Upload folder using huggingface_hub
Browse files- 138_128_e3_3e-5/adapter_config.json +39 -0
- 138_128_e3_3e-5/adapter_model.safetensors +3 -0
- 138_128_e3_3e-5/added_tokens.json +9 -0
- 138_128_e3_3e-5/all_results.json +9 -0
- 138_128_e3_3e-5/chat_template.jinja +62 -0
- 138_128_e3_3e-5/config.json +32 -0
- 138_128_e3_3e-5/merges.txt +0 -0
- 138_128_e3_3e-5/special_tokens_map.json +33 -0
- 138_128_e3_3e-5/tokenizer.json +0 -0
- 138_128_e3_3e-5/tokenizer_config.json +234 -0
- 138_128_e3_3e-5/train_results.json +9 -0
- 138_128_e3_3e-5/trainer_state.json +1730 -0
- 138_128_e3_3e-5/training_args.bin +3 -0
- 138_128_e3_3e-5/vocab.json +0 -0
138_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 |
+
"up_proj",
|
| 29 |
+
"q_proj",
|
| 30 |
+
"gate_proj",
|
| 31 |
+
"v_proj",
|
| 32 |
+
"down_proj",
|
| 33 |
+
"k_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
+
"use_dora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
138_128_e3_3e-5/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e17bbf66c9bb06fee64eed8ac63b994041b5024a8261e419cfa55d9048e8cb00
|
| 3 |
+
size 791751704
|
138_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 |
+
}
|
138_128_e3_3e-5/all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 1.5419277279871631e+18,
|
| 4 |
+
"train_loss": 0.36778768146438384,
|
| 5 |
+
"train_runtime": 743.0643,
|
| 6 |
+
"train_samples": 12843,
|
| 7 |
+
"train_samples_per_second": 51.852,
|
| 8 |
+
"train_steps_per_second": 1.623
|
| 9 |
+
}
|
138_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 %}
|
138_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 |
+
}
|
138_128_e3_3e-5/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
138_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 |
+
}
|
138_128_e3_3e-5/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
138_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 |
+
}
|
138_128_e3_3e-5/train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 1.5419277279871631e+18,
|
| 4 |
+
"train_loss": 0.36778768146438384,
|
| 5 |
+
"train_runtime": 743.0643,
|
| 6 |
+
"train_samples": 12843,
|
| 7 |
+
"train_samples_per_second": 51.852,
|
| 8 |
+
"train_steps_per_second": 1.623
|
| 9 |
+
}
|
138_128_e3_3e-5/trainer_state.json
ADDED
|
@@ -0,0 +1,1730 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 1206,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.012453300124533,
|
| 14 |
+
"grad_norm": 2.323019027709961,
|
| 15 |
+
"learning_rate": 1.9672131147540985e-06,
|
| 16 |
+
"loss": 1.5186,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.024906600249066,
|
| 21 |
+
"grad_norm": 1.8451788425445557,
|
| 22 |
+
"learning_rate": 4.426229508196722e-06,
|
| 23 |
+
"loss": 1.546,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.037359900373599,
|
| 28 |
+
"grad_norm": 0.8245519995689392,
|
| 29 |
+
"learning_rate": 6.885245901639345e-06,
|
| 30 |
+
"loss": 1.4463,
|
| 31 |
+
"step": 15
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.049813200498132,
|
| 35 |
+
"grad_norm": 0.5792524814605713,
|
| 36 |
+
"learning_rate": 9.344262295081968e-06,
|
| 37 |
+
"loss": 1.4437,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.062266500622665005,
|
| 42 |
+
"grad_norm": 0.5813663601875305,
|
| 43 |
+
"learning_rate": 1.180327868852459e-05,
|
| 44 |
+
"loss": 1.4231,
|
| 45 |
+
"step": 25
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.074719800747198,
|
| 49 |
+
"grad_norm": 0.46379655599594116,
|
| 50 |
+
"learning_rate": 1.4262295081967213e-05,
|
| 51 |
+
"loss": 1.3455,
|
| 52 |
+
"step": 30
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.08717310087173101,
|
| 56 |
+
"grad_norm": 0.5653128027915955,
|
| 57 |
+
"learning_rate": 1.6721311475409834e-05,
|
| 58 |
+
"loss": 1.3671,
|
| 59 |
+
"step": 35
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.099626400996264,
|
| 63 |
+
"grad_norm": 0.38007092475891113,
|
| 64 |
+
"learning_rate": 1.9180327868852462e-05,
|
| 65 |
+
"loss": 1.3294,
|
| 66 |
+
"step": 40
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.11207970112079702,
|
| 70 |
+
"grad_norm": 0.4134085774421692,
|
| 71 |
+
"learning_rate": 2.1639344262295084e-05,
|
| 72 |
+
"loss": 1.3512,
|
| 73 |
+
"step": 45
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.12453300124533001,
|
| 77 |
+
"grad_norm": 0.4001520574092865,
|
| 78 |
+
"learning_rate": 2.4098360655737705e-05,
|
| 79 |
+
"loss": 1.3662,
|
| 80 |
+
"step": 50
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.136986301369863,
|
| 84 |
+
"grad_norm": 0.3832428753376007,
|
| 85 |
+
"learning_rate": 2.6557377049180327e-05,
|
| 86 |
+
"loss": 1.2305,
|
| 87 |
+
"step": 55
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.149439601494396,
|
| 91 |
+
"grad_norm": 0.4886322319507599,
|
| 92 |
+
"learning_rate": 2.901639344262295e-05,
|
| 93 |
+
"loss": 1.3002,
|
| 94 |
+
"step": 60
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.16189290161892902,
|
| 98 |
+
"grad_norm": 0.3790438771247864,
|
| 99 |
+
"learning_rate": 2.9999491852149543e-05,
|
| 100 |
+
"loss": 1.2409,
|
| 101 |
+
"step": 65
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.17434620174346202,
|
| 105 |
+
"grad_norm": 0.4461272060871124,
|
| 106 |
+
"learning_rate": 2.999638662885322e-05,
|
| 107 |
+
"loss": 1.2484,
|
| 108 |
+
"step": 70
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.18679950186799502,
|
| 112 |
+
"grad_norm": 0.42311185598373413,
|
| 113 |
+
"learning_rate": 2.9990459070319718e-05,
|
| 114 |
+
"loss": 1.1704,
|
| 115 |
+
"step": 75
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.199252801992528,
|
| 119 |
+
"grad_norm": 0.49046602845191956,
|
| 120 |
+
"learning_rate": 2.9981710292121587e-05,
|
| 121 |
+
"loss": 1.2178,
|
| 122 |
+
"step": 80
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.21170610211706103,
|
| 126 |
+
"grad_norm": 0.4725804626941681,
|
| 127 |
+
"learning_rate": 2.9970141940787794e-05,
|
| 128 |
+
"loss": 1.1202,
|
| 129 |
+
"step": 85
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.22415940224159403,
|
| 133 |
+
"grad_norm": 0.5257315635681152,
|
| 134 |
+
"learning_rate": 2.9955756193493843e-05,
|
| 135 |
+
"loss": 1.1791,
|
| 136 |
+
"step": 90
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.23661270236612703,
|
| 140 |
+
"grad_norm": 0.5636014342308044,
|
| 141 |
+
"learning_rate": 2.9938555757652027e-05,
|
| 142 |
+
"loss": 1.1442,
|
| 143 |
+
"step": 95
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.24906600249066002,
|
| 147 |
+
"grad_norm": 0.541287899017334,
|
| 148 |
+
"learning_rate": 2.991854387040189e-05,
|
| 149 |
+
"loss": 1.1136,
|
| 150 |
+
"step": 100
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.261519302615193,
|
| 154 |
+
"grad_norm": 0.6065759658813477,
|
| 155 |
+
"learning_rate": 2.9895724298000995e-05,
|
| 156 |
+
"loss": 1.0232,
|
| 157 |
+
"step": 105
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.273972602739726,
|
| 161 |
+
"grad_norm": 0.596156120300293,
|
| 162 |
+
"learning_rate": 2.9870101335116107e-05,
|
| 163 |
+
"loss": 1.0837,
|
| 164 |
+
"step": 110
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.286425902864259,
|
| 168 |
+
"grad_norm": 0.6259438991546631,
