Upload folder using huggingface_hub
Browse files- 1_128_e3_3e-5/adapter_config.json +39 -0
- 1_128_e3_3e-5/adapter_model.safetensors +3 -0
- 1_128_e3_3e-5/added_tokens.json +9 -0
- 1_128_e3_3e-5/all_results.json +9 -0
- 1_128_e3_3e-5/chat_template.jinja +62 -0
- 1_128_e3_3e-5/config.json +32 -0
- 1_128_e3_3e-5/merges.txt +0 -0
- 1_128_e3_3e-5/special_tokens_map.json +33 -0
- 1_128_e3_3e-5/tokenizer.json +0 -0
- 1_128_e3_3e-5/tokenizer_config.json +234 -0
- 1_128_e3_3e-5/train_results.json +9 -0
- 1_128_e3_3e-5/trainer_state.json +2003 -0
- 1_128_e3_3e-5/training_args.bin +3 -0
- 1_128_e3_3e-5/vocab.json +0 -0
1_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 |
+
"up_proj",
|
| 29 |
+
"o_proj",
|
| 30 |
+
"q_proj",
|
| 31 |
+
"k_proj",
|
| 32 |
+
"down_proj",
|
| 33 |
+
"gate_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
+
"use_dora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
1_128_e3_3e-5/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c90e6d84ddb72a130ea4600019e8e502791a1fc3fe13972d49120d64224d307f
|
| 3 |
+
size 791751704
|
1_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 |
+
}
|
1_128_e3_3e-5/all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 2.0918875763098255e+18,
|
| 4 |
+
"train_loss": 0.5697678685996637,
|
| 5 |
+
"train_runtime": 1013.0729,
|
| 6 |
+
"train_samples": 14919,
|
| 7 |
+
"train_samples_per_second": 44.179,
|
| 8 |
+
"train_steps_per_second": 1.383
|
| 9 |
+
}
|
1_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 %}
|
1_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 |
+
}
|
1_128_e3_3e-5/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
1_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 |
+
}
|
1_128_e3_3e-5/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
1_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 |
+
}
|
1_128_e3_3e-5/train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 2.0918875763098255e+18,
|
| 4 |
+
"train_loss": 0.5697678685996637,
|
| 5 |
+
"train_runtime": 1013.0729,
|
| 6 |
+
"train_samples": 14919,
|
| 7 |
+
"train_samples_per_second": 44.179,
|
| 8 |
+
"train_steps_per_second": 1.383
|
| 9 |
+
}
|
1_128_e3_3e-5/trainer_state.json
ADDED
|
@@ -0,0 +1,2003 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 1401,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.010718113612004287,
|
| 14 |
+
"grad_norm": 3.0887272357940674,
|
| 15 |
+
"learning_rate": 1.6901408450704227e-06,
|
| 16 |
+
"loss": 1.5277,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.021436227224008574,
|
| 21 |
+
"grad_norm": 3.003511905670166,
|
| 22 |
+
"learning_rate": 3.8028169014084508e-06,
|
| 23 |
+
"loss": 1.5744,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.03215434083601286,
|
| 28 |
+
"grad_norm": 1.1555603742599487,
|
| 29 |
+
"learning_rate": 5.915492957746478e-06,
|
| 30 |
+
"loss": 1.4557,
|
| 31 |
+
"step": 15
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.04287245444801715,
|
| 35 |
+
"grad_norm": 0.6423429846763611,
|
| 36 |
+
"learning_rate": 8.028169014084507e-06,
|
| 37 |
+
"loss": 1.3571,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.05359056806002144,
|
| 42 |
+
"grad_norm": 0.5051082968711853,
|
| 43 |
+
"learning_rate": 1.0140845070422535e-05,
|
| 44 |
+
"loss": 1.3377,
|
| 45 |
+
"step": 25
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.06430868167202572,
|
| 49 |
+
"grad_norm": 0.4673773944377899,
|
| 50 |
+
"learning_rate": 1.2253521126760564e-05,
|
| 51 |
+
"loss": 1.3373,
|
| 52 |
+
"step": 30
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.07502679528403002,
|
| 56 |
+
"grad_norm": 0.5021124482154846,
|
| 57 |
+
"learning_rate": 1.436619718309859e-05,
|
| 58 |
+
"loss": 1.326,
|
| 59 |
+
"step": 35
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.0857449088960343,
|
| 63 |
+
"grad_norm": 0.4011324346065521,
|
| 64 |
+
"learning_rate": 1.6478873239436623e-05,
|
| 65 |
+
"loss": 1.3277,
|
| 66 |
+
"step": 40
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.09646302250803858,
|
| 70 |
+
"grad_norm": 0.3723503053188324,
|
| 71 |
+
"learning_rate": 1.8591549295774646e-05,
|
| 72 |
+
"loss": 1.3597,
|
| 73 |
+
"step": 45
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.10718113612004287,
|
| 77 |
+
"grad_norm": 0.3821893036365509,
|
| 78 |
+
"learning_rate": 2.0704225352112676e-05,
|
| 79 |
+
"loss": 1.248,
|
| 80 |
+
"step": 50
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.11789924973204716,
|
| 84 |
+
"grad_norm": 0.3873383104801178,
|
| 85 |
+
"learning_rate": 2.2816901408450703e-05,
|
| 86 |
+
"loss": 1.2794,
|
| 87 |
+
"step": 55
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.12861736334405144,
|
| 91 |
+
"grad_norm": 0.3538777232170105,
|
| 92 |
+
"learning_rate": 2.4929577464788733e-05,
|
| 93 |
+
"loss": 1.2397,
|
| 94 |
+
"step": 60
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.13933547695605572,
|
| 98 |
+
"grad_norm": 0.364370733499527,
|
| 99 |
+
"learning_rate": 2.7042253521126763e-05,
|
| 100 |
+
"loss": 1.2362,
|
| 101 |
+
"step": 65
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.15005359056806003,
|
| 105 |
+
"grad_norm": 0.3963067829608917,
|
| 106 |
+
"learning_rate": 2.915492957746479e-05,
|
| 107 |
+
"loss": 1.1983,
|
| 108 |
+
"step": 70
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.1607717041800643,
|
| 112 |
+
"grad_norm": 0.3728579580783844,
|
| 113 |
+
"learning_rate": 2.9999623384301385e-05,
|
| 114 |
+
"loss": 1.1624,
|
| 115 |
+
"step": 75
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.1714898177920686,
|
| 119 |
+
"grad_norm": 0.3975795805454254,
|
| 120 |
+
"learning_rate": 2.9997321912408203e-05,
|
| 121 |
+
"loss": 1.186,
|
| 122 |
+
"step": 80
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.18220793140407288,
|
| 126 |
+
"grad_norm": 0.3780006766319275,
|
| 127 |
+
"learning_rate": 2.999292852020009e-05,
|
| 128 |
+
"loss": 1.1793,
|
| 129 |
+
"step": 85
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.19292604501607716,
|
| 133 |
+
"grad_norm": 0.40317609906196594,
|
| 134 |
+
"learning_rate": 2.9986443820494872e-05,
|
| 135 |
+
"loss": 1.1755,
|
| 136 |
+
"step": 90
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.20364415862808147,
|
| 140 |
+
"grad_norm": 0.3940582573413849,
|
| 141 |
+
"learning_rate": 2.9977868717819053e-05,
|
| 142 |
+
"loss": 1.1347,
|
| 143 |
+
"step": 95
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.21436227224008575,
|
| 147 |
+
"grad_norm": 0.4203241765499115,
|
| 148 |
+
"learning_rate": 2.9967204408281618e-05,
|
| 149 |
+
"loss": 1.1216,
|
| 150 |
+
"step": 100
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.22508038585209003,
|
| 154 |
+
"grad_norm": 0.3849189579486847,
|
| 155 |
+
"learning_rate": 2.99544523794072e-05,
|
| 156 |
+
"loss": 1.1345,
|
| 157 |
+
"step": 105
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.2357984994640943,
|
| 161 |
+
"grad_norm": 0.5029954314231873,
|
| 162 |
+
"learning_rate": 2.993961440992859e-05,
|
| 163 |
+
"loss": 1.1428,
|
| 164 |
+
"step": 110
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.2465166130760986,
|
| 168 |
+
"grad_norm": 0.4647366404533386,
|
| 169 |
+
"learning_rate": 2.992269256953862e-05,
|
| 170 |
+
"loss": 1.0825,
|
| 171 |
+
"step": 115
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.2572347266881029,
|
| 175 |
+
"grad_norm": 0.5049901604652405,
|
| 176 |
+
"learning_rate": 2.9903689218601497e-05,
|
| 177 |
+
"loss": 1.0887,
|
| 178 |
+
"step": 120
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.2679528403001072,
|
| 182 |
+
"grad_norm": 0.4278225600719452,
|
| 183 |
+
"learning_rate": 2.9882607007823525e-05,
|
| 184 |
+
"loss": 1.023,
|
| 185 |
+
"step": 125
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.27867095391211144,
|
| 189 |
+
"grad_norm": 0.5523571372032166,
|
| 190 |
+
"learning_rate": 2.9859448877883407e-05,
|
| 191 |
+
"loss": 1.0886,
|
| 192 |
+
"step": 130
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.28938906752411575,
|
| 196 |
+
"grad_norm": 0.4693784713745117,
|
| 197 |
+
"learning_rate": 2.9834218059022027e-05,
|
| 198 |
+
"loss": 1.1008,
|
| 199 |
+
"step": 135
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.30010718113612006,
|
| 203 |
+
"grad_norm": 0.4722091555595398,
|
| 204 |
+
