Upload folder using huggingface_hub
Browse files- 102_128_e3_3e-5/adapter_config.json +39 -0
- 102_128_e3_3e-5/adapter_model.safetensors +3 -0
- 102_128_e3_3e-5/added_tokens.json +9 -0
- 102_128_e3_3e-5/all_results.json +9 -0
- 102_128_e3_3e-5/chat_template.jinja +62 -0
- 102_128_e3_3e-5/config.json +32 -0
- 102_128_e3_3e-5/merges.txt +0 -0
- 102_128_e3_3e-5/special_tokens_map.json +33 -0
- 102_128_e3_3e-5/tokenizer.json +0 -0
- 102_128_e3_3e-5/tokenizer_config.json +234 -0
- 102_128_e3_3e-5/train_results.json +9 -0
- 102_128_e3_3e-5/trainer_state.json +1898 -0
- 102_128_e3_3e-5/training_args.bin +3 -0
- 102_128_e3_3e-5/vocab.json +0 -0
102_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 |
+
"gate_proj",
|
| 29 |
+
"k_proj",
|
| 30 |
+
"up_proj",
|
| 31 |
+
"q_proj",
|
| 32 |
+
"down_proj",
|
| 33 |
+
"o_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
+
"use_dora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
102_128_e3_3e-5/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:16362267b3e7ff9f5a0ae99dda8621c4942216ca0b0b7c5043de791c3c6e5b6e
|
| 3 |
+
size 791751704
|
102_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 |
+
}
|
102_128_e3_3e-5/all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 1.918936913708843e+18,
|
| 4 |
+
"train_loss": 0.5796768012308734,
|
| 5 |
+
"train_runtime": 894.235,
|
| 6 |
+
"train_samples": 14160,
|
| 7 |
+
"train_samples_per_second": 47.504,
|
| 8 |
+
"train_steps_per_second": 1.486
|
| 9 |
+
}
|
102_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 %}
|
102_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 |
+
}
|
102_128_e3_3e-5/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
102_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 |
+
}
|
102_128_e3_3e-5/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
102_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 |
+
}
|
102_128_e3_3e-5/train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 1.918936913708843e+18,
|
| 4 |
+
"train_loss": 0.5796768012308734,
|
| 5 |
+
"train_runtime": 894.235,
|
| 6 |
+
"train_samples": 14160,
|
| 7 |
+
"train_samples_per_second": 47.504,
|
| 8 |
+
"train_steps_per_second": 1.486
|
| 9 |
+
}
|
102_128_e3_3e-5/trainer_state.json
ADDED
|
@@ -0,0 +1,1898 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 1329,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.011299435028248588,
|
| 14 |
+
"grad_norm": 3.0857901573181152,
|
| 15 |
+
"learning_rate": 1.791044776119403e-06,
|
| 16 |
+
"loss": 1.5559,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.022598870056497175,
|
| 21 |
+
"grad_norm": 2.556417226791382,
|
| 22 |
+
"learning_rate": 4.029850746268657e-06,
|
| 23 |
+
"loss": 1.5963,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.03389830508474576,
|
| 28 |
+
"grad_norm": 1.2317314147949219,
|
| 29 |
+
"learning_rate": 6.268656716417911e-06,
|
| 30 |
+
"loss": 1.4753,
|
| 31 |
+
"step": 15
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.04519774011299435,
|
| 35 |
+
"grad_norm": 0.599475085735321,
|
| 36 |
+
"learning_rate": 8.507462686567164e-06,
|
| 37 |
+
"loss": 1.3628,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.05649717514124294,
|
| 42 |
+
"grad_norm": 0.4953320026397705,
|
| 43 |
+
"learning_rate": 1.0746268656716418e-05,
|
| 44 |
+
"loss": 1.3298,
|
| 45 |
+
"step": 25
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.06779661016949153,
|
| 49 |
+
"grad_norm": 0.5787931084632874,
|
| 50 |
+
"learning_rate": 1.2985074626865672e-05,
|
| 51 |
+
"loss": 1.3489,
|
| 52 |
+
"step": 30
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.07909604519774012,
|
| 56 |
+
"grad_norm": 0.48433947563171387,
|
| 57 |
+
"learning_rate": 1.5223880597014927e-05,
|
| 58 |
+
"loss": 1.3143,
|
| 59 |
+
"step": 35
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.0903954802259887,
|
| 63 |
+
"grad_norm": 0.37891411781311035,
|
| 64 |
+
"learning_rate": 1.746268656716418e-05,
|
| 65 |
+
"loss": 1.2583,
|
| 66 |
+
"step": 40
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.1016949152542373,
|
| 70 |
+
"grad_norm": 0.4168344736099243,
|
| 71 |
+
"learning_rate": 1.9701492537313435e-05,
|
| 72 |
+
"loss": 1.2808,
|
| 73 |
+
"step": 45
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.11299435028248588,
|
| 77 |
+
"grad_norm": 0.4194926619529724,
|
| 78 |
+
"learning_rate": 2.194029850746269e-05,
|
| 79 |
+
"loss": 1.3015,
|
| 80 |
+
"step": 50
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.12429378531073447,
|
| 84 |
+
"grad_norm": 0.40536758303642273,
|
| 85 |
+
"learning_rate": 2.417910447761194e-05,
|
| 86 |
+
"loss": 1.3158,
|
| 87 |
+
"step": 55
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.13559322033898305,
|
| 91 |
+
"grad_norm": 0.3850628733634949,
|
| 92 |
+
"learning_rate": 2.6417910447761193e-05,
|
| 93 |
+
"loss": 1.2409,
|
| 94 |
+
"step": 60
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.14689265536723164,
|
| 98 |
+
"grad_norm": 0.39517489075660706,
|
| 99 |
+
"learning_rate": 2.8656716417910447e-05,
|
| 100 |
+
"loss": 1.2333,
|
| 101 |
+
"step": 65
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.15819209039548024,
|
| 105 |
+
"grad_norm": 0.37725552916526794,
|
| 106 |
+
"learning_rate": 2.9999814090581187e-05,
|
| 107 |
+
"loss": 1.3008,
|
| 108 |
+
"step": 70
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.1694915254237288,
|
| 112 |
+
"grad_norm": 0.426224946975708,
|
| 113 |
+
"learning_rate": 2.9997722662542733e-05,
|
| 114 |
+
"loss": 1.2296,
|
| 115 |
+
"step": 75
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.1807909604519774,
|
| 119 |
+
"grad_norm": 0.4203334450721741,
|
| 120 |
+
"learning_rate": 2.9993307744782344e-05,
|
| 121 |
+
"loss": 1.1987,
|
| 122 |
+
"step": 80
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.192090395480226,
|
| 126 |
+
"grad_norm": 0.44976547360420227,
|
| 127 |
+
"learning_rate": 2.9986570021271592e-05,
|
| 128 |
+
"loss": 1.2231,
|
| 129 |
+
"step": 85
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.2033898305084746,
|
| 133 |
+
"grad_norm": 0.49428609013557434,
|
| 134 |
+
"learning_rate": 2.997751053583772e-05,
|
| 135 |
+
"loss": 1.1701,
|
| 136 |
+
"step": 90
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.21468926553672316,
|
| 140 |
+
"grad_norm": 0.46584680676460266,
|
| 141 |
+
"learning_rate": 2.99661306920019e-05,
|
| 142 |
+
"loss": 1.1356,
|
| 143 |
+
"step": 95
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.22598870056497175,
|
| 147 |
+
"grad_norm": 0.43497881293296814,
|
| 148 |
+
"learning_rate": 2.9952432252761796e-05,
|
| 149 |
+
"loss": 1.1216,
|
| 150 |
+
"step": 100
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.23728813559322035,
|
| 154 |
+
"grad_norm": 0.39466479420661926,
|
| 155 |
+
"learning_rate": 2.9936417340318465e-05,
|
| 156 |
+
"loss": 1.1457,
|
| 157 |
+
"step": 105
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.24858757062146894,
|
| 161 |
+
"grad_norm": 0.39521124958992004,
|
| 162 |
+
"learning_rate": 2.9918088435747556e-05,
|
| 163 |
+
"loss": 1.1438,
|
| 164 |
+
"step": 110
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.2598870056497175,
|
| 168 |
+
"grad_norm": 0.4783444404602051,
|
| 169 |
+
"learning_rate": 2.9897448378614933e-05,
|
| 170 |
+
"loss": 1.1263,
|
| 171 |
+
"step": 115
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.2711864406779661,
|
| 175 |
+
"grad_norm": 0.5143007636070251,
|
| 176 |
+
"learning_rate": 2.9874500366536774e-05,
|
| 177 |
+
"loss": 1.1072,
|
| 178 |
+
"step": 120
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.2824858757062147,
|
| 182 |
+
"grad_norm": 0.4819560647010803,
|
| 183 |
+
"learning_rate": 2.9849247954684188e-05,
|
| 184 |
+
"loss": 1.1144,
|
| 185 |
+
"step": 125
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.2937853107344633,
|
| 189 |
+
"grad_norm": 0.4924561381340027,
