
| 358 |
+
"learning_rate": 2.767058993782323e-05,
|
| 359 |
+
"loss": 0.8201,
|
| 360 |
+
"step": 250
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.68,
|
| 364 |
+
"grad_norm": 0.7566134333610535,
|
| 365 |
+
"learning_rate": 2.7551142553541496e-05,
|
| 366 |
+
"loss": 0.8516,
|
| 367 |
+
"step": 255
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.6933333333333334,
|
| 371 |
+
"grad_norm": 0.8094231486320496,
|
| 372 |
+
"learning_rate": 2.742898015145485e-05,
|
| 373 |
+
"loss": 0.8045,
|
| 374 |
+
"step": 260
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.7066666666666667,
|
| 378 |
+
"grad_norm": 0.795017659664154,
|
| 379 |
+
"learning_rate": 2.7304129157292688e-05,
|
| 380 |
+
"loss": 0.8095,
|
| 381 |
+
"step": 265
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.72,
|
| 385 |
+
"grad_norm": 0.8331682682037354,
|
| 386 |
+
"learning_rate": 2.717661657837094e-05,
|
| 387 |
+
"loss": 0.7985,
|
| 388 |
+
"step": 270
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.7333333333333333,
|
| 392 |
+
"grad_norm": 0.8600038886070251,
|
| 393 |
+
"learning_rate": 2.7046469997749912e-05,
|
| 394 |
+
"loss": 0.7944,
|
| 395 |
+
"step": 275
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.7466666666666667,
|
| 399 |
+
"grad_norm": 0.8596172332763672,
|
| 400 |
+
"learning_rate": 2.6913717568267665e-05,
|
| 401 |
+
"loss": 0.7919,
|
| 402 |
+
"step": 280
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.76,
|
| 406 |
+
"grad_norm": 0.7767606377601624,
|
| 407 |
+
"learning_rate": 2.677838800645005e-05,
|
| 408 |
+
"loss": 0.7651,
|
| 409 |
+
"step": 285
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.7733333333333333,
|
| 413 |
+
"grad_norm": 0.8865847587585449,
|
| 414 |
+
"learning_rate": 2.664051058629888e-05,
|
| 415 |
+
"loss": 0.7668,
|
| 416 |
+
"step": 290
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.7866666666666666,
|
| 420 |
+
"grad_norm": 0.9619648456573486,
|
| 421 |
+
"learning_rate": 2.6500115132959478e-05,
|
| 422 |
+
"loss": 0.7353,
|
| 423 |
+
"step": 295
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.8,
|
| 427 |
+
"grad_norm": 0.8714637756347656,
|
| 428 |
+
"learning_rate": 2.6357232016269006e-05,
|
| 429 |
+
"loss": 0.7511,
|
| 430 |
+
"step": 300
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.8133333333333334,
|
| 434 |
+
"grad_norm": 0.9778738617897034,
|
| 435 |
+
"learning_rate": 2.621189214418697e-05,
|
| 436 |
+
"loss": 0.7541,
|
| 437 |
+
"step": 305
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.8266666666666667,
|
| 441 |
+
"grad_norm": 0.8684325814247131,
|
| 442 |
+
"learning_rate": 2.606412695610933e-05,
|
| 443 |
+
"loss": 0.7316,
|
| 444 |
+
"step": 310
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.84,
|
| 448 |
+
"grad_norm": 0.8607895374298096,
|
| 449 |
+
"learning_rate": 2.5913968416067644e-05,
|
| 450 |
+
"loss": 0.713,
|
| 451 |
+
"step": 315
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.8533333333333334,
|
| 455 |
+
"grad_norm": 0.9606837630271912,
|
| 456 |
+
"learning_rate": 2.57614490058147e-05,
|
| 457 |
+
"loss": 0.7389,
|
| 458 |
+
"step": 320
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.8666666666666667,
|
| 462 |
+
"grad_norm": 0.8882506489753723,
|
| 463 |
+
"learning_rate": 2.5606601717798212e-05,
|
| 464 |
+
"loss": 0.6839,
|
| 465 |
+
"step": 325
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.88,
|
| 469 |
+
"grad_norm": 0.9489732384681702,
|
| 470 |
+
"learning_rate": 2.5449460048024005e-05,
|
| 471 |
+
"loss": 0.7358,
|
| 472 |
+
"step": 330
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.8933333333333333,
|
| 476 |
+
"grad_norm": 1.0513393878936768,
|
| 477 |
+
"learning_rate": 2.5290057988810267e-05,
|
| 478 |
+
"loss": 0.7131,
|
| 479 |
+
"step": 335
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.9066666666666666,
|
| 483 |
+
"grad_norm": 0.9554797410964966,
|
| 484 |
+
"learning_rate": 2.512843002143446e-05,
|
| 485 |
+
"loss": 0.6798,
|
| 486 |
+
"step": 340
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.92,
|
| 490 |
+
"grad_norm": 1.0012837648391724,
|
| 491 |
+
"learning_rate": 2.4964611108674464e-05,
|
| 492 |
+
"loss": 0.6774,
|
| 493 |
+
"step": 345
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.9333333333333333,
|
| 497 |
+
"grad_norm": 0.9797089695930481,
|
| 498 |
+
"learning_rate": 2.479863668724554e-05,
|
| 499 |
+
"loss": 0.7059,
|
| 500 |
+
"step": 350
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.9466666666666667,
|
| 504 |
+
"grad_norm": 0.8635170459747314,
|
| 505 |
+
"learning_rate": 2.4630542660134808e-05,
|
| 506 |
+
"loss": 0.6797,
|
| 507 |
+
"step": 355
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.96,
|
| 511 |
+
"grad_norm": 1.0703717470169067,
|
| 512 |
+
"learning_rate": 2.4460365388834816e-05,
|
| 513 |
+
"loss": 0.6995,
|
| 514 |
+
"step": 360
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.9733333333333334,
|
| 518 |
+
"grad_norm": 1.0388541221618652,
|
