Upload folder using huggingface_hub
Browse files- 12_128_e3_3e-5/adapter_config.json +39 -0
- 12_128_e3_3e-5/adapter_model.safetensors +3 -0
- 12_128_e3_3e-5/added_tokens.json +9 -0
- 12_128_e3_3e-5/all_results.json +9 -0
- 12_128_e3_3e-5/chat_template.jinja +62 -0
- 12_128_e3_3e-5/config.json +32 -0
- 12_128_e3_3e-5/merges.txt +0 -0
- 12_128_e3_3e-5/special_tokens_map.json +33 -0
- 12_128_e3_3e-5/tokenizer.json +0 -0
- 12_128_e3_3e-5/tokenizer_config.json +234 -0
- 12_128_e3_3e-5/train_results.json +9 -0
- 12_128_e3_3e-5/trainer_state.json +1597 -0
- 12_128_e3_3e-5/training_args.bin +3 -0
- 12_128_e3_3e-5/vocab.json +0 -0
12_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 |
+
"v_proj",
|
| 28 |
+
"k_proj",
|
| 29 |
+
"o_proj",
|
| 30 |
+
"q_proj",
|
| 31 |
+
"gate_proj",
|
| 32 |
+
"down_proj",
|
| 33 |
+
"up_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
+
"use_dora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
12_128_e3_3e-5/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d689b786a8d7c78fcbf44d43a2ae6957c8f7139376fc4cd718d1fb3a7a89e77f
|
| 3 |
+
size 791751704
|
12_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 |
+
}
|
12_128_e3_3e-5/all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 1.620456557303038e+18,
|
| 4 |
+
"train_loss": 0.5424838511793463,
|
| 5 |
+
"train_runtime": 798.7465,
|
| 6 |
+
"train_samples": 11817,
|
| 7 |
+
"train_samples_per_second": 44.383,
|
| 8 |
+
"train_steps_per_second": 1.39
|
| 9 |
+
}
|
12_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 %}
|
12_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 |
+
}
|
12_128_e3_3e-5/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
12_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 |
+
}
|
12_128_e3_3e-5/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
12_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 |
+
}
|
12_128_e3_3e-5/train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 1.620456557303038e+18,
|
| 4 |
+
"train_loss": 0.5424838511793463,
|
| 5 |
+
"train_runtime": 798.7465,
|
| 6 |
+
"train_samples": 11817,
|
| 7 |
+
"train_samples_per_second": 44.383,
|
| 8 |
+
"train_steps_per_second": 1.39
|
| 9 |
+
}
|
12_128_e3_3e-5/trainer_state.json
ADDED
|
@@ -0,0 +1,1597 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 1110,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.013531799729364006,
|
| 14 |
+
"grad_norm": 3.785393238067627,
|
| 15 |
+
"learning_rate": 2.1428571428571427e-06,
|
| 16 |
+
"loss": 1.5494,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.02706359945872801,
|
| 21 |
+
"grad_norm": 2.1162548065185547,
|
| 22 |
+
"learning_rate": 4.821428571428572e-06,
|
| 23 |
+
"loss": 1.5108,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.04059539918809202,
|
| 28 |
+
"grad_norm": 0.9111731052398682,
|
| 29 |
+
"learning_rate": 7.5e-06,
|
| 30 |
+
"loss": 1.4187,
|
| 31 |
+
"step": 15
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.05412719891745602,
|
| 35 |
+
"grad_norm": 0.5022687315940857,
|
| 36 |
+
"learning_rate": 1.0178571428571429e-05,
|
| 37 |
+
"loss": 1.2971,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.06765899864682003,
|
| 42 |
+
"grad_norm": 0.4446107745170593,
|
| 43 |
+
"learning_rate": 1.2857142857142857e-05,
|
| 44 |
+
"loss": 1.3323,
|
| 45 |
+
"step": 25
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.08119079837618404,
|
| 49 |
+
"grad_norm": 0.40601515769958496,
|
| 50 |
+
"learning_rate": 1.553571428571429e-05,
|
| 51 |
+
"loss": 1.311,
|
| 52 |
+
"step": 30
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.09472259810554803,
|
| 56 |
+
"grad_norm": 0.36464670300483704,
|
| 57 |
+
"learning_rate": 1.8214285714285712e-05,
|
| 58 |
+
"loss": 1.2717,
|
| 59 |
+
"step": 35
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.10825439783491204,
|
| 63 |
+
"grad_norm": 0.4515382945537567,
|
| 64 |
+
"learning_rate": 2.089285714285714e-05,
|
| 65 |
+
"loss": 1.2395,
|
| 66 |
+
"step": 40
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.12178619756427606,
|
| 70 |
+
"grad_norm": 0.37066200375556946,
|
| 71 |
+
"learning_rate": 2.357142857142857e-05,
|
| 72 |
+
"loss": 1.2043,
|
| 73 |
+
"step": 45
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.13531799729364005,
|
| 77 |
+
"grad_norm": 0.39821431040763855,
|
| 78 |
+
"learning_rate": 2.625e-05,
|
| 79 |
+
"loss": 1.2329,
|
| 80 |
+
"step": 50
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.14884979702300405,
|
| 84 |
+
"grad_norm": 0.3693654239177704,
|
| 85 |
+
"learning_rate": 2.892857142857143e-05,
|
| 86 |
+
"loss": 1.1926,
|
| 87 |
+
"step": 55
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.16238159675236807,
|
| 91 |
+
"grad_norm": 0.4242394268512726,
|
| 92 |
+
"learning_rate": 2.999940032022394e-05,
|
| 93 |
+
"loss": 1.1749,
|
| 94 |
+
"step": 60
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.17591339648173207,
|
| 98 |
+
"grad_norm": 0.4013722836971283,
|
| 99 |
+
"learning_rate": 2.9995735784121558e-05,
|
| 100 |
+
"loss": 1.2168,
|
| 101 |
+
"step": 65
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.18944519621109607,
|
| 105 |
+
"grad_norm": 0.3405766785144806,
|
| 106 |
+
"learning_rate": 2.9988740680258434e-05,
|
| 107 |
+
"loss": 1.1125,
|
| 108 |
+
"step": 70
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.2029769959404601,
|
| 112 |
+
"grad_norm": 0.42999938130378723,
|
| 113 |
+
"learning_rate": 2.9978416562254055e-05,
|
| 114 |
+
"loss": 1.1144,
|
| 115 |
+
"step": 75
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.2165087956698241,
|
| 119 |
+
"grad_norm": 0.4004330635070801,
|
| 120 |
+
"learning_rate": 2.996476572310524e-05,
|
| 121 |
+
"loss": 1.2063,
|
| 122 |
+
"step": 80
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.23004059539918809,
|
| 126 |
+
"grad_norm": 0.41440436244010925,
|
| 127 |
+
"learning_rate": 2.9947791194676896e-05,
|
| 128 |
+
"loss": 1.1438,
|
| 129 |
+
"step": 85
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.2435723951285521,
|
| 133 |
+
"grad_norm": 0.4142892062664032,
|
| 134 |
+
"learning_rate": 2.9927496747028565e-05,
|
| 135 |
+
"loss": 1.1275,
|
| 136 |
+
"step": 90
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.2571041948579161,
|
| 140 |
+
"grad_norm": 0.4979764223098755,
|
| 141 |
+
"learning_rate": 2.9903886887577177e-05,
|
| 142 |
+
"loss": 1.0522,
|
| 143 |
+
"step": 95
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.2706359945872801,
|
| 147 |
+
"grad_norm": 0.41165459156036377,
|
| 148 |
+
"learning_rate": 2.987696686009588e-05,
|
| 149 |
+
"loss": 1.0862,
|
| 150 |
+
"step": 100