|
| 169 |
+
"learning_rate": 2.9841679804014938e-05,
|
| 170 |
+
"loss": 1.0564,
|
| 171 |
+
"step": 115
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.298879202988792,
|
| 175 |
+
"grad_norm": 0.6514918804168701,
|
| 176 |
+
"learning_rate": 2.981046505365859e-05,
|
| 177 |
+
"loss": 1.0463,
|
| 178 |
+
"step": 120
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.31133250311332505,
|
| 182 |
+
"grad_norm": 0.6386065483093262,
|
| 183 |
+
"learning_rate": 2.9776462958694873e-05,
|
| 184 |
+
"loss": 0.9898,
|
| 185 |
+
"step": 125
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.32378580323785805,
|
| 189 |
+
"grad_norm": 0.6327990293502808,
|
| 190 |
+
"learning_rate": 2.9739679918352686e-05,
|
| 191 |
+
"loss": 0.9676,
|
| 192 |
+
"step": 130
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.33623910336239105,
|
| 196 |
+
"grad_norm": 0.7084152698516846,
|
| 197 |
+
"learning_rate": 2.9700122855237685e-05,
|
| 198 |
+
"loss": 0.9841,
|
| 199 |
+
"step": 135
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.34869240348692404,
|
| 203 |
+
"grad_norm": 0.720888614654541,
|
| 204 |
+
"learning_rate": 2.965779921402944e-05,
|
| 205 |
+
"loss": 0.9515,
|
| 206 |
+
"step": 140
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.36114570361145704,
|
| 210 |
+
"grad_norm": 0.7035543918609619,
|
| 211 |
+
"learning_rate": 2.961271696008033e-05,
|
| 212 |
+
"loss": 0.8851,
|
| 213 |
+
"step": 145
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.37359900373599003,
|
| 217 |
+
"grad_norm": 0.8451811671257019,
|
| 218 |
+
"learning_rate": 2.9564884577916463e-05,
|
| 219 |
+
"loss": 0.9972,
|
| 220 |
+
"step": 150
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.386052303860523,
|
| 224 |
+
"grad_norm": 0.8046403527259827,
|
| 225 |
+
"learning_rate": 2.951431106964088e-05,
|
| 226 |
+
"loss": 0.8648,
|
| 227 |
+
"step": 155
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.398505603985056,
|
| 231 |
+
"grad_norm": 0.7956090569496155,
|
| 232 |
+
"learning_rate": 2.9461005953239347e-05,
|
| 233 |
+
"loss": 0.9028,
|
| 234 |
+
"step": 160
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.410958904109589,
|
| 238 |
+
"grad_norm": 0.7928311228752136,
|
| 239 |
+
"learning_rate": 2.9404979260789064e-05,
|
| 240 |
+
"loss": 0.8463,
|
| 241 |
+
"step": 165
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.42341220423412207,
|
| 245 |
+
"grad_norm": 0.886175274848938,
|
| 246 |
+
"learning_rate": 2.934624153657061e-05,
|
| 247 |
+
"loss": 0.8589,
|
| 248 |
+
"step": 170
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.43586550435865506,
|
| 252 |
+
"grad_norm": 0.8902182579040527,
|
| 253 |
+
"learning_rate": 2.9284803835083507e-05,
|
| 254 |
+
"loss": 0.8596,
|
| 255 |
+
"step": 175
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.44831880448318806,
|
| 259 |
+
"grad_norm": 0.8826771378517151,
|
| 260 |
+
"learning_rate": 2.9220677718965747e-05,
|
| 261 |
+
"loss": 0.7837,
|
| 262 |
+
"step": 180
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.46077210460772106,
|
| 266 |
+
"grad_norm": 1.0196400880813599,
|
| 267 |
+
"learning_rate": 2.9153875256817696e-05,
|
| 268 |
+
"loss": 0.8106,
|
| 269 |
+
"step": 185
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.47322540473225405,
|
| 273 |
+
"grad_norm": 0.962088406085968,
|
| 274 |
+
"learning_rate": 2.9084409020930767e-05,
|
| 275 |
+
"loss": 0.8387,
|
| 276 |
+
"step": 190
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.48567870485678705,
|
| 280 |
+
"grad_norm": 0.8833624720573425,
|
| 281 |
+
"learning_rate": 2.9012292084921306e-05,
|
| 282 |
+
"loss": 0.7938,
|
| 283 |
+
"step": 195
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.49813200498132004,
|
| 287 |
+
"grad_norm": 1.0000145435333252,
|
| 288 |
+
"learning_rate": 2.893753802127012e-05,
|
| 289 |
+
"loss": 0.7249,
|
| 290 |
+
"step": 200
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.5105853051058531,
|
| 294 |
+
"grad_norm": 0.9227517247200012,
|
| 295 |
+
"learning_rate": 2.8860160898768123e-05,
|
| 296 |
+
"loss": 0.7459,
|
| 297 |
+
"step": 205
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.523038605230386,
|
| 301 |
+
"grad_norm": 1.0462753772735596,
|
| 302 |
+
"learning_rate": 2.8780175279868577e-05,
|
| 303 |
+
"loss": 0.7374,
|
| 304 |
+
"step": 210
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.5354919053549191,
|
| 308 |
+
"grad_norm": 1.087003469467163,
|
| 309 |
+
"learning_rate": 2.8697596217946426e-05,
|
| 310 |
+
"loss": 0.705,
|
| 311 |
+
"step": 215
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.547945205479452,
|
| 315 |
+
"grad_norm": 0.9915927648544312,
|
| 316 |
+
"learning_rate": 2.861243925446523e-05,
|
| 317 |
+
"loss": 0.7014,
|
| 318 |
+
"step": 220
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.5603985056039851,
|
| 322 |
+
"grad_norm": 1.0102894306182861,
|
| 323 |
+
"learning_rate": 2.8524720416052243e-05,
|
| 324 |
+
"loss": 0.715,
|
| 325 |
+
"step": 225
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.572851805728518,
|
| 329 |
+
"grad_norm": 1.088186264038086,
|
| 330 |
+
"learning_rate": 2.84344562114822e-05,
|
| 331 |
+
"loss": 0.697,
|
| 332 |
+
"step": 230
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.5853051058530511,
|
| 336 |
+
"grad_norm": 0.9590082764625549,
|
| 337 |
+
"learning_rate": 2.8341663628570328e-05,
|
| 338 |
+
"loss": 0.6556,
|
| 339 |
+
"step": 235
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.597758405977584,
|
| 343 |
+
"grad_norm": 0.9584166407585144,
|
| 344 |
+
"learning_rate": 2.824636013097524e-05,
|
| 345 |
+
"loss": 0.6216,
|
| 346 |
+
"step": 240
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.6102117061021171,
|
| 350 |
+
"grad_norm": 1.1738195419311523,
|
| 351 |
+
"learning_rate": 2.8148563654912257e-05,
|
| 352 |
+
"loss": 0.6812,
|
| 353 |
+
"step": 245
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.6226650062266501,
|
| 357 |
+
"grad_norm": 1.0906168222427368,
|
| 358 |
+
"learning_rate": 2.8048292605777766e-05,
|
| 359 |
+
"loss": 0.6138,
|
| 360 |
+
"step": 250
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.635118306351183,
|
| 364 |
+
"grad_norm": 1.1087127923965454,
|
| 365 |
+
"learning_rate": 2.7945565854685348e-05,
|
| 366 |
+
"loss": 0.6539,
|
| 367 |
+
"step": 255
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.6475716064757161,
|
| 371 |
+
"grad_norm": 1.215636968612671,
|
| 372 |
+
"learning_rate": 2.7840402734914182e-05,
|
| 373 |
+
"loss": 0.5769,
|
| 374 |
+
"step": 260
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.660024906600249,
|
| 378 |
+
"grad_norm": 1.24242103099823,
|
| 379 |
+
"learning_rate": 2.773282303827052e-05,
|
| 380 |
+
"loss": 0.6366,
|
| 381 |
+
"step": 265
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.6724782067247821,
|
| 385 |
+
"grad_norm": 1.1535454988479614,
|
| 386 |
+
"learning_rate": 2.762284701136283e-05,
|
| 387 |
+
"loss": 0.6169,
|
| 388 |
+
"step": 270
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.684931506849315,
|
| 392 |
+
"grad_norm": 1.2355749607086182,
|
| 393 |
+
"learning_rate": 2.7510495351791397e-05,
|
| 394 |
+
"loss": 0.6002,
|
| 395 |