"learning_rate": 2.98069180705919e-05,
|
| 205 |
+
"loss": 1.0736,
|
| 206 |
+
"step": 140
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.3108252947481243,
|
| 210 |
+
"grad_norm": 0.5182387828826904,
|
| 211 |
+
"learning_rate": 2.9777552720566256e-05,
|
| 212 |
+
"loss": 1.0933,
|
| 213 |
+
"step": 145
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.3215434083601286,
|
| 217 |
+
"grad_norm": 0.5157468318939209,
|
| 218 |
+
"learning_rate": 2.9746126105007885e-05,
|
| 219 |
+
"loss": 1.0064,
|
| 220 |
+
"step": 150
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.3322615219721329,
|
| 224 |
+
"grad_norm": 0.6086942553520203,
|
| 225 |
+
"learning_rate": 2.9712642607497795e-05,
|
| 226 |
+
"loss": 1.013,
|
| 227 |
+
"step": 155
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.3429796355841372,
|
| 231 |
+
"grad_norm": 0.5298618674278259,
|
| 232 |
+
"learning_rate": 2.967710689852377e-05,
|
| 233 |
+
"loss": 1.0182,
|
| 234 |
+
"step": 160
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.3536977491961415,
|
| 238 |
+
"grad_norm": 0.5256823897361755,
|
| 239 |
+
"learning_rate": 2.9639523934828877e-05,
|
| 240 |
+
"loss": 0.9936,
|
| 241 |
+
"step": 165
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.36441586280814575,
|
| 245 |
+
"grad_norm": 0.5341989994049072,
|
| 246 |
+
"learning_rate": 2.9599898958720088e-05,
|
| 247 |
+
"loss": 0.9879,
|
| 248 |
+
"step": 170
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.37513397642015006,
|
| 252 |
+
"grad_norm": 0.5580112934112549,
|
| 253 |
+
"learning_rate": 2.9558237497337054e-05,
|
| 254 |
+
"loss": 0.9816,
|
| 255 |
+
"step": 175
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.3858520900321543,
|
| 259 |
+
"grad_norm": 0.5546361207962036,
|
| 260 |
+
"learning_rate": 2.951454536188112e-05,
|
| 261 |
+
"loss": 1.0271,
|
| 262 |
+
"step": 180
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.3965702036441586,
|
| 266 |
+
"grad_norm": 0.5890166759490967,
|
| 267 |
+
"learning_rate": 2.946882864680478e-05,
|
| 268 |
+
"loss": 1.0203,
|
| 269 |
+
"step": 185
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.40728831725616294,
|
| 273 |
+
"grad_norm": 0.5653389692306519,
|
| 274 |
+
"learning_rate": 2.9421093728961545e-05,
|
| 275 |
+
"loss": 0.9802,
|
| 276 |
+
"step": 190
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.4180064308681672,
|
| 280 |
+
"grad_norm": 0.6572825312614441,
|
| 281 |
+
"learning_rate": 2.9371347266716485e-05,
|
| 282 |
+
"loss": 0.9758,
|
| 283 |
+
"step": 195
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.4287245444801715,
|
| 287 |
+
"grad_norm": 0.5875082612037659,
|
| 288 |
+
"learning_rate": 2.9319596199017478e-05,
|
| 289 |
+
"loss": 0.9279,
|
| 290 |
+
"step": 200
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.43944265809217575,
|
| 294 |
+
"grad_norm": 0.680169939994812,
|
| 295 |
+
"learning_rate": 2.9265847744427305e-05,
|
| 296 |
+
"loss": 0.9596,
|
| 297 |
+
"step": 205
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.45016077170418006,
|
| 301 |
+
"grad_norm": 0.6569834351539612,
|
| 302 |
+
"learning_rate": 2.9210109400116773e-05,
|
| 303 |
+
"loss": 0.9432,
|
| 304 |
+
"step": 210
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.4608788853161844,
|
| 308 |
+
"grad_norm": 0.6418343782424927,
|
| 309 |
+
"learning_rate": 2.9152388940818966e-05,
|
| 310 |
+
"loss": 0.9818,
|
| 311 |
+
"step": 215
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.4715969989281886,
|
| 315 |
+
"grad_norm": 0.6328263878822327,
|
| 316 |
+
"learning_rate": 2.9092694417744764e-05,
|
| 317 |
+
"loss": 0.9972,
|
| 318 |
+
"step": 220
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.48231511254019294,
|
| 322 |
+
"grad_norm": 0.671103298664093,
|
| 323 |
+
"learning_rate": 2.903103415745982e-05,
|
| 324 |
+
"loss": 0.8934,
|
| 325 |
+
"step": 225
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.4930332261521972,
|
| 329 |
+
"grad_norm": 0.63865727186203,
|
| 330 |
+
"learning_rate": 2.8967416760723113e-05,
|
| 331 |
+
"loss": 0.8765,
|
| 332 |
+
"step": 230
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.5037513397642015,
|
| 336 |
+
"grad_norm": 0.655642569065094,
|
| 337 |
+
"learning_rate": 2.890185110128727e-05,
|
| 338 |
+
"loss": 0.8878,
|
| 339 |
+
"step": 235
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.5144694533762058,
|
| 343 |
+
"grad_norm": 0.7347690463066101,
|
| 344 |
+
"learning_rate": 2.883434632466077e-05,
|
| 345 |
+
"loss": 0.875,
|
| 346 |
+
"step": 240
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.5251875669882101,
|
| 350 |
+
"grad_norm": 0.695117712020874,
|
| 351 |
+
"learning_rate": 2.8764911846832326e-05,
|
| 352 |
+
"loss": 0.8948,
|
| 353 |
+
"step": 245
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.5359056806002144,
|
| 357 |
+
"grad_norm": 0.7315117120742798,
|
| 358 |
+
"learning_rate": 2.8693557352957418e-05,
|
| 359 |
+
"loss": 0.9388,
|
| 360 |
+
"step": 250
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.5466237942122186,
|
| 364 |
+
"grad_norm": 0.6662325263023376,
|
| 365 |
+
"learning_rate": 2.8620292796007404e-05,
|
| 366 |
+
"loss": 0.8706,
|
| 367 |
+
"step": 255
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.5573419078242229,
|
| 371 |
+
"grad_norm": 0.7294781804084778,
|
| 372 |
+
"learning_rate": 2.8545128395381175e-05,
|
| 373 |
+
"loss": 0.8584,
|
| 374 |
+
"step": 260
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.5680600214362272,
|
| 378 |
+
"grad_norm": 0.643936038017273,
|
| 379 |
+
"learning_rate": 2.8468074635479725e-05,
|
| 380 |
+
"loss": 0.8689,
|
| 381 |
+
"step": 265
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.5787781350482315,
|
| 385 |
+
"grad_norm": 0.7401193976402283,
|
| 386 |
+
"learning_rate": 2.8389142264243692e-05,
|
| 387 |
+
"loss": 0.9149,
|
| 388 |
+
"step": 270
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.5894962486602358,
|
| 392 |
+
"grad_norm": 0.7772344946861267,
|
| 393 |
+
"learning_rate": 2.830834229165418e-05,
|
| 394 |
+
"loss": 0.8159,
|
| 395 |
+
"step": 275
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.6002143622722401,
|
| 399 |
+
"grad_norm": 0.7441154718399048,
|
| 400 |
+
"learning_rate": 2.8225685988197018e-05,
|
| 401 |
+
"loss": 0.8516,
|
| 402 |
+
"step": 280
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.6109324758842444,
|
| 406 |
+
"grad_norm": 0.7265426516532898,
|
| 407 |
+
"learning_rate": 2.8141184883290684e-05,
|
| 408 |
+
"loss": 0.8496,
|
| 409 |
+
"step": 285
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.6216505894962486,
|
| 413 |
+
"grad_norm": 0.7406579256057739,
|
| 414 |
+
"learning_rate": 2.8054850763678107e-05,
|
| 415 |
+
"loss": 0.8442,
|
| 416 |
+
"step": 290
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.632368703108253,
|
| 420 |
+
"grad_norm": 0.7769656181335449,
|
| 421 |
+
"learning_rate": 2.796669567178258e-05,
|
| 422 |
+
"loss": 0.8525,
|
| 423 |
+
"step": 295
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.6430868167202572,
|
| 427 |
+
"grad_norm": 0.7615723013877869,
|
| 428 |
+
"learning_rate": 2.7876731904027994e-05,
|
| 429 |
+
"loss": 0.8502,
|
| 430 |
+
"step": 300
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.6538049303322615,
|
| 434 |
+
"grad_norm": 0.7499276995658875,
|
| 435 |
+
"learning_rate": 2.7784972009123682e-05,
|
| 436 |
+
"loss": 0.8079,
|
| 437 |
+
"step": 305
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.6645230439442658,
|
| 441 |
+
"grad_norm": 0.8167960047721863,
|
| 442 |
+
"learning_rate": 2.769142878631403e-05,
|
| 443 |
+
"loss": 0.7955,
|
| 444 |
+
"step": 310
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.6752411575562701,
|
| 448 |
+
"grad_norm": 0.7172262072563171,
|
| 449 |
+
"learning_rate": 2.759611528359316e-05,
|
| 450 |
+
"loss": 0.7914,
|
| 451 |
+
"step": 315
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.6859592711682744,
|
| 455 |
+
"grad_norm": 0.821480393409729,
|
| 456 |
+
"learning_rate": 2.7499044795884903e-05,
|
| 457 |
+
"loss": 0.7418,
|
| 458 |
+
"step": 320
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.6966773847802786,
|
| 462 |
+
"grad_norm": 0.7819322347640991,
|
| 463 |
+
"learning_rate": 2.740023086318836e-05,
|
| 464 |
+
"loss": 0.8093,
|
| 465 |
+
"step": 325