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.28416779431664413,
|
| 154 |
+
"grad_norm": 0.4432730972766876,
|
| 155 |
+
"learning_rate": 2.9846742643549418e-05,
|
| 156 |
+
"loss": 1.0619,
|
| 157 |
+
"step": 105
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.2976995940460081,
|
| 161 |
+
"grad_norm": 0.4751802086830139,
|
| 162 |
+
"learning_rate": 2.9813220950766205e-05,
|
| 163 |
+
"loss": 1.0491,
|
| 164 |
+
"step": 110
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.3112313937753721,
|
| 168 |
+
"grad_norm": 0.5307507514953613,
|
| 169 |
+
"learning_rate": 2.9776409226947394e-05,
|
| 170 |
+
"loss": 1.0921,
|
| 171 |
+
"step": 115
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.32476319350473615,
|
| 175 |
+
"grad_norm": 0.5337587594985962,
|
| 176 |
+
"learning_rate": 2.9736315648013272e-05,
|
| 177 |
+
"loss": 1.0157,
|
| 178 |
+
"step": 120
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.3382949932341001,
|
| 182 |
+
"grad_norm": 0.5446403622627258,
|
| 183 |
+
"learning_rate": 2.969294911878742e-05,
|
| 184 |
+
"loss": 1.0292,
|
| 185 |
+
"step": 125
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.35182679296346414,
|
| 189 |
+
"grad_norm": 0.5381000638008118,
|
| 190 |
+
"learning_rate": 2.9646319271018888e-05,
|
| 191 |
+
"loss": 0.9927,
|
| 192 |
+
"step": 130
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.36535859269282817,
|
| 196 |
+
"grad_norm": 0.4728102684020996,
|
| 197 |
+
"learning_rate": 2.959643646124303e-05,
|
| 198 |
+
"loss": 0.9993,
|
| 199 |
+
"step": 135
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.37889039242219213,
|
| 203 |
+
"grad_norm": 0.6446573138237,
|
| 204 |
+
"learning_rate": 2.9543311768481276e-05,
|
| 205 |
+
"loss": 1.0324,
|
| 206 |
+
"step": 140
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.39242219215155616,
|
| 210 |
+
"grad_norm": 0.614909827709198,
|
| 211 |
+
"learning_rate": 2.9486956991780463e-05,
|
| 212 |
+
"loss": 0.9267,
|
| 213 |
+
"step": 145
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.4059539918809202,
|
| 217 |
+
"grad_norm": 0.5676555633544922,
|
| 218 |
+
"learning_rate": 2.942738464759229e-05,
|
| 219 |
+
"loss": 0.9562,
|
| 220 |
+
"step": 150
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.41948579161028415,
|
| 224 |
+
"grad_norm": 0.6821476221084595,
|
| 225 |
+
"learning_rate": 2.9364607966993347e-05,
|
| 226 |
+
"loss": 0.9722,
|
| 227 |
+
"step": 155
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.4330175913396482,
|
| 231 |
+
"grad_norm": 0.5614897608757019,
|
| 232 |
+
"learning_rate": 2.929864089274655e-05,
|
| 233 |
+
"loss": 0.9587,
|
| 234 |
+
"step": 160
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.4465493910690122,
|
| 238 |
+
"grad_norm": 0.6017680168151855,
|
| 239 |
+
"learning_rate": 2.922949807620438e-05,
|
| 240 |
+
"loss": 0.9663,
|
| 241 |
+
"step": 165
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.46008119079837617,
|
| 245 |
+
"grad_norm": 0.6314606070518494,
|
| 246 |
+
"learning_rate": 2.9157194874054826e-05,
|
| 247 |
+
"loss": 0.9321,
|
| 248 |
+
"step": 170
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.4736129905277402,
|
| 252 |
+
"grad_norm": 0.5941213369369507,
|
| 253 |
+
"learning_rate": 2.908174734491066e-05,
|
| 254 |
+
"loss": 0.8962,
|
| 255 |
+
"step": 175
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.4871447902571042,
|
| 259 |
+
"grad_norm": 0.6001120209693909,
|
| 260 |
+
"learning_rate": 2.9003172245742778e-05,
|
| 261 |
+
"loss": 0.8725,
|
| 262 |
+
"step": 180
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.5006765899864682,
|
| 266 |
+
"grad_norm": 0.6858236789703369,
|
| 267 |
+
"learning_rate": 2.892148702815848e-05,
|
| 268 |
+
"loss": 0.9028,
|
| 269 |
+
"step": 185
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.5142083897158322,
|
| 273 |
+
"grad_norm": 0.7041531801223755,
|
| 274 |
+
"learning_rate": 2.8836709834525455e-05,
|
| 275 |
+
"loss": 0.8666,
|
| 276 |
+
"step": 190
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.5277401894451962,
|
| 280 |
+
"grad_norm": 0.6731634736061096,
|
| 281 |
+
"learning_rate": 2.874885949394231e-05,
|
| 282 |
+
"loss": 0.9023,
|
| 283 |
+
"step": 195
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.5412719891745602,
|
| 287 |
+
"grad_norm": 0.6808884143829346,
|
| 288 |
+
"learning_rate": 2.8657955518056653e-05,
|
| 289 |
+
"loss": 0.9147,
|
| 290 |
+
"step": 200
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.5548037889039242,
|
| 294 |
+
"grad_norm": 0.8456588983535767,
|
| 295 |
+
"learning_rate": 2.8564018096731507e-05,
|
| 296 |
+
"loss": 0.8314,
|
| 297 |
+
"step": 205
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.5683355886332883,
|
| 301 |
+
"grad_norm": 0.7181119322776794,
|
| 302 |
+
"learning_rate": 2.8467068093561125e-05,
|
| 303 |
+
"loss": 0.8267,
|
| 304 |
+
"step": 210
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.5818673883626523,
|
| 308 |
+
"grad_norm": 0.7056394219398499,
|
| 309 |
+
"learning_rate": 2.8367127041237178e-05,
|
| 310 |
+
"loss": 0.8645,
|
| 311 |
+
"step": 215
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.5953991880920162,
|
| 315 |
+
"grad_norm": 0.7876498103141785,
|
| 316 |
+
"learning_rate": 2.8264217136766306e-05,
|
| 317 |
+
"loss": 0.8084,
|
| 318 |
+
"step": 220
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.6089309878213802,
|
| 322 |
+
"grad_norm": 0.7355566620826721,
|
| 323 |
+
"learning_rate": 2.8158361236540166e-05,
|
| 324 |
+
"loss": 0.8296,
|
| 325 |
+
"step": 225
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.6224627875507442,
|
| 329 |
+
"grad_norm": 0.7613966464996338,
|
| 330 |
+
"learning_rate": 2.8049582851258958e-05,
|
| 331 |
+
"loss": 0.8516,
|
| 332 |
+
"step": 230
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.6359945872801083,
|
| 336 |
+
"grad_norm": 0.6759623289108276,
|
| 337 |
+
"learning_rate": 2.7937906140709742e-05,
|
| 338 |
+
"loss": 0.8434,
|
| 339 |
+
"step": 235
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.6495263870094723,
|
| 343 |
+
"grad_norm": 0.7637921571731567,
|
| 344 |
+
"learning_rate": 2.782335590840046e-05,
|
| 345 |
+
"loss": 0.8248,
|
| 346 |
+
"step": 240
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.6630581867388363,
|
| 350 |
+
"grad_norm": 0.6608057022094727,
|
| 351 |
+
"learning_rate": 2.7705957596051096e-05,
|
| 352 |
+
"loss": 0.7679,
|
| 353 |
+
"step": 245
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.6765899864682002,
|
| 357 |
+
"grad_norm": 0.817314863204956,
|
| 358 |
+
"learning_rate": 2.7585737277943023e-05,
|
| 359 |
+
"loss": 0.8033,
|
| 360 |
+