| 519 |
+
"learning_rate": 2.428814168547798e-05,
|
| 520 |
+
"loss": 0.6986,
|
| 521 |
+
"step": 365
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.9866666666666667,
|
| 525 |
+
"grad_norm": 0.9200866222381592,
|
| 526 |
+
"learning_rate": 2.4113908804873486e-05,
|
| 527 |
+
"loss": 0.6602,
|
| 528 |
+
"step": 370
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.0,
|
| 532 |
+
"grad_norm": 0.9522541761398315,
|
| 533 |
+
"learning_rate": 2.3937704436448502e-05,
|
| 534 |
+
"loss": 0.6696,
|
| 535 |
+
"step": 375
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.0133333333333334,
|
| 539 |
+
"grad_norm": 0.9973103404045105,
|
| 540 |
+
"learning_rate": 2.3759566696095304e-05,
|
| 541 |
+
"loss": 0.5718,
|
| 542 |
+
"step": 380
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.0266666666666666,
|
| 546 |
+
"grad_norm": 0.9664887189865112,
|
| 547 |
+
"learning_rate": 2.3579534117926214e-05,
|
| 548 |
+
"loss": 0.5753,
|
| 549 |
+
"step": 385
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.04,
|
| 553 |
+
"grad_norm": 1.1464637517929077,
|
| 554 |
+
"learning_rate": 2.3397645645938002e-05,
|
| 555 |
+
"loss": 0.5618,
|
| 556 |
+
"step": 390
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.0533333333333332,
|
| 560 |
+
"grad_norm": 0.9304021000862122,
|
| 561 |
+
"learning_rate": 2.321394062558769e-05,
|
| 562 |
+
"loss": 0.6236,
|
| 563 |
+
"step": 395
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.0666666666666667,
|
| 567 |
+
"grad_norm": 0.9449813365936279,
|
| 568 |
+
"learning_rate": 2.3028458795281487e-05,
|
| 569 |
+
"loss": 0.6067,
|
| 570 |
+
"step": 400
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.08,
|
| 574 |
+
"grad_norm": 0.9770338535308838,
|
| 575 |
+
"learning_rate": 2.284124027777871e-05,
|
| 576 |
+
"loss": 0.5788,
|
| 577 |
+
"step": 405
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.0933333333333333,
|
| 581 |
+
"grad_norm": 0.9186968207359314,
|
| 582 |
+
"learning_rate": 2.2652325571512562e-05,
|
| 583 |
+
"loss": 0.5651,
|
| 584 |
+
"step": 410
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.1066666666666667,
|
| 588 |
+
"grad_norm": 1.202286720275879,
|
| 589 |
+
"learning_rate": 2.246175554182968e-05,
|
| 590 |
+
"loss": 0.59,
|
| 591 |
+
"step": 415
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.12,
|
| 595 |
+
"grad_norm": 0.9755830764770508,
|
| 596 |
+
"learning_rate": 2.2269571412150283e-05,
|
| 597 |
+
"loss": 0.5374,
|
| 598 |
+
"step": 420
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.1333333333333333,
|
| 602 |
+
"grad_norm": 1.0108706951141357,
|
| 603 |
+
"learning_rate": 2.207581475505086e-05,
|
| 604 |
+
"loss": 0.5692,
|
| 605 |
+
"step": 425
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.1466666666666667,
|
| 609 |
+
"grad_norm": 1.0483158826828003,
|
| 610 |
+
"learning_rate": 2.1880527483271357e-05,
|
| 611 |
+
"loss": 0.5286,
|
| 612 |
+
"step": 430
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.16,
|
| 616 |
+
"grad_norm": 1.0590232610702515,
|
| 617 |
+
"learning_rate": 2.168375184064876e-05,
|
| 618 |
+
"loss": 0.5471,
|
| 619 |
+
"step": 435
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.1733333333333333,
|
| 623 |
+
"grad_norm": 1.013076663017273,
|
| 624 |
+
"learning_rate": 2.1485530392979047e-05,
|
| 625 |
+
"loss": 0.5204,
|
| 626 |
+
"step": 440
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.1866666666666668,
|
| 630 |
+
"grad_norm": 1.0279020071029663,
|
| 631 |
+
"learning_rate": 2.1285906018809524e-05,
|
| 632 |
+
"loss": 0.4985,
|
| 633 |
+
"step": 445
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.2,
|
| 637 |
+
"grad_norm": 0.9609928131103516,
|
| 638 |
+
"learning_rate": 2.1084921900163495e-05,
|
| 639 |
+
"loss": 0.4906,
|
| 640 |
+
"step": 450
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.2133333333333334,
|
| 644 |
+
"grad_norm": 1.0580848455429077,
|
| 645 |
+
"learning_rate": 2.0882621513199265e-05,
|
| 646 |
+
"loss": 0.4999,
|
| 647 |
+
"step": 455
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.2266666666666666,
|
| 651 |
+
"grad_norm": 1.028907299041748,
|
| 652 |
+
"learning_rate": 2.0679048618805552e-05,
|
| 653 |
+
"loss": 0.5286,
|
| 654 |
+
"step": 460
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.24,
|
| 658 |
+
"grad_norm": 0.9270009398460388,
|
| 659 |
+
"learning_rate": 2.0474247253135284e-05,
|
| 660 |
+
"loss": 0.49,
|
| 661 |
+
"step": 465
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.2533333333333334,
|
| 665 |
+
"grad_norm": 1.1451140642166138,
|
| 666 |
+
"learning_rate": 2.0268261718079842e-05,
|
| 667 |
+
"loss": 0.4956,
|
| 668 |
+
"step": 470
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.2666666666666666,
|
| 672 |
+
"grad_norm": 1.1311115026474,
|
| 673 |
+
"learning_rate": 2.0061136571685875e-05,
|
| 674 |
+
"loss": 0.5308,
|
| 675 |
+
"step": 475
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.28,
|
| 679 |
+
"grad_norm": 1.0913636684417725,
|
| 680 |