+
"step": 275
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.6973848069738481,
|
| 399 |
+
"grad_norm": 1.3292158842086792,
|
| 400 |
+
"learning_rate": 2.739578920425297e-05,
|
| 401 |
+
"loss": 0.6211,
|
| 402 |
+
"step": 280
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.709838107098381,
|
| 406 |
+
"grad_norm": 1.1527949571609497,
|
| 407 |
+
"learning_rate": 2.727875015656135e-05,
|
| 408 |
+
"loss": 0.5783,
|
| 409 |
+
"step": 285
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.7222914072229141,
|
| 413 |
+
"grad_norm": 1.1179882287979126,
|
| 414 |
+
"learning_rate": 2.7159400235584507e-05,
|
| 415 |
+
"loss": 0.5671,
|
| 416 |
+
"step": 290
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.7347447073474471,
|
| 420 |
+
"grad_norm": 1.2739359140396118,
|
| 421 |
+
"learning_rate": 2.703776190309914e-05,
|
| 422 |
+
"loss": 0.5554,
|
| 423 |
+
"step": 295
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.7471980074719801,
|
| 427 |
+
"grad_norm": 0.9971826672554016,
|
| 428 |
+
"learning_rate": 2.691385805156329e-05,
|
| 429 |
+
"loss": 0.5924,
|
| 430 |
+
"step": 300
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.7596513075965131,
|
| 434 |
+
"grad_norm": 1.2298365831375122,
|
| 435 |
+
"learning_rate": 2.6787711999808026e-05,
|
| 436 |
+
"loss": 0.5327,
|
| 437 |
+
"step": 305
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.772104607721046,
|
| 441 |
+
"grad_norm": 1.261979103088379,
|
| 442 |
+
"learning_rate": 2.6659347488648763e-05,
|
| 443 |
+
"loss": 0.5346,
|
| 444 |
+
"step": 310
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.7845579078455791,
|
| 448 |
+
"grad_norm": 1.2995227575302124,
|
| 449 |
+
"learning_rate": 2.6528788676417238e-05,
|
| 450 |
+
"loss": 0.4872,
|
| 451 |
+
"step": 315
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.797011207970112,
|
| 455 |
+
"grad_norm": 1.2352875471115112,
|
| 456 |
+
"learning_rate": 2.6396060134414883e-05,
|
| 457 |
+
"loss": 0.5071,
|
| 458 |
+
"step": 320
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.8094645080946451,
|
| 462 |
+
"grad_norm": 1.1811374425888062,
|
| 463 |
+
"learning_rate": 2.6261186842288482e-05,
|
| 464 |
+
"loss": 0.4827,
|
| 465 |
+
"step": 325
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.821917808219178,
|
| 469 |
+
"grad_norm": 1.282472848892212,
|
| 470 |
+
"learning_rate": 2.6124194183328992e-05,
|
| 471 |
+
"loss": 0.4938,
|
| 472 |
+
"step": 330
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.8343711083437111,
|
| 476 |
+
"grad_norm": 1.451218843460083,
|
| 477 |
+
"learning_rate": 2.5985107939694346e-05,
|
| 478 |
+
"loss": 0.5276,
|
| 479 |
+
"step": 335
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.8468244084682441,
|
| 483 |
+
"grad_norm": 1.2093241214752197,
|
| 484 |
+
"learning_rate": 2.5843954287557253e-05,
|
| 485 |
+
"loss": 0.4534,
|
| 486 |
+
"step": 340
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.8592777085927771,
|
| 490 |
+
"grad_norm": 1.2220991849899292,
|
| 491 |
+
"learning_rate": 2.5700759792178813e-05,
|
| 492 |
+
"loss": 0.5149,
|
| 493 |
+
"step": 345
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.8717310087173101,
|
| 497 |
+
"grad_norm": 1.2086710929870605,
|
| 498 |
+
"learning_rate": 2.5555551402908896e-05,
|
| 499 |
+
"loss": 0.4665,
|
| 500 |
+
"step": 350
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.8841843088418431,
|
| 504 |
+
"grad_norm": 1.1186401844024658,
|
| 505 |
+
"learning_rate": 2.5408356448114255e-05,
|
| 506 |
+
"loss": 0.4481,
|
| 507 |
+
"step": 355
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.8966376089663761,
|
| 511 |
+
"grad_norm": 1.3668131828308105,
|
| 512 |
+
"learning_rate": 2.5259202630035296e-05,
|
| 513 |
+
"loss": 0.4252,
|
| 514 |
+
"step": 360
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.9090909090909091,
|
| 518 |
+
"grad_norm": 1.2898318767547607,
|
| 519 |
+
"learning_rate": 2.51081180195725e-05,
|
| 520 |
+
"loss": 0.4391,
|
| 521 |
+
"step": 365
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.9215442092154421,
|
| 525 |
+
"grad_norm": 1.1851130723953247,
|
| 526 |
+
"learning_rate": 2.4955131051003427e-05,
|
| 527 |
+
"loss": 0.445,
|
| 528 |
+
"step": 370
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.933997509339975,
|
| 532 |
+
"grad_norm": 1.300045371055603,
|
| 533 |
+
"learning_rate": 2.4800270516631376e-05,
|
| 534 |
+
"loss": 0.409,
|
| 535 |
+
"step": 375
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.9464508094645081,
|
| 539 |
+
"grad_norm": 1.2191306352615356,
|
| 540 |
+
"learning_rate": 2.4643565561366644e-05,
|
| 541 |
+
"loss": 0.4263,
|
| 542 |
+
"step": 380
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.958904109589041,
|
| 546 |
+
"grad_norm": 1.302882432937622,
|
| 547 |
+
"learning_rate": 2.4485045677241415e-05,
|
| 548 |
+
"loss": 0.3978,
|
| 549 |
+
"step": 385
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.9713574097135741,
|
| 553 |
+
"grad_norm": 1.3422915935516357,
|
| 554 |
+
"learning_rate": 2.4324740697859326e-05,
|
| 555 |
+
"loss": 0.4484,
|
| 556 |
+
"step": 390
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.9838107098381071,
|
| 560 |
+
"grad_norm": 1.2685996294021606,
|
| 561 |
+
"learning_rate": 2.4162680792780775e-05,
|
| 562 |
+
"loss": 0.3977,
|
| 563 |
+
"step": 395
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.9962640099626401,
|
| 567 |
+
"grad_norm": 1.2416200637817383,
|
| 568 |
+
"learning_rate": 2.399889646184494e-05,
|
| 569 |
+
"loss": 0.3922,
|
| 570 |
+
"step": 400
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.0074719800747198,
|
| 574 |
+
"grad_norm": 1.244289517402649,
|
| 575 |
+
"learning_rate": 2.3833418529429728e-05,
|
| 576 |
+
"loss": 0.3346,
|
| 577 |
+
"step": 405
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.0199252801992529,
|
| 581 |
+
"grad_norm": 1.170119047164917,
|
| 582 |
+
"learning_rate": 2.366627813865055e-05,
|
| 583 |
+
"loss": 0.2807,
|
| 584 |
+
"step": 410
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.0323785803237857,
|
| 588 |
+
"grad_norm": 1.3378503322601318,
|
| 589 |
+
"learning_rate": 2.349750674549918e-05,
|
| 590 |
+
"loss": 0.3212,
|
| 591 |
+
"step": 415
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.0448318804483188,
|
| 595 |
+
"grad_norm": 1.0091121196746826,
|
| 596 |
+
"learning_rate": 2.332713611292371e-05,
|
| 597 |
+
"loss": 0.3109,
|
| 598 |
+
"step": 420
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.0572851805728518,
|
| 602 |
+
"grad_norm": 1.1977916955947876,
|
| 603 |
+
"learning_rate": 2.3155198304850694e-05,
|
| 604 |
+
"loss": 0.2953,
|
| 605 |
+
"step": 425
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.0697384806973849,
|
| 609 |
+
"grad_norm": 1.1469180583953857,
|
| 610 |
+
"learning_rate": 2.2981725680150745e-05,
|
| 611 |
+
"loss": 0.2876,
|
| 612 |
+
"step": 430
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.0821917808219177,
|
| 616 |
+
"grad_norm": 1.2730803489685059,
|
| 617 |
+
"learning_rate": 2.2806750886548508e-05,
|
| 618 |
+
"loss": 0.323,
|
| 619 |
+
"step": 435
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.0946450809464507,
|