"step": 250
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.6901217861975643,
|
| 364 |
+
"grad_norm": 0.8700020909309387,
|
| 365 |
+
"learning_rate": 2.7462721655127897e-05,
|
| 366 |
+
"loss": 0.7744,
|
| 367 |
+
"step": 255
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.7036535859269283,
|
| 371 |
+
"grad_norm": 0.8407606482505798,
|
| 372 |
+
"learning_rate": 2.73369380494973e-05,
|
| 373 |
+
"loss": 0.7934,
|
| 374 |
+
"step": 260
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.7171853856562923,
|
| 378 |
+
"grad_norm": 0.71098393201828,
|
| 379 |
+
"learning_rate": 2.7208414397714553e-05,
|
| 380 |
+
"loss": 0.7696,
|
| 381 |
+
"step": 265
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.7307171853856563,
|
| 385 |
+
"grad_norm": 0.8703633546829224,
|
| 386 |
+
"learning_rate": 2.7077179245009923e-05,
|
| 387 |
+
"loss": 0.7844,
|
| 388 |
+
"step": 270
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.7442489851150202,
|
| 392 |
+
"grad_norm": 0.8267477750778198,
|
| 393 |
+
"learning_rate": 2.6943261738840738e-05,
|
| 394 |
+
"loss": 0.7426,
|
| 395 |
+
"step": 275
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.7577807848443843,
|
| 399 |
+
"grad_norm": 0.7508859038352966,
|
| 400 |
+
"learning_rate": 2.6806691622417662e-05,
|
| 401 |
+
"loss": 0.7394,
|
| 402 |
+
"step": 280
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.7713125845737483,
|
| 406 |
+
"grad_norm": 0.8901416063308716,
|
| 407 |
+
"learning_rate": 2.6667499228098735e-05,
|
| 408 |
+
"loss": 0.686,
|
| 409 |
+
"step": 285
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.7848443843031123,
|
| 413 |
+
"grad_norm": 0.8121469020843506,
|
| 414 |
+
"learning_rate": 2.6525715470652516e-05,
|
| 415 |
+
"loss": 0.7318,
|
| 416 |
+
"step": 290
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.7983761840324763,
|
| 420 |
+
"grad_norm": 0.85890132188797,
|
| 421 |
+
"learning_rate": 2.6381371840391862e-05,
|
| 422 |
+
"loss": 0.7364,
|
| 423 |
+
"step": 295
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.8119079837618404,
|
| 427 |
+
"grad_norm": 0.8046591877937317,
|
| 428 |
+
"learning_rate": 2.6234500396179943e-05,
|
| 429 |
+
"loss": 0.7052,
|
| 430 |
+
"step": 300
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.8254397834912043,
|
| 434 |
+
"grad_norm": 0.8877843618392944,
|
| 435 |
+
"learning_rate": 2.6085133758309887e-05,
|
| 436 |
+
"loss": 0.6731,
|
| 437 |
+
"step": 305
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.8389715832205683,
|
| 441 |
+
"grad_norm": 0.8684395551681519,
|
| 442 |
+
"learning_rate": 2.5933305101259812e-05,
|
| 443 |
+
"loss": 0.6835,
|
| 444 |
+
"step": 310
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.8525033829499323,
|
| 448 |
+
"grad_norm": 0.8872131705284119,
|
| 449 |
+
"learning_rate": 2.5779048146324735e-05,
|
| 450 |
+
"loss": 0.6894,
|
| 451 |
+
"step": 315
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.8660351826792964,
|
| 455 |
+
"grad_norm": 0.8687784671783447,
|
| 456 |
+
"learning_rate": 2.562239715412703e-05,
|
| 457 |
+
"loss": 0.6814,
|
| 458 |
+
"step": 320
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.8795669824086604,
|
| 462 |
+
"grad_norm": 0.8363562822341919,
|
| 463 |
+
"learning_rate": 2.5463386917007118e-05,
|
| 464 |
+
"loss": 0.6319,
|
| 465 |
+
"step": 325
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.8930987821380244,
|
| 469 |
+
"grad_norm": 0.9140112996101379,
|
| 470 |
+
"learning_rate": 2.5302052751296064e-05,
|
| 471 |
+
"loss": 0.6997,
|
| 472 |
+
"step": 330
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.9066305818673883,
|
| 476 |
+
"grad_norm": 0.819125771522522,
|
| 477 |
+
"learning_rate": 2.5138430489471753e-05,
|
| 478 |
+
"loss": 0.6845,
|
| 479 |
+
"step": 335
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.9201623815967523,
|
| 483 |
+
"grad_norm": 0.9193775653839111,
|
| 484 |
+
"learning_rate": 2.4972556472200507e-05,
|
| 485 |
+
"loss": 0.6369,
|
| 486 |
+
"step": 340
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.9336941813261164,
|
| 490 |
+
"grad_norm": 0.8432621955871582,
|
| 491 |
+
"learning_rate": 2.4804467540265734e-05,
|
| 492 |
+
"loss": 0.6675,
|
| 493 |
+
"step": 345
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.9472259810554804,
|
| 497 |
+
"grad_norm": 0.8799031376838684,
|
| 498 |
+
"learning_rate": 2.46342010263856e-05,
|
| 499 |
+
"loss": 0.6632,
|
| 500 |
+
"step": 350
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.9607577807848444,
|
| 504 |
+
"grad_norm": 0.9400159120559692,
|
| 505 |
+
"learning_rate": 2.4461794746921375e-05,
|
| 506 |
+
"loss": 0.6519,
|
| 507 |
+
"step": 355
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.9742895805142084,
|
| 511 |
+
"grad_norm": 0.8699827194213867,
|
| 512 |
+
"learning_rate": 2.4287286993478373e-05,
|
| 513 |
+
"loss": 0.6804,
|
| 514 |
+
"step": 360
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.9878213802435724,
|
| 518 |
+
"grad_norm": 0.98729008436203,
|
| 519 |
+
"learning_rate": 2.4110716524401367e-05,
|
| 520 |
+
"loss": 0.6521,
|
| 521 |
+
"step": 365
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.0,
|
| 525 |
+
"grad_norm": 1.3903419971466064,
|
| 526 |
+
"learning_rate": 2.3932122556166317e-05,
|
| 527 |
+
"loss": 0.6573,
|
| 528 |
+
"step": 370
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.013531799729364,
|
| 532 |
+
"grad_norm": 1.041748046875,
|
| 533 |
+
"learning_rate": 2.375154475467034e-05,
|
| 534 |
+
"loss": 0.5245,
|
| 535 |
+
"step": 375
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.027063599458728,
|
| 539 |
+
"grad_norm": 0.9009564518928528,
|
| 540 |
+
"learning_rate": 2.3569023226421885e-05,
|
| 541 |
+
"loss": 0.5383,
|
| 542 |
+
"step": 380
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.040595399188092,
|
| 546 |
+
"grad_norm": 1.0839605331420898,
|
| 547 |
+
"learning_rate": 2.3384598509633044e-05,
|
| 548 |
+
"loss": 0.5482,
|
| 549 |
+
"step": 385
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.054127198917456,
|
| 553 |
+
"grad_norm": 0.9137062430381775,
|
| 554 |
+
"learning_rate": 2.3198311565215963e-05,
|
| 555 |
+
"loss": 0.5474,
|
| 556 |
+
"step": 390
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.0676589986468201,
|
| 560 |
+
"grad_norm": 0.9517074227333069,
|
| 561 |
+
"learning_rate": 2.3010203767685384e-05,
|
| 562 |
+
"loss": 0.5251,
|
| 563 |
+
"step": 395
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.0811907983761841,
|
| 567 |
+
"grad_norm": 0.9569497108459473,
|
| 568 |
+
"learning_rate": 2.2820316895969337e-05,
|
| 569 |
+
"loss": 0.5294,
|
| 570 |
+