+
"learning_rate": 1.9852916618516622e-05,
|
| 681 |
+
"loss": 0.5331,
|
| 682 |
+
"step": 480
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.2933333333333334,
|
| 686 |
+
"grad_norm": 1.0560921430587769,
|
| 687 |
+
"learning_rate": 1.9643646899959972e-05,
|
| 688 |
+
"loss": 0.5041,
|
| 689 |
+
"step": 485
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.3066666666666666,
|
| 693 |
+
"grad_norm": 1.0420132875442505,
|
| 694 |
+
"learning_rate": 1.9433372684485264e-05,
|
| 695 |
+
"loss": 0.5461,
|
| 696 |
+
"step": 490
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.32,
|
| 700 |
+
"grad_norm": 1.014164924621582,
|
| 701 |
+
"learning_rate": 1.922213945785098e-05,
|
| 702 |
+
"loss": 0.5002,
|
| 703 |
+
"step": 495
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.3333333333333333,
|
| 707 |
+
"grad_norm": 1.1519591808319092,
|
| 708 |
+
"learning_rate": 1.9009992913265453e-05,
|
| 709 |
+
"loss": 0.4696,
|
| 710 |
+
"step": 500
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.3466666666666667,
|
| 714 |
+
"grad_norm": 1.036902904510498,
|
| 715 |
+
"learning_rate": 1.8796978941502626e-05,
|
| 716 |
+
"loss": 0.4911,
|
| 717 |
+
"step": 505
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.3599999999999999,
|
| 721 |
+
"grad_norm": 1.1804707050323486,
|
| 722 |
+
"learning_rate": 1.8583143620975167e-05,
|
| 723 |
+
"loss": 0.4873,
|
| 724 |
+
"step": 510
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.3733333333333333,
|
| 728 |
+
"grad_norm": 0.9840912222862244,
|
| 729 |
+
"learning_rate": 1.8368533207766945e-05,
|
| 730 |
+
"loss": 0.4973,
|
| 731 |
+
"step": 515
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.3866666666666667,
|
| 735 |
+
"grad_norm": 0.9903191924095154,
|
| 736 |
+
"learning_rate": 1.815319412562707e-05,
|
| 737 |
+
"loss": 0.4985,
|
| 738 |
+
"step": 520
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.4,
|
| 742 |
+
"grad_norm": 1.0903496742248535,
|
| 743 |
+
"learning_rate": 1.7937172955927677e-05,
|
| 744 |
+
"loss": 0.465,
|
| 745 |
+
"step": 525
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.4133333333333333,
|
| 749 |
+
"grad_norm": 1.314017415046692,
|
| 750 |
+
"learning_rate": 1.7720516427587637e-05,
|
| 751 |
+
"loss": 0.4833,
|
| 752 |
+
"step": 530
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.4266666666666667,
|
| 756 |
+
"grad_norm": 1.1070406436920166,
|
| 757 |
+
"learning_rate": 1.750327140696429e-05,
|
| 758 |
+
"loss": 0.4434,
|
| 759 |
+
"step": 535
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.44,
|
| 763 |
+
"grad_norm": 1.1966391801834106,
|
| 764 |
+
"learning_rate": 1.7285484887715505e-05,
|
| 765 |
+
"loss": 0.4782,
|
| 766 |
+
"step": 540
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.4533333333333334,
|
| 770 |
+
"grad_norm": 1.1694577932357788,
|
| 771 |
+
"learning_rate": 1.7067203980634176e-05,
|
| 772 |
+
"loss": 0.4105,
|
| 773 |
+
"step": 545
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.4666666666666668,
|
| 777 |
+
"grad_norm": 1.1524282693862915,
|
| 778 |
+
"learning_rate": 1.6848475903457378e-05,
|
| 779 |
+
"loss": 0.4618,
|
| 780 |
+
"step": 550
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.48,
|
| 784 |
+
"grad_norm": 1.1326038837432861,
|
| 785 |
+
"learning_rate": 1.6629347970652434e-05,
|
| 786 |
+
"loss": 0.4091,
|
| 787 |
+
"step": 555
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.4933333333333334,
|
| 791 |
+
"grad_norm": 1.0674124956130981,
|
| 792 |
+
"learning_rate": 1.6409867583181957e-05,
|
| 793 |
+
"loss": 0.4774,
|
| 794 |
+
"step": 560
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.5066666666666668,
|
| 798 |
+
"grad_norm": 1.0575978755950928,
|
| 799 |
+
"learning_rate": 1.6190082218250297e-05,
|
| 800 |
+
"loss": 0.4327,
|
| 801 |
+
"step": 565
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.52,
|
| 805 |
+
"grad_norm": 1.0775343179702759,
|
| 806 |
+
"learning_rate": 1.5970039419033428e-05,
|
| 807 |
+
"loss": 0.4213,
|
| 808 |
+
"step": 570
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.5333333333333332,
|
| 812 |
+
"grad_norm": 1.094995379447937,
|
| 813 |
+
"learning_rate": 1.574978678439457e-05,
|
| 814 |
+
"loss": 0.4757,
|
| 815 |
+
"step": 575
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.5466666666666666,
|
| 819 |
+
"grad_norm": 1.0848252773284912,
|
| 820 |
+
"learning_rate": 1.5529371958587788e-05,
|
| 821 |
+
"loss": 0.4728,
|
| 822 |
+
"step": 580
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.56,
|
| 826 |
+
"grad_norm": 1.0148414373397827,
|
| 827 |
+
"learning_rate": 1.530884262095176e-05,
|
| 828 |
+
"loss": 0.4514,
|
| 829 |
+
"step": 585
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.5733333333333333,
|
| 833 |
+
"grad_norm": 0.9920549392700195,
|
| 834 |
+
"learning_rate": 1.5088246475595933e-05,
|
| 835 |
+
"loss": 0.4347,
|
| 836 |
+
"step": 590
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.5866666666666667,
|
| 840 |
+