| 623 |
+
"grad_norm": 1.2842358350753784,
|
| 624 |
+
"learning_rate": 2.2630306854478335e-05,
|
| 625 |
+
"loss": 0.312,
|
| 626 |
+
"step": 440
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.1070983810709838,
|
| 630 |
+
"grad_norm": 1.187873125076294,
|
| 631 |
+
"learning_rate": 2.245242679088679e-05,
|
| 632 |
+
"loss": 0.2954,
|
| 633 |
+
"step": 445
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.1195516811955168,
|
| 637 |
+
"grad_norm": 1.6430953741073608,
|
| 638 |
+
"learning_rate": 2.2273144172982985e-05,
|
| 639 |
+
"loss": 0.301,
|
| 640 |
+
"step": 450
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.13200498132005,
|
| 644 |
+
"grad_norm": 1.2372331619262695,
|
| 645 |
+
"learning_rate": 2.2092492741938222e-05,
|
| 646 |
+
"loss": 0.2978,
|
| 647 |
+
"step": 455
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.1444582814445827,
|
| 651 |
+
"grad_norm": 1.7149838209152222,
|
| 652 |
+
"learning_rate": 2.1910506496535816e-05,
|
| 653 |
+
"loss": 0.2622,
|
| 654 |
+
"step": 460
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.1569115815691158,
|
| 658 |
+
"grad_norm": 1.116036057472229,
|
| 659 |
+
"learning_rate": 2.1727219686772494e-05,
|
| 660 |
+
"loss": 0.273,
|
| 661 |
+
"step": 465
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.1693648816936488,
|
| 665 |
+
"grad_norm": 1.1681700944900513,
|
| 666 |
+
"learning_rate": 2.154266680741253e-05,
|
| 667 |
+
"loss": 0.285,
|
| 668 |
+
"step": 470
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.1818181818181819,
|
| 672 |
+
"grad_norm": 1.3372962474822998,
|
| 673 |
+
"learning_rate": 2.1356882591495795e-05,
|
| 674 |
+
"loss": 0.2748,
|
| 675 |
+
"step": 475
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.1942714819427147,
|
| 679 |
+
"grad_norm": 1.126945972442627,
|
| 680 |
+
"learning_rate": 2.116990200380093e-05,
|
| 681 |
+
"loss": 0.3039,
|
| 682 |
+
"step": 480
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.2067247820672478,
|
| 686 |
+
"grad_norm": 1.4096333980560303,
|
| 687 |
+
"learning_rate": 2.0981760234264983e-05,
|
| 688 |
+
"loss": 0.2728,
|
| 689 |
+
"step": 485
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.2191780821917808,
|
| 693 |
+
"grad_norm": 1.2791043519973755,
|
| 694 |
+
"learning_rate": 2.07924926913606e-05,
|
| 695 |
+
"loss": 0.2793,
|
| 696 |
+
"step": 490
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.2316313823163139,
|
| 700 |
+
"grad_norm": 1.4474986791610718,
|
| 701 |
+
"learning_rate": 2.0602134995432124e-05,
|
| 702 |
+
"loss": 0.2218,
|
| 703 |
+
"step": 495
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.244084682440847,
|
| 707 |
+
"grad_norm": 1.5396515130996704,
|
| 708 |
+
"learning_rate": 2.0410722971991802e-05,
|
| 709 |
+
"loss": 0.2663,
|
| 710 |
+
"step": 500
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.25653798256538,
|
| 714 |
+
"grad_norm": 1.1788588762283325,
|
| 715 |
+
"learning_rate": 2.0218292644977396e-05,
|
| 716 |
+
"loss": 0.2495,
|
| 717 |
+
"step": 505
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.2689912826899128,
|
| 721 |
+
"grad_norm": 1.346476435661316,
|
| 722 |
+
"learning_rate": 2.002488022997244e-05,
|
| 723 |
+
"loss": 0.2553,
|
| 724 |
+
"step": 510
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.2814445828144458,
|
| 728 |
+
"grad_norm": 1.3967148065567017,
|
| 729 |
+
"learning_rate": 1.9830522127390428e-05,
|
| 730 |
+
"loss": 0.2351,
|
| 731 |
+
"step": 515
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.293897882938979,
|
| 735 |
+
"grad_norm": 1.3045532703399658,
|
| 736 |
+
"learning_rate": 1.963525491562421e-05,
|
| 737 |
+
"loss": 0.2415,
|
| 738 |
+
"step": 520
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.3063511830635117,
|
| 742 |
+
"grad_norm": 1.0762789249420166,
|
| 743 |
+
"learning_rate": 1.943911534416193e-05,
|
| 744 |
+
"loss": 0.2423,
|
| 745 |
+
"step": 525
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.3188044831880448,
|
| 749 |
+
"grad_norm": 1.443464756011963,
|
| 750 |
+
"learning_rate": 1.924214032667069e-05,
|
| 751 |
+
"loss": 0.2234,
|
| 752 |
+
"step": 530
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.3312577833125778,
|
| 756 |
+
"grad_norm": 1.273149013519287,
|
| 757 |
+
"learning_rate": 1.9044366934049408e-05,
|
| 758 |
+
"loss": 0.2725,
|
| 759 |
+
"step": 535
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.3437110834371109,
|
| 763 |
+
"grad_norm": 1.1968226432800293,
|
| 764 |
+
"learning_rate": 1.8845832387451995e-05,
|
| 765 |
+
"loss": 0.209,
|
| 766 |
+
"step": 540
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.356164383561644,
|
| 770 |
+
"grad_norm": 1.4278267621994019,
|
| 771 |
+
"learning_rate": 1.8646574051282337e-05,
|
| 772 |
+
"loss": 0.2271,
|
| 773 |
+
"step": 545
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.3686176836861768,
|
| 777 |
+
"grad_norm": 1.155118703842163,
|
| 778 |
+
"learning_rate": 1.844662942616224e-05,
|
| 779 |
+
"loss": 0.2143,
|
| 780 |
+
"step": 550
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.3810709838107098,
|
| 784 |
+
"grad_norm": 1.3056758642196655,
|
| 785 |
+
"learning_rate": 1.8246036141873786e-05,
|
| 786 |
+
"loss": 0.2258,
|
| 787 |
+
"step": 555
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.3935242839352429,
|
| 791 |
+
"grad_norm": 1.4385669231414795,
|
| 792 |
+
"learning_rate": 1.804483195027739e-05,
|
| 793 |
+
"loss": 0.2225,
|
| 794 |
+
"step": 560
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.405977584059776,
|
| 798 |
+
"grad_norm": 1.2106066942214966,
|
| 799 |
+
"learning_rate": 1.7843054718206818e-05,
|
| 800 |
+
"loss": 0.1869,
|
| 801 |
+
"step": 565
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.4184308841843087,
|
| 805 |
+
"grad_norm": 1.2372570037841797,
|
| 806 |
+
"learning_rate": 1.7640742420342672e-05,
|
| 807 |
+
"loss": 0.2307,
|
| 808 |
+
"step": 570
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.4308841843088418,
|
| 812 |
+
"grad_norm": 1.3531502485275269,
|
| 813 |
+
"learning_rate": 1.7437933132065452e-05,
|
| 814 |
+
"loss": 0.2345,
|
| 815 |
+
"step": 575
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.4433374844333748,
|
| 819 |
+
"grad_norm": 1.2152862548828125,
|
| 820 |
+
"learning_rate": 1.7234665022289777e-05,
|
| 821 |
+
"loss": 0.2211,
|
| 822 |
+
"step": 580
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.455790784557908,
|
| 826 |
+
"grad_norm": 1.3017277717590332,
|
| 827 |
+
"learning_rate": 1.7030976346280924e-05,
|
| 828 |
+
"loss": 0.1936,
|
| 829 |
+
"step": 585
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.468244084682441,
|
| 833 |
+
"grad_norm": 1.1975960731506348,
|
| 834 |
+
"learning_rate": 1.6826905438455174e-05,
|
| 835 |
+
"loss": 0.195,
|
| 836 |
+
"step": 590
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.4806973848069738,
|
| 840 |
+
"grad_norm": 1.2248194217681885,
|
| 841 |
+
"learning_rate": 1.662249070516523e-05,
|
| 842 |
+
"loss": 0.1987,
|
| 843 |
+
"step": 595
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.4931506849315068,
|
| 847 |
+
"grad_norm": 1.175775408744812,
|
| 848 |
+
"learning_rate": 1.641777061747209e-05,
|
| 849 |
+