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.707395498392283,
|
| 469 |
+
"grad_norm": 0.7632163166999817,
|
| 470 |
+
"learning_rate": 2.729968726868926e-05,
|
| 471 |
+
"loss": 0.8056,
|
| 472 |
+
"step": 330
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.7181136120042872,
|
| 476 |
+
"grad_norm": 0.8228573799133301,
|
| 477 |
+
"learning_rate": 2.719742803683737e-05,
|
| 478 |
+
"loss": 0.7894,
|
| 479 |
+
"step": 335
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.7288317256162915,
|
| 483 |
+
"grad_norm": 0.8302276730537415,
|
| 484 |
+
"learning_rate": 2.7093467431390292e-05,
|
| 485 |
+
"loss": 0.7707,
|
| 486 |
+
"step": 340
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.7395498392282959,
|
| 490 |
+
"grad_norm": 0.8125790953636169,
|
| 491 |
+
"learning_rate": 2.698781995342387e-05,
|
| 492 |
+
"loss": 0.7816,
|
| 493 |
+
"step": 345
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.7502679528403001,
|
| 497 |
+
"grad_norm": 0.747488796710968,
|
| 498 |
+
"learning_rate": 2.6880500339309487e-05,
|
| 499 |
+
"loss": 0.7731,
|
| 500 |
+
"step": 350
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.7609860664523044,
|
| 504 |
+
"grad_norm": 0.7809923887252808,
|
| 505 |
+
"learning_rate": 2.6771523558658536e-05,
|
| 506 |
+
"loss": 0.779,
|
| 507 |
+
"step": 355
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.7717041800643086,
|
| 511 |
+
"grad_norm": 0.8691802620887756,
|
| 512 |
+
"learning_rate": 2.6660904812234362e-05,
|
| 513 |
+
"loss": 0.735,
|
| 514 |
+
"step": 360
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.782422293676313,
|
| 518 |
+
"grad_norm": 0.893549919128418,
|
| 519 |
+
"learning_rate": 2.6548659529831983e-05,
|
| 520 |
+
"loss": 0.8121,
|
| 521 |
+
"step": 365
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.7931404072883173,
|
| 525 |
+
"grad_norm": 0.9593718647956848,
|
| 526 |
+
"learning_rate": 2.6434803368125823e-05,
|
| 527 |
+
"loss": 0.7941,
|
| 528 |
+
"step": 370
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.8038585209003215,
|
| 532 |
+
"grad_norm": 0.8554571270942688,
|
| 533 |
+
"learning_rate": 2.631935220848585e-05,
|
| 534 |
+
"loss": 0.7689,
|
| 535 |
+
"step": 375
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.8145766345123259,
|
| 539 |
+
"grad_norm": 0.9226988554000854,
|
| 540 |
+
"learning_rate": 2.620232215476231e-05,
|
| 541 |
+
"loss": 0.7713,
|
| 542 |
+
"step": 380
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.8252947481243301,
|
| 546 |
+
"grad_norm": 0.8403868079185486,
|
| 547 |
+
"learning_rate": 2.6083729531039478e-05,
|
| 548 |
+
"loss": 0.7161,
|
| 549 |
+
"step": 385
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.8360128617363344,
|
| 553 |
+
"grad_norm": 0.8821732401847839,
|
| 554 |
+
"learning_rate": 2.5963590879358675e-05,
|
| 555 |
+
"loss": 0.7215,
|
| 556 |
+
"step": 390
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.8467309753483387,
|
| 560 |
+
"grad_norm": 0.8705371618270874,
|
| 561 |
+
"learning_rate": 2.5841922957410875e-05,
|
| 562 |
+
"loss": 0.7329,
|
| 563 |
+
"step": 395
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.857449088960343,
|
| 567 |
+
"grad_norm": 0.873972475528717,
|
| 568 |
+
"learning_rate": 2.5718742736199245e-05,
|
| 569 |
+
"loss": 0.744,
|
| 570 |
+
"step": 400
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.8681672025723473,
|
| 574 |
+
"grad_norm": 0.8475459218025208,
|
| 575 |
+
"learning_rate": 2.5594067397671902e-05,
|
| 576 |
+
"loss": 0.7254,
|
| 577 |
+
"step": 405
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.8788853161843515,
|
| 581 |
+
"grad_norm": 0.9166616797447205,
|
| 582 |
+
"learning_rate": 2.5467914332325312e-05,
|
| 583 |
+
"loss": 0.6777,
|
| 584 |
+
"step": 410
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.8896034297963559,
|
| 588 |
+
"grad_norm": 0.9241714477539062,
|
| 589 |
+
"learning_rate": 2.534030113677849e-05,
|
| 590 |
+
"loss": 0.7371,
|
| 591 |
+
"step": 415
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.9003215434083601,
|
| 595 |
+
"grad_norm": 0.9209508895874023,
|
| 596 |
+
"learning_rate": 2.5211245611318572e-05,
|
| 597 |
+
"loss": 0.7243,
|
| 598 |
+
"step": 420
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.9110396570203644,
|
| 602 |
+
"grad_norm": 0.9531940817832947,
|
| 603 |
+
"learning_rate": 2.5080765757417888e-05,
|
| 604 |
+
"loss": 0.693,
|
| 605 |
+
"step": 425
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.9217577706323687,
|
| 609 |
+
"grad_norm": 0.9694628119468689,
|
| 610 |
+
"learning_rate": 2.4948879775223015e-05,
|
| 611 |
+
"loss": 0.7073,
|
| 612 |
+
"step": 430
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.932475884244373,
|
| 616 |
+
"grad_norm": 1.0857443809509277,
|
| 617 |
+
"learning_rate": 2.4815606061016113e-05,
|
| 618 |
+
"loss": 0.684,
|
| 619 |
+
"step": 435
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.9431939978563773,
|
| 623 |
+
"grad_norm": 0.9990167021751404,
|
| 624 |
+
"learning_rate": 2.4680963204648868e-05,
|
| 625 |
+
"loss": 0.6846,
|
| 626 |
+
"step": 440
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.9539121114683816,
|
| 630 |
+
"grad_norm": 0.9203422665596008,
|
| 631 |
+
"learning_rate": 2.454496998694949e-05,
|
| 632 |
+
"loss": 0.6949,
|
| 633 |
+
"step": 445
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.9646302250803859,
|
| 637 |
+
"grad_norm": 0.9075927138328552,
|
| 638 |
+
"learning_rate": 2.4407645377103056e-05,
|
| 639 |
+
"loss": 0.6958,
|
| 640 |
+
"step": 450
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.9753483386923901,
|
| 644 |
+
"grad_norm": 0.9560758471488953,
|
| 645 |
+
"learning_rate": 2.4269008530005523e-05,
|
| 646 |
+
"loss": 0.6689,
|
| 647 |
+
"step": 455
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.9860664523043944,
|
| 651 |
+
"grad_norm": 0.9292932152748108,
|
| 652 |
+
"learning_rate": 2.4129078783591937e-05,
|
| 653 |
+
"loss": 0.6569,
|
| 654 |
+
"step": 460
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.9967845659163987,
|
| 658 |
+
"grad_norm": 0.9375683665275574,
|
| 659 |
+
"learning_rate": 2.3987875656139015e-05,
|
| 660 |
+
"loss": 0.6234,
|
| 661 |
+
"step": 465
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.0064308681672025,
|
| 665 |
+
"grad_norm": 0.9741694927215576,
|
| 666 |
+
"learning_rate": 2.3845418843542636e-05,
|
| 667 |
+
"loss": 0.5924,
|
| 668 |
+
"step": 470
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.0171489817792068,
|
| 672 |
+
"grad_norm": 0.8870618939399719,
|
| 673 |
+
"learning_rate": 2.3701728216570526e-05,
|
| 674 |
+
"loss": 0.574,
|
| 675 |
+
"step": 475
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.0278670953912112,
|
| 679 |
+
"grad_norm": 0.926276445388794,
|
| 680 |
+
"learning_rate": 2.3556823818090574e-05,
|
| 681 |
+
"loss": 0.6145,
|
| 682 |
+
"step": 480
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.0385852090032155,
|
| 686 |
+
"grad_norm": 1.0420550107955933,
|
| 687 |
+
"learning_rate": 2.3410725860275092e-05,
|
| 688 |
+
"loss": 0.5587,
|
| 689 |
+
"step": 485
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.0493033226152197,
|
| 693 |
+
"grad_norm": 0.9387816190719604,
|
| 694 |
+
"learning_rate": 2.3263454721781537e-05,
|
| 695 |
+
"loss": 0.5542,
|
| 696 |
+
"step": 490
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.060021436227224,
|
| 700 |
+
"grad_norm": 0.9477695822715759,
|
| 701 |
+
"learning_rate": 2.3115030944909946e-05,
|
| 702 |
+
"loss": 0.5623,
|
| 703 |
+
"step": 495
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.0707395498392283,
|
| 707 |
+
"grad_norm": 1.0408620834350586,
|
| 708 |
+
"learning_rate": 2.296547523273756e-05,
|
| 709 |
+
"loss": 0.5846,
|
| 710 |
+
"step": 500
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.0814576634512325,
|
| 714 |
+
"grad_norm": 0.8958512544631958,
|
| 715 |
+
"learning_rate": 2.2814808446231047e-05,
|
| 716 |
+
"loss": 0.5283,
|
| 717 |
+
"step": 505
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.092175777063237,
|
| 721 |
+
"grad_norm": 0.9695740938186646,
|
| 722 |
+
"learning_rate": 2.266305160133668e-05,
|
| 723 |
+
"loss": 0.5534,
|
| 724 |
+
"step": 510
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.1028938906752412,
|
| 728 |
+