"step": 400
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.094722598105548,
|
| 574 |
+
"grad_norm": 0.8410139083862305,
|
| 575 |
+
"learning_rate": 2.262869312412998e-05,
|
| 576 |
+
"loss": 0.5251,
|
| 577 |
+
"step": 405
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.108254397834912,
|
| 581 |
+
"grad_norm": 0.9338341951370239,
|
| 582 |
+
"learning_rate": 2.2435375011996718e-05,
|
| 583 |
+
"loss": 0.5812,
|
| 584 |
+
"step": 410
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.121786197564276,
|
| 588 |
+
"grad_norm": 0.9952208995819092,
|
| 589 |
+
"learning_rate": 2.2240405495713596e-05,
|
| 590 |
+
"loss": 0.5147,
|
| 591 |
+
"step": 415
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.13531799729364,
|
| 595 |
+
"grad_norm": 0.8791113495826721,
|
| 596 |
+
"learning_rate": 2.2043827878203168e-05,
|
| 597 |
+
"loss": 0.5026,
|
| 598 |
+
"step": 420
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.148849797023004,
|
| 602 |
+
"grad_norm": 0.9727234840393066,
|
| 603 |
+
"learning_rate": 2.184568581954887e-05,
|
| 604 |
+
"loss": 0.4929,
|
| 605 |
+
"step": 425
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.162381596752368,
|
| 609 |
+
"grad_norm": 1.0093767642974854,
|
| 610 |
+
"learning_rate": 2.1646023327298046e-05,
|
| 611 |
+
"loss": 0.5608,
|
| 612 |
+
"step": 430
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.175913396481732,
|
| 616 |
+
"grad_norm": 0.9270041584968567,
|
| 617 |
+
"learning_rate": 2.144488474668785e-05,
|
| 618 |
+
"loss": 0.4939,
|
| 619 |
+
"step": 435
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.1894451962110961,
|
| 623 |
+
"grad_norm": 1.0936297178268433,
|
| 624 |
+
"learning_rate": 2.1242314750796133e-05,
|
| 625 |
+
"loss": 0.4855,
|
| 626 |
+
"step": 440
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.2029769959404601,
|
| 630 |
+
"grad_norm": 0.9255858659744263,
|
| 631 |
+
"learning_rate": 2.1038358330619494e-05,
|
| 632 |
+
"loss": 0.4946,
|
| 633 |
+
"step": 445
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.2165087956698242,
|
| 637 |
+
"grad_norm": 0.9487866163253784,
|
| 638 |
+
"learning_rate": 2.0833060785080733e-05,
|
| 639 |
+
"loss": 0.5014,
|
| 640 |
+
"step": 450
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.230040595399188,
|
| 644 |
+
"grad_norm": 1.049197793006897,
|
| 645 |
+
"learning_rate": 2.0626467710967915e-05,
|
| 646 |
+
"loss": 0.5003,
|
| 647 |
+
"step": 455
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.243572395128552,
|
| 651 |
+
"grad_norm": 0.9660554528236389,
|
| 652 |
+
"learning_rate": 2.0418624992807297e-05,
|
| 653 |
+
"loss": 0.498,
|
| 654 |
+
"step": 460
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.257104194857916,
|
| 658 |
+
"grad_norm": 1.20200514793396,
|
| 659 |
+
"learning_rate": 2.0209578792672304e-05,
|
| 660 |
+
"loss": 0.5145,
|
| 661 |
+
"step": 465
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.27063599458728,
|
| 665 |
+
"grad_norm": 1.0493929386138916,
|
| 666 |
+
"learning_rate": 1.9999375539930915e-05,
|
| 667 |
+
"loss": 0.4915,
|
| 668 |
+
"step": 470
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.284167794316644,
|
| 672 |
+
"grad_norm": 1.1650580167770386,
|
| 673 |
+
"learning_rate": 1.9788061920933612e-05,
|
| 674 |
+
"loss": 0.4764,
|
| 675 |
+
"step": 475
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.297699594046008,
|
| 679 |
+
"grad_norm": 0.9494034051895142,
|
| 680 |
+
"learning_rate": 1.9575684868644352e-05,
|
| 681 |
+
"loss": 0.4549,
|
| 682 |
+
"step": 480
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.3112313937753721,
|
| 686 |
+
"grad_norm": 0.9705236554145813,
|
| 687 |
+
"learning_rate": 1.9362291552216657e-05,
|
| 688 |
+
"loss": 0.5294,
|
| 689 |
+
"step": 485
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.3247631935047361,
|
| 693 |
+
"grad_norm": 1.1208583116531372,
|
| 694 |
+
"learning_rate": 1.9147929366517325e-05,
|
| 695 |
+
"loss": 0.5026,
|
| 696 |
+
"step": 490
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.3382949932341002,
|
| 700 |
+
"grad_norm": 0.9968125820159912,
|
| 701 |
+
"learning_rate": 1.893264592159998e-05,
|
| 702 |
+
"loss": 0.5132,
|
| 703 |
+
"step": 495
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.3518267929634642,
|
| 707 |
+
"grad_norm": 0.9367004036903381,
|
| 708 |
+
"learning_rate": 1.871648903213084e-05,
|
| 709 |
+
"loss": 0.4097,
|
| 710 |
+
"step": 500
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.3653585926928282,
|
| 714 |
+
"grad_norm": 1.2116801738739014,
|
| 715 |
+
"learning_rate": 1.8499506706768995e-05,
|
| 716 |
+
"loss": 0.4628,
|
| 717 |
+
"step": 505
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.3788903924221922,
|
| 721 |
+
"grad_norm": 0.9847371578216553,
|
| 722 |
+
"learning_rate": 1.8281747137503697e-05,
|
| 723 |
+
"loss": 0.415,
|
| 724 |
+
"step": 510
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.3924221921515563,
|
| 728 |
+
"grad_norm": 1.1159377098083496,
|
| 729 |
+
"learning_rate": 1.8063258688950818e-05,
|
| 730 |
+
"loss": 0.4461,
|
| 731 |
+
"step": 515
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.4059539918809203,
|
| 735 |
+
"grad_norm": 0.9392749071121216,
|
| 736 |
+
"learning_rate": 1.784408988761104e-05,
|
| 737 |
+
"loss": 0.4631,
|
| 738 |
+
"step": 520
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.419485791610284,
|
| 742 |
+
"grad_norm": 1.0314615964889526,
|
| 743 |
+
"learning_rate": 1.762428941109209e-05,
|
| 744 |
+
"loss": 0.4245,
|
| 745 |
+
"step": 525
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.4330175913396481,
|
| 749 |
+
"grad_norm": 1.0419405698776245,
|
| 750 |
+
"learning_rate": 1.7403906077297358e-05,
|
| 751 |
+
"loss": 0.4406,
|
| 752 |
+
"step": 530
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.4465493910690121,
|
| 756 |
+
"grad_norm": 0.9040926694869995,
|
| 757 |
+
"learning_rate": 1.718298883358342e-05,
|
| 758 |
+
"loss": 0.4223,
|
| 759 |
+
"step": 535
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.4600811907983762,
|
| 763 |
+
"grad_norm": 1.2367652654647827,
|
| 764 |
+
"learning_rate": 1.6961586745888772e-05,
|
| 765 |
+
"loss": 0.4598,
|
| 766 |
+
"step": 540
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.4736129905277402,
|
| 770 |
+
"grad_norm": 0.9918299913406372,
|
| 771 |
+
"learning_rate": 1.6739748987836247e-05,
|
| 772 |
+
"loss": 0.435,
|
| 773 |
+
"step": 545
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.4871447902571042,
|
| 777 |
+
"grad_norm": 1.061131238937378,
|
| 778 |
+
"learning_rate": 1.6517524829811485e-05,
|
| 779 |
+
"loss": 0.4172,
|
