Upload folder using huggingface_hub
Browse files- instruct/132_128_e3_3e-5/adapter_config.json +39 -0
- instruct/132_128_e3_3e-5/adapter_model.safetensors +3 -0
- instruct/132_128_e3_3e-5/added_tokens.json +9 -0
- instruct/132_128_e3_3e-5/all_results.json +9 -0
- instruct/132_128_e3_3e-5/chat_template.jinja +62 -0
- instruct/132_128_e3_3e-5/config.json +32 -0
- instruct/132_128_e3_3e-5/merges.txt +0 -0
- instruct/132_128_e3_3e-5/special_tokens_map.json +33 -0
- instruct/132_128_e3_3e-5/tokenizer.json +0 -0
- instruct/132_128_e3_3e-5/tokenizer_config.json +234 -0
- instruct/132_128_e3_3e-5/train_results.json +9 -0
- instruct/132_128_e3_3e-5/trainer_state.json +2213 -0
- instruct/132_128_e3_3e-5/training_args.bin +3 -0
- instruct/132_128_e3_3e-5/vocab.json +0 -0
instruct/132_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 |
+
"down_proj",
|
| 28 |
+
"gate_proj",
|
| 29 |
+
"up_proj",
|
| 30 |
+
"o_proj",
|
| 31 |
+
"v_proj",
|
| 32 |
+
"k_proj",
|
| 33 |
+
"q_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
+
"use_dora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
instruct/132_128_e3_3e-5/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a77dbf3b763a0dd613cb9dd3d8bcd478ded74a1c17bcd5593e6c7db12eb78154
|
| 3 |
+
size 791751704
|
instruct/132_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 |
+
}
|
instruct/132_128_e3_3e-5/all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 1.9777146565039227e+18,
|
| 4 |
+
"train_loss": 0.34789815965888576,
|
| 5 |
+
"train_runtime": 958.473,
|
| 6 |
+
"train_samples": 16515,
|
| 7 |
+
"train_samples_per_second": 51.692,
|
| 8 |
+
"train_steps_per_second": 1.618
|
| 9 |
+
}
|
instruct/132_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 %}
|
instruct/132_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 |
+
}
|
instruct/132_128_e3_3e-5/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
instruct/132_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 |
+
}
|
instruct/132_128_e3_3e-5/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
instruct/132_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 |
+
}
|
instruct/132_128_e3_3e-5/train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 1.9777146565039227e+18,
|
| 4 |
+
"train_loss": 0.34789815965888576,
|
| 5 |
+
"train_runtime": 958.473,
|
| 6 |
+
"train_samples": 16515,
|
| 7 |
+
"train_samples_per_second": 51.692,
|
| 8 |
+
"train_steps_per_second": 1.618
|
| 9 |
+
}
|
instruct/132_128_e3_3e-5/trainer_state.json
ADDED
|
@@ -0,0 +1,2213 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 1551,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.00968054211035818,
|
| 14 |
+
"grad_norm": 2.583279848098755,
|
| 15 |
+
"learning_rate": 1.5384615384615385e-06,
|
| 16 |
+
"loss": 1.5901,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.01936108422071636,
|
| 21 |
+
"grad_norm": 2.327331781387329,
|
| 22 |
+
"learning_rate": 3.4615384615384617e-06,
|
| 23 |
+
"loss": 1.5452,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.02904162633107454,
|
| 28 |
+
"grad_norm": 1.163156509399414,
|
| 29 |
+
"learning_rate": 5.384615384615385e-06,
|
| 30 |
+
"loss": 1.5435,
|
| 31 |
+
"step": 15
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.03872216844143272,
|
| 35 |
+
"grad_norm": 0.7100193500518799,
|
| 36 |
+
"learning_rate": 7.307692307692308e-06,
|
| 37 |
+
"loss": 1.4538,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.0484027105517909,
|
| 42 |
+
"grad_norm": 0.5339156985282898,
|
| 43 |
+
"learning_rate": 9.230769230769232e-06,
|
| 44 |
+
"loss": 1.4066,
|
| 45 |
+
"step": 25