"grad_norm": 0.98930823802948,
|
| 729 |
+
"learning_rate": 2.2510225866048883e-05,
|
| 730 |
+
"loss": 0.5456,
|
| 731 |
+
"step": 515
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.1136120042872455,
|
| 735 |
+
"grad_norm": 0.9378038644790649,
|
| 736 |
+
"learning_rate": 2.2356352557457624e-05,
|
| 737 |
+
"loss": 0.5921,
|
| 738 |
+
"step": 520
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.1243301178992497,
|
| 742 |
+
"grad_norm": 0.9949179291725159,
|
| 743 |
+
"learning_rate": 2.220145313877493e-05,
|
| 744 |
+
"loss": 0.5601,
|
| 745 |
+
"step": 525
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.135048231511254,
|
| 749 |
+
"grad_norm": 0.9769328832626343,
|
| 750 |
+
"learning_rate": 2.2045549216341093e-05,
|
| 751 |
+
"loss": 0.5052,
|
| 752 |
+
"step": 530
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.1457663451232583,
|
| 756 |
+
"grad_norm": 0.9389580488204956,
|
| 757 |
+
"learning_rate": 2.1888662536610878e-05,
|
| 758 |
+
"loss": 0.5548,
|
| 759 |
+
"step": 535
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.1564844587352625,
|
| 763 |
+
"grad_norm": 0.9294964075088501,
|
| 764 |
+
"learning_rate": 2.1730814983120185e-05,
|
| 765 |
+
"loss": 0.5304,
|
| 766 |
+
"step": 540
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.167202572347267,
|
| 770 |
+
"grad_norm": 1.0978158712387085,
|
| 771 |
+
"learning_rate": 2.1572028573433597e-05,
|
| 772 |
+
"loss": 0.5773,
|
| 773 |
+
"step": 545
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.1779206859592712,
|
| 777 |
+
"grad_norm": 1.0091325044631958,
|
| 778 |
+
"learning_rate": 2.1412325456073242e-05,
|
| 779 |
+
"loss": 0.5252,
|
| 780 |
+
"step": 550
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.1886387995712755,
|
| 784 |
+
"grad_norm": 1.0558208227157593,
|
| 785 |
+
"learning_rate": 2.1251727907429357e-05,
|
| 786 |
+
"loss": 0.5077,
|
| 787 |
+
"step": 555
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.1993569131832797,
|
| 791 |
+
"grad_norm": 1.1253631114959717,
|
| 792 |
+
"learning_rate": 2.1090258328653068e-05,
|
| 793 |
+
"loss": 0.5602,
|
| 794 |
+
"step": 560
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.210075026795284,
|
| 798 |
+
"grad_norm": 0.9343472123146057,
|
| 799 |
+
"learning_rate": 2.092793924253171e-05,
|
| 800 |
+
"loss": 0.532,
|
| 801 |
+
"step": 565
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.2207931404072883,
|
| 805 |
+
"grad_norm": 1.0394799709320068,
|
| 806 |
+
"learning_rate": 2.0764793290347223e-05,
|
| 807 |
+
"loss": 0.5257,
|
| 808 |
+
"step": 570
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.2315112540192925,
|
| 812 |
+
"grad_norm": 0.9338717460632324,
|
| 813 |
+
"learning_rate": 2.0600843228718007e-05,
|
| 814 |
+
"loss": 0.5452,
|
| 815 |
+
"step": 575
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.242229367631297,
|
| 819 |
+
"grad_norm": 0.9719412326812744,
|
| 820 |
+
"learning_rate": 2.0436111926424664e-05,
|
| 821 |
+
"loss": 0.5261,
|
| 822 |
+
"step": 580
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.2529474812433012,
|
| 826 |
+
"grad_norm": 1.0428558588027954,
|
| 827 |
+
"learning_rate": 2.0270622361220143e-05,
|
| 828 |
+
"loss": 0.5194,
|
| 829 |
+
"step": 585
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.2636655948553055,
|
| 833 |
+
"grad_norm": 0.9435470700263977,
|
| 834 |
+
"learning_rate": 2.0104397616624646e-05,
|
| 835 |
+
"loss": 0.488,
|
| 836 |
+
"step": 590
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.2743837084673098,
|
| 840 |
+
"grad_norm": 1.222658395767212,
|
| 841 |
+
"learning_rate": 1.9937460878705804e-05,
|
| 842 |
+
"loss": 0.4917,
|
| 843 |
+
"step": 595
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.285101822079314,
|
| 847 |
+
"grad_norm": 0.9916781187057495,
|
| 848 |
+
"learning_rate": 1.9769835432844523e-05,
|
| 849 |
+
"loss": 0.569,
|
| 850 |
+
"step": 600
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.2958199356913183,
|
| 854 |
+
"grad_norm": 1.005410075187683,
|
| 855 |
+
"learning_rate": 1.9601544660487004e-05,
|
| 856 |
+
"loss": 0.529,
|
| 857 |
+
"step": 605
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.3065380493033225,
|
| 861 |
+
"grad_norm": 0.9904552102088928,
|
| 862 |
+
"learning_rate": 1.9432612035883365e-05,
|
| 863 |
+
"loss": 0.5502,
|
| 864 |
+
"step": 610
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.317256162915327,
|
| 868 |
+
"grad_norm": 0.9880082607269287,
|
| 869 |
+
"learning_rate": 1.9263061122813267e-05,
|
| 870 |
+
"loss": 0.5261,
|
| 871 |
+
"step": 615
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.3279742765273312,
|
| 875 |
+
"grad_norm": 0.973067045211792,
|
| 876 |
+
"learning_rate": 1.9092915571299145e-05,
|
| 877 |
+
"loss": 0.5278,
|
| 878 |
+
"step": 620
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.3386923901393355,
|
| 882 |
+
"grad_norm": 1.0253452062606812,
|
| 883 |
+
"learning_rate": 1.8922199114307297e-05,
|
| 884 |
+
"loss": 0.4605,
|
| 885 |
+
"step": 625
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.3494105037513398,
|
| 889 |
+
"grad_norm": 1.1278691291809082,
|
| 890 |
+
"learning_rate": 1.875093556443751e-05,
|
| 891 |
+
"loss": 0.5462,
|
| 892 |
+
"step": 630
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 1.360128617363344,
|
| 896 |
+
"grad_norm": 1.059043288230896,
|
| 897 |
+
"learning_rate": 1.8579148810601506e-05,
|
| 898 |
+
"loss": 0.4737,
|
| 899 |
+
"step": 635
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 1.3708467309753483,
|
| 903 |
+
"grad_norm": 1.0425230264663696,
|
| 904 |
+
"learning_rate": 1.840686281469076e-05,
|
| 905 |
+
"loss": 0.457,
|
| 906 |
+
"step": 640
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.3815648445873525,
|
| 910 |
+
"grad_norm": 1.047011375427246,
|
| 911 |
+
"learning_rate": 1.8234101608234164e-05,
|
| 912 |
+
"loss": 0.5136,
|
| 913 |
+
"step": 645
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.392282958199357,
|
| 917 |
+
"grad_norm": 1.019850730895996,
|
| 918 |
+
"learning_rate": 1.8060889289045953e-05,
|
| 919 |
+
"loss": 0.4722,
|
| 920 |
+
"step": 650
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.4030010718113612,
|
| 924 |
+
"grad_norm": 0.8991992473602295,
|
| 925 |
+
"learning_rate": 1.788725001786438e-05,
|
| 926 |
+
"loss": 0.5307,
|
| 927 |
+
"step": 655
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.4137191854233655,
|
| 931 |
+
"grad_norm": 1.1788007020950317,
|
| 932 |
+
"learning_rate": 1.771320801498165e-05,
|
| 933 |
+
"loss": 0.4754,
|
| 934 |
+
"step": 660
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.4244372990353698,
|
| 938 |
+
"grad_norm": 1.0433146953582764,
|
| 939 |
+
"learning_rate": 1.7538787556865487e-05,
|
| 940 |
+
"loss": 0.4966,
|
| 941 |
+
"step": 665
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.435155412647374,
|
| 945 |
+
"grad_norm": 1.0864899158477783,
|
| 946 |
+
"learning_rate": 1.736401297277293e-05,
|
| 947 |
+
"loss": 0.436,
|
| 948 |
+
"step": 670
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 1.4458735262593785,
|
| 952 |
+
"grad_norm": 1.0527467727661133,
|
| 953 |
+
"learning_rate": 1.718890864135672e-05,
|
| 954 |
+
"loss": 0.4955,
|
| 955 |
+
"step": 675
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.4565916398713825,
|
| 959 |
+
"grad_norm": 0.9378105401992798,
|
| 960 |
+
"learning_rate": 1.7013498987264832e-05,
|
| 961 |
+
"loss": 0.4454,
|
| 962 |
+
"step": 680
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.467309753483387,
|
| 966 |
+
"grad_norm": 1.0318783521652222,
|
| 967 |
+
"learning_rate": 1.683780847773354e-05,
|
| 968 |
+
"loss": 0.4757,
|
| 969 |
+
"step": 685
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.4780278670953912,
|
| 973 |
+
"grad_norm": 1.0822546482086182,
|
| 974 |
+
"learning_rate": 1.6661861619174603e-05,
|
| 975 |
+
"loss": 0.4646,
|
| 976 |
+
"step": 690
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.4887459807073955,
|
| 980 |
+
"grad_norm": 1.0907413959503174,
|
| 981 |
+
"learning_rate": 1.6485682953756945e-05,
|
| 982 |
+
"loss": 0.4508,
|
| 983 |
+
"step": 695
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.4994640943193998,
|
| 987 |
+
"grad_norm": 1.0934693813323975,
|
| 988 |
+
"learning_rate": 1.6309297055983353e-05,
|
| 989 |