|
| 190 |
+
"learning_rate": 2.9821695055232415e-05,
|
| 191 |
+
"loss": 1.125,
|
| 192 |
+
"step": 130
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.3050847457627119,
|
| 196 |
+
"grad_norm": 0.48472464084625244,
|
| 197 |
+
"learning_rate": 2.9791845936754768e-05,
|
| 198 |
+
"loss": 1.0658,
|
| 199 |
+
"step": 135
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.3163841807909605,
|
| 203 |
+
"grad_norm": 0.4859028160572052,
|
| 204 |
+
"learning_rate": 2.975970522356133e-05,
|
| 205 |
+
"loss": 1.0659,
|
| 206 |
+
"step": 140
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.327683615819209,
|
| 210 |
+
"grad_norm": 0.5269531607627869,
|
| 211 |
+
"learning_rate": 2.972527789498251e-05,
|
| 212 |
+
"loss": 1.0653,
|
| 213 |
+
"step": 145
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.3389830508474576,
|
| 217 |
+
"grad_norm": 0.4960964024066925,
|
| 218 |
+
"learning_rate": 2.9688569284597687e-05,
|
| 219 |
+
"loss": 1.0411,
|
| 220 |
+
"step": 150
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.3502824858757062,
|
| 224 |
+
"grad_norm": 0.5750166773796082,
|
| 225 |
+
"learning_rate": 2.9649585079408865e-05,
|
| 226 |
+
"loss": 1.0428,
|
| 227 |
+
"step": 155
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.3615819209039548,
|
| 231 |
+
"grad_norm": 0.5849672555923462,
|
| 232 |
+
"learning_rate": 2.9608331318959652e-05,
|
| 233 |
+
"loss": 1.053,
|
| 234 |
+
"step": 160
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.3728813559322034,
|
| 238 |
+
"grad_norm": 0.5839733481407166,
|
| 239 |
+
"learning_rate": 2.95648143943996e-05,
|
| 240 |
+
"loss": 0.9993,
|
| 241 |
+
"step": 165
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.384180790960452,
|
| 245 |
+
"grad_norm": 0.5899782180786133,
|
| 246 |
+
"learning_rate": 2.951904104749405e-05,
|
| 247 |
+
"loss": 1.0274,
|
| 248 |
+
"step": 170
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.3954802259887006,
|
| 252 |
+
"grad_norm": 0.5473635792732239,
|
| 253 |
+
"learning_rate": 2.9471018369579708e-05,
|
| 254 |
+
"loss": 0.9956,
|
| 255 |
+
"step": 175
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.4067796610169492,
|
| 259 |
+
"grad_norm": 0.5684501528739929,
|
| 260 |
+
"learning_rate": 2.9420753800466003e-05,
|
| 261 |
+
"loss": 1.0193,
|
| 262 |
+
"step": 180
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.4180790960451977,
|
| 266 |
+
"grad_norm": 0.588405966758728,
|
| 267 |
+
"learning_rate": 2.9368255127282504e-05,
|
| 268 |
+
"loss": 1.0191,
|
| 269 |
+
"step": 185
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.4293785310734463,
|
| 273 |
+
"grad_norm": 0.6258564591407776,
|
| 274 |
+
"learning_rate": 2.9313530483272536e-05,
|
| 275 |
+
"loss": 0.9201,
|
| 276 |
+
"step": 190
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.4406779661016949,
|
| 280 |
+
"grad_norm": 0.5802227854728699,
|
| 281 |
+
"learning_rate": 2.9256588346533116e-05,
|
| 282 |
+
"loss": 0.9925,
|
| 283 |
+
"step": 195
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.4519774011299435,
|
| 287 |
+
"grad_norm": 0.6095137596130371,
|
| 288 |
+
"learning_rate": 2.9197437538701534e-05,
|
| 289 |
+
"loss": 0.9631,
|
| 290 |
+
"step": 200
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.4632768361581921,
|
| 294 |
+
"grad_norm": 0.6588829159736633,
|
| 295 |
+
"learning_rate": 2.9136087223588666e-05,
|
| 296 |
+
"loss": 0.9211,
|
| 297 |
+
"step": 205
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.4745762711864407,
|
| 301 |
+
"grad_norm": 0.6170017719268799,
|
| 302 |
+
"learning_rate": 2.907254690575929e-05,
|
| 303 |
+
"loss": 0.9499,
|
| 304 |
+
"step": 210
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.4858757062146893,
|
| 308 |
+
"grad_norm": 0.6972135901451111,
|
| 309 |
+
"learning_rate": 2.900682642905962e-05,
|
| 310 |
+
"loss": 0.9781,
|
| 311 |
+
"step": 215
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.4971751412429379,
|
| 315 |
+
"grad_norm": 0.7225595712661743,
|
| 316 |
+
"learning_rate": 2.8938935975092258e-05,
|
| 317 |
+
"loss": 0.9418,
|
| 318 |
+
"step": 220
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.5084745762711864,
|
| 322 |
+
"grad_norm": 0.7638112306594849,
|
| 323 |
+
"learning_rate": 2.8868886061638844e-05,
|
| 324 |
+
"loss": 0.9543,
|
| 325 |
+
"step": 225
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.519774011299435,
|
| 329 |
+
"grad_norm": 0.6980622410774231,
|
| 330 |
+
"learning_rate": 2.8796687541030595e-05,
|
| 331 |
+
"loss": 0.9423,
|
| 332 |
+
"step": 230
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.5310734463276836,
|
| 336 |
+
"grad_norm": 0.7166441679000854,
|
| 337 |
+
"learning_rate": 2.8722351598467057e-05,
|
| 338 |
+
"loss": 0.9119,
|
| 339 |
+
"step": 235
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.5423728813559322,
|
| 343 |
+
"grad_norm": 0.7469143271446228,
|
| 344 |
+
"learning_rate": 2.8645889750283227e-05,
|
| 345 |
+
"loss": 0.9081,
|
| 346 |
+
"step": 240
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.5536723163841808,
|
| 350 |
+
"grad_norm": 0.6664925813674927,
|
| 351 |
+
"learning_rate": 2.8567313842165448e-05,
|
| 352 |
+
"loss": 0.9028,
|
| 353 |
+
"step": 245
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.5649717514124294,
|
| 357 |
+
"grad_norm": 0.7710598707199097,
|
| 358 |
+
"learning_rate": 2.8486636047316203e-05,
|
| 359 |
+
"loss": 0.8607,
|
| 360 |
+
"step": 250
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.576271186440678,
|
| 364 |
+
"grad_norm": 0.7417610883712769,
|
| 365 |
+
"learning_rate": 2.8403868864568244e-05,
|
| 366 |
+
"loss": 0.9316,
|
| 367 |
+
"step": 255
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.5875706214689266,
|
| 371 |
+
"grad_norm": 0.6854378581047058,
|
| 372 |
+
"learning_rate": 2.8319025116448215e-05,
|
| 373 |
+
"loss": 0.9121,
|
| 374 |
+
"step": 260
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.5988700564971752,
|
| 378 |
+
"grad_norm": 0.6760811805725098,
|
| 379 |
+
"learning_rate": 2.8232117947190148e-05,
|
| 380 |
+
"loss": 0.8903,
|
| 381 |
+
"step": 265
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.6101694915254238,
|
| 385 |
+
"grad_norm": 0.7594468593597412,
|
| 386 |
+
"learning_rate": 2.814316082069914e-05,
|
| 387 |
+
"loss": 0.9013,
|
| 388 |
+
"step": 270
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.6214689265536724,
|
| 392 |
+
"grad_norm": 0.7125830054283142,
|
| 393 |
+
"learning_rate": 2.805216751846547e-05,
|
| 394 |
+
"loss": 0.8906,
|
| 395 |
+
"step": 275
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.632768361581921,
|
| 399 |
+
"grad_norm": 0.7869139313697815,
|
| 400 |
+
"learning_rate": 2.795915213742954e-05,
|
| 401 |
+
"loss": 0.8886,
|
| 402 |
+
"step": 280
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.6440677966101694,
|
| 406 |
+
"grad_norm": 0.7613300085067749,
|
| 407 |
+
"learning_rate": 2.7864129087797935e-05,
|
| 408 |
+
"loss": 0.8702,
|
| 409 |
+
"step": 285
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.655367231638418,
|
| 413 |
+
"grad_norm": 0.8529829382896423,
|
| 414 |
+
"learning_rate": 2.7767113090810937e-05,
|
| 415 |
+
"loss": 0.8923,
|
| 416 |
+
"step": 290
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.6666666666666666,
|
| 420 |
+
"grad_norm": 0.7996538877487183,
|
| 421 |
+
"learning_rate": 2.76681191764619e-05,
|
| 422 |
+
"loss": 0.8306,
|
| 423 |
+
"step": 295
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.6779661016949152,
|
| 427 |
+
"grad_norm": 0.8224160671234131,
|
| 428 |
+
"learning_rate": 2.7567162681168743e-05,
|
| 429 |
+
"loss": 0.8414,
|
| 430 |
+
"step": 300
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.6892655367231638,
|
| 434 |
+
"grad_norm": 0.8216344714164734,
|
| 435 |
+
"learning_rate": 2.7464259245397976e-05,
|
| 436 |
+
"loss": 0.8324,
|
| 437 |
+