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.05808325266214908,
|
| 49 |
+
"grad_norm": 1.694186806678772,
|
| 50 |
+
"learning_rate": 1.1153846153846154e-05,
|
| 51 |
+
"loss": 1.4152,
|
| 52 |
+
"step": 30
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.06776379477250725,
|
| 56 |
+
"grad_norm": 0.439001202583313,
|
| 57 |
+
"learning_rate": 1.3076923076923078e-05,
|
| 58 |
+
"loss": 1.3806,
|
| 59 |
+
"step": 35
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.07744433688286544,
|
| 63 |
+
"grad_norm": 0.39944788813591003,
|
| 64 |
+
"learning_rate": 1.5e-05,
|
| 65 |
+
"loss": 1.3968,
|
| 66 |
+
"step": 40
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.08712487899322362,
|
| 70 |
+
"grad_norm": 0.38715052604675293,
|
| 71 |
+
"learning_rate": 1.6923076923076924e-05,
|
| 72 |
+
"loss": 1.3906,
|
| 73 |
+
"step": 45
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.0968054211035818,
|
| 77 |
+
"grad_norm": 0.38308534026145935,
|
| 78 |
+
"learning_rate": 1.8846153846153846e-05,
|
| 79 |
+
"loss": 1.2742,
|
| 80 |
+
"step": 50
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.10648596321393998,
|
| 84 |
+
"grad_norm": 0.38592132925987244,
|
| 85 |
+
"learning_rate": 2.076923076923077e-05,
|
| 86 |
+
"loss": 1.3535,
|
| 87 |
+
"step": 55
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.11616650532429816,
|
| 91 |
+
"grad_norm": 0.4268631041049957,
|
| 92 |
+
"learning_rate": 2.269230769230769e-05,
|
| 93 |
+
"loss": 1.3148,
|
| 94 |
+
"step": 60
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.12584704743465633,
|
| 98 |
+
"grad_norm": 0.4614173471927643,
|
| 99 |
+
"learning_rate": 2.4615384615384616e-05,
|
| 100 |
+
"loss": 1.3011,
|
| 101 |
+
"step": 65
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.1355275895450145,
|
| 105 |
+
"grad_norm": 0.4473826587200165,
|
| 106 |
+
"learning_rate": 2.6538461538461538e-05,
|
| 107 |
+
"loss": 1.2748,
|
| 108 |
+
"step": 70
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.1452081316553727,
|
| 112 |
+
"grad_norm": 0.49146828055381775,
|
| 113 |
+
"learning_rate": 2.846153846153846e-05,
|
| 114 |
+
"loss": 1.2566,
|
| 115 |
+
"step": 75
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.15488867376573087,
|
| 119 |
+
"grad_norm": 0.4352293908596039,
|
| 120 |
+
"learning_rate": 2.9999965884216442e-05,
|
| 121 |
+
"loss": 1.2518,
|
| 122 |
+
"step": 80
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.16456921587608905,
|
| 126 |
+
"grad_norm": 0.49563130736351013,
|
| 127 |
+
"learning_rate": 2.9998771848086157e-05,
|
| 128 |
+
"loss": 1.2032,
|
| 129 |
+
"step": 85
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.17424975798644723,
|
| 133 |
+
"grad_norm": 0.4918646216392517,
|
| 134 |
+
"learning_rate": 2.999587217795956e-05,
|
| 135 |
+
"loss": 1.2152,
|
| 136 |
+
"step": 90
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.18393030009680542,
|
| 140 |
+
"grad_norm": 0.4999397099018097,
|
| 141 |
+
"learning_rate": 2.9991267203582057e-05,
|
| 142 |
+
"loss": 1.2425,
|
| 143 |
+
"step": 95
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.1936108422071636,
|
| 147 |
+
"grad_norm": 0.5701794028282166,
|
| 148 |
+
"learning_rate": 2.9984957448623232e-05,
|
| 149 |
+
"loss": 1.1597,
|
| 150 |
+
"step": 100
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.20329138431752178,
|
| 154 |
+
"grad_norm": 0.5733001232147217,
|
| 155 |
+
"learning_rate": 2.997694363061735e-05,
|
| 156 |
+
"loss": 1.1118,
|
| 157 |
+
"step": 105
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.21297192642787996,
|
| 161 |
+