| 780 |
+
"step": 550
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.5006765899864682,
|
| 784 |
+
"grad_norm": 1.1273703575134277,
|
| 785 |
+
"learning_rate": 1.6294963628019942e-05,
|
| 786 |
+
"loss": 0.4272,
|
| 787 |
+
"step": 555
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.514208389715832,
|
| 791 |
+
"grad_norm": 1.013617992401123,
|
| 792 |
+
"learning_rate": 1.607211481352483e-05,
|
| 793 |
+
"loss": 0.4078,
|
| 794 |
+
"step": 560
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.527740189445196,
|
| 798 |
+
"grad_norm": 1.0132904052734375,
|
| 799 |
+
"learning_rate": 1.5849027881268434e-05,
|
| 800 |
+
"loss": 0.4118,
|
| 801 |
+
"step": 565
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.54127198917456,
|
| 805 |
+
"grad_norm": 1.1008814573287964,
|
| 806 |
+
"learning_rate": 1.5625752379079225e-05,
|
| 807 |
+
"loss": 0.4325,
|
| 808 |
+
"step": 570
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.5548037889039241,
|
| 812 |
+
"grad_norm": 1.112791895866394,
|
| 813 |
+
"learning_rate": 1.5402337896667243e-05,
|
| 814 |
+
"loss": 0.4296,
|
| 815 |
+
"step": 575
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.5683355886332881,
|
| 819 |
+
"grad_norm": 1.125413179397583,
|
| 820 |
+
"learning_rate": 1.5178834054610161e-05,
|
| 821 |
+
"loss": 0.4539,
|
| 822 |
+
"step": 580
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.5818673883626522,
|
| 826 |
+
"grad_norm": 1.1011008024215698,
|
| 827 |
+
"learning_rate": 1.4955290493332539e-05,
|
| 828 |
+
"loss": 0.4007,
|
| 829 |
+
"step": 585
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.5953991880920162,
|
| 833 |
+
"grad_norm": 0.97327721118927,
|
| 834 |
+
"learning_rate": 1.4731756862080606e-05,
|
| 835 |
+
"loss": 0.4511,
|
| 836 |
+
"step": 590
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.6089309878213802,
|
| 840 |
+
"grad_norm": 1.1381677389144897,
|
| 841 |
+
"learning_rate": 1.4508282807895118e-05,
|
| 842 |
+
"loss": 0.4341,
|
| 843 |
+
"step": 595
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.6224627875507442,
|
| 847 |
+
"grad_norm": 1.0669630765914917,
|
| 848 |
+
"learning_rate": 1.4284917964584706e-05,
|
| 849 |
+
"loss": 0.3831,
|
| 850 |
+
"step": 600
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.6359945872801083,
|
| 854 |
+
"grad_norm": 1.026521921157837,
|
| 855 |
+
"learning_rate": 1.4061711941702159e-05,
|
| 856 |
+
"loss": 0.4631,
|
| 857 |
+
"step": 605
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.6495263870094723,
|
| 861 |
+
"grad_norm": 1.066266417503357,
|
| 862 |
+
"learning_rate": 1.3838714313526098e-05,
|
| 863 |
+
"loss": 0.3684,
|
| 864 |
+
"step": 610
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.6630581867388363,
|
| 868 |
+
"grad_norm": 1.0638641119003296,
|
| 869 |
+
"learning_rate": 1.3615974608050472e-05,
|
| 870 |
+
"loss": 0.3989,
|
| 871 |
+
"step": 615
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.6765899864682003,
|
| 875 |
+
"grad_norm": 1.2850046157836914,
|
| 876 |
+
"learning_rate": 1.3393542295984333e-05,
|
| 877 |
+
"loss": 0.4005,
|
| 878 |
+
"step": 620
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.6901217861975644,
|
| 882 |
+
"grad_norm": 1.115999698638916,
|
| 883 |
+
"learning_rate": 1.317146677976436e-05,
|
| 884 |
+
"loss": 0.3953,
|
| 885 |
+
"step": 625
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.7036535859269284,
|
| 889 |
+
"grad_norm": 1.0890486240386963,
|
| 890 |
+
"learning_rate": 1.2949797382582523e-05,
|
| 891 |
+
"loss": 0.3922,
|
| 892 |
+
"step": 630
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 1.7171853856562924,
|
| 896 |
+
"grad_norm": 1.3127589225769043,
|
| 897 |
+
"learning_rate": 1.2728583337431355e-05,
|
| 898 |
+
"loss": 0.3827,
|
| 899 |
+
"step": 635
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 1.7307171853856564,
|
| 903 |
+
"grad_norm": 1.1222238540649414,
|
| 904 |
+
"learning_rate": 1.2507873776169231e-05,
|
| 905 |
+
"loss": 0.4016,
|
| 906 |
+
"step": 640
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.7442489851150202,
|
| 910 |
+
"grad_norm": 1.185115098953247,
|
| 911 |
+
"learning_rate": 1.228771771860818e-05,
|
| 912 |
+
"loss": 0.3527,
|
| 913 |
+
"step": 645
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.7577807848443843,
|
| 917 |
+
"grad_norm": 1.1147173643112183,
|
| 918 |
+
"learning_rate": 1.2068164061626498e-05,
|
| 919 |
+
"loss": 0.3428,
|
| 920 |
+
"step": 650
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.7713125845737483,
|
| 924 |
+
"grad_norm": 0.9522579312324524,
|
| 925 |
+
"learning_rate": 1.1849261568308726e-05,
|
| 926 |
+
"loss": 0.3817,
|
| 927 |
+
"step": 655
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.7848443843031123,
|
| 931 |
+
"grad_norm": 1.113958477973938,
|
| 932 |
+
"learning_rate": 1.1631058857115297e-05,
|
| 933 |
+
"loss": 0.3691,
|
| 934 |
+
"step": 660
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.7983761840324763,
|
| 938 |
+
"grad_norm": 1.0620990991592407,
|
| 939 |
+
"learning_rate": 1.141360439108435e-05,
|
| 940 |
+
"loss": 0.3793,
|
| 941 |
+
"step": 665
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.8119079837618404,
|
| 945 |
+
"grad_norm": 1.1647844314575195,
|
| 946 |
+
"learning_rate": 1.1196946467068038e-05,
|
| 947 |
+
"loss": 0.3552,
|
| 948 |
+
"step": 670
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 1.8254397834912042,
|
| 952 |
+
"grad_norm": 1.0172837972640991,
|
| 953 |
+
"learning_rate": 1.0981133205005732e-05,
|
| 954 |
+
"loss": 0.329,
|
| 955 |
+
"step": 675
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.8389715832205682,
|
| 959 |
+
"grad_norm": 1.2275112867355347,
|
| 960 |
+
"learning_rate": 1.076621253723655e-05,
|
| 961 |
+
"loss": 0.3142,
|
| 962 |
+
"step": 680
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.8525033829499322,
|
| 966 |
+
"grad_norm": 1.0226279497146606,
|
| 967 |
+
"learning_rate": 1.0552232197853538e-05,
|
| 968 |
+
"loss": 0.3438,
|
| 969 |
+
"step": 685
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.8660351826792962,
|
| 973 |
+
"grad_norm": 1.1138184070587158,
|
| 974 |
+
"learning_rate": 1.0339239712101875e-05,
|
| 975 |
+
"loss": 0.341,
|
| 976 |
+
"step": 690
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.8795669824086603,
|
| 980 |
+
"grad_norm": 1.0525020360946655,
|
| 981 |
+
"learning_rate": 1.0127282385823478e-05,
|
| 982 |
+
"loss": 0.3492,
|
| 983 |
+
"step": 695
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.8930987821380243,
|
| 987 |
+
"grad_norm": 1.0607911348342896,
|
| 988 |
+
"learning_rate": 9.916407294950304e-06,
|
| 989 |