"step": 305
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.7005649717514124,
|
| 441 |
+
"grad_norm": 0.8234724402427673,
|
| 442 |
+
"learning_rate": 2.735942481124167e-05,
|
| 443 |
+
"loss": 0.8415,
|
| 444 |
+
"step": 310
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.711864406779661,
|
| 448 |
+
"grad_norm": 0.7917332053184509,
|
| 449 |
+
"learning_rate": 2.7252675619947625e-05,
|
| 450 |
+
"loss": 0.8224,
|
| 451 |
+
"step": 315
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.7231638418079096,
|
| 455 |
+
"grad_norm": 0.8194693922996521,
|
| 456 |
+
"learning_rate": 2.7144028209403248e-05,
|
| 457 |
+
"loss": 0.8575,
|
| 458 |
+
"step": 320
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.7344632768361582,
|
| 462 |
+
"grad_norm": 0.7861095070838928,
|
| 463 |
+
"learning_rate": 2.7033499411573457e-05,
|
| 464 |
+
"loss": 0.7868,
|
| 465 |
+
"step": 325
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.7457627118644068,
|
| 469 |
+
"grad_norm": 0.7693805694580078,
|
| 470 |
+
"learning_rate": 2.6921106349893032e-05,
|
| 471 |
+
"loss": 0.8195,
|
| 472 |
+
"step": 330
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.7570621468926554,
|
| 476 |
+
"grad_norm": 0.7841665148735046,
|
| 477 |
+
"learning_rate": 2.6806866436613774e-05,
|
| 478 |
+
"loss": 0.7745,
|
| 479 |
+
"step": 335
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.768361581920904,
|
| 483 |
+
"grad_norm": 0.8027680516242981,
|
| 484 |
+
"learning_rate": 2.6690797370106995e-05,
|
| 485 |
+
"loss": 0.7719,
|
| 486 |
+
"step": 340
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.7796610169491526,
|
| 490 |
+
"grad_norm": 0.8157889246940613,
|
| 491 |
+
"learning_rate": 2.6572917132121592e-05,
|
| 492 |
+
"loss": 0.7623,
|
| 493 |
+
"step": 345
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.7909604519774012,
|
| 497 |
+
"grad_norm": 0.9143925309181213,
|
| 498 |
+
"learning_rate": 2.6453243984998298e-05,
|
| 499 |
+
"loss": 0.7891,
|
| 500 |
+
"step": 350
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.8022598870056498,
|
| 504 |
+
"grad_norm": 0.8712047338485718,
|
| 505 |
+
"learning_rate": 2.63317964688404e-05,
|
| 506 |
+
"loss": 0.7852,
|
| 507 |
+
"step": 355
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.8135593220338984,
|
| 511 |
+
"grad_norm": 0.8119410276412964,
|
| 512 |
+
"learning_rate": 2.6208593398641477e-05,
|
| 513 |
+
"loss": 0.7688,
|
| 514 |
+
"step": 360
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.8248587570621468,
|
| 518 |
+
"grad_norm": 0.9128645658493042,
|
| 519 |
+
"learning_rate": 2.6083653861370512e-05,
|
| 520 |
+
"loss": 0.7564,
|
| 521 |
+
"step": 365
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.8361581920903954,
|
| 525 |
+
"grad_norm": 0.8086043000221252,
|
| 526 |
+
"learning_rate": 2.59569972130149e-05,
|
| 527 |
+
"loss": 0.7753,
|
| 528 |
+
"step": 370
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.847457627118644,
|
| 532 |
+
"grad_norm": 0.8716402053833008,
|
| 533 |
+
"learning_rate": 2.582864307558174e-05,
|
| 534 |
+
"loss": 0.7411,
|
| 535 |
+
"step": 375
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.8587570621468926,
|
| 539 |
+
"grad_norm": 0.8887103796005249,
|
| 540 |
+
"learning_rate": 2.5698611334057965e-05,
|
| 541 |
+
"loss": 0.7269,
|
| 542 |
+
"step": 380
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.8700564971751412,
|
| 546 |
+
"grad_norm": 0.8046791553497314,
|
| 547 |
+
"learning_rate": 2.5566922133329685e-05,
|
| 548 |
+
"loss": 0.7204,
|
| 549 |
+
"step": 385
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.8813559322033898,
|
| 553 |
+
"grad_norm": 0.8097022175788879,
|
| 554 |
+
"learning_rate": 2.5433595875061284e-05,
|
| 555 |
+
"loss": 0.7311,
|
| 556 |
+
"step": 390
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.8926553672316384,
|
| 560 |
+
"grad_norm": 0.8284101486206055,
|
| 561 |
+
"learning_rate": 2.529865321453476e-05,
|
| 562 |
+
"loss": 0.7147,
|
| 563 |
+
"step": 395
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.903954802259887,
|
| 567 |
+
"grad_norm": 0.9441022276878357,
|
| 568 |
+
"learning_rate": 2.5162115057449713e-05,
|
| 569 |
+
"loss": 0.711,
|
| 570 |
+
"step": 400
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.9152542372881356,
|
| 574 |
+
"grad_norm": 0.8779711127281189,
|
| 575 |
+
"learning_rate": 2.5024002556684603e-05,
|
| 576 |
+
"loss": 0.7169,
|
| 577 |
+
"step": 405
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.9265536723163842,
|
| 581 |
+
"grad_norm": 0.8313904404640198,
|
| 582 |
+
"learning_rate": 2.4884337109019675e-05,
|
| 583 |
+
"loss": 0.688,
|
| 584 |
+
"step": 410
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.9378531073446328,
|
| 588 |
+
"grad_norm": 0.9618987441062927,
|
| 589 |
+
"learning_rate": 2.4743140351822117e-05,
|
| 590 |
+
"loss": 0.7121,
|
| 591 |
+
"step": 415
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.9491525423728814,
|
| 595 |
+
"grad_norm": 0.8377029895782471,
|
| 596 |
+
"learning_rate": 2.4600434159693922e-05,
|
| 597 |
+
"loss": 0.7176,
|
| 598 |
+
"step": 420
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.96045197740113,
|
| 602 |
+
"grad_norm": 0.8737752437591553,
|
| 603 |
+
"learning_rate": 2.4456240641083026e-05,
|
| 604 |
+
"loss": 0.6456,
|
| 605 |
+
"step": 425
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.9717514124293786,
|
| 609 |
+
"grad_norm": 0.8436824083328247,
|
| 610 |
+
"learning_rate": 2.431058213485821e-05,
|
| 611 |
+
"loss": 0.7042,
|
| 612 |
+
"step": 430
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.9830508474576272,
|
| 616 |
+
"grad_norm": 0.9141050577163696,
|
| 617 |
+
"learning_rate": 2.4163481206848276e-05,
|
| 618 |
+
"loss": 0.6907,
|
| 619 |
+
"step": 435
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.9943502824858758,
|
| 623 |
+
"grad_norm": 0.9013184309005737,
|
| 624 |
+
"learning_rate": 2.4014960646346112e-05,
|
| 625 |
+
"loss": 0.7133,
|
| 626 |
+
"step": 440
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.0045197740112994,
|
| 630 |
+
"grad_norm": 0.8982263207435608,
|
| 631 |
+
"learning_rate": 2.386504346257808e-05,
|
| 632 |
+
"loss": 0.6462,
|
| 633 |
+
"step": 445
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.015819209039548,
|
| 637 |
+
"grad_norm": 1.030466079711914,
|
| 638 |
+
"learning_rate": 2.37137528811394e-05,
|
| 639 |
+
"loss": 0.6005,
|
| 640 |
+
"step": 450
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.0271186440677966,
|
| 644 |
+
"grad_norm": 0.9753005504608154,
|
| 645 |
+
"learning_rate": 2.356111234039594e-05,
|
| 646 |
+
"loss": 0.5533,
|
| 647 |
+
"step": 455
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.038418079096045,
|
| 651 |
+
"grad_norm": 0.9078965187072754,
|
| 652 |
+
"learning_rate": 2.34071454878531e-05,
|
| 653 |
+
"loss": 0.607,
|
| 654 |
+
"step": 460
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.0497175141242938,
|
| 658 |
+
"grad_norm": 0.9584876298904419,
|
| 659 |
+
"learning_rate": 2.325187617649225e-05,
|
| 660 |
+
"loss": 0.5682,
|
| 661 |
+
"step": 465
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.0610169491525423,
|
| 665 |
+
"grad_norm": 0.9169408679008484,
|
| 666 |
+
"learning_rate": 2.3095328461075387e-05,
|
| 667 |
+
"loss": 0.574,
|
| 668 |
+
"step": 470
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.072316384180791,
|
| 672 |
+
"grad_norm": 1.0348643064498901,
|
| 673 |
+
"learning_rate": 2.2937526594418482e-05,
|
| 674 |
+
"loss": 0.5554,
|
| 675 |
+
"step": 475
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.0836158192090395,
|
| 679 |
+
"grad_norm": 0.9443817734718323,
|
| 680 |
+
"learning_rate": 2.277849502363418e-05,
|
| 681 |
+
"loss": 0.5769,
|
| 682 |
+
"step": 480
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.0949152542372882,
|
| 686 |
+