"loss": 0.1816,
|
| 850 |
+
"step": 600
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.5056039850560399,
|
| 854 |
+
"grad_norm": 1.116485357284546,
|
| 855 |
+
"learning_rate": 1.621278370390476e-05,
|
| 856 |
+
"loss": 0.1969,
|
| 857 |
+
"step": 605
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.5180572851805727,
|
| 861 |
+
"grad_norm": 1.2391877174377441,
|
| 862 |
+
"learning_rate": 1.6007568543209153e-05,
|
| 863 |
+
"loss": 0.185,
|
| 864 |
+
"step": 610
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.5305105853051058,
|
| 868 |
+
"grad_norm": 1.2541625499725342,
|
| 869 |
+
"learning_rate": 1.5802163757087513e-05,
|
| 870 |
+
"loss": 0.1798,
|
| 871 |
+
"step": 615
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.5429638854296388,
|
| 875 |
+
"grad_norm": 1.1040685176849365,
|
| 876 |
+
"learning_rate": 1.5596608002929793e-05,
|
| 877 |
+
"loss": 0.1657,
|
| 878 |
+
"step": 620
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.5554171855541719,
|
| 882 |
+
"grad_norm": 1.1332441568374634,
|
| 883 |
+
"learning_rate": 1.539093996653829e-05,
|
| 884 |
+
"loss": 0.1842,
|
| 885 |
+
"step": 625
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.567870485678705,
|
| 889 |
+
"grad_norm": 1.1989057064056396,
|
| 890 |
+
"learning_rate": 1.518519835484691e-05,
|
| 891 |
+
"loss": 0.1726,
|
| 892 |
+
"step": 630
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 1.580323785803238,
|
| 896 |
+
"grad_norm": 1.2308235168457031,
|
| 897 |
+
"learning_rate": 1.4979421888636532e-05,
|
| 898 |
+
"loss": 0.1717,
|
| 899 |
+
"step": 635
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 1.592777085927771,
|
| 903 |
+
"grad_norm": 1.0793812274932861,
|
| 904 |
+
"learning_rate": 1.4773649295247668e-05,
|
| 905 |
+
"loss": 0.1885,
|
| 906 |
+
"step": 640
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.6052303860523038,
|
| 910 |
+
"grad_norm": 1.2486377954483032,
|
| 911 |
+
"learning_rate": 1.4567919301291976e-05,
|
| 912 |
+
"loss": 0.1866,
|
| 913 |
+
"step": 645
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.6176836861768369,
|
| 917 |
+
"grad_norm": 1.1979202032089233,
|
| 918 |
+
"learning_rate": 1.4362270625363852e-05,
|
| 919 |
+
"loss": 0.1766,
|
| 920 |
+
"step": 650
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.6301369863013697,
|
| 924 |
+
"grad_norm": 1.1210886240005493,
|
| 925 |
+
"learning_rate": 1.415674197075355e-05,
|
| 926 |
+
"loss": 0.1752,
|
| 927 |
+
"step": 655
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.6425902864259028,
|
| 931 |
+
"grad_norm": 1.15273916721344,
|
| 932 |
+
"learning_rate": 1.3951372018163197e-05,
|
| 933 |
+
"loss": 0.1524,
|
| 934 |
+
"step": 660
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.6550435865504358,
|
| 938 |
+
"grad_norm": 1.2123425006866455,
|
| 939 |
+
"learning_rate": 1.3746199418427044e-05,
|
| 940 |
+
"loss": 0.1681,
|
| 941 |
+
"step": 665
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.6674968866749689,
|
| 945 |
+
"grad_norm": 1.0621817111968994,
|
| 946 |
+
"learning_rate": 1.3541262785237321e-05,
|
| 947 |
+
"loss": 0.1727,
|
| 948 |
+
"step": 670
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 1.679950186799502,
|
| 952 |
+
"grad_norm": 1.2401793003082275,
|
| 953 |
+
"learning_rate": 1.3336600687877124e-05,
|
| 954 |
+
"loss": 0.1589,
|
| 955 |
+
"step": 675
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.692403486924035,
|
| 959 |
+
"grad_norm": 1.0771820545196533,
|
| 960 |
+
"learning_rate": 1.313225164396162e-05,
|
| 961 |
+
"loss": 0.1615,
|
| 962 |
+
"step": 680
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.704856787048568,
|
| 966 |
+
"grad_norm": 1.0819141864776611,
|
| 967 |
+
"learning_rate": 1.2928254112189e-05,
|
| 968 |
+
"loss": 0.1611,
|
| 969 |
+
"step": 685
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.7173100871731009,
|
| 973 |
+
"grad_norm": 1.2320258617401123,
|
| 974 |
+
"learning_rate": 1.272464648510251e-05,
|
| 975 |
+
"loss": 0.1418,
|
| 976 |
+
"step": 690
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.729763387297634,
|
| 980 |
+
"grad_norm": 1.4835878610610962,
|
| 981 |
+
"learning_rate": 1.2521467081864945e-05,
|
| 982 |
+
"loss": 0.1493,
|
| 983 |
+
"step": 695
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.7422166874221667,
|
| 987 |
+
"grad_norm": 1.1545857191085815,
|
| 988 |
+
"learning_rate": 1.2318754141046936e-05,
|
| 989 |
+
"loss": 0.145,
|
| 990 |
+
"step": 700
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.7546699875466998,
|
| 994 |
+
"grad_norm": 1.1143786907196045,
|
| 995 |
+
"learning_rate": 1.211654581343039e-05,
|
| 996 |
+
"loss": 0.1404,
|
| 997 |
+
"step": 705
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 1.7671232876712328,
|
| 1001 |
+
"grad_norm": 1.0791460275650024,
|
| 1002 |
+
"learning_rate": 1.1914880154828514e-05,
|
| 1003 |
+
"loss": 0.1326,
|
| 1004 |
+
"step": 710
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.7795765877957659,
|
| 1008 |
+
"grad_norm": 1.2453776597976685,
|
| 1009 |
+
"learning_rate": 1.1713795118923659e-05,
|
| 1010 |
+
"loss": 0.1572,
|
| 1011 |
+
"step": 715
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 1.792029887920299,
|
| 1015 |
+
"grad_norm": 1.0310232639312744,
|
| 1016 |
+
"learning_rate": 1.1513328550124379e-05,
|
| 1017 |
+
"loss": 0.1338,
|
| 1018 |
+
"step": 720
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.804483188044832,
|
| 1022 |
+
"grad_norm": 1.0175222158432007,
|
| 1023 |
+
"learning_rate": 1.1313518176443099e-05,
|
| 1024 |
+
"loss": 0.1306,
|
| 1025 |
+
"step": 725
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 1.816936488169365,
|
| 1029 |
+
"grad_norm": 1.0287436246871948,
|
| 1030 |
+
"learning_rate": 1.1114401602395647e-05,
|
| 1031 |
+
"loss": 0.1513,
|
| 1032 |
+
"step": 730
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 1.8293897882938979,
|
| 1036 |
+
"grad_norm": 1.144381046295166,
|
| 1037 |
+
"learning_rate": 1.0916016301924056e-05,
|
| 1038 |
+
"loss": 0.1569,
|
| 1039 |
+
"step": 735
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 1.841843088418431,
|
| 1043 |
+
"grad_norm": 1.124574899673462,
|
| 1044 |
+
"learning_rate": 1.071839961134393e-05,
|
| 1045 |
+
"loss": 0.1287,
|
| 1046 |
+
"step": 740
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.8542963885429637,
|
| 1050 |
+
"grad_norm": 1.0954211950302124,
|
| 1051 |
+
"learning_rate": 1.0521588722317707e-05,
|
| 1052 |
+
"loss": 0.1388,
|
| 1053 |
+
"step": 745
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 1.8667496886674968,
|
| 1057 |
+
"grad_norm": 1.1026991605758667,
|
| 1058 |
+
"learning_rate": 1.0325620674855147e-05,
|
| 1059 |
+
"loss": 0.134,
|
| 1060 |
+
"step": 750
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 1.8792029887920298,
|
| 1064 |
+
"grad_norm": 0.9430744647979736,
|
| 1065 |
+
"learning_rate": 1.0130532350342381e-05,
|
| 1066 |
+
"loss": 0.1148,
|
| 1067 |
+
"step": 755
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 1.891656288916563,
|
| 1071 |
+
"grad_norm": 0.9424226880073547,
|
| 1072 |
+
"learning_rate": 9.936360464600769e-06,
|
| 1073 |
+
"loss": 0.1314,
|
| 1074 |
+
"step": 760