"grad_norm": 1.2604056596755981,
|
| 841 |
+
"learning_rate": 1.4867631241081384e-05,
|
| 842 |
+
"loss": 0.3995,
|
| 843 |
+
"step": 595
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.6,
|
| 847 |
+
"grad_norm": 1.182700514793396,
|
| 848 |
+
"learning_rate": 1.4647044640098456e-05,
|
| 849 |
+
"loss": 0.4107,
|
| 850 |
+
"step": 600
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.6133333333333333,
|
| 854 |
+
"grad_norm": 1.2505168914794922,
|
| 855 |
+
"learning_rate": 1.4426534389143615e-05,
|
| 856 |
+
"loss": 0.3935,
|
| 857 |
+
"step": 605
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.6266666666666667,
|
| 861 |
+
"grad_norm": 1.1328589916229248,
|
| 862 |
+
"learning_rate": 1.4206148188197552e-05,
|
| 863 |
+
"loss": 0.4046,
|
| 864 |
+
"step": 610
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.6400000000000001,
|
| 868 |
+
"grad_norm": 1.1202021837234497,
|
| 869 |
+
"learning_rate": 1.398593371040692e-05,
|
| 870 |
+
"loss": 0.4324,
|
| 871 |
+
"step": 615
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.6533333333333333,
|
| 875 |
+
"grad_norm": 1.0203434228897095,
|
| 876 |
+
"learning_rate": 1.3765938591771832e-05,
|
| 877 |
+
"loss": 0.4425,
|
| 878 |
+
"step": 620
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.6666666666666665,
|
| 882 |
+
"grad_norm": 1.1289211511611938,
|
| 883 |
+
"learning_rate": 1.354621042084141e-05,
|
| 884 |
+
"loss": 0.4714,
|
| 885 |
+
"step": 625
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.6800000000000002,
|
| 889 |
+
"grad_norm": 1.0630546808242798,
|
| 890 |
+
"learning_rate": 1.3326796728419634e-05,
|
| 891 |
+
"loss": 0.4267,
|
| 892 |
+
"step": 630
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 1.6933333333333334,
|
| 896 |
+
"grad_norm": 1.0783942937850952,
|
| 897 |
+
"learning_rate": 1.3107744977283614e-05,
|
| 898 |
+
"loss": 0.4064,
|
| 899 |
+
"step": 635
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 1.7066666666666666,
|
| 903 |
+
"grad_norm": 1.0532513856887817,
|
| 904 |
+
"learning_rate": 1.2889102551916645e-05,
|
| 905 |
+
"loss": 0.4225,
|
| 906 |
+
"step": 640
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.72,
|
| 910 |
+
"grad_norm": 1.0506393909454346,
|
| 911 |
+
"learning_rate": 1.267091674825813e-05,
|
| 912 |
+
"loss": 0.4293,
|
| 913 |
+
"step": 645
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.7333333333333334,
|
| 917 |
+
"grad_norm": 1.100321888923645,
|
| 918 |
+
"learning_rate": 1.2453234763472723e-05,
|
| 919 |
+
"loss": 0.399,
|
| 920 |
+
"step": 650
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.7466666666666666,
|
| 924 |
+
"grad_norm": 1.1636956930160522,
|
| 925 |
+
"learning_rate": 1.2236103685740808e-05,
|
| 926 |
+
"loss": 0.4178,
|
| 927 |
+
"step": 655
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.76,
|
| 931 |
+
"grad_norm": 1.0189099311828613,
|
| 932 |
+
"learning_rate": 1.2019570484072535e-05,
|
| 933 |
+
"loss": 0.373,
|
| 934 |
+
"step": 660
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.7733333333333334,
|
| 938 |
+
"grad_norm": 1.0093544721603394,
|
| 939 |
+
"learning_rate": 1.1803681998147677e-05,
|
| 940 |
+
"loss": 0.4317,
|
| 941 |
+
"step": 665
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.7866666666666666,
|
| 945 |
+
"grad_norm": 1.148498773574829,
|
| 946 |
+
"learning_rate": 1.1588484928183407e-05,
|
| 947 |
+
"loss": 0.3826,
|
| 948 |
+
"step": 670
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 1.8,
|
| 952 |
+
"grad_norm": 1.0801362991333008,
|
| 953 |
+
"learning_rate": 1.1374025824832307e-05,
|
| 954 |
+
"loss": 0.4278,
|
| 955 |
+
"step": 675
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.8133333333333335,
|
| 959 |
+
"grad_norm": 1.1769850254058838,
|
| 960 |
+
"learning_rate": 1.11603510791127e-05,
|
| 961 |
+
"loss": 0.4101,
|
| 962 |
+
"step": 680
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.8266666666666667,
|
| 966 |
+
"grad_norm": 1.0906442403793335,
|
| 967 |
+
"learning_rate": 1.094750691237347e-05,
|
| 968 |
+
"loss": 0.4355,
|
| 969 |
+
"step": 685
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.8399999999999999,
|
| 973 |
+
"grad_norm": 1.1384433507919312,
|
| 974 |
+
"learning_rate": 1.0735539366295697e-05,
|
| 975 |
+
"loss": 0.3545,
|
| 976 |
+
"step": 690
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.8533333333333335,
|
| 980 |
+
"grad_norm": 1.0473315715789795,
|
| 981 |
+
"learning_rate": 1.0524494292933008e-05,
|
| 982 |
+
"loss": 0.3263,
|
| 983 |
+
"step": 695
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.8666666666666667,
|
| 987 |
+
"grad_norm": 1.1796642541885376,
|
| 988 |
+
"learning_rate": 1.0314417344793088e-05,
|
| 989 |
+
"loss": 0.3627,
|
| 990 |
+
"step": 700
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.88,
|
| 994 |
+
"grad_norm": 1.1376944780349731,
|
| 995 |
+
"learning_rate": 1.0105353964962273e-05,
|
| 996 |
+
"loss": 0.3625,
|
| 997 |
+
"step": 705
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 1.8933333333333333,