"grad_norm": 0.8611088395118713,
|
| 687 |
+
"learning_rate": 2.2618258386344367e-05,
|
| 688 |
+
"loss": 0.5382,
|
| 689 |
+
"step": 485
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.1062146892655367,
|
| 693 |
+
"grad_norm": 1.0105209350585938,
|
| 694 |
+
"learning_rate": 2.2456841506863262e-05,
|
| 695 |
+
"loss": 0.5967,
|
| 696 |
+
"step": 490
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.1175141242937854,
|
| 700 |
+
"grad_norm": 0.9772942066192627,
|
| 701 |
+
"learning_rate": 2.2294269392351532e-05,
|
| 702 |
+
"loss": 0.5982,
|
| 703 |
+
"step": 495
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.1288135593220339,
|
| 707 |
+
"grad_norm": 0.9487956166267395,
|
| 708 |
+
"learning_rate": 2.213056722894215e-05,
|
| 709 |
+
"loss": 0.5429,
|
| 710 |
+
"step": 500
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.1401129943502826,
|
| 714 |
+
"grad_norm": 1.0030889511108398,
|
| 715 |
+
"learning_rate": 2.1965760377838453e-05,
|
| 716 |
+
"loss": 0.5695,
|
| 717 |
+
"step": 505
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.151412429378531,
|
| 721 |
+
"grad_norm": 1.0144139528274536,
|
| 722 |
+
"learning_rate": 2.179987437138514e-05,
|
| 723 |
+
"loss": 0.5647,
|
| 724 |
+
"step": 510
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.1627118644067798,
|
| 728 |
+
"grad_norm": 1.02457594871521,
|
| 729 |
+
"learning_rate": 2.163293490911271e-05,
|
| 730 |
+
"loss": 0.5168,
|
| 731 |
+
"step": 515
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.1740112994350282,
|
| 735 |
+
"grad_norm": 1.013403058052063,
|
| 736 |
+
"learning_rate": 2.1464967853756026e-05,
|
| 737 |
+
"loss": 0.5401,
|
| 738 |
+
"step": 520
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.1853107344632767,
|
| 742 |
+
"grad_norm": 1.1431137323379517,
|
| 743 |
+
"learning_rate": 2.1295999227247584e-05,
|
| 744 |
+
"loss": 0.5688,
|
| 745 |
+
"step": 525
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.1966101694915254,
|
| 749 |
+
"grad_norm": 0.9857562184333801,
|
| 750 |
+
"learning_rate": 2.1126055206686127e-05,
|
| 751 |
+
"loss": 0.601,
|
| 752 |
+
"step": 530
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.207909604519774,
|
| 756 |
+
"grad_norm": 0.9799157977104187,
|
| 757 |
+
"learning_rate": 2.095516212028121e-05,
|
| 758 |
+
"loss": 0.5569,
|
| 759 |
+
"step": 535
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.2192090395480226,
|
| 763 |
+
"grad_norm": 0.9711302518844604,
|
| 764 |
+
"learning_rate": 2.078334644327435e-05,
|
| 765 |
+
"loss": 0.4992,
|
| 766 |
+
"step": 540
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.230508474576271,
|
| 770 |
+
"grad_norm": 0.9672480225563049,
|
| 771 |
+
"learning_rate": 2.0610634793837433e-05,
|
| 772 |
+
"loss": 0.5272,
|
| 773 |
+
"step": 545
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.2418079096045198,
|
| 777 |
+
"grad_norm": 1.1377589702606201,
|
| 778 |
+
"learning_rate": 2.043705392894892e-05,
|
| 779 |
+
"loss": 0.5075,
|
| 780 |
+
"step": 550
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.2531073446327683,
|
| 784 |
+
"grad_norm": 0.9882428050041199,
|
| 785 |
+
"learning_rate": 2.0262630740248605e-05,
|
| 786 |
+
"loss": 0.5312,
|
| 787 |
+
"step": 555
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.264406779661017,
|
| 791 |
+
"grad_norm": 1.0094331502914429,
|
| 792 |
+
"learning_rate": 2.0087392249871465e-05,
|
| 793 |
+
"loss": 0.553,
|
| 794 |
+
"step": 560
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.2757062146892655,
|
| 798 |
+
"grad_norm": 1.0151430368423462,
|
| 799 |
+
"learning_rate": 1.991136560626133e-05,
|
| 800 |
+
"loss": 0.5189,
|
| 801 |
+
"step": 565
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.2870056497175142,
|
| 805 |
+
"grad_norm": 0.9799350500106812,
|
| 806 |
+
"learning_rate": 1.9734578079964964e-05,
|
| 807 |
+
"loss": 0.5491,
|
| 808 |
+
"step": 570
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.2983050847457627,
|
| 812 |
+
"grad_norm": 1.0021573305130005,
|
| 813 |
+
"learning_rate": 1.9557057059407234e-05,
|
| 814 |
+
"loss": 0.5067,
|
| 815 |
+
"step": 575
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.3096045197740114,
|
| 819 |
+
"grad_norm": 0.9888397455215454,
|
| 820 |
+
"learning_rate": 1.937883004664802e-05,
|
| 821 |
+
"loss": 0.5153,
|
| 822 |
+
"step": 580
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.3209039548022599,
|
| 826 |
+
"grad_norm": 1.0663667917251587,
|
| 827 |
+
"learning_rate": 1.919992465312151e-05,
|
| 828 |
+
"loss": 0.5531,
|
| 829 |
+
"step": 585
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.3322033898305086,
|
| 833 |
+
"grad_norm": 0.9768710136413574,
|
| 834 |
+
"learning_rate": 1.902036859535857e-05,
|
| 835 |
+
"loss": 0.4747,
|
| 836 |
+
"step": 590
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.343502824858757,
|
| 840 |
+
"grad_norm": 0.9723271727561951,
|
| 841 |
+
"learning_rate": 1.8840189690692813e-05,
|
| 842 |
+
"loss": 0.5362,
|
| 843 |
+
"step": 595
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.3548022598870055,
|
| 847 |
+
"grad_norm": 1.0646779537200928,
|
| 848 |
+
"learning_rate": 1.8659415852951055e-05,
|
| 849 |
+
"loss": 0.5132,
|
| 850 |
+
"step": 600
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.3661016949152542,
|
| 854 |
+
"grad_norm": 0.9773317575454712,
|
| 855 |
+
"learning_rate": 1.8478075088128835e-05,
|
| 856 |
+
"loss": 0.4878,
|
| 857 |
+
"step": 605
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.377401129943503,
|
| 861 |
+
"grad_norm": 1.1835554838180542,
|
| 862 |
+
"learning_rate": 1.829619549005165e-05,
|
| 863 |
+
"loss": 0.5072,
|
| 864 |
+
"step": 610
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.3887005649717514,
|
| 868 |
+
"grad_norm": 0.9552049040794373,
|
| 869 |
+
"learning_rate": 1.8113805236022562e-05,
|
| 870 |
+
"loss": 0.4588,
|
| 871 |
+
"step": 615
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.4,
|
| 875 |
+
"grad_norm": 1.1068223714828491,
|
| 876 |
+
"learning_rate": 1.79309325824569e-05,
|
| 877 |
+
"loss": 0.4878,
|
| 878 |
+
"step": 620
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.4112994350282486,
|
| 882 |
+
"grad_norm": 1.0641181468963623,
|
| 883 |
+
"learning_rate": 1.774760586050471e-05,
|
| 884 |
+
"loss": 0.4694,
|
| 885 |
+
"step": 625
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.422598870056497,
|
| 889 |
+
"grad_norm": 1.185801386833191,
|
| 890 |
+
"learning_rate": 1.7563853471661587e-05,
|
| 891 |
+
"loss": 0.4976,
|
| 892 |
+
"step": 630
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 1.4338983050847458,
|
| 896 |
+
"grad_norm": 1.0717343091964722,
|
| 897 |
+
"learning_rate": 1.7379703883368655e-05,
|
| 898 |
+
"loss": 0.494,
|
| 899 |
+
"step": 635
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 1.4451977401129943,
|
| 903 |
+
"grad_norm": 0.9612589478492737,
|
| 904 |
+
"learning_rate": 1.7195185624602305e-05,
|
| 905 |
+
"loss": 0.4955,
|
| 906 |
+
"step": 640
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.456497175141243,
|
| 910 |
+
"grad_norm": 0.9304859638214111,
|
| 911 |
+
"learning_rate": 1.701032728145439e-05,
|
| 912 |
+
"loss": 0.4477,
|
| 913 |
+
"step": 645
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.4677966101694915,
|
| 917 |
+
"grad_norm": 1.0756772756576538,
|
| 918 |
+
"learning_rate": 1.6825157492703617e-05,
|
| 919 |
+
"loss": 0.5038,
|
| 920 |
+
"step": 650
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.4790960451977402,
|
| 924 |
+
"grad_norm": 1.153087854385376,
|
| 925 |
+
"learning_rate": 1.6639704945378714e-05,
|
| 926 |
+
"loss": 0.5029,
|
| 927 |
+
"step": 655
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.4903954802259887,
|
| 931 |
+
"grad_norm": 1.1517761945724487,
|
| 932 |
+
"learning_rate": 1.645399837031418e-05,
|
| 933 |
+
"loss": 0.4531,
|
| 934 |
+
"step": 660