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.904109589041096,
|
| 1078 |
+
"grad_norm": 0.9517638683319092,
|
| 1079 |
+
"learning_rate": 9.74314156097697e-06,
|
| 1080 |
+
"loss": 0.1132,
|
| 1081 |
+
"step": 765
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 1.916562889165629,
|
| 1085 |
+
"grad_norm": 1.1850603818893433,
|
| 1086 |
+
"learning_rate": 9.550912003465442e-06,
|
| 1087 |
+
"loss": 0.1181,
|
| 1088 |
+
"step": 770
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 1.929016189290162,
|
| 1092 |
+
"grad_norm": 0.9696543216705322,
|
| 1093 |
+
"learning_rate": 9.359707969864688e-06,
|
| 1094 |
+
"loss": 0.1112,
|
| 1095 |
+
"step": 775
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 1.9414694894146949,
|
| 1099 |
+
"grad_norm": 1.0155787467956543,
|
| 1100 |
+
"learning_rate": 9.16956544496857e-06,
|
| 1101 |
+
"loss": 0.1213,
|
| 1102 |
+
"step": 780
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 1.953922789539228,
|
| 1106 |
+
"grad_norm": 1.0327125787734985,
|
| 1107 |
+
"learning_rate": 8.980520213793934e-06,
|
| 1108 |
+
"loss": 0.1327,
|
| 1109 |
+
"step": 785
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 1.9663760896637608,
|
| 1113 |
+
"grad_norm": 0.8658395409584045,
|
| 1114 |
+
"learning_rate": 8.792607854845829e-06,
|
| 1115 |
+
"loss": 0.1132,
|
| 1116 |
+
"step": 790
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 1.9788293897882938,
|
| 1120 |
+
"grad_norm": 0.8833078742027283,
|
| 1121 |
+
"learning_rate": 8.605863733421594e-06,
|
| 1122 |
+
"loss": 0.1127,
|
| 1123 |
+
"step": 795
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 1.9912826899128269,
|
| 1127 |
+
"grad_norm": 1.1244515180587769,
|
| 1128 |
+
"learning_rate": 8.420322994955074e-06,
|
| 1129 |
+
"loss": 0.1059,
|
| 1130 |
+
"step": 800
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 2.0024906600249066,
|
| 1134 |
+
"grad_norm": 0.8100209832191467,
|
| 1135 |
+
"learning_rate": 8.236020558402222e-06,
|
| 1136 |
+
"loss": 0.1078,
|
| 1137 |
+
"step": 805
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 2.0149439601494397,
|
| 1141 |
+
"grad_norm": 0.6915018558502197,
|
| 1142 |
+
"learning_rate": 8.052991109669306e-06,
|
| 1143 |
+
"loss": 0.0878,
|
| 1144 |
+
"step": 810
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 2.0273972602739727,
|
| 1148 |
+
"grad_norm": 0.9379139542579651,
|
| 1149 |
+
"learning_rate": 7.87126909508499e-06,
|
| 1150 |
+
"loss": 0.0898,
|
| 1151 |
+
"step": 815
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 2.0398505603985058,
|
| 1155 |
+
"grad_norm": 0.8109155297279358,
|
| 1156 |
+
"learning_rate": 7.690888714917507e-06,
|
| 1157 |
+
"loss": 0.0984,
|
| 1158 |
+
"step": 820
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 2.052303860523039,
|
| 1162 |
+
"grad_norm": 0.9438534379005432,
|
| 1163 |
+
"learning_rate": 7.511883916938109e-06,
|
| 1164 |
+
"loss": 0.0869,
|
| 1165 |
+
"step": 825
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 2.0647571606475714,
|
| 1169 |
+
"grad_norm": 0.8569890856742859,
|
| 1170 |
+
"learning_rate": 7.334288390032098e-06,
|
| 1171 |
+
"loss": 0.0882,
|
| 1172 |
+
"step": 830
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 2.0772104607721045,
|
| 1176 |
+
"grad_norm": 0.9603305459022522,
|
| 1177 |
+
"learning_rate": 7.158135557858515e-06,
|
| 1178 |
+
"loss": 0.0887,
|
| 1179 |
+
"step": 835
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 2.0896637608966375,
|
| 1183 |
+
"grad_norm": 0.829105019569397,
|
| 1184 |
+
"learning_rate": 6.983458572559782e-06,
|
| 1185 |
+
"loss": 0.0886,
|
| 1186 |
+
"step": 840
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 2.1021170610211706,
|
| 1190 |
+
"grad_norm": 0.6731156706809998,
|
| 1191 |
+
"learning_rate": 6.81029030852244e-06,
|
| 1192 |
+
"loss": 0.0807,
|
| 1193 |
+
"step": 845
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 2.1145703611457036,
|
| 1197 |
+
"grad_norm": 0.7731700539588928,
|
| 1198 |
+
"learning_rate": 6.63866335619015e-06,
|
| 1199 |
+
"loss": 0.0823,
|
| 1200 |
+
"step": 850
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 2.1270236612702367,
|
| 1204 |
+
"grad_norm": 0.8372194766998291,
|
| 1205 |
+
"learning_rate": 6.468610015930143e-06,
|
| 1206 |
+
"loss": 0.087,
|
| 1207 |
+
"step": 855
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 2.1394769613947697,
|
| 1211 |
+
"grad_norm": 0.7078593373298645,
|
| 1212 |
+
"learning_rate": 6.3001622919542495e-06,
|
| 1213 |
+
"loss": 0.0917,
|
| 1214 |
+
"step": 860
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 2.151930261519303,
|
| 1218 |
+
"grad_norm": 0.8801110982894897,
|
| 1219 |
+
"learning_rate": 6.133351886295691e-06,
|
| 1220 |
+
"loss": 0.0887,
|
| 1221 |
+
"step": 865
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 2.1643835616438354,
|
| 1225 |
+
"grad_norm": 0.6602491736412048,
|
| 1226 |
+
"learning_rate": 5.9682101928426966e-06,
|
| 1227 |
+
"loss": 0.0769,
|
| 1228 |
+
"step": 870
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 2.1768368617683684,
|
| 1232 |
+
"grad_norm": 0.8794203996658325,
|
| 1233 |
+
"learning_rate": 5.804768291430174e-06,
|
| 1234 |
+
"loss": 0.089,
|
| 1235 |
+
"step": 875
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 2.1892901618929015,
|
| 1239 |
+
"grad_norm": 0.712538480758667,
|
| 1240 |
+
"learning_rate": 5.643056941990433e-06,
|
| 1241 |
+
"loss": 0.0779,
|
| 1242 |
+
"step": 880
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 2.2017434620174345,
|
| 1246 |
+
"grad_norm": 0.9360284805297852,
|
| 1247 |
+
"learning_rate": 5.483106578764136e-06,
|
| 1248 |
+
"loss": 0.0772,
|
| 1249 |
+
"step": 885
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 2.2141967621419676,
|
| 1253 |
+
"grad_norm": 1.0328861474990845,
|
| 1254 |
+
"learning_rate": 5.324947304572553e-06,
|
| 1255 |
+
"loss": 0.083,
|
| 1256 |
+
"step": 890
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 2.2266500622665006,
|
| 1260 |
+
"grad_norm": 0.7821430563926697,
|
| 1261 |
+
"learning_rate": 5.1686088851521685e-06,
|
| 1262 |
+
"loss": 0.0824,
|
| 1263 |
+
"step": 895
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 2.2391033623910337,
|
| 1267 |
+
"grad_norm": 0.7114161252975464,
|
| 1268 |
+
"learning_rate": 5.014120743552749e-06,
|
| 1269 |
+
"loss": 0.0834,
|
| 1270 |
+
"step": 900
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 2.2515566625155667,
|
| 1274 |
+
"grad_norm": 0.8093134760856628,
|
| 1275 |
+
"learning_rate": 4.861511954599883e-06,
|
| 1276 |
+
"loss": 0.0754,
|
| 1277 |
+
"step": 905
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 2.2640099626401,
|
| 1281 |
+
"grad_norm": 1.0690568685531616,
|
| 1282 |
+
"learning_rate": 4.710811239423083e-06,
|
| 1283 |
+
"loss": 0.0743,
|
| 1284 |
+
"step": 910
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 2.276463262764633,
|
| 1288 |
+
"grad_norm": 0.9506732225418091,
|
| 1289 |
+
"learning_rate": 4.5620469600504355e-06,
|
| 1290 |
+
"loss": 0.0751,
|
| 1291 |
+
"step": 915
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 2.2889165628891655,
|
| 1295 |
+
"grad_norm": 0.6726131439208984,
|
| 1296 |
+