|
| 1001 |
+
"grad_norm": 1.1427693367004395,
|
| 1002 |
+
"learning_rate": 9.897349377275447e-06,
|
| 1003 |
+
"loss": 0.3528,
|
| 1004 |
+
"step": 710
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.9066666666666667,
|
| 1008 |
+
"grad_norm": 1.239563226699829,
|
| 1009 |
+
"learning_rate": 9.690448576533427e-06,
|
| 1010 |
+
"loss": 0.4004,
|
| 1011 |
+
"step": 715
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 1.92,
|
| 1015 |
+
"grad_norm": 1.1515874862670898,
|
| 1016 |
+
"learning_rate": 9.484696318769813e-06,
|
| 1017 |
+
"loss": 0.3758,
|
| 1018 |
+
"step": 720
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.9333333333333333,
|
| 1022 |
+
"grad_norm": 1.1046693325042725,
|
| 1023 |
+
"learning_rate": 9.280137111569525e-06,
|
| 1024 |
+
"loss": 0.3634,
|
| 1025 |
+
"step": 725
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 1.9466666666666668,
|
| 1029 |
+
"grad_norm": 1.1880930662155151,
|
| 1030 |
+
"learning_rate": 9.076815204441133e-06,
|
| 1031 |
+
"loss": 0.3501,
|
| 1032 |
+
"step": 730
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 1.96,
|
| 1036 |
+
"grad_norm": 1.389449954032898,
|
| 1037 |
+
"learning_rate": 8.874774579244886e-06,
|
| 1038 |
+
"loss": 0.375,
|
| 1039 |
+
"step": 735
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 1.9733333333333334,
|
| 1043 |
+
"grad_norm": 1.304689645767212,
|
| 1044 |
+
"learning_rate": 8.674058940678784e-06,
|
| 1045 |
+
"loss": 0.3731,
|
| 1046 |
+
"step": 740
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.9866666666666668,
|
| 1050 |
+
"grad_norm": 1.04849112033844,
|
| 1051 |
+
"learning_rate": 8.474711706824494e-06,
|
| 1052 |
+
"loss": 0.3764,
|
| 1053 |
+
"step": 745
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 2.0,
|
| 1057 |
+
"grad_norm": 1.3312870264053345,
|
| 1058 |
+
"learning_rate": 8.27677599975532e-06,
|
| 1059 |
+
"loss": 0.3503,
|
| 1060 |
+
"step": 750
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 2.013333333333333,
|
| 1064 |
+
"grad_norm": 1.1290007829666138,
|
| 1065 |
+
"learning_rate": 8.080294636208196e-06,
|
| 1066 |
+
"loss": 0.3045,
|
| 1067 |
+
"step": 755
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 2.026666666666667,
|
| 1071 |
+
"grad_norm": 1.2411856651306152,
|
| 1072 |
+
"learning_rate": 7.885310118321713e-06,
|
| 1073 |
+
"loss": 0.2743,
|
| 1074 |
+
"step": 760
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 2.04,
|
| 1078 |
+
"grad_norm": 1.0991859436035156,
|
| 1079 |
+
"learning_rate": 7.69186462444224e-06,
|
| 1080 |
+
"loss": 0.3052,
|
| 1081 |
+
"step": 765
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 2.0533333333333332,
|
| 1085 |
+
"grad_norm": 1.1960595846176147,
|
| 1086 |
+
"learning_rate": 7.500000000000004e-06,
|
| 1087 |
+
"loss": 0.298,
|
| 1088 |
+
"step": 770
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 2.066666666666667,
|
| 1092 |
+
"grad_norm": 1.1829774379730225,
|
| 1093 |
+
"learning_rate": 7.309757748457277e-06,
|
| 1094 |
+
"loss": 0.2764,
|
| 1095 |
+
"step": 775
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 2.08,
|
| 1099 |
+
"grad_norm": 1.2188671827316284,
|
| 1100 |
+
"learning_rate": 7.12117902233051e-06,
|
| 1101 |
+
"loss": 0.2806,
|
| 1102 |
+
"step": 780
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 2.0933333333333333,
|
| 1106 |
+
"grad_norm": 1.2058488130569458,
|
| 1107 |
+
"learning_rate": 6.934304614288306e-06,
|
| 1108 |
+
"loss": 0.2695,
|
| 1109 |
+
"step": 785
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 2.1066666666666665,
|
| 1113 |
+
"grad_norm": 1.151790738105774,
|
| 1114 |
+
"learning_rate": 6.74917494832738e-06,
|
| 1115 |
+
"loss": 0.2805,
|
| 1116 |
+
"step": 790
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 2.12,
|
| 1120 |
+
"grad_norm": 1.260259985923767,
|
| 1121 |
+
"learning_rate": 6.5658300710281226e-06,
|
| 1122 |
+
"loss": 0.2839,
|
| 1123 |
+
"step": 795
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 2.1333333333333333,
|
| 1127 |
+
"grad_norm": 1.1096916198730469,
|
| 1128 |
+
"learning_rate": 6.38430964289188e-06,
|
| 1129 |
+
"loss": 0.2981,
|
| 1130 |
+
"step": 800
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 2.1466666666666665,
|
| 1134 |
+
"grad_norm": 1.1928279399871826,
|
| 1135 |
+
"learning_rate": 6.204652929761774e-06,
|
| 1136 |
+
"loss": 0.2855,
|
| 1137 |
+
"step": 805
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 2.16,
|
| 1141 |
+
"grad_norm": 1.05479097366333,
|
| 1142 |
+
"learning_rate": 6.026898794328814e-06,
|
| 1143 |
+
"loss": 0.3015,
|
| 1144 |
+
"step": 810
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 2.1733333333333333,
|
| 1148 |
+
"grad_norm": 1.2515015602111816,
|
| 1149 |
+
"learning_rate": 5.8510856877252805e-06,
|
| 1150 |
+
"loss": 0.2635,
|
| 1151 |
+
"step": 815
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 2.1866666666666665,
|
| 1155 |
+
"grad_norm": 1.3012957572937012,
|
| 1156 |
+
"learning_rate": 5.6772516412071115e-06,