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.5016949152542374,
|
| 938 |
+
"grad_norm": 1.0546455383300781,
|
| 939 |
+
"learning_rate": 1.6268066537699206e-05,
|
| 940 |
+
"loss": 0.4492,
|
| 941 |
+
"step": 665
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.5129943502824859,
|
| 945 |
+
"grad_norm": 1.0537352561950684,
|
| 946 |
+
"learning_rate": 1.608193825262053e-05,
|
| 947 |
+
"loss": 0.464,
|
| 948 |
+
"step": 670
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 1.5242937853107343,
|
| 952 |
+
"grad_norm": 1.025883674621582,
|
| 953 |
+
"learning_rate": 1.5895642350599838e-05,
|
| 954 |
+
"loss": 0.4509,
|
| 955 |
+
"step": 675
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.535593220338983,
|
| 959 |
+
"grad_norm": 0.985380232334137,
|
| 960 |
+
"learning_rate": 1.5709207693126543e-05,
|
| 961 |
+
"loss": 0.4999,
|
| 962 |
+
"step": 680
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.5468926553672318,
|
| 966 |
+
"grad_norm": 1.1545135974884033,
|
| 967 |
+
"learning_rate": 1.5522663163186422e-05,
|
| 968 |
+
"loss": 0.4544,
|
| 969 |
+
"step": 685
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.5581920903954802,
|
| 973 |
+
"grad_norm": 1.1191048622131348,
|
| 974 |
+
"learning_rate": 1.5336037660787012e-05,
|
| 975 |
+
"loss": 0.4344,
|
| 976 |
+
"step": 690
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.5694915254237287,
|
| 980 |
+
"grad_norm": 1.0922521352767944,
|
| 981 |
+
"learning_rate": 1.5149360098480341e-05,
|
| 982 |
+
"loss": 0.4363,
|
| 983 |
+
"step": 695
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.5807909604519774,
|
| 987 |
+
"grad_norm": 1.0418857336044312,
|
| 988 |
+
"learning_rate": 1.4962659396883689e-05,
|
| 989 |
+
"loss": 0.4243,
|
| 990 |
+
"step": 700
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.5920903954802261,
|
| 994 |
+
"grad_norm": 1.130102276802063,
|
| 995 |
+
"learning_rate": 1.4775964480199151e-05,
|
| 996 |
+
"loss": 0.428,
|
| 997 |
+
"step": 705
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 1.6033898305084746,
|
| 1001 |
+
"grad_norm": 1.1816492080688477,
|
| 1002 |
+
"learning_rate": 1.458930427173261e-05,
|
| 1003 |
+
"loss": 0.4471,
|
| 1004 |
+
"step": 710
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.614689265536723,
|
| 1008 |
+
"grad_norm": 1.117671012878418,
|
| 1009 |
+
"learning_rate": 1.4402707689412851e-05,
|
| 1010 |
+
"loss": 0.4556,
|
| 1011 |
+
"step": 715
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 1.6259887005649718,
|
| 1015 |
+
"grad_norm": 0.9830794334411621,
|
| 1016 |
+
"learning_rate": 1.4216203641311507e-05,
|
| 1017 |
+
"loss": 0.4512,
|
| 1018 |
+
"step": 720
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.6372881355932203,
|
| 1022 |
+
"grad_norm": 1.1071224212646484,
|
| 1023 |
+
"learning_rate": 1.4029821021164558e-05,
|
| 1024 |
+
"loss": 0.4743,
|
| 1025 |
+
"step": 725
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 1.6485875706214688,
|
| 1029 |
+
"grad_norm": 1.240033507347107,
|
| 1030 |
+
"learning_rate": 1.384358870389602e-05,
|
| 1031 |
+
"loss": 0.4303,
|
| 1032 |
+
"step": 730
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 1.6598870056497175,
|
| 1036 |
+
"grad_norm": 0.9482849836349487,
|
| 1037 |
+
"learning_rate": 1.3657535541144559e-05,
|
| 1038 |
+
"loss": 0.4497,
|
| 1039 |
+
"step": 735
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 1.6711864406779662,
|
| 1043 |
+
"grad_norm": 1.1365591287612915,
|
| 1044 |
+
"learning_rate": 1.3471690356793709e-05,
|
| 1045 |
+
"loss": 0.435,
|
| 1046 |
+
"step": 740
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.6824858757062147,
|
| 1050 |
+
"grad_norm": 1.2575817108154297,
|
| 1051 |
+
"learning_rate": 1.328608194250641e-05,
|
| 1052 |
+
"loss": 0.4612,
|
| 1053 |
+
"step": 745
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 1.6937853107344631,
|
| 1057 |
+
"grad_norm": 1.0304065942764282,
|
| 1058 |
+
"learning_rate": 1.3100739053264506e-05,
|
| 1059 |
+
"loss": 0.4566,
|
| 1060 |
+
"step": 750
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 1.7050847457627119,
|
| 1064 |
+
"grad_norm": 1.1461726427078247,
|
| 1065 |
+
"learning_rate": 1.2915690402913957e-05,
|
| 1066 |
+
"loss": 0.4565,
|
| 1067 |
+
"step": 755
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 1.7163841807909606,
|
| 1071 |
+
"grad_norm": 1.08915114402771,
|
| 1072 |
+
"learning_rate": 1.2730964659716387e-05,
|
| 1073 |
+
"loss": 0.4333,
|
| 1074 |
+
"step": 760
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.727683615819209,
|
| 1078 |
+
"grad_norm": 1.1089566946029663,
|
| 1079 |
+
"learning_rate": 1.2546590441907736e-05,
|
| 1080 |
+
"loss": 0.3888,
|
| 1081 |
+
"step": 765
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 1.7389830508474575,
|
| 1085 |
+
"grad_norm": 1.203813076019287,
|
| 1086 |
+
"learning_rate": 1.236259631326463e-05,
|
| 1087 |
+
"loss": 0.4167,
|
| 1088 |
+
"step": 770
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 1.7502824858757062,
|
| 1092 |
+
"grad_norm": 1.073231816291809,
|
| 1093 |
+
"learning_rate": 1.2179010778679217e-05,
|
| 1094 |
+
"loss": 0.4027,
|
| 1095 |
+
"step": 775
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 1.761581920903955,
|
| 1099 |
+
"grad_norm": 0.9994603991508484,
|
| 1100 |
+
"learning_rate": 1.1995862279743069e-05,
|
| 1101 |
+
"loss": 0.4048,
|
| 1102 |
+
"step": 780
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 1.7728813559322034,
|
| 1106 |
+
"grad_norm": 1.242895483970642,
|
| 1107 |
+
"learning_rate": 1.181317919034098e-05,
|
| 1108 |
+
"loss": 0.3919,
|
| 1109 |
+
"step": 785
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 1.784180790960452,
|
| 1113 |
+
"grad_norm": 1.0206263065338135,
|
| 1114 |
+
"learning_rate": 1.1630989812255171e-05,
|
| 1115 |
+
"loss": 0.4568,
|
| 1116 |
+
"step": 790
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 1.7954802259887006,
|
| 1120 |
+
"grad_norm": 1.2044389247894287,
|
| 1121 |
+
"learning_rate": 1.1449322370780701e-05,
|
| 1122 |
+
"loss": 0.3924,
|
| 1123 |
+
"step": 795
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 1.8067796610169493,
|
| 1127 |
+
"grad_norm": 1.02643620967865,
|
| 1128 |
+
"learning_rate": 1.1268205010352735e-05,
|
| 1129 |
+
"loss": 0.3948,
|
| 1130 |
+
"step": 800
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 1.8180790960451978,
|
| 1134 |
+
"grad_norm": 1.060969352722168,
|
| 1135 |
+
"learning_rate": 1.1087665790186316e-05,
|
| 1136 |
+
"loss": 0.4183,
|
| 1137 |
+
"step": 805
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 1.8293785310734463,
|
| 1141 |
+
"grad_norm": 1.0182231664657593,
|
| 1142 |
+
"learning_rate": 1.0907732679929378e-05,
|
| 1143 |
+
"loss": 0.3891,
|
| 1144 |
+
"step": 810
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 1.840677966101695,
|
| 1148 |
+
"grad_norm": 1.3241688013076782,
|
| 1149 |
+
"learning_rate": 1.072843355532956e-05,
|
| 1150 |
+
"loss": 0.3778,
|
| 1151 |
+
"step": 815
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.8519774011299435,
|
| 1155 |
+
"grad_norm": 1.1447961330413818,
|
| 1156 |
+
"learning_rate": 1.0549796193915667e-05,
|
| 1157 |
+
"loss": 0.3966,
|
| 1158 |
+
"step": 820
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 1.863276836158192,
|
| 1162 |
+
"grad_norm": 1.1509546041488647,
|
| 1163 |
+
"learning_rate": 1.0371848270694263e-05,
|
| 1164 |
+
"loss": 0.4385,
|
| 1165 |
+
"step": 825
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 1.8745762711864407,
|
| 1169 |
+
"grad_norm": 1.2081464529037476,
|
| 1170 |
+
"learning_rate": 1.0194617353862204e-05,
|
| 1171 |
+
"loss": 0.3876,
|
| 1172 |
+
"step": 830
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 1.8858757062146894,
|
| 1176 |
+
"grad_norm": 1.0531032085418701,
|
| 1177 |
+
"learning_rate": 1.001813090053567e-05,
|
| 1178 |
+