+
"loss": 0.3537,
|
| 990 |
+
"step": 700
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.9066305818673883,
|
| 994 |
+
"grad_norm": 1.114538311958313,
|
| 995 |
+
"learning_rate": 9.706661275048774e-06,
|
| 996 |
+
"loss": 0.3725,
|
| 997 |
+
"step": 705
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 1.9201623815967523,
|
| 1001 |
+
"grad_norm": 1.1288905143737793,
|
| 1002 |
+
"learning_rate": 9.498090910917508e-06,
|
| 1003 |
+
"loss": 0.3637,
|
| 1004 |
+
"step": 710
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.9336941813261164,
|
| 1008 |
+
"grad_norm": 1.2061598300933838,
|
| 1009 |
+
"learning_rate": 9.290742526240834e-06,
|
| 1010 |
+
"loss": 0.4081,
|
| 1011 |
+
"step": 715
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 1.9472259810554804,
|
| 1015 |
+
"grad_norm": 1.1844569444656372,
|
| 1016 |
+
"learning_rate": 9.084662173300224e-06,
|
| 1017 |
+
"loss": 0.3914,
|
| 1018 |
+
"step": 720
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.9607577807848444,
|
| 1022 |
+
"grad_norm": 1.064042091369629,
|
| 1023 |
+
"learning_rate": 8.879895622746049e-06,
|
| 1024 |
+
"loss": 0.3585,
|
| 1025 |
+
"step": 725
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 1.9742895805142084,
|
| 1029 |
+
"grad_norm": 1.22542142868042,
|
| 1030 |
+
"learning_rate": 8.676488353431868e-06,
|
| 1031 |
+
"loss": 0.3493,
|
| 1032 |
+
"step": 730
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 1.9878213802435725,
|
| 1036 |
+
"grad_norm": 0.988435685634613,
|
| 1037 |
+
"learning_rate": 8.474485542313535e-06,
|
| 1038 |
+
"loss": 0.3196,
|
| 1039 |
+
"step": 735
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 2.0,
|
| 1043 |
+
"grad_norm": 1.3808515071868896,
|
| 1044 |
+
"learning_rate": 8.27393205441535e-06,
|
| 1045 |
+
"loss": 0.3486,
|
| 1046 |
+
"step": 740
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 2.013531799729364,
|
| 1050 |
+
"grad_norm": 0.9448047876358032,
|
| 1051 |
+
"learning_rate": 8.074872432865477e-06,
|
| 1052 |
+
"loss": 0.2481,
|
| 1053 |
+
"step": 745
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 2.027063599458728,
|
| 1057 |
+
"grad_norm": 1.0030453205108643,
|
| 1058 |
+
"learning_rate": 7.877350889002908e-06,
|
| 1059 |
+
"loss": 0.321,
|
| 1060 |
+
"step": 750
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 2.040595399188092,
|
| 1064 |
+
"grad_norm": 1.1310234069824219,
|
| 1065 |
+
"learning_rate": 7.681411292558035e-06,
|
| 1066 |
+
"loss": 0.2736,
|
| 1067 |
+
"step": 755
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 2.054127198917456,
|
| 1071 |
+
"grad_norm": 1.08480966091156,
|
| 1072 |
+
"learning_rate": 7.487097161909175e-06,
|
| 1073 |
+
"loss": 0.265,
|
| 1074 |
+
"step": 760
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 2.06765899864682,
|
| 1078 |
+
"grad_norm": 1.0154072046279907,
|
| 1079 |
+
"learning_rate": 7.2944516544170845e-06,
|
| 1080 |
+
"loss": 0.3005,
|
| 1081 |
+
"step": 765
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 2.081190798376184,
|
| 1085 |
+
"grad_norm": 1.0939288139343262,
|
| 1086 |
+
"learning_rate": 7.103517556839661e-06,
|
| 1087 |
+
"loss": 0.3121,
|
| 1088 |
+
"step": 770
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 2.094722598105548,
|
| 1092 |
+
"grad_norm": 0.992812991142273,
|
| 1093 |
+
"learning_rate": 6.914337275828969e-06,
|
| 1094 |
+
"loss": 0.2549,
|
| 1095 |
+
"step": 775
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 2.108254397834912,
|
| 1099 |
+
"grad_norm": 0.9731753468513489,
|
| 1100 |
+
"learning_rate": 6.726952828512677e-06,
|
| 1101 |
+
"loss": 0.2679,
|
| 1102 |
+
"step": 780
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 2.121786197564276,
|
| 1106 |
+
"grad_norm": 1.1630011796951294,
|
| 1107 |
+
"learning_rate": 6.5414058331620036e-06,
|
| 1108 |
+
"loss": 0.2685,
|
| 1109 |
+
"step": 785
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 2.1353179972936402,
|
| 1113 |
+
"grad_norm": 1.0000211000442505,
|
| 1114 |
+
"learning_rate": 6.3577374999482855e-06,
|
| 1115 |
+
"loss": 0.2794,
|
| 1116 |
+
"step": 790
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 2.1488497970230043,
|
| 1120 |
+
"grad_norm": 1.1677303314208984,
|
| 1121 |
+
"learning_rate": 6.175988621790115e-06,
|
| 1122 |
+
"loss": 0.2983,
|
| 1123 |
+
"step": 795
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 2.1623815967523683,
|
| 1127 |
+
"grad_norm": 1.2600786685943604,
|
| 1128 |
+
"learning_rate": 5.996199565293236e-06,
|
| 1129 |
+
"loss": 0.2717,
|
| 1130 |
+
"step": 800
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 2.175913396481732,
|
| 1134 |
+
"grad_norm": 1.1151149272918701,
|
| 1135 |
+
"learning_rate": 5.818410261785056e-06,
|
| 1136 |
+
"loss": 0.2383,
|
| 1137 |
+
"step": 805
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 2.189445196211096,
|
| 1141 |
+
"grad_norm": 1.0019928216934204,
|
| 1142 |
+
"learning_rate": 5.6426601984458655e-06,
|
| 1143 |
+
"loss": 0.2754,
|
| 1144 |
+
"step": 810
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 2.20297699594046,
|
| 1148 |
+
"grad_norm": 1.0929207801818848,
|
| 1149 |
+
"learning_rate": 5.468988409538695e-06,
|
| 1150 |
+
"loss": 0.2764,
|
| 1151 |
+
"step": 815
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 2.216508795669824,
|
| 1155 |
+
"grad_norm": 1.1664960384368896,
|
| 1156 |
+
"learning_rate": 5.297433467739757e-06,
|
| 1157 |
+
"loss": 0.2757,
|
| 1158 |
+
"step": 820
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 2.230040595399188,
|
| 1162 |
+
"grad_norm": 1.0976636409759521,
|
| 1163 |
+
"learning_rate": 5.128033475571437e-06,
|
| 1164 |
+
"loss": 0.2513,
|
| 1165 |
+
"step": 825
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 2.243572395128552,
|
| 1169 |
+
"grad_norm": 1.2279311418533325,
|
| 1170 |
+
"learning_rate": 4.960826056939678e-06,
|
| 1171 |
+
"loss": 0.2948,
|
| 1172 |
+
"step": 830
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 2.257104194857916,
|
| 1176 |
+
"grad_norm": 1.1249443292617798,
|
| 1177 |
+
"learning_rate": 4.795848348777652e-06,
|
| 1178 |
+
"loss": 0.244,
|
| 1179 |
+
"step": 835
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 2.27063599458728,
|
| 1183 |
+
"grad_norm": 1.0498460531234741,
|
| 1184 |
+
"learning_rate": 4.633136992797645e-06,
|
| 1185 |
+
"loss": 0.2459,
|
| 1186 |
+
"step": 840
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 2.284167794316644,
|
| 1190 |
+
"grad_norm": 1.0207273960113525,
|
| 1191 |
+
"learning_rate": 4.472728127352879e-06,
|
| 1192 |
+
"loss": 0.276,
|
| 1193 |
+
"step": 845
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 2.297699594046008,