|
| 1157 |
+
"loss": 0.2855,
|
| 1158 |
+
"step": 820
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 2.2,
|
| 1162 |
+
"grad_norm": 1.0602593421936035,
|
| 1163 |
+
"learning_rate": 5.505434257927118e-06,
|
| 1164 |
+
"loss": 0.2757,
|
| 1165 |
+
"step": 825
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 2.2133333333333334,
|
| 1169 |
+
"grad_norm": 1.3124569654464722,
|
| 1170 |
+
"learning_rate": 5.335670704800805e-06,
|
| 1171 |
+
"loss": 0.3012,
|
| 1172 |
+
"step": 830
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 2.2266666666666666,
|
| 1176 |
+
"grad_norm": 1.0135294198989868,
|
| 1177 |
+
"learning_rate": 5.167997704466564e-06,
|
| 1178 |
+
"loss": 0.3105,
|
| 1179 |
+
"step": 835
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 2.24,
|
| 1183 |
+
"grad_norm": 1.0726760625839233,
|
| 1184 |
+
"learning_rate": 5.0024515273419514e-06,
|
| 1185 |
+
"loss": 0.2566,
|
| 1186 |
+
"step": 840
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 2.2533333333333334,
|
| 1190 |
+
"grad_norm": 1.191777229309082,
|
| 1191 |
+
"learning_rate": 4.839067983777836e-06,
|
| 1192 |
+
"loss": 0.2751,
|
| 1193 |
+
"step": 845
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 2.2666666666666666,
|
| 1197 |
+
"grad_norm": 1.1390310525894165,
|
| 1198 |
+
"learning_rate": 4.6778824163119685e-06,
|
| 1199 |
+
"loss": 0.2639,
|
| 1200 |
+
"step": 850
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 2.2800000000000002,
|
| 1204 |
+
"grad_norm": 1.081075668334961,
|
| 1205 |
+
"learning_rate": 4.518929692023891e-06,
|
| 1206 |
+
"loss": 0.2806,
|
| 1207 |
+
"step": 855
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 2.2933333333333334,
|
| 1211 |
+
"grad_norm": 1.111984372138977,
|
| 1212 |
+
"learning_rate": 4.362244194992565e-06,
|
| 1213 |
+
"loss": 0.2742,
|
| 1214 |
+
"step": 860
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 2.3066666666666666,
|
| 1218 |
+
"grad_norm": 1.0463660955429077,
|
| 1219 |
+
"learning_rate": 4.2078598188585235e-06,
|
| 1220 |
+
"loss": 0.2655,
|
| 1221 |
+
"step": 865
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 2.32,
|
| 1225 |
+
"grad_norm": 1.165935754776001,
|
| 1226 |
+
"learning_rate": 4.055809959492176e-06,
|
| 1227 |
+
"loss": 0.3026,
|
| 1228 |
+
"step": 870
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 2.3333333333333335,
|
| 1232 |
+
"grad_norm": 1.1260473728179932,
|
| 1233 |
+
"learning_rate": 3.906127507769677e-06,
|
| 1234 |
+
"loss": 0.2787,
|
| 1235 |
+
"step": 875
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 2.3466666666666667,
|
| 1239 |
+
"grad_norm": 1.1946828365325928,
|
| 1240 |
+
"learning_rate": 3.7588448424581247e-06,
|
| 1241 |
+
"loss": 0.2371,
|
| 1242 |
+
"step": 880
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 2.36,
|
| 1246 |
+
"grad_norm": 1.1841825246810913,
|
| 1247 |
+
"learning_rate": 3.6139938232114844e-06,
|
| 1248 |
+
"loss": 0.2457,
|
| 1249 |
+
"step": 885
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 2.3733333333333335,
|
| 1253 |
+
"grad_norm": 1.198198676109314,
|
| 1254 |
+
"learning_rate": 3.4716057836788375e-06,
|
| 1255 |
+
"loss": 0.2955,
|
| 1256 |
+
"step": 890
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 2.3866666666666667,
|
| 1260 |
+
"grad_norm": 1.108260989189148,
|
| 1261 |
+
"learning_rate": 3.3317115247263906e-06,
|
| 1262 |
+
"loss": 0.3095,
|
| 1263 |
+
"step": 895
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 2.4,
|
| 1267 |
+
"grad_norm": 1.2986464500427246,
|
| 1268 |
+
"learning_rate": 3.1943413077747426e-06,
|
| 1269 |
+
"loss": 0.2983,
|
| 1270 |
+
"step": 900
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 2.413333333333333,
|
| 1274 |
+
"grad_norm": 1.2423778772354126,
|
| 1275 |
+
"learning_rate": 3.059524848252858e-06,
|
| 1276 |
+
"loss": 0.2972,
|
| 1277 |
+
"step": 905
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 2.4266666666666667,
|
| 1281 |
+
"grad_norm": 1.027319312095642,
|
| 1282 |
+
"learning_rate": 2.927291309170117e-06,
|
| 1283 |
+
"loss": 0.2628,
|
| 1284 |
+
"step": 910
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 2.44,
|
| 1288 |
+
"grad_norm": 1.115038514137268,
|
| 1289 |
+
"learning_rate": 2.797669294807871e-06,
|
| 1290 |
+
"loss": 0.2556,
|
| 1291 |
+
"step": 915
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 2.453333333333333,
|
| 1295 |
+
"grad_norm": 1.2947417497634888,
|
| 1296 |
+
"learning_rate": 2.670686844531899e-06,
|
| 1297 |
+
"loss": 0.2826,
|
| 1298 |
+
"step": 920
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 2.466666666666667,
|
| 1302 |
+
"grad_norm": 1.0587910413742065,
|
| 1303 |
+
"learning_rate": 2.5463714267270026e-06,
|
| 1304 |
+
"loss": 0.2826,
|
| 1305 |
+
"step": 925
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 2.48,
|
| 1309 |
+
"grad_norm": 1.1960229873657227,
|
| 1310 |
+
"learning_rate": 2.4247499328551646e-06,
|
| 1311 |
+
"loss": 0.2476,
|
| 1312 |
+
"step": 930