"loss": 0.4254,
|
| 1179 |
+
"step": 835
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 1.8971751412429378,
|
| 1183 |
+
"grad_norm": 1.1229294538497925,
|
| 1184 |
+
"learning_rate": 9.842416252496449e-06,
|
| 1185 |
+
"loss": 0.3989,
|
| 1186 |
+
"step": 840
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 1.9084745762711863,
|
| 1190 |
+
"grad_norm": 1.1701585054397583,
|
| 1191 |
+
"learning_rate": 9.667500631956068e-06,
|
| 1192 |
+
"loss": 0.3722,
|
| 1193 |
+
"step": 845
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 1.919774011299435,
|
| 1197 |
+
"grad_norm": 1.0944764614105225,
|
| 1198 |
+
"learning_rate": 9.493411137338449e-06,
|
| 1199 |
+
"loss": 0.3878,
|
| 1200 |
+
"step": 850
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 1.9310734463276837,
|
| 1204 |
+
"grad_norm": 1.0983238220214844,
|
| 1205 |
+
"learning_rate": 9.320174739081734e-06,
|
| 1206 |
+
"loss": 0.3966,
|
| 1207 |
+
"step": 855
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 1.9423728813559322,
|
| 1211 |
+
"grad_norm": 1.1566952466964722,
|
| 1212 |
+
"learning_rate": 9.147818275459966e-06,
|
| 1213 |
+
"loss": 0.4071,
|
| 1214 |
+
"step": 860
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 1.9536723163841807,
|
| 1218 |
+
"grad_norm": 1.2071325778961182,
|
| 1219 |
+
"learning_rate": 8.97636844842522e-06,
|
| 1220 |
+
"loss": 0.3861,
|
| 1221 |
+
"step": 865
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 1.9649717514124294,
|
| 1225 |
+
"grad_norm": 1.457877516746521,
|
| 1226 |
+
"learning_rate": 8.805851819470862e-06,
|
| 1227 |
+
"loss": 0.4133,
|
| 1228 |
+
"step": 870
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 1.9762711864406781,
|
| 1232 |
+
"grad_norm": 1.1521238088607788,
|
| 1233 |
+
"learning_rate": 8.63629480551655e-06,
|
| 1234 |
+
"loss": 0.3448,
|
| 1235 |
+
"step": 875
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 1.9875706214689266,
|
| 1239 |
+
"grad_norm": 1.0822957754135132,
|
| 1240 |
+
"learning_rate": 8.467723674815689e-06,
|
| 1241 |
+
"loss": 0.3655,
|
| 1242 |
+
"step": 880
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 1.998870056497175,
|
| 1246 |
+
"grad_norm": 1.1210577487945557,
|
| 1247 |
+
"learning_rate": 8.300164542885836e-06,
|
| 1248 |
+
"loss": 0.4021,
|
| 1249 |
+
"step": 885
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 2.009039548022599,
|
| 1253 |
+
"grad_norm": 1.1246051788330078,
|
| 1254 |
+
"learning_rate": 8.133643368462827e-06,
|
| 1255 |
+
"loss": 0.2939,
|
| 1256 |
+
"step": 890
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 2.0203389830508476,
|
| 1260 |
+
"grad_norm": 1.225960612297058,
|
| 1261 |
+
"learning_rate": 7.9681859494792e-06,
|
| 1262 |
+
"loss": 0.2968,
|
| 1263 |
+
"step": 895
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 2.031638418079096,
|
| 1267 |
+
"grad_norm": 1.1250094175338745,
|
| 1268 |
+
"learning_rate": 7.803817919067456e-06,
|
| 1269 |
+
"loss": 0.3429,
|
| 1270 |
+
"step": 900
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 2.0429378531073445,
|
| 1274 |
+
"grad_norm": 1.1910196542739868,
|
| 1275 |
+
"learning_rate": 7.640564741588954e-06,
|
| 1276 |
+
"loss": 0.2955,
|
| 1277 |
+
"step": 905
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 2.0542372881355933,
|
| 1281 |
+
"grad_norm": 1.0813297033309937,
|
| 1282 |
+
"learning_rate": 7.478451708688861e-06,
|
| 1283 |
+
"loss": 0.3167,
|
| 1284 |
+
"step": 910
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 2.065536723163842,
|
| 1288 |
+
"grad_norm": 1.1154721975326538,
|
| 1289 |
+
"learning_rate": 7.317503935377909e-06,
|
| 1290 |
+
"loss": 0.2829,
|
| 1291 |
+
"step": 915
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 2.07683615819209,
|
| 1295 |
+
"grad_norm": 1.0373843908309937,
|
| 1296 |
+
"learning_rate": 7.15774635614153e-06,
|
| 1297 |
+
"loss": 0.2975,
|
| 1298 |
+
"step": 920
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 2.088135593220339,
|
| 1302 |
+
"grad_norm": 1.148111343383789,
|
| 1303 |
+
"learning_rate": 6.999203721076896e-06,
|
| 1304 |
+
"loss": 0.3146,
|
| 1305 |
+
"step": 925
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 2.0994350282485876,
|
| 1309 |
+
"grad_norm": 1.0868595838546753,
|
| 1310 |
+
"learning_rate": 6.841900592058584e-06,
|
| 1311 |
+
"loss": 0.3014,
|
| 1312 |
+
"step": 930
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 2.1107344632768363,
|
| 1316 |
+
"grad_norm": 1.0902693271636963,
|
| 1317 |
+
"learning_rate": 6.685861338933398e-06,
|
| 1318 |
+
"loss": 0.2791,
|
| 1319 |
+
"step": 935
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 2.1220338983050846,
|
| 1323 |
+
"grad_norm": 1.2496689558029175,
|
| 1324 |
+
"learning_rate": 6.531110135744879e-06,
|
| 1325 |
+
"loss": 0.3139,
|
| 1326 |
+
"step": 940
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 2.1333333333333333,
|
| 1330 |
+
"grad_norm": 1.204729676246643,
|
| 1331 |
+
"learning_rate": 6.377670956988244e-06,
|
| 1332 |
+
"loss": 0.326,
|
| 1333 |
+
"step": 945
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 2.144632768361582,
|
| 1337 |
+
"grad_norm": 1.1265090703964233,
|
| 1338 |
+
"learning_rate": 6.2255675738961475e-06,
|
| 1339 |
+
"loss": 0.2874,
|
| 1340 |
+
"step": 950
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 2.1559322033898307,
|
| 1344 |
+
"grad_norm": 1.2344650030136108,
|
| 1345 |
+
"learning_rate": 6.074823550755993e-06,
|
| 1346 |
+
"loss": 0.3135,
|
| 1347 |
+
"step": 955
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 2.167231638418079,
|
| 1351 |
+
"grad_norm": 1.1562491655349731,
|
| 1352 |
+
"learning_rate": 5.9254622412593e-06,
|
| 1353 |
+
"loss": 0.3208,
|
| 1354 |
+
"step": 960
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 2.1785310734463277,
|
| 1358 |
+
"grad_norm": 1.0815485715866089,
|
| 1359 |
+
"learning_rate": 5.777506784883655e-06,
|
| 1360 |
+
"loss": 0.2856,
|
| 1361 |
+
"step": 965
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 2.1898305084745764,
|
| 1365 |
+
"grad_norm": 1.126382827758789,
|
| 1366 |
+
"learning_rate": 5.630980103307891e-06,
|
| 1367 |
+
"loss": 0.3128,
|
| 1368 |
+
"step": 970
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 2.201129943502825,
|
| 1372 |
+
"grad_norm": 1.2667649984359741,
|
| 1373 |
+
"learning_rate": 5.485904896861015e-06,
|
| 1374 |
+
"loss": 0.2767,
|
| 1375 |
+
"step": 975
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 2.2124293785310734,
|
| 1379 |
+
"grad_norm": 1.2229074239730835,
|
| 1380 |
+
"learning_rate": 5.342303641005371e-06,
|
| 1381 |
+
"loss": 0.3196,
|
| 1382 |
+
"step": 980
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 2.223728813559322,
|
| 1386 |
+
"grad_norm": 1.1595052480697632,
|
| 1387 |
+
"learning_rate": 5.200198582854717e-06,
|
| 1388 |
+
"loss": 0.2785,
|
| 1389 |
+
"step": 985
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 2.2350282485875708,
|
| 1393 |
+
"grad_norm": 1.0601240396499634,
|
| 1394 |
+
"learning_rate": 5.059611737727603e-06,
|
| 1395 |
+
"loss": 0.2716,
|
| 1396 |
+
"step": 990
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 2.246327683615819,
|
| 1400 |
+
"grad_norm": 1.0637054443359375,
|
| 1401 |
+
"learning_rate": 4.920564885736718e-06,
|
| 1402 |
+
"loss": 0.2993,
|
| 1403 |
+
"step": 995
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 2.2576271186440677,
|
| 1407 |
+
"grad_norm": 1.0439788103103638,
|
| 1408 |
+
"learning_rate": 4.783079568414657e-06,
|
| 1409 |
+
"loss": 0.279,
|
| 1410 |
+
"step": 1000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 2.2689265536723164,
|
| 1414 |
+
"grad_norm": 1.1727694272994995,
|
| 1415 |
+
"learning_rate": 4.647177085376624e-06,
|
| 1416 |
+
"loss": 0.3081,
|
| 1417 |
+
"step": 1005
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 2.280225988700565,
|
| 1421 |
+
"grad_norm": 1.1366053819656372,
|