+
"loss": 0.4696,
|
| 990 |
+
"step": 700
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.510182207931404,
|
| 994 |
+
"grad_norm": 1.2902297973632812,
|
| 995 |
+
"learning_rate": 1.6132728529262695e-05,
|
| 996 |
+
"loss": 0.453,
|
| 997 |
+
"step": 705
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 1.5209003215434085,
|
| 1001 |
+
"grad_norm": 1.0547277927398682,
|
| 1002 |
+
"learning_rate": 1.5956002002478062e-05,
|
| 1003 |
+
"loss": 0.4546,
|
| 1004 |
+
"step": 710
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.5316184351554125,
|
| 1008 |
+
"grad_norm": 1.058367133140564,
|
| 1009 |
+
"learning_rate": 1.5779142126551372e-05,
|
| 1010 |
+
"loss": 0.5181,
|
| 1011 |
+
"step": 715
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 1.542336548767417,
|
| 1015 |
+
"grad_norm": 0.9945155382156372,
|
| 1016 |
+
"learning_rate": 1.5602173571004934e-05,
|
| 1017 |
+
"loss": 0.4595,
|
| 1018 |
+
"step": 720
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.5530546623794212,
|
| 1022 |
+
"grad_norm": 1.053295373916626,
|
| 1023 |
+
"learning_rate": 1.542512102052035e-05,
|
| 1024 |
+
"loss": 0.4461,
|
| 1025 |
+
"step": 725
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 1.5637727759914255,
|
| 1029 |
+
"grad_norm": 1.1239274740219116,
|
| 1030 |
+
"learning_rate": 1.524800917149538e-05,
|
| 1031 |
+
"loss": 0.483,
|
| 1032 |
+
"step": 730
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 1.5744908896034298,
|
| 1036 |
+
"grad_norm": 1.2165591716766357,
|
| 1037 |
+
"learning_rate": 1.5070862728599102e-05,
|
| 1038 |
+
"loss": 0.4554,
|
| 1039 |
+
"step": 735
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 1.585209003215434,
|
| 1043 |
+
"grad_norm": 1.1676536798477173,
|
| 1044 |
+
"learning_rate": 1.4893706401325978e-05,
|
| 1045 |
+
"loss": 0.449,
|
| 1046 |
+
"step": 740
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.5959271168274385,
|
| 1050 |
+
"grad_norm": 1.1839724779129028,
|
| 1051 |
+
"learning_rate": 1.4716564900549194e-05,
|
| 1052 |
+
"loss": 0.457,
|
| 1053 |
+
"step": 745
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 1.6066452304394425,
|
| 1057 |
+
"grad_norm": 0.9654883146286011,
|
| 1058 |
+
"learning_rate": 1.4539462935073841e-05,
|
| 1059 |
+
"loss": 0.4448,
|
| 1060 |
+
"step": 750
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 1.617363344051447,
|
| 1064 |
+
"grad_norm": 1.1264455318450928,
|
| 1065 |
+
"learning_rate": 1.4362425208190388e-05,
|
| 1066 |
+
"loss": 0.425,
|
| 1067 |
+
"step": 755
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 1.6280814576634512,
|
| 1071 |
+
"grad_norm": 1.0239930152893066,
|
| 1072 |
+
"learning_rate": 1.4185476414228896e-05,
|
| 1073 |
+
"loss": 0.4439,
|
| 1074 |
+
"step": 760
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.6387995712754555,
|
| 1078 |
+
"grad_norm": 1.0360668897628784,
|
| 1079 |
+
"learning_rate": 1.400864123511451e-05,
|
| 1080 |
+
"loss": 0.4323,
|
| 1081 |
+
"step": 765
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 1.6495176848874598,
|
| 1085 |
+
"grad_norm": 1.0796645879745483,
|
| 1086 |
+
"learning_rate": 1.3831944336924664e-05,
|
| 1087 |
+
"loss": 0.4695,
|
| 1088 |
+
"step": 770
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 1.660235798499464,
|
| 1092 |
+
"grad_norm": 1.2254120111465454,
|
| 1093 |
+
"learning_rate": 1.36554103664485e-05,
|
| 1094 |
+
"loss": 0.4084,
|
| 1095 |
+
"step": 775
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 1.6709539121114685,
|
| 1099 |
+
"grad_norm": 1.1006470918655396,
|
| 1100 |
+
"learning_rate": 1.3479063947748985e-05,
|
| 1101 |
+
"loss": 0.4321,
|
| 1102 |
+
"step": 780
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 1.6816720257234725,
|
| 1106 |
+
"grad_norm": 1.0820367336273193,
|
| 1107 |
+
"learning_rate": 1.33029296787282e-05,
|
| 1108 |
+
"loss": 0.4448,
|
| 1109 |
+
"step": 785
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 1.692390139335477,
|
| 1113 |
+
"grad_norm": 0.962052583694458,
|
| 1114 |
+
"learning_rate": 1.3127032127696238e-05,
|
| 1115 |
+
"loss": 0.3765,
|
| 1116 |
+
"step": 790
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 1.7031082529474812,
|
| 1120 |
+
"grad_norm": 1.1583343744277954,
|
| 1121 |
+
"learning_rate": 1.2951395829944309e-05,
|
| 1122 |
+
"loss": 0.4514,
|
| 1123 |
+
"step": 795
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 1.7138263665594855,
|
| 1127 |
+
"grad_norm": 1.0421403646469116,
|
| 1128 |
+
"learning_rate": 1.277604528432237e-05,
|
| 1129 |
+
"loss": 0.4345,
|
| 1130 |
+
"step": 800
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 1.72454448017149,
|
| 1134 |
+
"grad_norm": 1.0921709537506104,
|
| 1135 |
+
"learning_rate": 1.2601004949821887e-05,
|
| 1136 |
+
"loss": 0.3865,
|
| 1137 |
+
"step": 805
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 1.735262593783494,
|
| 1141 |
+
"grad_norm": 1.1072250604629517,
|
| 1142 |
+
"learning_rate": 1.2426299242164125e-05,
|
| 1143 |
+
"loss": 0.4062,
|
| 1144 |
+
"step": 810
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 1.7459807073954985,
|
| 1148 |
+
"grad_norm": 0.9601326584815979,
|
| 1149 |
+
"learning_rate": 1.2251952530394523e-05,
|
| 1150 |
+
"loss": 0.3729,
|
| 1151 |
+
"step": 815
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.7566988210075025,
|
| 1155 |
+
"grad_norm": 1.044776439666748,
|
| 1156 |
+
"learning_rate": 1.2077989133483506e-05,
|
| 1157 |
+
"loss": 0.3919,
|
| 1158 |
+
"step": 820
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 1.767416934619507,
|
| 1162 |
+
"grad_norm": 1.214371919631958,
|
| 1163 |
+
"learning_rate": 1.1904433316934363e-05,
|
| 1164 |
+
"loss": 0.4077,
|
| 1165 |
+
"step": 825
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 1.7781350482315113,
|
| 1169 |
+
"grad_norm": 1.1787620782852173,
|
| 1170 |
+
"learning_rate": 1.1731309289398509e-05,
|
| 1171 |
+
"loss": 0.4086,
|
| 1172 |
+
"step": 830
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 1.7888531618435155,
|
| 1176 |
+
"grad_norm": 1.2586784362792969,
|
| 1177 |
+
"learning_rate": 1.1558641199298728e-05,
|
| 1178 |
+
"loss": 0.3981,
|
| 1179 |
+
"step": 835
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 1.79957127545552,
|
| 1183 |
+
"grad_norm": 1.162297248840332,
|
| 1184 |
+
"learning_rate": 1.1386453131460803e-05,
|
| 1185 |
+
"loss": 0.3964,
|
| 1186 |
+
"step": 840
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 1.810289389067524,
|
| 1190 |
+
"grad_norm": 1.202858567237854,
|
| 1191 |
+
"learning_rate": 1.1214769103754011e-05,
|
| 1192 |
+
"loss": 0.4095,
|
| 1193 |
+
"step": 845
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 1.8210075026795285,
|
| 1197 |
+
"grad_norm": 1.3784211874008179,
|
| 1198 |
+
"learning_rate": 1.104361306374094e-05,
|
| 1199 |
+
"loss": 0.405,
|
| 1200 |
+
"step": 850
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 1.8317256162915327,
|
| 1204 |
+
"grad_norm": 1.1413683891296387,
|
| 1205 |
+
"learning_rate": 1.0873008885337162e-05,
|
| 1206 |
+
"loss": 0.3835,
|
| 1207 |
+
"step": 855
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 1.842443729903537,
|
| 1211 |
+
"grad_norm": 1.101449728012085,
|
| 1212 |
+
"learning_rate": 1.0702980365481143e-05,
|
| 1213 |
+
"loss": 0.39,
|
| 1214 |
+
"step": 860
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 1.8531618435155413,
|
| 1218 |
+
"grad_norm": 1.161899447441101,
|
| 1219 |
+
"learning_rate": 1.0533551220814889e-05,
|
| 1220 |
+
"loss": 0.4405,
|
| 1221 |
+
"step": 865
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 1.8638799571275455,
|
| 1225 |
+
"grad_norm": 1.1374167203903198,
|
| 1226 |
+
"learning_rate": 1.036474508437579e-05,
|
| 1227 |
+
"loss": 0.3693,
|
| 1228 |
+
"step": 870
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 1.87459807073955,
|
| 1232 |
+
"grad_norm": 1.0448237657546997,
|
| 1233 |
+
"learning_rate": 1.0196585502300169e-05,
|
| 1234 |
+
"loss": 0.4154,
|
| 1235 |
+
"step": 875
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 1.885316184351554,
|
| 1239 |
+
"grad_norm": 1.2724683284759521,
|
| 1240 |
+
"learning_rate": 1.0029095930538886e-05,
|
| 1241 |
+
"loss": 0.3727,
|
| 1242 |
+
"step": 880
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 1.8960342979635585,
|
| 1246 |