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 2.493333333333333,
|
| 1316 |
+
"grad_norm": 1.1127303838729858,
|
| 1317 |
+
"learning_rate": 2.305848671638469e-06,
|
| 1318 |
+
"loss": 0.274,
|
| 1319 |
+
"step": 935
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 2.506666666666667,
|
| 1323 |
+
"grad_norm": 1.1100138425827026,
|
| 1324 |
+
"learning_rate": 2.189693363368106e-06,
|
| 1325 |
+
"loss": 0.2427,
|
| 1326 |
+
"step": 940
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 2.52,
|
| 1330 |
+
"grad_norm": 1.157330870628357,
|
| 1331 |
+
"learning_rate": 2.076309134340644e-06,
|
| 1332 |
+
"loss": 0.2585,
|
| 1333 |
+
"step": 945
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 2.533333333333333,
|
| 1337 |
+
"grad_norm": 1.175873875617981,
|
| 1338 |
+
"learning_rate": 1.9657205114228033e-06,
|
| 1339 |
+
"loss": 0.2738,
|
| 1340 |
+
"step": 950
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 2.546666666666667,
|
| 1344 |
+
"grad_norm": 1.2530473470687866,
|
| 1345 |
+
"learning_rate": 1.8579514167458989e-06,
|
| 1346 |
+
"loss": 0.2899,
|
| 1347 |
+
"step": 955
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 2.56,
|
| 1351 |
+
"grad_norm": 1.1226650476455688,
|
| 1352 |
+
"learning_rate": 1.7530251625310723e-06,
|
| 1353 |
+
"loss": 0.271,
|
| 1354 |
+
"step": 960
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 2.5733333333333333,
|
| 1358 |
+
"grad_norm": 1.0813995599746704,
|
| 1359 |
+
"learning_rate": 1.6509644460464934e-06,
|
| 1360 |
+
"loss": 0.2362,
|
| 1361 |
+
"step": 965
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 2.586666666666667,
|
| 1365 |
+
"grad_norm": 1.1135228872299194,
|
| 1366 |
+
"learning_rate": 1.5517913446975745e-06,
|
| 1367 |
+
"loss": 0.2649,
|
| 1368 |
+
"step": 970
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 2.6,
|
| 1372 |
+
"grad_norm": 1.1312683820724487,
|
| 1373 |
+
"learning_rate": 1.4555273112512386e-06,
|
| 1374 |
+
"loss": 0.2547,
|
| 1375 |
+
"step": 975
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 2.6133333333333333,
|
| 1379 |
+
"grad_norm": 1.236370325088501,
|
| 1380 |
+
"learning_rate": 1.362193169195366e-06,
|
| 1381 |
+
"loss": 0.2461,
|
| 1382 |
+
"step": 980
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 2.626666666666667,
|
| 1386 |
+
"grad_norm": 1.1148097515106201,
|
| 1387 |
+
"learning_rate": 1.2718091082343103e-06,
|
| 1388 |
+
"loss": 0.2749,
|
| 1389 |
+
"step": 985
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 2.64,
|
| 1393 |
+
"grad_norm": 1.1325016021728516,
|
| 1394 |
+
"learning_rate": 1.1843946799215476e-06,
|
| 1395 |
+
"loss": 0.298,
|
| 1396 |
+
"step": 990
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 2.6533333333333333,
|
| 1400 |
+
"grad_norm": 1.0611364841461182,
|
| 1401 |
+
"learning_rate": 1.099968793430347e-06,
|
| 1402 |
+
"loss": 0.2609,
|
| 1403 |
+
"step": 995
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 2.6666666666666665,
|
| 1407 |
+
"grad_norm": 1.1944174766540527,
|
| 1408 |
+
"learning_rate": 1.0185497114634067e-06,
|
| 1409 |
+
"loss": 0.2764,
|
| 1410 |
+
"step": 1000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 2.68,
|
| 1414 |
+
"grad_norm": 1.0602160692214966,
|
| 1415 |
+
"learning_rate": 9.401550463023417e-07,
|
| 1416 |
+
"loss": 0.2651,
|
| 1417 |
+
"step": 1005
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 2.6933333333333334,
|
| 1421 |
+
"grad_norm": 1.0739070177078247,
|
| 1422 |
+
"learning_rate": 8.648017559978471e-07,
|
| 1423 |
+
"loss": 0.2618,
|
| 1424 |
+
"step": 1010
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 2.7066666666666666,
|
| 1428 |
+
"grad_norm": 1.1494011878967285,
|
| 1429 |
+
"learning_rate": 7.925061407013967e-07,
|
| 1430 |
+
"loss": 0.2609,
|
| 1431 |
+
"step": 1015
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 2.7199999999999998,
|
| 1435 |
+
"grad_norm": 1.1180745363235474,
|
| 1436 |
+
"learning_rate": 7.232838391392676e-07,
|
| 1437 |
+
"loss": 0.2801,
|
| 1438 |
+
"step": 1020
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 2.7333333333333334,
|
| 1442 |
+
"grad_norm": 1.1310865879058838,
|
| 1443 |
+
"learning_rate": 6.571498252295971e-07,
|
| 1444 |
+
"loss": 0.2344,
|
| 1445 |
+
"step": 1025
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 2.7466666666666666,
|
| 1449 |
+
"grad_norm": 1.2756072282791138,
|
| 1450 |
+
"learning_rate": 5.941184048433113e-07,
|
| 1451 |
+
"loss": 0.3023,
|
| 1452 |
+
"step": 1030
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 2.76,
|
| 1456 |
+
"grad_norm": 1.1661157608032227,
|
| 1457 |
+
"learning_rate": 5.342032127095092e-07,
|
| 1458 |
+
"loss": 0.2704,
|
| 1459 |
+
"step": 1035
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 2.7733333333333334,
|
| 1463 |
+
"grad_norm": 1.0685588121414185,
|
| 1464 |
+
"learning_rate": 4.774172094660523e-07,
|
| 1465 |
+
"loss": 0.2468,
|
| 1466 |
+
"step": 1040
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 2.7866666666666666,
|
| 1470 |
+