|
| 1197 |
+
"grad_norm": 0.9971548318862915,
|
| 1198 |
+
"learning_rate": 4.314657379411145e-06,
|
| 1199 |
+
"loss": 0.2601,
|
| 1200 |
+
"step": 850
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 2.311231393775372,
|
| 1204 |
+
"grad_norm": 1.0325058698654175,
|
| 1205 |
+
"learning_rate": 4.158959856642016e-06,
|
| 1206 |
+
"loss": 0.24,
|
| 1207 |
+
"step": 855
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 2.324763193504736,
|
| 1211 |
+
"grad_norm": 1.0620962381362915,
|
| 1212 |
+
"learning_rate": 4.005670139619415e-06,
|
| 1213 |
+
"loss": 0.2815,
|
| 1214 |
+
"step": 860
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 2.3382949932341,
|
| 1218 |
+
"grad_norm": 1.127296805381775,
|
| 1219 |
+
"learning_rate": 3.854822274141223e-06,
|
| 1220 |
+
"loss": 0.243,
|
| 1221 |
+
"step": 865
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 2.351826792963464,
|
| 1225 |
+
"grad_norm": 1.0954281091690063,
|
| 1226 |
+
"learning_rate": 3.706449763667681e-06,
|
| 1227 |
+
"loss": 0.2471,
|
| 1228 |
+
"step": 870
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 2.365358592692828,
|
| 1232 |
+
"grad_norm": 1.0184557437896729,
|
| 1233 |
+
"learning_rate": 3.5605855618802153e-06,
|
| 1234 |
+
"loss": 0.2641,
|
| 1235 |
+
"step": 875
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 2.3788903924221922,
|
| 1239 |
+
"grad_norm": 1.1217528581619263,
|
| 1240 |
+
"learning_rate": 3.417262065362429e-06,
|
| 1241 |
+
"loss": 0.2551,
|
| 1242 |
+
"step": 880
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 2.3924221921515563,
|
| 1246 |
+
"grad_norm": 1.029388427734375,
|
| 1247 |
+
"learning_rate": 3.2765111064047663e-06,
|
| 1248 |
+
"loss": 0.28,
|
| 1249 |
+
"step": 885
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 2.4059539918809203,
|
| 1253 |
+
"grad_norm": 1.133617639541626,
|
| 1254 |
+
"learning_rate": 3.1383639459345237e-06,
|
| 1255 |
+
"loss": 0.2322,
|
| 1256 |
+
"step": 890
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 2.4194857916102843,
|
| 1260 |
+
"grad_norm": 1.100874900817871,
|
| 1261 |
+
"learning_rate": 3.0028512665727845e-06,
|
| 1262 |
+
"loss": 0.243,
|
| 1263 |
+
"step": 895
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 2.4330175913396483,
|
| 1267 |
+
"grad_norm": 0.9537081122398376,
|
| 1268 |
+
"learning_rate": 2.8700031658197682e-06,
|
| 1269 |
+
"loss": 0.2224,
|
| 1270 |
+
"step": 900
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 2.4465493910690124,
|
| 1274 |
+
"grad_norm": 1.277233362197876,
|
| 1275 |
+
"learning_rate": 2.7398491493701503e-06,
|
| 1276 |
+
"loss": 0.28,
|
| 1277 |
+
"step": 905
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 2.460081190798376,
|
| 1281 |
+
"grad_norm": 1.141201138496399,
|
| 1282 |
+
"learning_rate": 2.6124181245598145e-06,
|
| 1283 |
+
"loss": 0.2531,
|
| 1284 |
+
"step": 910
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 2.47361299052774,
|
| 1288 |
+
"grad_norm": 1.0353566408157349,
|
| 1289 |
+
"learning_rate": 2.4877383939454986e-06,
|
| 1290 |
+
"loss": 0.2445,
|
| 1291 |
+
"step": 915
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 2.487144790257104,
|
| 1295 |
+
"grad_norm": 1.1602693796157837,
|
| 1296 |
+
"learning_rate": 2.3658376490187905e-06,
|
| 1297 |
+
"loss": 0.2526,
|
| 1298 |
+
"step": 920
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 2.500676589986468,
|
| 1302 |
+
"grad_norm": 0.9862504601478577,
|
| 1303 |
+
"learning_rate": 2.2467429640557903e-06,
|
| 1304 |
+
"loss": 0.2925,
|
| 1305 |
+
"step": 925
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 2.514208389715832,
|
| 1309 |
+
"grad_norm": 1.0675078630447388,
|
| 1310 |
+
"learning_rate": 2.1304807901039146e-06,
|
| 1311 |
+
"loss": 0.2384,
|
| 1312 |
+
"step": 930
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 2.527740189445196,
|
| 1316 |
+
"grad_norm": 0.9645246267318726,
|
| 1317 |
+
"learning_rate": 2.017076949107077e-06,
|
| 1318 |
+
"loss": 0.2497,
|
| 1319 |
+
"step": 935
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 2.54127198917456,
|
| 1323 |
+
"grad_norm": 1.2519577741622925,
|
| 1324 |
+
"learning_rate": 1.9065566281706126e-06,
|
| 1325 |
+
"loss": 0.2444,
|
| 1326 |
+
"step": 940
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 2.554803788903924,
|
| 1330 |
+
"grad_norm": 1.2773398160934448,
|
| 1331 |
+
"learning_rate": 1.7989443739671968e-06,
|
| 1332 |
+
"loss": 0.2484,
|
| 1333 |
+
"step": 945
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 2.568335588633288,
|
| 1337 |
+
"grad_norm": 1.0503301620483398,
|
| 1338 |
+
"learning_rate": 1.6942640872850085e-06,
|
| 1339 |
+
"loss": 0.24,
|
| 1340 |
+
"step": 950
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 2.581867388362652,
|
| 1344 |
+
"grad_norm": 1.0840834379196167,
|
| 1345 |
+
"learning_rate": 1.5925390177193266e-06,
|
| 1346 |
+
"loss": 0.2469,
|
| 1347 |
+
"step": 955
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 2.595399188092016,
|
| 1351 |
+
"grad_norm": 1.1381151676177979,
|
| 1352 |
+
"learning_rate": 1.4937917585087978e-06,
|
| 1353 |
+
"loss": 0.2608,
|
| 1354 |
+
"step": 960
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 2.60893098782138,
|
| 1358 |
+
"grad_norm": 1.1541297435760498,
|
| 1359 |
+
"learning_rate": 1.3980442415174305e-06,
|
| 1360 |
+
"loss": 0.27,
|
| 1361 |
+
"step": 965
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 2.6224627875507442,
|
| 1365 |
+
"grad_norm": 1.3066866397857666,
|
| 1366 |
+
"learning_rate": 1.3053177323635224e-06,
|
| 1367 |
+
"loss": 0.2502,
|
| 1368 |
+
"step": 970
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 2.6359945872801083,
|
| 1372 |
+
"grad_norm": 1.0633459091186523,
|
| 1373 |
+
"learning_rate": 1.215632825696541e-06,
|
| 1374 |
+
"loss": 0.2545,
|
| 1375 |
+
"step": 975
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 2.6495263870094723,
|
| 1379 |
+
"grad_norm": 1.055385708808899,
|
| 1380 |
+
"learning_rate": 1.1290094406230273e-06,
|
| 1381 |
+
"loss": 0.2772,
|
| 1382 |
+
"step": 980
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 2.6630581867388363,
|
| 1386 |
+
"grad_norm": 1.0563002824783325,
|
| 1387 |
+
"learning_rate": 1.045466816282551e-06,
|
| 1388 |
+
"loss": 0.2571,
|
| 1389 |
+
"step": 985
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 2.6765899864682003,
|
| 1393 |
+
"grad_norm": 1.1020985841751099,
|
| 1394 |
+
"learning_rate": 9.650235075746688e-07,
|
| 1395 |
+
"loss": 0.2679,
|
| 1396 |
+
"step": 990
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 2.6901217861975644,
|
| 1400 |
+
"grad_norm": 1.145774483680725,