+
"grad_norm": 1.1472162008285522,
|
| 1247 |
+
"learning_rate": 9.862299731585581e-06,
|
| 1248 |
+
"loss": 0.4096,
|
| 1249 |
+
"step": 885
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 1.9067524115755627,
|
| 1253 |
+
"grad_norm": 1.1890227794647217,
|
| 1254 |
+
"learning_rate": 9.696220171217907e-06,
|
| 1255 |
+
"loss": 0.4087,
|
| 1256 |
+
"step": 890
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 1.917470525187567,
|
| 1260 |
+
"grad_norm": 1.1401933431625366,
|
| 1261 |
+
"learning_rate": 9.530880415252282e-06,
|
| 1262 |
+
"loss": 0.3603,
|
| 1263 |
+
"step": 895
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 1.9281886387995713,
|
| 1267 |
+
"grad_norm": 1.0883911848068237,
|
| 1268 |
+
"learning_rate": 9.366303526312582e-06,
|
| 1269 |
+
"loss": 0.3789,
|
| 1270 |
+
"step": 900
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 1.9389067524115755,
|
| 1274 |
+
"grad_norm": 1.1235276460647583,
|
| 1275 |
+
"learning_rate": 9.20251246061322e-06,
|
| 1276 |
+
"loss": 0.3796,
|
| 1277 |
+
"step": 905
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 1.94962486602358,
|
| 1281 |
+
"grad_norm": 1.133574366569519,
|
| 1282 |
+
"learning_rate": 9.039530064757047e-06,
|
| 1283 |
+
"loss": 0.3886,
|
| 1284 |
+
"step": 910
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 1.960342979635584,
|
| 1288 |
+
"grad_norm": 1.122624158859253,
|
| 1289 |
+
"learning_rate": 8.877379072548599e-06,
|
| 1290 |
+
"loss": 0.4236,
|
| 1291 |
+
"step": 915
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 1.9710610932475885,
|
| 1295 |
+
"grad_norm": 1.1602848768234253,
|
| 1296 |
+
"learning_rate": 8.71608210182303e-06,
|
| 1297 |
+
"loss": 0.3688,
|
| 1298 |
+
"step": 920
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 1.9817792068595927,
|
| 1302 |
+
"grad_norm": 1.1969410181045532,
|
| 1303 |
+
"learning_rate": 8.555661651291226e-06,
|
| 1304 |
+
"loss": 0.3748,
|
| 1305 |
+
"step": 925
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 1.992497320471597,
|
| 1309 |
+
"grad_norm": 1.0584759712219238,
|
| 1310 |
+
"learning_rate": 8.39614009740155e-06,
|
| 1311 |
+
"loss": 0.4203,
|
| 1312 |
+
"step": 930
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 2.002143622722401,
|
| 1316 |
+
"grad_norm": 1.0526671409606934,
|
| 1317 |
+
"learning_rate": 8.237539691218637e-06,
|
| 1318 |
+
"loss": 0.3389,
|
| 1319 |
+
"step": 935
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 2.012861736334405,
|
| 1323 |
+
"grad_norm": 1.169420599937439,
|
| 1324 |
+
"learning_rate": 8.079882555319685e-06,
|
| 1325 |
+
"loss": 0.2913,
|
| 1326 |
+
"step": 940
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 2.0235798499464095,
|
| 1330 |
+
"grad_norm": 1.2719544172286987,
|
| 1331 |
+
"learning_rate": 7.923190680708636e-06,
|
| 1332 |
+
"loss": 0.3158,
|
| 1333 |
+
"step": 945
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 2.0342979635584135,
|
| 1337 |
+
"grad_norm": 0.9886611700057983,
|
| 1338 |
+
"learning_rate": 7.767485923748754e-06,
|
| 1339 |
+
"loss": 0.3127,
|
| 1340 |
+
"step": 950
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 2.045016077170418,
|
| 1344 |
+
"grad_norm": 1.1227387189865112,
|
| 1345 |
+
"learning_rate": 7.612790003113949e-06,
|
| 1346 |
+
"loss": 0.2765,
|
| 1347 |
+
"step": 955
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 2.0557341907824225,
|
| 1351 |
+
"grad_norm": 1.1321218013763428,
|
| 1352 |
+
"learning_rate": 7.459124496759343e-06,
|
| 1353 |
+
"loss": 0.3418,
|
| 1354 |
+
"step": 960
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 2.0664523043944265,
|
| 1358 |
+
"grad_norm": 1.1055247783660889,
|
| 1359 |
+
"learning_rate": 7.30651083891141e-06,
|
| 1360 |
+
"loss": 0.3159,
|
| 1361 |
+
"step": 965
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 2.077170418006431,
|
| 1365 |
+
"grad_norm": 1.1450848579406738,
|
| 1366 |
+
"learning_rate": 7.154970317078214e-06,
|
| 1367 |
+
"loss": 0.3193,
|
| 1368 |
+
"step": 970
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 2.087888531618435,
|
| 1372 |
+
"grad_norm": 1.1955426931381226,
|
| 1373 |
+
"learning_rate": 7.0045240690800975e-06,
|
| 1374 |
+
"loss": 0.3228,
|
| 1375 |
+
"step": 975
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 2.0986066452304395,
|
| 1379 |
+
"grad_norm": 1.1087688207626343,
|
| 1380 |
+
"learning_rate": 6.85519308010123e-06,
|
| 1381 |
+
"loss": 0.3161,
|
| 1382 |
+
"step": 980
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 2.1093247588424435,
|
| 1386 |
+
"grad_norm": 1.0273271799087524,
|
| 1387 |
+
"learning_rate": 6.7069981797625005e-06,
|
| 1388 |
+
"loss": 0.3124,
|
| 1389 |
+
"step": 985
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 2.120042872454448,
|
| 1393 |
+
"grad_norm": 1.1378201246261597,
|
| 1394 |
+
"learning_rate": 6.559960039215999e-06,
|
| 1395 |
+
"loss": 0.3218,
|
| 1396 |
+
"step": 990
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 2.1307609860664525,
|
| 1400 |
+
"grad_norm": 1.1623541116714478,
|
| 1401 |
+
"learning_rate": 6.4140991682617676e-06,
|
| 1402 |
+
"loss": 0.3021,
|
| 1403 |
+
"step": 995
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 2.1414790996784565,
|
| 1407 |
+
"grad_norm": 1.109506368637085,
|
| 1408 |
+
"learning_rate": 6.2694359124868825e-06,
|
| 1409 |
+
"loss": 0.2786,
|
| 1410 |
+
"step": 1000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 2.152197213290461,
|
| 1414 |
+
"grad_norm": 1.1443182229995728,
|
| 1415 |
+
"learning_rate": 6.12599045042759e-06,
|
| 1416 |
+
"loss": 0.3026,
|
| 1417 |
+
"step": 1005
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 2.162915326902465,
|
| 1421 |
+
"grad_norm": 1.078079104423523,
|
| 1422 |
+
"learning_rate": 5.983782790754624e-06,
|
| 1423 |
+
"loss": 0.3064,
|
| 1424 |
+
"step": 1010
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 2.1736334405144695,
|
| 1428 |
+
"grad_norm": 1.052649974822998,
|
| 1429 |
+
"learning_rate": 5.842832769482306e-06,
|
| 1430 |
+
"loss": 0.3002,
|
| 1431 |
+
"step": 1015
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 2.184351554126474,
|
| 1435 |
+
"grad_norm": 1.3214424848556519,
|
| 1436 |
+
"learning_rate": 5.703160047201675e-06,
|
| 1437 |
+
"loss": 0.2909,
|
| 1438 |
+
"step": 1020
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 2.195069667738478,
|
| 1442 |
+
"grad_norm": 1.2034846544265747,
|
| 1443 |
+
"learning_rate": 5.564784106338131e-06,
|
| 1444 |
+
"loss": 0.3251,
|
| 1445 |
+
"step": 1025
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 2.2057877813504825,
|
| 1449 |
+
"grad_norm": 1.2458229064941406,
|
| 1450 |
+
"learning_rate": 5.427724248433868e-06,
|
| 1451 |
+
"loss": 0.3009,
|
| 1452 |
+
"step": 1030
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 2.2165058949624865,
|
| 1456 |
+
"grad_norm": 1.1213204860687256,
|
| 1457 |
+
"learning_rate": 5.291999591455599e-06,
|
| 1458 |
+
"loss": 0.2865,
|
| 1459 |
+
"step": 1035
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 2.227224008574491,
|
| 1463 |
+
"grad_norm": 1.0876282453536987,
|
| 1464 |
+
"learning_rate": 5.157629067127857e-06,
|
| 1465 |
+
"loss": 0.2958,
|
| 1466 |
+
"step": 1040
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 2.237942122186495,
|
| 1470 |
+
"grad_norm": 1.2595003843307495,
|
| 1471 |
+
"learning_rate": 5.024631418292275e-06,
|
| 1472 |
+
"loss": 0.3109,
|
| 1473 |
+
"step": 1045
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 2.2486602357984995,
|
| 1477 |
+
"grad_norm": 1.1336579322814941,
|
| 1478 |
+
"learning_rate": 4.893025196293236e-06,
|
| 1479 |
+
"loss": 0.3117,
|
| 1480 |
+
"step": 1050
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 2.259378349410504,
|
| 1484 |
+
"grad_norm": 1.175622582435608,
|
| 1485 |
+
"learning_rate": 4.7628287583901695e-06,
|
| 1486 |
+
"loss": 0.316,
|
| 1487 |
+
"step": 1055
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 2.270096463022508,
|
| 1491 |
+
"grad_norm": 1.1397731304168701,
|
| 1492 |
+
"learning_rate": 4.6340602651970304e-06,
|
| 1493 |
+
"loss": 0.3321,
|
| 1494 |
+
"step": 1060
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 2.2808145766345125,
|
| 1498 |
+
"grad_norm": 1.2002718448638916,
|
| 1499 |
+
"learning_rate": 4.5067376781490855e-06,
|
| 1500 |
+
"loss": 0.3078,