"learning_rate": 4.415247114070834e-06,
|
| 1297 |
+
"loss": 0.0701,
|
| 1298 |
+
"step": 920
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 2.3013698630136985,
|
| 1302 |
+
"grad_norm": 0.6878358721733093,
|
| 1303 |
+
"learning_rate": 4.270439329364799e-06,
|
| 1304 |
+
"loss": 0.0721,
|
| 1305 |
+
"step": 925
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 2.3138231631382316,
|
| 1309 |
+
"grad_norm": 0.8972549438476562,
|
| 1310 |
+
"learning_rate": 4.1276508589048986e-06,
|
| 1311 |
+
"loss": 0.0759,
|
| 1312 |
+
"step": 930
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 2.3262764632627646,
|
| 1316 |
+
"grad_norm": 0.6929914355278015,
|
| 1317 |
+
"learning_rate": 3.986908575626699e-06,
|
| 1318 |
+
"loss": 0.0799,
|
| 1319 |
+
"step": 935
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 2.3387297633872977,
|
| 1323 |
+
"grad_norm": 0.9535344243049622,
|
| 1324 |
+
"learning_rate": 3.848238967371265e-06,
|
| 1325 |
+
"loss": 0.0676,
|
| 1326 |
+
"step": 940
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 2.3511830635118307,
|
| 1330 |
+
"grad_norm": 0.6658231616020203,
|
| 1331 |
+
"learning_rate": 3.7116681319001018e-06,
|
| 1332 |
+
"loss": 0.0728,
|
| 1333 |
+
"step": 945
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 2.3636363636363638,
|
| 1337 |
+
"grad_norm": 0.7737366557121277,
|
| 1338 |
+
"learning_rate": 3.5772217719835384e-06,
|
| 1339 |
+
"loss": 0.0831,
|
| 1340 |
+
"step": 950
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 2.376089663760897,
|
| 1344 |
+
"grad_norm": 0.5599685907363892,
|
| 1345 |
+
"learning_rate": 3.444925190563445e-06,
|
| 1346 |
+
"loss": 0.0648,
|
| 1347 |
+
"step": 955
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 2.3885429638854294,
|
| 1351 |
+
"grad_norm": 0.6603100299835205,
|
| 1352 |
+
"learning_rate": 3.3148032859911844e-06,
|
| 1353 |
+
"loss": 0.0734,
|
| 1354 |
+
"step": 960
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 2.4009962640099625,
|
| 1358 |
+
"grad_norm": 0.7781059145927429,
|
| 1359 |
+
"learning_rate": 3.186880547341727e-06,
|
| 1360 |
+
"loss": 0.0725,
|
| 1361 |
+
"step": 965
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 2.4134495641344955,
|
| 1365 |
+
"grad_norm": 0.7224042415618896,
|
| 1366 |
+
"learning_rate": 3.0611810498047742e-06,
|
| 1367 |
+
"loss": 0.0774,
|
| 1368 |
+
"step": 970
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 2.4259028642590286,
|
| 1372 |
+
"grad_norm": 0.631102442741394,
|
| 1373 |
+
"learning_rate": 2.937728450153789e-06,
|
| 1374 |
+
"loss": 0.0713,
|
| 1375 |
+
"step": 975
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 2.4383561643835616,
|
| 1379 |
+
"grad_norm": 0.8373669385910034,
|
| 1380 |
+
"learning_rate": 2.816545982293752e-06,
|
| 1381 |
+
"loss": 0.0677,
|
| 1382 |
+
"step": 980
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 2.4508094645080947,
|
| 1386 |
+
"grad_norm": 0.7206551432609558,
|
| 1387 |
+
"learning_rate": 2.6976564528885422e-06,
|
| 1388 |
+
"loss": 0.0707,
|
| 1389 |
+
"step": 985
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 2.4632627646326277,
|
| 1393 |
+
"grad_norm": 0.8052924275398254,
|
| 1394 |
+
"learning_rate": 2.5810822370686804e-06,
|
| 1395 |
+
"loss": 0.0711,
|
| 1396 |
+
"step": 990
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 2.4757160647571608,
|
| 1400 |
+
"grad_norm": 0.6548148989677429,
|
| 1401 |
+
"learning_rate": 2.466845274220316e-06,
|
| 1402 |
+
"loss": 0.073,
|
| 1403 |
+
"step": 995
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 2.488169364881694,
|
| 1407 |
+
"grad_norm": 0.7128301858901978,
|
| 1408 |
+
"learning_rate": 2.3549670638562016e-06,
|
| 1409 |
+
"loss": 0.0632,
|
| 1410 |
+
"step": 1000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 2.500622665006227,
|
| 1414 |
+
"grad_norm": 0.6294408440589905,
|
| 1415 |
+
"learning_rate": 2.2454686615694785e-06,
|
| 1416 |
+
"loss": 0.065,
|
| 1417 |
+
"step": 1005
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 2.51307596513076,
|
| 1421 |
+
"grad_norm": 0.5605584979057312,
|
| 1422 |
+
"learning_rate": 2.138370675070977e-06,
|
| 1423 |
+
"loss": 0.0722,
|
| 1424 |
+
"step": 1010
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 2.5255292652552925,
|
| 1428 |
+
"grad_norm": 0.6864460706710815,
|
| 1429 |
+
"learning_rate": 2.0336932603108355e-06,
|
| 1430 |
+
"loss": 0.0667,
|
| 1431 |
+
"step": 1015
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 2.5379825653798256,
|
| 1435 |
+
"grad_norm": 0.6694821119308472,
|
| 1436 |
+
"learning_rate": 1.9314561176851235e-06,
|
| 1437 |
+
"loss": 0.0692,
|
| 1438 |
+
"step": 1020
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 2.5504358655043586,
|
| 1442 |
+
"grad_norm": 0.6386405229568481,
|
| 1443 |
+
"learning_rate": 1.8316784883282105e-06,
|
| 1444 |
+
"loss": 0.0703,
|
| 1445 |
+
"step": 1025
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 2.5628891656288917,
|
| 1449 |
+
"grad_norm": 0.7209354043006897,
|
| 1450 |
+
"learning_rate": 1.7343791504915684e-06,
|
| 1451 |
+
"loss": 0.0733,
|
| 1452 |
+
"step": 1030
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 2.5753424657534247,
|
| 1456 |
+
"grad_norm": 0.8404210209846497,
|
| 1457 |
+
"learning_rate": 1.6395764160096678e-06,
|
| 1458 |
+
"loss": 0.0713,
|
| 1459 |
+
"step": 1035
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 2.587795765877958,
|
| 1463 |
+
"grad_norm": 0.7585222721099854,
|
| 1464 |
+
"learning_rate": 1.547288126853697e-06,
|
| 1465 |
+
"loss": 0.0717,
|
| 1466 |
+
"step": 1040
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 2.6002490660024904,
|
| 1470 |
+
"grad_norm": 0.5720264315605164,
|
| 1471 |
+
"learning_rate": 1.4575316517736714e-06,
|
| 1472 |
+
"loss": 0.07,
|
| 1473 |
+
"step": 1045
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 2.6127023661270234,
|
| 1477 |
+
"grad_norm": 0.7315094470977783,
|
| 1478 |
+
"learning_rate": 1.370323883029615e-06,
|
| 1479 |
+
"loss": 0.0765,
|
| 1480 |
+
"step": 1050
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 2.6251556662515565,
|
| 1484 |
+
"grad_norm": 0.6323287487030029,
|
| 1485 |
+
"learning_rate": 1.2856812332124274e-06,
|
| 1486 |
+
"loss": 0.0682,
|
| 1487 |
+
"step": 1055
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 2.6376089663760895,
|
| 1491 |
+
"grad_norm": 0.5976901054382324,
|
| 1492 |
+
"learning_rate": 1.2036196321550096e-06,
|
| 1493 |
+
"loss": 0.0607,
|
| 1494 |
+
"step": 1060
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 2.6500622665006226,
|
| 1498 |
+
"grad_norm": 0.6853218674659729,
|
| 1499 |
+
"learning_rate": 1.1241545239342609e-06,
|
| 1500 |
+
"loss": 0.0673,
|
| 1501 |
+
"step": 1065
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 2.6625155666251556,
|
| 1505 |
+
"grad_norm": 0.5944624543190002,
|
| 1506 |
+
"learning_rate": 1.0473008639644814e-06,
|
| 1507 |
+
"loss": 0.0596,
|
| 1508 |
+
"step": 1070
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 2.6749688667496887,
|
| 1512 |
+
"grad_norm": 0.5547900795936584,
|
| 1513 |
+
"learning_rate": 9.730731161827528e-07,
|
| 1514 |
+
"loss": 0.0631,
|
| 1515 |
+
"step": 1075