| 1422 |
+
"learning_rate": 4.512878491020646e-06,
|
| 1423 |
+
"loss": 0.3132,
|
| 1424 |
+
"step": 1010
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 2.2915254237288134,
|
| 1428 |
+
"grad_norm": 1.1635701656341553,
|
| 1429 |
+
"learning_rate": 4.380204591265785e-06,
|
| 1430 |
+
"loss": 0.2881,
|
| 1431 |
+
"step": 1015
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 2.302824858757062,
|
| 1435 |
+
"grad_norm": 1.103509545326233,
|
| 1436 |
+
"learning_rate": 4.249175940328786e-06,
|
| 1437 |
+
"loss": 0.2832,
|
| 1438 |
+
"step": 1020
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 2.314124293785311,
|
| 1442 |
+
"grad_norm": 1.0600485801696777,
|
| 1443 |
+
"learning_rate": 4.119812837539803e-06,
|
| 1444 |
+
"loss": 0.2906,
|
| 1445 |
+
"step": 1025
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 2.3254237288135595,
|
| 1449 |
+
"grad_norm": 1.2363098859786987,
|
| 1450 |
+
"learning_rate": 3.992135324197531e-06,
|
| 1451 |
+
"loss": 0.2769,
|
| 1452 |
+
"step": 1030
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 2.336723163841808,
|
| 1456 |
+
"grad_norm": 1.129071593284607,
|
| 1457 |
+
"learning_rate": 3.866163180464373e-06,
|
| 1458 |
+
"loss": 0.2879,
|
| 1459 |
+
"step": 1035
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 2.3480225988700565,
|
| 1463 |
+
"grad_norm": 1.09531569480896,
|
| 1464 |
+
"learning_rate": 3.7419159223020474e-06,
|
| 1465 |
+
"loss": 0.2866,
|
| 1466 |
+
"step": 1040
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 2.359322033898305,
|
| 1470 |
+
"grad_norm": 1.4555847644805908,
|
| 1471 |
+
"learning_rate": 3.6194127984480902e-06,
|
| 1472 |
+
"loss": 0.2842,
|
| 1473 |
+
"step": 1045
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 2.3706214689265535,
|
| 1477 |
+
"grad_norm": 1.0226173400878906,
|
| 1478 |
+
"learning_rate": 3.4986727874338237e-06,
|
| 1479 |
+
"loss": 0.2934,
|
| 1480 |
+
"step": 1050
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 2.381920903954802,
|
| 1484 |
+
"grad_norm": 1.2312229871749878,
|
| 1485 |
+
"learning_rate": 3.379714594644117e-06,
|
| 1486 |
+
"loss": 0.3012,
|
| 1487 |
+
"step": 1055
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 2.393220338983051,
|
| 1491 |
+
"grad_norm": 1.1659260988235474,
|
| 1492 |
+
"learning_rate": 3.262556649419506e-06,
|
| 1493 |
+
"loss": 0.3003,
|
| 1494 |
+
"step": 1060
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 2.4045197740112996,
|
| 1498 |
+
"grad_norm": 1.136291265487671,
|
| 1499 |
+
"learning_rate": 3.147217102201085e-06,
|
| 1500 |
+
"loss": 0.2605,
|
| 1501 |
+
"step": 1065
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 2.415819209039548,
|
| 1505 |
+
"grad_norm": 1.0087354183197021,
|
| 1506 |
+
"learning_rate": 3.033713821718553e-06,
|
| 1507 |
+
"loss": 0.2504,
|
| 1508 |
+
"step": 1070
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 2.4271186440677965,
|
| 1512 |
+
"grad_norm": 1.133941888809204,
|
| 1513 |
+
"learning_rate": 2.922064392221969e-06,
|
| 1514 |
+
"loss": 0.2725,
|
| 1515 |
+
"step": 1075
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 2.4384180790960452,
|
| 1519 |
+
"grad_norm": 1.248903512954712,
|
| 1520 |
+
"learning_rate": 2.8122861107575477e-06,
|
| 1521 |
+
"loss": 0.2942,
|
| 1522 |
+
"step": 1080
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 2.449717514124294,
|
| 1526 |
+
"grad_norm": 1.1069386005401611,
|
| 1527 |
+
"learning_rate": 2.7043959844879267e-06,
|
| 1528 |
+
"loss": 0.2797,
|
| 1529 |
+
"step": 1085
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 2.461016949152542,
|
| 1533 |
+
"grad_norm": 1.0444649457931519,
|
| 1534 |
+
"learning_rate": 2.598410728057407e-06,
|
| 1535 |
+
"loss": 0.2923,
|
| 1536 |
+
"step": 1090
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 2.472316384180791,
|
| 1540 |
+
"grad_norm": 1.1024730205535889,
|
| 1541 |
+
"learning_rate": 2.494346761002439e-06,
|
| 1542 |
+
"loss": 0.2655,
|
| 1543 |
+
"step": 1095
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 2.4836158192090396,
|
| 1547 |
+
"grad_norm": 1.271557331085205,
|
| 1548 |
+
"learning_rate": 2.3922202052078764e-06,
|
| 1549 |
+
"loss": 0.2924,
|
| 1550 |
+
"step": 1100
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 2.4949152542372883,
|
| 1554 |
+
"grad_norm": 1.158363699913025,
|
| 1555 |
+
"learning_rate": 2.292046882409337e-06,
|
| 1556 |
+
"loss": 0.2657,
|
| 1557 |
+
"step": 1105
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 2.5062146892655366,
|
| 1561 |
+
"grad_norm": 1.0947177410125732,
|
| 1562 |
+
"learning_rate": 2.1938423117420304e-06,
|
| 1563 |
+
"loss": 0.264,
|
| 1564 |
+
"step": 1110
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 2.5175141242937853,
|
| 1568 |
+
"grad_norm": 1.267616868019104,
|
| 1569 |
+
"learning_rate": 2.0976217073365094e-06,
|
| 1570 |
+
"loss": 0.2796,
|
| 1571 |
+
"step": 1115
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 2.528813559322034,
|
| 1575 |
+
"grad_norm": 0.9850753545761108,
|
| 1576 |
+
"learning_rate": 2.0033999759616557e-06,
|
| 1577 |
+
"loss": 0.3079,
|
| 1578 |
+
"step": 1120
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 2.5401129943502827,
|
| 1582 |
+
"grad_norm": 1.1006895303726196,
|
| 1583 |
+
"learning_rate": 1.9111917147152573e-06,
|
| 1584 |
+
"loss": 0.3087,
|
| 1585 |
+
"step": 1125
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 2.551412429378531,
|
| 1589 |
+
"grad_norm": 1.4215548038482666,
|
| 1590 |
+
"learning_rate": 1.8210112087626174e-06,
|
| 1591 |
+
"loss": 0.2889,
|
| 1592 |
+
"step": 1130
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 2.5627118644067797,
|
| 1596 |
+
"grad_norm": 1.1595913171768188,
|
| 1597 |
+
"learning_rate": 1.7328724291234267e-06,
|
| 1598 |
+
"loss": 0.2783,
|
| 1599 |
+
"step": 1135
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 2.5740112994350284,
|
| 1603 |
+
"grad_norm": 1.1364566087722778,
|
| 1604 |
+
"learning_rate": 1.646789030507348e-06,
|
| 1605 |
+
"loss": 0.2854,
|
| 1606 |
+
"step": 1140
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 2.5853107344632766,
|
| 1610 |
+
"grad_norm": 1.0633364915847778,
|
| 1611 |
+
"learning_rate": 1.562774349198597e-06,
|
| 1612 |
+
"loss": 0.2833,
|
| 1613 |
+
"step": 1145
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 2.5966101694915253,
|
| 1617 |
+
"grad_norm": 1.0371564626693726,
|
| 1618 |
+
"learning_rate": 1.4808414009898236e-06,
|
| 1619 |
+
"loss": 0.258,
|
| 1620 |
+
"step": 1150
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 2.607909604519774,
|
| 1624 |
+
"grad_norm": 0.9083572626113892,
|
| 1625 |
+
"learning_rate": 1.4010028791656932e-06,
|
| 1626 |
+
"loss": 0.2591,
|
| 1627 |
+
"step": 1155
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 2.6192090395480228,
|
| 1631 |
+
"grad_norm": 1.1071724891662598,
|
| 1632 |
+
"learning_rate": 1.3232711525364e-06,
|
| 1633 |
+
"loss": 0.263,
|
| 1634 |
+
"step": 1160
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 2.6305084745762715,
|
| 1638 |
+
"grad_norm": 1.0949277877807617,
|
| 1639 |
+
"learning_rate": 1.2476582635214422e-06,
|
| 1640 |
+
"loss": 0.3076,
|
| 1641 |
+
"step": 1165
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 2.6418079096045197,
|
| 1645 |
+
"grad_norm": 1.021916151046753,
|
| 1646 |
+
"learning_rate": 1.1741759262839896e-06,
|
| 1647 |
+
"loss": 0.2635,
|
| 1648 |
+
"step": 1170
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 2.6531073446327684,
|
| 1652 |
+
"grad_norm": 1.1492416858673096,
|
| 1653 |
+
"learning_rate": 1.102835524916096e-06,
|
| 1654 |
+
"loss": 0.2803,
|
| 1655 |
+
"step": 1175
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 2.664406779661017,
|
| 1659 |
+
"grad_norm": 1.1435718536376953,
|
| 1660 |
+
"learning_rate": 1.0336481116750256e-06,
|
| 1661 |
+
"loss": 0.2952,
|
| 1662 |
+
"step": 1180