|
| 1501 |
+
"step": 1065
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 2.2915326902465165,
|
| 1505 |
+
"grad_norm": 1.1895092725753784,
|
| 1506 |
+
"learning_rate": 4.380878756997584e-06,
|
| 1507 |
+
"loss": 0.265,
|
| 1508 |
+
"step": 1070
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 2.302250803858521,
|
| 1512 |
+
"grad_norm": 1.1748250722885132,
|
| 1513 |
+
"learning_rate": 4.256501057332468e-06,
|
| 1514 |
+
"loss": 0.2896,
|
| 1515 |
+
"step": 1075
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 2.312968917470525,
|
| 1519 |
+
"grad_norm": 1.0516598224639893,
|
| 1520 |
+
"learning_rate": 4.133621928133666e-06,
|
| 1521 |
+
"loss": 0.2785,
|
| 1522 |
+
"step": 1080
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 2.3236870310825295,
|
| 1526 |
+
"grad_norm": 1.0863022804260254,
|
| 1527 |
+
"learning_rate": 4.012258509351105e-06,
|
| 1528 |
+
"loss": 0.2786,
|
| 1529 |
+
"step": 1085
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 2.334405144694534,
|
| 1533 |
+
"grad_norm": 1.1100490093231201,
|
| 1534 |
+
"learning_rate": 3.892427729513937e-06,
|
| 1535 |
+
"loss": 0.2645,
|
| 1536 |
+
"step": 1090
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 2.345123258306538,
|
| 1540 |
+
"grad_norm": 1.0852088928222656,
|
| 1541 |
+
"learning_rate": 3.7741463033692487e-06,
|
| 1542 |
+
"loss": 0.2874,
|
| 1543 |
+
"step": 1095
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 2.3558413719185425,
|
| 1547 |
+
"grad_norm": 1.2049472332000732,
|
| 1548 |
+
"learning_rate": 3.657430729550567e-06,
|
| 1549 |
+
"loss": 0.3039,
|
| 1550 |
+
"step": 1100
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 2.3665594855305465,
|
| 1554 |
+
"grad_norm": 1.1067779064178467,
|
| 1555 |
+
"learning_rate": 3.5422972882765557e-06,
|
| 1556 |
+
"loss": 0.2861,
|
| 1557 |
+
"step": 1105
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 2.377277599142551,
|
| 1561 |
+
"grad_norm": 1.2369863986968994,
|
| 1562 |
+
"learning_rate": 3.428762039080115e-06,
|
| 1563 |
+
"loss": 0.2849,
|
| 1564 |
+
"step": 1110
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 2.387995712754555,
|
| 1568 |
+
"grad_norm": 1.100407600402832,
|
| 1569 |
+
"learning_rate": 3.3168408185683153e-06,
|
| 1570 |
+
"loss": 0.3062,
|
| 1571 |
+
"step": 1115
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 2.3987138263665595,
|
| 1575 |
+
"grad_norm": 1.0821059942245483,
|
| 1576 |
+
"learning_rate": 3.206549238213403e-06,
|
| 1577 |
+
"loss": 0.2769,
|
| 1578 |
+
"step": 1120
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 2.409431939978564,
|
| 1582 |
+
"grad_norm": 1.2019745111465454,
|
| 1583 |
+
"learning_rate": 3.0979026821752297e-06,
|
| 1584 |
+
"loss": 0.2872,
|
| 1585 |
+
"step": 1125
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 2.420150053590568,
|
| 1589 |
+
"grad_norm": 0.9468026161193848,
|
| 1590 |
+
"learning_rate": 2.9909163051553473e-06,
|
| 1591 |
+
"loss": 0.295,
|
| 1592 |
+
"step": 1130
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 2.4308681672025725,
|
| 1596 |
+
"grad_norm": 1.1377627849578857,
|
| 1597 |
+
"learning_rate": 2.8856050302831527e-06,
|
| 1598 |
+
"loss": 0.2722,
|
| 1599 |
+
"step": 1135
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 2.4415862808145765,
|
| 1603 |
+
"grad_norm": 1.1497541666030884,
|
| 1604 |
+
"learning_rate": 2.781983547034307e-06,
|
| 1605 |
+
"loss": 0.2657,
|
| 1606 |
+
"step": 1140
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 2.452304394426581,
|
| 1610 |
+
"grad_norm": 1.1820542812347412,
|
| 1611 |
+
"learning_rate": 2.6800663091817767e-06,
|
| 1612 |
+
"loss": 0.2529,
|
| 1613 |
+
"step": 1145
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 2.463022508038585,
|
| 1617 |
+
"grad_norm": 1.1529977321624756,
|
| 1618 |
+
"learning_rate": 2.5798675327796994e-06,
|
| 1619 |
+
"loss": 0.2759,
|
| 1620 |
+
"step": 1150
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 2.4737406216505895,
|
| 1624 |
+
"grad_norm": 1.1461573839187622,
|
| 1625 |
+
"learning_rate": 2.4814011941804603e-06,
|
| 1626 |
+
"loss": 0.2752,
|
| 1627 |
+
"step": 1155
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 2.484458735262594,
|
| 1631 |
+
"grad_norm": 0.9810699820518494,
|
| 1632 |
+
"learning_rate": 2.384681028085181e-06,
|
| 1633 |
+
"loss": 0.2762,
|
| 1634 |
+
"step": 1160
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 2.495176848874598,
|
| 1638 |
+
"grad_norm": 1.044024109840393,
|
| 1639 |
+
"learning_rate": 2.2897205256279048e-06,
|
| 1640 |
+
"loss": 0.2872,
|
| 1641 |
+
"step": 1165
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 2.5058949624866025,
|
| 1645 |
+
"grad_norm": 1.1893457174301147,
|
| 1646 |
+
"learning_rate": 2.1965329324938e-06,
|
| 1647 |
+
"loss": 0.2854,
|
| 1648 |
+
"step": 1170
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 2.5166130760986065,
|
| 1652 |
+
"grad_norm": 1.0847933292388916,
|
| 1653 |
+
"learning_rate": 2.1051312470715175e-06,
|
| 1654 |
+
"loss": 0.2922,
|
| 1655 |
+
"step": 1175
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 2.527331189710611,
|
| 1659 |
+
"grad_norm": 1.1810137033462524,
|
| 1660 |
+
"learning_rate": 2.015528218640149e-06,
|
| 1661 |
+
"loss": 0.265,
|
| 1662 |
+
"step": 1180
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 2.538049303322615,
|
| 1666 |
+
"grad_norm": 1.0281888246536255,
|
| 1667 |
+
"learning_rate": 1.927736345590839e-06,
|
| 1668 |
+
"loss": 0.2838,
|
| 1669 |
+
"step": 1185
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 2.5487674169346195,
|
| 1673 |
+
"grad_norm": 1.0966765880584717,
|
| 1674 |
+
"learning_rate": 1.8417678736834604e-06,
|
| 1675 |
+
"loss": 0.3181,
|
| 1676 |
+
"step": 1190
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 2.559485530546624,
|
| 1680 |
+
"grad_norm": 1.1331520080566406,
|
| 1681 |
+
"learning_rate": 1.757634794338459e-06,
|
| 1682 |
+
"loss": 0.2779,
|
| 1683 |
+
"step": 1195
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 2.570203644158628,
|
| 1687 |
+
"grad_norm": 1.120964765548706,
|
| 1688 |
+
"learning_rate": 1.6753488429642638e-06,
|
| 1689 |
+
"loss": 0.2884,
|
| 1690 |
+
"step": 1200
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 2.5809217577706325,
|
| 1694 |
+
"grad_norm": 1.1420046091079712,
|
| 1695 |
+
"learning_rate": 1.594921497320324e-06,
|
| 1696 |
+
"loss": 0.2797,
|
| 1697 |
+
"step": 1205
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 2.5916398713826365,
|
| 1701 |
+
"grad_norm": 1.1691547632217407,
|
| 1702 |
+
"learning_rate": 1.516363975916128e-06,
|
| 1703 |
+
"loss": 0.2825,
|
| 1704 |
+
"step": 1210
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 2.602357984994641,
|
| 1708 |
+
"grad_norm": 1.0935206413269043,
|
| 1709 |
+
"learning_rate": 1.4396872364463853e-06,
|
| 1710 |
+
"loss": 0.2599,
|
| 1711 |
+
"step": 1215
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 2.613076098606645,
|
| 1715 |
+
"grad_norm": 1.1766819953918457,
|
| 1716 |
+
"learning_rate": 1.3649019742625624e-06,
|
| 1717 |
+
"loss": 0.3039,
|
| 1718 |
+
"step": 1220
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 2.6237942122186495,
|
| 1722 |
+
"grad_norm": 1.1887208223342896,
|
| 1723 |
+
"learning_rate": 1.292018620881048e-06,
|
| 1724 |
+
"loss": 0.2869,
|
| 1725 |
+
"step": 1225
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 2.634512325830654,
|
| 1729 |
+
"grad_norm": 1.1644409894943237,
|
| 1730 |
+
"learning_rate": 1.2210473425280783e-06,
|
| 1731 |
+
"loss": 0.2885,
|
| 1732 |
+
"step": 1230
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 2.645230439442658,
|
| 1736 |
+
"grad_norm": 1.2318623065948486,
|
| 1737 |
+
"learning_rate": 1.1519980387217032e-06,
|
| 1738 |
+
"loss": 0.2926,
|
| 1739 |
+
"step": 1235
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 2.6559485530546625,
|
| 1743 |
+
"grad_norm": 1.1559414863586426,
|
| 1744 |
+
"learning_rate": 1.0848803408909309e-06,
|
| 1745 |
+
"loss": 0.3042,
|
| 1746 |
+
"step": 1240
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 2.6666666666666665,
|
| 1750 |
+
"grad_norm": 1.075410008430481,
|
| 1751 |
+
"learning_rate": 1.019703611032292e-06,
|
| 1752 |
+
"loss": 0.2863,
|
| 1753 |
+
"step": 1245
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 2.677384780278671,