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 2.6874221668742218,
|
| 1519 |
+
"grad_norm": 0.7503756880760193,
|
| 1520 |
+
"learning_rate": 9.014852503268045e-07,
|
| 1521 |
+
"loss": 0.0637,
|
| 1522 |
+
"step": 1080
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 2.699875466998755,
|
| 1526 |
+
"grad_norm": 0.6030451655387878,
|
| 1527 |
+
"learning_rate": 8.325507393059101e-07,
|
| 1528 |
+
"loss": 0.0573,
|
| 1529 |
+
"step": 1085
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 2.712328767123288,
|
| 1533 |
+
"grad_norm": 0.6738685965538025,
|
| 1534 |
+
"learning_rate": 7.662825566652442e-07,
|
| 1535 |
+
"loss": 0.0662,
|
| 1536 |
+
"step": 1090
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 2.724782067247821,
|
| 1540 |
+
"grad_norm": 0.6543871760368347,
|
| 1541 |
+
"learning_rate": 7.026931741442783e-07,
|
| 1542 |
+
"loss": 0.072,
|
| 1543 |
+
"step": 1095
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 2.7372353673723535,
|
| 1547 |
+
"grad_norm": 0.5266416072845459,
|
| 1548 |
+
"learning_rate": 6.417945593295638e-07,
|
| 1549 |
+
"loss": 0.0735,
|
| 1550 |
+
"step": 1100
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 2.7496886674968866,
|
| 1554 |
+
"grad_norm": 0.7614601850509644,
|
| 1555 |
+
"learning_rate": 5.835981734024348e-07,
|
| 1556 |
+
"loss": 0.0746,
|
| 1557 |
+
"step": 1105
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 2.7621419676214196,
|
| 1561 |
+
"grad_norm": 0.7067199945449829,
|
| 1562 |
+
"learning_rate": 5.281149689819981e-07,
|
| 1563 |
+
"loss": 0.0645,
|
| 1564 |
+
"step": 1110
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 2.7745952677459527,
|
| 1568 |
+
"grad_norm": 0.7431591153144836,
|
| 1569 |
+
"learning_rate": 4.7535538806383006e-07,
|
| 1570 |
+
"loss": 0.0679,
|
| 1571 |
+
"step": 1115
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 2.7870485678704857,
|
| 1575 |
+
"grad_norm": 0.5334625840187073,
|
| 1576 |
+
"learning_rate": 4.2532936005479585e-07,
|
| 1577 |
+
"loss": 0.0655,
|
| 1578 |
+
"step": 1120
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 2.7995018679950188,
|
| 1582 |
+
"grad_norm": 0.5616161823272705,
|
| 1583 |
+
"learning_rate": 3.7804629990431884e-07,
|
| 1584 |
+
"loss": 0.0618,
|
| 1585 |
+
"step": 1125
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 2.811955168119552,
|
| 1589 |
+
"grad_norm": 0.7120090126991272,
|
| 1590 |
+
"learning_rate": 3.335151063324765e-07,
|
| 1591 |
+
"loss": 0.0665,
|
| 1592 |
+
"step": 1130
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 2.8244084682440844,
|
| 1596 |
+
"grad_norm": 0.5271226763725281,
|
| 1597 |
+
"learning_rate": 2.917441601552534e-07,
|
| 1598 |
+
"loss": 0.0631,
|
| 1599 |
+
"step": 1135
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 2.8368617683686175,
|
| 1603 |
+
"grad_norm": 0.7041694521903992,
|
| 1604 |
+
"learning_rate": 2.527413227072628e-07,
|
| 1605 |
+
"loss": 0.0778,
|
| 1606 |
+
"step": 1140
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 2.8493150684931505,
|
| 1610 |
+
"grad_norm": 0.6397244930267334,
|
| 1611 |
+
"learning_rate": 2.165139343622352e-07,
|
| 1612 |
+
"loss": 0.0796,
|
| 1613 |
+
"step": 1145
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 2.8617683686176836,
|
| 1617 |
+
"grad_norm": 0.6322922110557556,
|
| 1618 |
+
"learning_rate": 1.830688131515551e-07,
|
| 1619 |
+
"loss": 0.0741,
|
| 1620 |
+
"step": 1150
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 2.8742216687422166,
|
| 1624 |
+
"grad_norm": 0.6011943817138672,
|
| 1625 |
+
"learning_rate": 1.5241225348109898e-07,
|
| 1626 |
+
"loss": 0.0698,
|
| 1627 |
+
"step": 1155
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 2.8866749688667497,
|
| 1631 |
+
"grad_norm": 0.7942560315132141,
|
| 1632 |
+
"learning_rate": 1.2455002494661972e-07,
|
| 1633 |
+
"loss": 0.0747,
|
| 1634 |
+
"step": 1160
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 2.8991282689912827,
|
| 1638 |
+
"grad_norm": 0.6241059303283691,
|
| 1639 |
+
"learning_rate": 9.948737124790331e-08,
|
| 1640 |
+
"loss": 0.0633,
|
| 1641 |
+
"step": 1165
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 2.911581569115816,
|
| 1645 |
+
"grad_norm": 0.6511146426200867,
|
| 1646 |
+
"learning_rate": 7.722900920190179e-08,
|
| 1647 |
+
"loss": 0.0669,
|
| 1648 |
+
"step": 1170
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 2.924034869240349,
|
| 1652 |
+
"grad_norm": 0.5726321339607239,
|
| 1653 |
+
"learning_rate": 5.777912785502493e-08,
|
| 1654 |
+
"loss": 0.0674,
|
| 1655 |
+
"step": 1175
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 2.936488169364882,
|
| 1659 |
+
"grad_norm": 0.6145641207695007,
|
| 1660 |
+
"learning_rate": 4.114138769474918e-08,
|
| 1661 |
+
"loss": 0.0703,
|
| 1662 |
+
"step": 1180
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 2.948941469489415,
|
| 1666 |
+
"grad_norm": 0.6198668479919434,
|
| 1667 |
+
"learning_rate": 2.731891996071878e-08,
|
| 1668 |
+
"loss": 0.0641,
|
| 1669 |
+
"step": 1185
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 2.9613947696139475,
|
| 1673 |
+
"grad_norm": 0.6175679564476013,
|
| 1674 |
+
"learning_rate": 1.6314326055440475e-08,
|
| 1675 |
+
"loss": 0.0652,
|
| 1676 |
+
"step": 1190
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 2.9738480697384806,
|
| 1680 |
+
"grad_norm": 0.673772394657135,
|
| 1681 |
+
"learning_rate": 8.129677054693474e-09,
|
| 1682 |
+
"loss": 0.0678,
|
| 1683 |
+
"step": 1195
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 2.9863013698630136,
|
| 1687 |
+
"grad_norm": 0.668915331363678,
|
| 1688 |
+
"learning_rate": 2.7665133177545708e-09,
|
| 1689 |
+
"loss": 0.0644,
|
| 1690 |
+
"step": 1200
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 2.9987546699875467,
|
| 1694 |
+
"grad_norm": 0.7095440030097961,
|
| 1695 |
+
"learning_rate": 2.2584419750504293e-10,
|
| 1696 |
+
"loss": 0.0753,
|
| 1697 |
+
"step": 1205
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 3.0,
|
| 1701 |
+
"step": 1206,
|
| 1702 |
+
"total_flos": 1.5419277279871631e+18,
|
| 1703 |
+
"train_loss": 0.36778768146438384,
|
| 1704 |
+
"train_runtime": 743.0643,
|
| 1705 |
+
"train_samples_per_second": 51.852,
|
| 1706 |
+
"train_steps_per_second": 1.623
|
| 1707 |
+
}
|
| 1708 |
+
],
|
| 1709 |
+
"logging_steps": 5,
|
| 1710 |
+
"max_steps": 1206,
|
| 1711 |
+
"num_input_tokens_seen": 0,
|
| 1712 |
+
"num_train_epochs": 3,
|
| 1713 |
+
"save_steps": 20000,
|
| 1714 |
+
"stateful_callbacks": {
|
| 1715 |
+
"TrainerControl": {
|
| 1716 |
+
"args": {
|
| 1717 |
+
"should_epoch_stop": false,
|
| 1718 |
+
"should_evaluate": false,
|
| 1719 |
+
"should_log": false,
|
| 1720 |
+
"should_save": false,
|
| 1721 |
+
"should_training_stop": false
|
| 1722 |
+
},
|
| 1723 |
+
"attributes": {}
|
| 1724 |
+
}
|
| 1725 |
+
},
|
| 1726 |
+
"total_flos": 1.5419277279871631e+18,
|
| 1727 |
+
"train_batch_size": 2,
|
| 1728 |
+
"trial_name": null,
|
| 1729 |
+
"trial_params": null
|
| 1730 |
+
}
|
138_128_e3_3e-5/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e49dd4d82a92b5d2764b301e241a56c5b0d9670ccf0c3807bca00aaaf826521c
|
| 3 |
+
size 8273
|
138_128_e3_3e-5/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|