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 2.6757062146892654,
|
| 1666 |
+
"grad_norm": 1.075101375579834,
|
| 1667 |
+
"learning_rate": 9.6662440527103e-07,
|
| 1668 |
+
"loss": 0.2934,
|
| 1669 |
+
"step": 1185
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 2.687005649717514,
|
| 1673 |
+
"grad_norm": 1.0726203918457031,
|
| 1674 |
+
"learning_rate": 9.017747892067529e-07,
|
| 1675 |
+
"loss": 0.2555,
|
| 1676 |
+
"step": 1190
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 2.698305084745763,
|
| 1680 |
+
"grad_norm": 1.043176293373108,
|
| 1681 |
+
"learning_rate": 8.391093101685959e-07,
|
| 1682 |
+
"loss": 0.2609,
|
| 1683 |
+
"step": 1195
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 2.709604519774011,
|
| 1687 |
+
"grad_norm": 1.0333880186080933,
|
| 1688 |
+
"learning_rate": 7.786376764702719e-07,
|
| 1689 |
+
"loss": 0.2957,
|
| 1690 |
+
"step": 1200
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 2.7209039548022598,
|
| 1694 |
+
"grad_norm": 1.2315031290054321,
|
| 1695 |
+
"learning_rate": 7.203692565487402e-07,
|
| 1696 |
+
"loss": 0.28,
|
| 1697 |
+
"step": 1205
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 2.7322033898305085,
|
| 1701 |
+
"grad_norm": 1.2239551544189453,
|
| 1702 |
+
"learning_rate": 6.643130775128365e-07,
|
| 1703 |
+
"loss": 0.2921,
|
| 1704 |
+
"step": 1210
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 2.743502824858757,
|
| 1708 |
+
"grad_norm": 1.2057119607925415,
|
| 1709 |
+
"learning_rate": 6.104778237447739e-07,
|
| 1710 |
+
"loss": 0.2751,
|
| 1711 |
+
"step": 1215
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 2.754802259887006,
|
| 1715 |
+
"grad_norm": 1.125115156173706,
|
| 1716 |
+
"learning_rate": 5.588718355547168e-07,
|
| 1717 |
+
"loss": 0.2761,
|
| 1718 |
+
"step": 1220
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 2.766101694915254,
|
| 1722 |
+
"grad_norm": 1.167059302330017,
|
| 1723 |
+
"learning_rate": 5.09503107888687e-07,
|
| 1724 |
+
"loss": 0.2747,
|
| 1725 |
+
"step": 1225
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 2.777401129943503,
|
| 1729 |
+
"grad_norm": 1.0621166229248047,
|
| 1730 |
+
"learning_rate": 4.623792890899664e-07,
|
| 1731 |
+
"loss": 0.2609,
|
| 1732 |
+
"step": 1230
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 2.7887005649717516,
|
| 1736 |
+
"grad_norm": 1.1934231519699097,
|
| 1737 |
+
"learning_rate": 4.1750767971418026e-07,
|
| 1738 |
+
"loss": 0.2946,
|
| 1739 |
+
"step": 1235
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 2.8,
|
| 1743 |
+
"grad_norm": 1.167839527130127,
|
| 1744 |
+
"learning_rate": 3.748952313982945e-07,
|
| 1745 |
+
"loss": 0.2892,
|
| 1746 |
+
"step": 1240
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 2.8112994350282485,
|
| 1750 |
+
"grad_norm": 1.166350245475769,
|
| 1751 |
+
"learning_rate": 3.3454854578363116e-07,
|
| 1752 |
+
"loss": 0.3104,
|
| 1753 |
+
"step": 1245
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 2.8225988700564972,
|
| 1757 |
+
"grad_norm": 1.1335365772247314,
|
| 1758 |
+
"learning_rate": 2.9647387349313107e-07,
|
| 1759 |
+
"loss": 0.2906,
|
| 1760 |
+
"step": 1250
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 2.8338983050847455,
|
| 1764 |
+
"grad_norm": 1.101298451423645,
|
| 1765 |
+
"learning_rate": 2.6067711316299035e-07,
|
| 1766 |
+
"loss": 0.2596,
|
| 1767 |
+
"step": 1255
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 2.845197740112994,
|
| 1771 |
+
"grad_norm": 1.2413262128829956,
|
| 1772 |
+
"learning_rate": 2.2716381052881986e-07,
|
| 1773 |
+
"loss": 0.2634,
|
| 1774 |
+
"step": 1260
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 2.856497175141243,
|
| 1778 |
+
"grad_norm": 1.0802109241485596,
|
| 1779 |
+
"learning_rate": 1.9593915756649704e-07,
|
| 1780 |
+
"loss": 0.257,
|
| 1781 |
+
"step": 1265
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 2.8677966101694916,
|
| 1785 |
+
"grad_norm": 1.2962003946304321,
|
| 1786 |
+
"learning_rate": 1.6700799168779645e-07,
|
| 1787 |
+
"loss": 0.304,
|
| 1788 |
+
"step": 1270
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 2.8790960451977403,
|
| 1792 |
+
"grad_norm": 1.152857780456543,
|
| 1793 |
+
"learning_rate": 1.403747949909706e-07,
|
| 1794 |
+
"loss": 0.2765,
|
| 1795 |
+
"step": 1275
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 2.8903954802259886,
|
| 1799 |
+
"grad_norm": 1.122905969619751,
|
| 1800 |
+
"learning_rate": 1.1604369356637557e-07,
|
| 1801 |
+
"loss": 0.2701,
|
| 1802 |
+
"step": 1280
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 2.9016949152542373,
|
| 1806 |
+
"grad_norm": 1.0660308599472046,
|
| 1807 |
+
"learning_rate": 9.401845685723387e-08,
|
| 1808 |
+
"loss": 0.3024,
|
| 1809 |
+
"step": 1285
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 2.912994350282486,
|
| 1813 |
+
"grad_norm": 1.068687915802002,
|
| 1814 |
+
"learning_rate": 7.430249707567172e-08,
|
| 1815 |
+
"loss": 0.2894,
|
| 1816 |
+
"step": 1290
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 2.9242937853107343,
|
| 1820 |
+
"grad_norm": 1.0857810974121094,
|
| 1821 |
+
"learning_rate": 5.6898868674085115e-08,
|
| 1822 |
+
"loss": 0.2767,
|
| 1823 |
+
"step": 1295
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 2.935593220338983,
|
| 1827 |
+
"grad_norm": 1.0800501108169556,
|
| 1828 |
+
"learning_rate": 4.181026787193343e-08,
|
| 1829 |
+
"loss": 0.2676,
|
| 1830 |
+
"step": 1300
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 2.9468926553672317,
|
| 1834 |
+
"grad_norm": 1.186694622039795,
|
| 1835 |
+
"learning_rate": 2.90390322380385e-08,
|
| 1836 |
+
"loss": 0.2851,
|
| 1837 |
+
"step": 1305
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 2.9581920903954804,
|
| 1841 |
+
"grad_norm": 1.070082426071167,
|
| 1842 |
+
"learning_rate": 1.858714032843767e-08,
|
| 1843 |
+
"loss": 0.2583,
|
| 1844 |
+
"step": 1310
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 2.969491525423729,
|
| 1848 |
+
"grad_norm": 1.0884267091751099,
|
| 1849 |
+
"learning_rate": 1.0456211379863966e-08,
|
| 1850 |
+
"loss": 0.2742,
|
| 1851 |
+
"step": 1315
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 2.9807909604519773,
|
| 1855 |
+
"grad_norm": 1.1682034730911255,
|
| 1856 |
+
"learning_rate": 4.647505058885115e-09,
|
| 1857 |
+
"loss": 0.2781,
|
| 1858 |
+
"step": 1320
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 2.992090395480226,
|
| 1862 |
+
"grad_norm": 1.1969527006149292,
|
| 1863 |
+
"learning_rate": 1.1619212667562939e-09,
|
| 1864 |
+
"loss": 0.2931,
|
| 1865 |
+
"step": 1325
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 3.0,
|
| 1869 |
+
"step": 1329,
|
| 1870 |
+
"total_flos": 1.918936913708843e+18,
|
| 1871 |
+
"train_loss": 0.5796768012308734,
|
| 1872 |
+
"train_runtime": 894.235,
|
| 1873 |
+
"train_samples_per_second": 47.504,
|
| 1874 |
+
"train_steps_per_second": 1.486
|
| 1875 |
+
}
|
| 1876 |
+
],
|
| 1877 |
+
"logging_steps": 5,
|
| 1878 |
+
"max_steps": 1329,
|
| 1879 |
+
"num_input_tokens_seen": 0,
|
| 1880 |
+
"num_train_epochs": 3,
|
| 1881 |
+
"save_steps": 20000,
|
| 1882 |
+
"stateful_callbacks": {
|
| 1883 |
+
"TrainerControl": {
|
| 1884 |
+
"args": {
|
| 1885 |
+
"should_epoch_stop": false,
|
| 1886 |
+
"should_evaluate": false,
|
| 1887 |
+
"should_log": false,
|
| 1888 |
+
"should_save": false,
|
| 1889 |
+
"should_training_stop": false
|
| 1890 |
+
},
|
| 1891 |
+
"attributes": {}
|
| 1892 |
+
}
|
| 1893 |
+
},
|
| 1894 |
+
"total_flos": 1.918936913708843e+18,
|
| 1895 |
+
"train_batch_size": 2,
|
| 1896 |
+
"trial_name": null,
|
| 1897 |
+
"trial_params": null
|
| 1898 |
+
}
|
102_128_e3_3e-5/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81900c820c4cea7ac726f555e6a081dec4a335ed9de14ddf6f7c56d4f341321e
|
| 3 |
+
size 8273
|
102_128_e3_3e-5/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|