|
| 1401 |
+
"learning_rate": 8.876973810378663e-07,
|
| 1402 |
+
"loss": 0.2384,
|
| 1403 |
+
"step": 995
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 2.7036535859269284,
|
| 1407 |
+
"grad_norm": 1.0645357370376587,
|
| 1408 |
+
"learning_rate": 8.135056108813898e-07,
|
| 1409 |
+
"loss": 0.2428,
|
| 1410 |
+
"step": 1000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 2.7171853856562924,
|
| 1414 |
+
"grad_norm": 1.1874662637710571,
|
| 1415 |
+
"learning_rate": 7.424646751708247e-07,
|
| 1416 |
+
"loss": 0.268,
|
| 1417 |
+
"step": 1005
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 2.7307171853856564,
|
| 1421 |
+
"grad_norm": 1.2051515579223633,
|
| 1422 |
+
"learning_rate": 6.745903521683128e-07,
|
| 1423 |
+
"loss": 0.2501,
|
| 1424 |
+
"step": 1010
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 2.7442489851150205,
|
| 1428 |
+
"grad_norm": 1.0964494943618774,
|
| 1429 |
+
"learning_rate": 6.098977168281738e-07,
|
| 1430 |
+
"loss": 0.2556,
|
| 1431 |
+
"step": 1015
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 2.7577807848443845,
|
| 1435 |
+
"grad_norm": 1.283424973487854,
|
| 1436 |
+
"learning_rate": 5.48401137448754e-07,
|
| 1437 |
+
"loss": 0.231,
|
| 1438 |
+
"step": 1020
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 2.7713125845737485,
|
| 1442 |
+
"grad_norm": 1.014931559562683,
|
| 1443 |
+
"learning_rate": 4.901142724812019e-07,
|
| 1444 |
+
"loss": 0.2861,
|
| 1445 |
+
"step": 1025
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 2.7848443843031125,
|
| 1449 |
+
"grad_norm": 0.9084144234657288,
|
| 1450 |
+
"learning_rate": 4.350500674959212e-07,
|
| 1451 |
+
"loss": 0.2482,
|
| 1452 |
+
"step": 1030
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 2.7983761840324766,
|
| 1456 |
+
"grad_norm": 1.0819071531295776,
|
| 1457 |
+
"learning_rate": 3.832207523073433e-07,
|
| 1458 |
+
"loss": 0.2294,
|
| 1459 |
+
"step": 1035
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 2.8119079837618406,
|
| 1463 |
+
"grad_norm": 1.1103460788726807,
|
| 1464 |
+
"learning_rate": 3.346378382576726e-07,
|
| 1465 |
+
"loss": 0.2379,
|
| 1466 |
+
"step": 1040
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 2.825439783491204,
|
| 1470 |
+
"grad_norm": 0.9478303790092468,
|
| 1471 |
+
"learning_rate": 2.8931211566020854e-07,
|
| 1472 |
+
"loss": 0.2474,
|
| 1473 |
+
"step": 1045
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 2.838971583220568,
|
| 1477 |
+
"grad_norm": 1.0987522602081299,
|
| 1478 |
+
"learning_rate": 2.4725365140280123e-07,
|
| 1479 |
+
"loss": 0.2524,
|
| 1480 |
+
"step": 1050
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 2.852503382949932,
|
| 1484 |
+
"grad_norm": 1.190110206604004,
|
| 1485 |
+
"learning_rate": 2.0847178671199785e-07,
|
| 1486 |
+
"loss": 0.2737,
|
| 1487 |
+
"step": 1055
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 2.8660351826792962,
|
| 1491 |
+
"grad_norm": 1.024021029472351,
|
| 1492 |
+
"learning_rate": 1.729751350783293e-07,
|
| 1493 |
+
"loss": 0.226,
|
| 1494 |
+
"step": 1060
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 2.8795669824086603,
|
| 1498 |
+
"grad_norm": 1.1473637819290161,
|
| 1499 |
+
"learning_rate": 1.407715803432602e-07,
|
| 1500 |
+
"loss": 0.2253,
|
| 1501 |
+
"step": 1065
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 2.8930987821380243,
|
| 1505 |
+
"grad_norm": 1.0962029695510864,
|
| 1506 |
+
"learning_rate": 1.1186827494817308e-07,
|
| 1507 |
+
"loss": 0.2422,
|
| 1508 |
+
"step": 1070
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 2.9066305818673883,
|
| 1512 |
+
"grad_norm": 1.0986852645874023,
|
| 1513 |
+
"learning_rate": 8.627163834580565e-08,
|
| 1514 |
+
"loss": 0.2634,
|
| 1515 |
+
"step": 1075
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 2.9201623815967523,
|
| 1519 |
+
"grad_norm": 0.9209463000297546,
|
| 1520 |
+
"learning_rate": 6.398735557448299e-08,
|
| 1521 |
+
"loss": 0.2501,
|
| 1522 |
+
"step": 1080
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 2.9336941813261164,
|
| 1526 |
+
"grad_norm": 1.043014645576477,
|
| 1527 |
+
"learning_rate": 4.502037599546427e-08,
|
| 1528 |
+
"loss": 0.2378,
|
| 1529 |
+
"step": 1085
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 2.9472259810554804,
|
| 1533 |
+
"grad_norm": 1.1035783290863037,
|
| 1534 |
+
"learning_rate": 2.9374912193690374e-08,
|
| 1535 |
+
"loss": 0.2506,
|
| 1536 |
+
"step": 1090
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 2.9607577807848444,
|
| 1540 |
+
"grad_norm": 1.0485913753509521,
|
| 1541 |
+
"learning_rate": 1.705443904215731e-08,
|
| 1542 |
+
"loss": 0.2222,
|
| 1543 |
+
"step": 1095
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 2.9742895805142084,
|
| 1547 |
+
"grad_norm": 1.0534766912460327,
|
| 1548 |
+
"learning_rate": 8.061692930146913e-09,
|
| 1549 |
+
"loss": 0.2496,
|
| 1550 |
+
"step": 1100
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 2.9878213802435725,
|
| 1554 |
+
"grad_norm": 1.0232808589935303,
|
| 1555 |
+
"learning_rate": 2.3986711554713215e-09,
|
| 1556 |
+
"loss": 0.2411,
|
| 1557 |
+
"step": 1105
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 3.0,
|
| 1561 |
+
"grad_norm": 1.2917823791503906,
|
| 1562 |
+
"learning_rate": 6.663148087282522e-11,
|
| 1563 |
+
"loss": 0.2244,
|
| 1564 |
+
"step": 1110
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 3.0,
|
| 1568 |
+
"step": 1110,
|
| 1569 |
+
"total_flos": 1.620456557303038e+18,
|
| 1570 |
+
"train_loss": 0.5424838511793463,
|
| 1571 |
+
"train_runtime": 798.7465,
|
| 1572 |
+
"train_samples_per_second": 44.383,
|
| 1573 |
+
"train_steps_per_second": 1.39
|
| 1574 |
+
}
|
| 1575 |
+
],
|
| 1576 |
+
"logging_steps": 5,
|
| 1577 |
+
"max_steps": 1110,
|
| 1578 |
+
"num_input_tokens_seen": 0,
|
| 1579 |
+
"num_train_epochs": 3,
|
| 1580 |
+
"save_steps": 20000,
|
| 1581 |
+
"stateful_callbacks": {
|
| 1582 |
+
"TrainerControl": {
|
| 1583 |
+
"args": {
|
| 1584 |
+
"should_epoch_stop": false,
|
| 1585 |
+
"should_evaluate": false,
|
| 1586 |
+
"should_log": false,
|
| 1587 |
+
"should_save": false,
|
| 1588 |
+
"should_training_stop": false
|
| 1589 |
+
},
|
| 1590 |
+
"attributes": {}
|
| 1591 |
+
}
|
| 1592 |
+
},
|
| 1593 |
+
"total_flos": 1.620456557303038e+18,
|
| 1594 |
+
"train_batch_size": 2,
|
| 1595 |
+
"trial_name": null,
|
| 1596 |
+
"trial_params": null
|
| 1597 |
+
}
|
12_128_e3_3e-5/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ec3300fcebb6a07b6e43557c6a16656b65a56e73d5fdcaa81b52979748e5d06
|
| 3 |
+
size 8209
|
12_128_e3_3e-5/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|