"grad_norm": 1.100810170173645,
|
| 1471 |
+
"learning_rate": 4.237726788559748e-07,
|
| 1472 |
+
"loss": 0.2462,
|
| 1473 |
+
"step": 1045
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 2.8,
|
| 1477 |
+
"grad_norm": 1.175557017326355,
|
| 1478 |
+
"learning_rate": 3.7328122507029994e-07,
|
| 1479 |
+
"loss": 0.2836,
|
| 1480 |
+
"step": 1050
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 2.8133333333333335,
|
| 1484 |
+
"grad_norm": 1.2640366554260254,
|
| 1485 |
+
"learning_rate": 3.25953770237864e-07,
|
| 1486 |
+
"loss": 0.2554,
|
| 1487 |
+
"step": 1055
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 2.8266666666666667,
|
| 1491 |
+
"grad_norm": 1.1299501657485962,
|
| 1492 |
+
"learning_rate": 2.818005520626832e-07,
|
| 1493 |
+
"loss": 0.2602,
|
| 1494 |
+
"step": 1060
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 2.84,
|
| 1498 |
+
"grad_norm": 1.0881595611572266,
|
| 1499 |
+
"learning_rate": 2.408311216093684e-07,
|
| 1500 |
+
"loss": 0.272,
|
| 1501 |
+
"step": 1065
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 2.8533333333333335,
|
| 1505 |
+
"grad_norm": 1.0344923734664917,
|
| 1506 |
+
"learning_rate": 2.030543412370811e-07,
|
| 1507 |
+
"loss": 0.2606,
|
| 1508 |
+
"step": 1070
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 2.8666666666666667,
|
| 1512 |
+
"grad_norm": 1.2394707202911377,
|
| 1513 |
+
"learning_rate": 1.684783826824421e-07,
|
| 1514 |
+
"loss": 0.2561,
|
| 1515 |
+
"step": 1075
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 2.88,
|
| 1519 |
+
"grad_norm": 1.0574387311935425,
|
| 1520 |
+
"learning_rate": 1.3711072529187686e-07,
|
| 1521 |
+
"loss": 0.2515,
|
| 1522 |
+
"step": 1080
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 2.8933333333333335,
|
| 1526 |
+
"grad_norm": 1.0961966514587402,
|
| 1527 |
+
"learning_rate": 1.0895815440368328e-07,
|
| 1528 |
+
"loss": 0.2672,
|
| 1529 |
+
"step": 1085
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 2.9066666666666667,
|
| 1533 |
+
"grad_norm": 1.0254484415054321,
|
| 1534 |
+
"learning_rate": 8.402675988027076e-08,
|
| 1535 |
+
"loss": 0.2682,
|
| 1536 |
+
"step": 1090
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 2.92,
|
| 1540 |
+
"grad_norm": 1.1589972972869873,
|
| 1541 |
+
"learning_rate": 6.23219347908155e-08,
|
| 1542 |
+
"loss": 0.2533,
|
| 1543 |
+
"step": 1095
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 2.9333333333333336,
|
| 1547 |
+
"grad_norm": 1.3366988897323608,
|
| 1548 |
+
"learning_rate": 4.3848374244652156e-08,
|
| 1549 |
+
"loss": 0.2613,
|
| 1550 |
+
"step": 1100
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 2.9466666666666668,
|
| 1554 |
+
"grad_norm": 1.1757328510284424,
|
| 1555 |
+
"learning_rate": 2.861007437564622e-08,
|
| 1556 |
+
"loss": 0.2309,
|
| 1557 |
+
"step": 1105
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 2.96,
|
| 1561 |
+
"grad_norm": 1.1434340476989746,
|
| 1562 |
+
"learning_rate": 1.6610331477763806e-08,
|
| 1563 |
+
"loss": 0.2869,
|
| 1564 |
+
"step": 1110
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 2.9733333333333336,
|
| 1568 |
+
"grad_norm": 1.1423622369766235,
|
| 1569 |
+
"learning_rate": 7.851741292028702e-09,
|
| 1570 |
+
"loss": 0.2519,
|
| 1571 |
+
"step": 1115
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 2.986666666666667,
|
| 1575 |
+
"grad_norm": 1.092671513557434,
|
| 1576 |
+
"learning_rate": 2.3361984450215314e-09,
|
| 1577 |
+
"loss": 0.2661,
|
| 1578 |
+
"step": 1120
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 3.0,
|
| 1582 |
+
"grad_norm": 1.1551599502563477,
|
| 1583 |
+
"learning_rate": 6.489603903925278e-11,
|
| 1584 |
+
"loss": 0.2498,
|
| 1585 |
+
"step": 1125
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 3.0,
|
| 1589 |
+
"step": 1125,
|
| 1590 |
+
"total_flos": 1.5976229698011136e+18,
|
| 1591 |
+
"train_loss": 0.5715485998789469,
|
| 1592 |
+
"train_runtime": 747.2338,
|
| 1593 |
+
"train_samples_per_second": 48.178,
|
| 1594 |
+
"train_steps_per_second": 1.506
|
| 1595 |
+
}
|
| 1596 |
+
],
|
| 1597 |
+
"logging_steps": 5,
|
| 1598 |
+
"max_steps": 1125,
|
| 1599 |
+
"num_input_tokens_seen": 0,
|
| 1600 |
+
"num_train_epochs": 3,
|
| 1601 |
+
"save_steps": 20000,
|
| 1602 |
+
"stateful_callbacks": {
|
| 1603 |
+
"TrainerControl": {
|
| 1604 |
+
"args": {
|
| 1605 |
+
"should_epoch_stop": false,
|
| 1606 |
+
"should_evaluate": false,
|
| 1607 |
+
"should_log": false,
|
| 1608 |
+
"should_save": false,
|
| 1609 |
+
"should_training_stop": false
|
| 1610 |
+
},
|
| 1611 |
+
"attributes": {}
|
| 1612 |
+
}
|
| 1613 |
+
},
|
| 1614 |
+
"total_flos": 1.5976229698011136e+18,
|
| 1615 |
+
"train_batch_size": 2,
|
| 1616 |
+
"trial_name": null,
|
| 1617 |
+
"trial_params": null
|
| 1618 |
+
}
|
119_128_e3_3e-5/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5a22306207f057ed416ce4e51450cda497239cfe8f51f7821631802d28fa7b0
|
| 3 |
+
size 8273
|
119_128_e3_3e-5/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|