|
| 1757 |
+
"grad_norm": 1.1436070203781128,
|
| 1758 |
+
"learning_rate": 9.56476940403942e-07,
|
| 1759 |
+
"loss": 0.275,
|
| 1760 |
+
"step": 1250
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 2.688102893890675,
|
| 1764 |
+
"grad_norm": 1.185698390007019,
|
| 1765 |
+
"learning_rate": 8.952091482575825e-07,
|
| 1766 |
+
"loss": 0.2804,
|
| 1767 |
+
"step": 1255
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 2.6988210075026795,
|
| 1771 |
+
"grad_norm": 1.2179303169250488,
|
| 1772 |
+
"learning_rate": 8.359087806082761e-07,
|
| 1773 |
+
"loss": 0.3004,
|
| 1774 |
+
"step": 1260
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 2.709539121114684,
|
| 1778 |
+
"grad_norm": 1.2889785766601562,
|
| 1779 |
+
"learning_rate": 7.785841090424151e-07,
|
| 1780 |
+
"loss": 0.2774,
|
| 1781 |
+
"step": 1265
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 2.720257234726688,
|
| 1785 |
+
"grad_norm": 1.172799825668335,
|
| 1786 |
+
"learning_rate": 7.232431295639303e-07,
|
| 1787 |
+
"loss": 0.258,
|
| 1788 |
+
"step": 1270
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 2.7309753483386925,
|
| 1792 |
+
"grad_norm": 1.1804120540618896,
|
| 1793 |
+
"learning_rate": 6.698935614789676e-07,
|
| 1794 |
+
"loss": 0.2829,
|
| 1795 |
+
"step": 1275
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 2.7416934619506965,
|
| 1799 |
+
"grad_norm": 1.1490246057510376,
|
| 1800 |
+
"learning_rate": 6.185428463191512e-07,
|
| 1801 |
+
"loss": 0.2829,
|
| 1802 |
+
"step": 1280
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 2.752411575562701,
|
| 1806 |
+
"grad_norm": 1.0342978239059448,
|
| 1807 |
+
"learning_rate": 5.691981468035873e-07,
|
| 1808 |
+
"loss": 0.2558,
|
| 1809 |
+
"step": 1285
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 2.763129689174705,
|
| 1813 |
+
"grad_norm": 0.9746224880218506,
|
| 1814 |
+
"learning_rate": 5.218663458397716e-07,
|
| 1815 |
+
"loss": 0.2701,
|
| 1816 |
+
"step": 1290
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 2.7738478027867095,
|
| 1820 |
+
"grad_norm": 1.1627681255340576,
|
| 1821 |
+
"learning_rate": 4.765540455635037e-07,
|
| 1822 |
+
"loss": 0.3193,
|
| 1823 |
+
"step": 1295
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 2.784565916398714,
|
| 1827 |
+
"grad_norm": 1.17820405960083,
|
| 1828 |
+
"learning_rate": 4.332675664179975e-07,
|
| 1829 |
+
"loss": 0.2819,
|
| 1830 |
+
"step": 1300
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 2.795284030010718,
|
| 1834 |
+
"grad_norm": 0.9921414852142334,
|
| 1835 |
+
"learning_rate": 3.9201294627225605e-07,
|
| 1836 |
+
"loss": 0.2562,
|
| 1837 |
+
"step": 1305
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 2.8060021436227225,
|
| 1841 |
+
"grad_norm": 1.149877905845642,
|
| 1842 |
+
"learning_rate": 3.5279593957887213e-07,
|
| 1843 |
+
"loss": 0.2906,
|
| 1844 |
+
"step": 1310
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 2.816720257234727,
|
| 1848 |
+
"grad_norm": 1.0398290157318115,
|
| 1849 |
+
"learning_rate": 3.156220165713603e-07,
|
| 1850 |
+
"loss": 0.2893,
|
| 1851 |
+
"step": 1315
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 2.827438370846731,
|
| 1855 |
+
"grad_norm": 1.1763765811920166,
|
| 1856 |
+
"learning_rate": 2.8049636250114195e-07,
|
| 1857 |
+
"loss": 0.2905,
|
| 1858 |
+
"step": 1320
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 2.838156484458735,
|
| 1862 |
+
"grad_norm": 1.200230360031128,
|
| 1863 |
+
"learning_rate": 2.474238769142645e-07,
|
| 1864 |
+
"loss": 0.2506,
|
| 1865 |
+
"step": 1325
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 2.8488745980707395,
|
| 1869 |
+
"grad_norm": 1.0414636135101318,
|
| 1870 |
+
"learning_rate": 2.1640917296799069e-07,
|
| 1871 |
+
"loss": 0.2513,
|
| 1872 |
+
"step": 1330
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 2.859592711682744,
|
| 1876 |
+
"grad_norm": 1.1210410594940186,
|
| 1877 |
+
"learning_rate": 1.8745657678731875e-07,
|
| 1878 |
+
"loss": 0.2751,
|
| 1879 |
+
"step": 1335
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 2.870310825294748,
|
| 1883 |
+
"grad_norm": 1.1431525945663452,
|
| 1884 |
+
"learning_rate": 1.6057012686154836e-07,
|
| 1885 |
+
"loss": 0.2908,
|
| 1886 |
+
"step": 1340
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 2.8810289389067525,
|
| 1890 |
+
"grad_norm": 1.0242949724197388,
|
| 1891 |
+
"learning_rate": 1.357535734809795e-07,
|
| 1892 |
+
"loss": 0.2896,
|
| 1893 |
+
"step": 1345
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 2.891747052518757,
|
| 1897 |
+
"grad_norm": 1.0368810892105103,
|
| 1898 |
+
"learning_rate": 1.1301037821377758e-07,
|
| 1899 |
+
"loss": 0.2749,
|
| 1900 |
+
"step": 1350
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 2.902465166130761,
|
| 1904 |
+
"grad_norm": 1.0779223442077637,
|
| 1905 |
+
"learning_rate": 9.234371342314807e-08,
|
| 1906 |
+
"loss": 0.2734,
|
| 1907 |
+
"step": 1355
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 2.913183279742765,
|
| 1911 |
+
"grad_norm": 1.1738801002502441,
|
| 1912 |
+
"learning_rate": 7.375646182482875e-08,
|
| 1913 |
+
"loss": 0.3016,
|
| 1914 |
+
"step": 1360
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 2.9239013933547695,
|
| 1918 |
+
"grad_norm": 0.9701231122016907,
|
| 1919 |
+
"learning_rate": 5.725121608499639e-08,
|
| 1920 |
+
"loss": 0.2292,
|
| 1921 |
+
"step": 1365
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 2.934619506966774,
|
| 1925 |
+
"grad_norm": 1.090383529663086,
|
| 1926 |
+
"learning_rate": 4.283027845861598e-08,
|
| 1927 |
+
"loss": 0.2655,
|
| 1928 |
+
"step": 1370
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 2.945337620578778,
|
| 1932 |
+
"grad_norm": 1.1737515926361084,
|
| 1933 |
+
"learning_rate": 3.0495660468315975e-08,
|
| 1934 |
+
"loss": 0.2342,
|
| 1935 |
+
"step": 1375
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 2.9560557341907825,
|
| 1939 |
+
"grad_norm": 1.060263752937317,
|
| 1940 |
+
"learning_rate": 2.0249082623802762e-08,
|
| 1941 |
+
"loss": 0.2814,
|
| 1942 |
+
"step": 1380
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 2.966773847802787,
|
| 1946 |
+
"grad_norm": 1.067541241645813,
|
| 1947 |
+
"learning_rate": 1.2091974181880905e-08,
|
| 1948 |
+
"loss": 0.2686,
|
| 1949 |
+
"step": 1385
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 2.977491961414791,
|
| 1953 |
+
"grad_norm": 1.249548077583313,
|
| 1954 |
+
"learning_rate": 6.025472947082667e-09,
|
| 1955 |
+
"loss": 0.2855,
|
| 1956 |
+
"step": 1390
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 2.988210075026795,
|
| 1960 |
+
"grad_norm": 1.3081293106079102,
|
| 1961 |
+
"learning_rate": 2.0504251129649378e-09,
|
| 1962 |
+
"loss": 0.2527,
|
| 1963 |
+
"step": 1395
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 2.9989281886387995,
|
| 1967 |
+
"grad_norm": 1.1735353469848633,
|
| 1968 |
+
"learning_rate": 1.6738514407699246e-10,
|
| 1969 |
+
"loss": 0.2382,
|
| 1970 |
+
"step": 1400
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 3.0,
|
| 1974 |
+
"step": 1401,
|
| 1975 |
+
"total_flos": 2.0918875763098255e+18,
|
| 1976 |
+
"train_loss": 0.5697678685996637,
|
| 1977 |
+
"train_runtime": 1013.0729,
|
| 1978 |
+
"train_samples_per_second": 44.179,
|
| 1979 |
+
"train_steps_per_second": 1.383
|
| 1980 |
+
}
|
| 1981 |
+
],
|
| 1982 |
+
"logging_steps": 5,
|
| 1983 |
+
"max_steps": 1401,
|
| 1984 |
+
"num_input_tokens_seen": 0,
|
| 1985 |
+
"num_train_epochs": 3,
|
| 1986 |
+
"save_steps": 20000,
|
| 1987 |
+
"stateful_callbacks": {
|
| 1988 |
+
"TrainerControl": {
|
| 1989 |
+
"args": {
|
| 1990 |
+
"should_epoch_stop": false,
|
| 1991 |
+
"should_evaluate": false,
|
| 1992 |
+
"should_log": false,
|
| 1993 |
+
"should_save": false,
|
| 1994 |
+
"should_training_stop": false
|
| 1995 |
+
},
|
| 1996 |
+
"attributes": {}
|
| 1997 |
+
}
|
| 1998 |
+
},
|
| 1999 |
+
"total_flos": 2.0918875763098255e+18,
|
| 2000 |
+
"train_batch_size": 2,
|
| 2001 |
+
"trial_name": null,
|
| 2002 |
+
"trial_params": null
|
| 2003 |
+
}
|
1_128_e3_3e-5/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b8d41448c15f291508ace36349b25b9dc9f2192192f986d94bbe9a1558f10bc6
|
| 3 |
+
size 8209
|
1_128_e3_3e-5/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|