"grad_norm": 0.5916318297386169,
|
| 162 |
+
"learning_rate": 2.9967226660881714e-05,
|
| 163 |
+
"loss": 1.1079,
|
| 164 |
+
"step": 110
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.22265246853823814,
|
| 168 |
+
"grad_norm": 0.6237680315971375,
|
| 169 |
+
"learning_rate": 2.995580764441307e-05,
|
| 170 |
+
"loss": 1.1602,
|
| 171 |
+
"step": 115
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.23233301064859632,
|
| 175 |
+
"grad_norm": 0.6868143081665039,
|
| 176 |
+
"learning_rate": 2.9942687879761912e-05,
|
| 177 |
+
"loss": 1.1234,
|
| 178 |
+
"step": 120
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.2420135527589545,
|
| 182 |
+
"grad_norm": 0.71219402551651,
|
| 183 |
+
"learning_rate": 2.9927868858884833e-05,
|
| 184 |
+
"loss": 1.1008,
|
| 185 |
+
"step": 125
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.25169409486931266,
|
| 189 |
+
"grad_norm": 0.6303288340568542,
|
| 190 |
+
"learning_rate": 2.9911352266974873e-05,
|
| 191 |
+
"loss": 1.0822,
|
| 192 |
+
"step": 130
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.26137463697967084,
|
| 196 |
+
"grad_norm": 0.6709757447242737,
|
| 197 |
+
"learning_rate": 2.989313998226986e-05,
|
| 198 |
+
"loss": 1.0946,
|
| 199 |
+
"step": 135
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.271055179090029,
|
| 203 |
+
"grad_norm": 0.6479235291481018,
|
| 204 |
+
"learning_rate": 2.987323407583882e-05,
|
| 205 |
+
"loss": 0.9723,
|
| 206 |
+
"step": 140
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.2807357212003872,
|
| 210 |
+
"grad_norm": 0.754619300365448,
|
| 211 |
+
"learning_rate": 2.9851636811346486e-05,
|
| 212 |
+
"loss": 0.9898,
|
| 213 |
+
"step": 145
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.2904162633107454,
|
| 217 |
+
"grad_norm": 0.7568475008010864,
|
| 218 |
+
"learning_rate": 2.982835064479585e-05,
|
| 219 |
+
"loss": 1.0191,
|
| 220 |
+
"step": 150
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.30009680542110356,
|
| 224 |
+
"grad_norm": 0.744417130947113,
|
| 225 |
+
"learning_rate": 2.9803378224248876e-05,
|
| 226 |
+
"loss": 0.9737,
|
| 227 |
+
"step": 155
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.30977734753146174,
|
| 231 |
+
"grad_norm": 0.7898931503295898,
|
| 232 |
+
"learning_rate": 2.9776722389525376e-05,
|
| 233 |
+
"loss": 0.9596,
|
| 234 |
+
"step": 160
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.3194578896418199,
|
| 238 |
+
"grad_norm": 0.8161885738372803,
|
| 239 |
+
"learning_rate": 2.9748386171880074e-05,
|
| 240 |
+
"loss": 0.9326,
|
| 241 |
+
"step": 165
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.3291384317521781,
|
| 245 |
+
"grad_norm": 0.824617326259613,
|
| 246 |
+
"learning_rate": 2.9718372793657878e-05,
|
| 247 |
+
"loss": 0.9664,
|
| 248 |
+
"step": 170
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.3388189738625363,
|
| 252 |
+
"grad_norm": 0.7713361978530884,
|
| 253 |
+
"learning_rate": 2.9686685667927455e-05,
|
| 254 |
+
"loss": 0.8652,
|
| 255 |
+
"step": 175
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.34849951597289447,
|
| 259 |
+
"grad_norm": 0.8308248519897461,
|
| 260 |
+
"learning_rate": 2.9653328398093098e-05,
|
| 261 |
+
"loss": 0.8885,
|
| 262 |
+
"step": 180
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.35818005808325265,
|
| 266 |
+
"grad_norm": 0.9614322185516357,
|
| 267 |
+
"learning_rate": 2.9618304777484954e-05,
|
| 268 |
+
"loss": 0.9107,
|
| 269 |
+
"step": 185
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.36786060019361083,
|
| 273 |
+
"grad_norm": 0.8611675500869751,
|
| 274 |
+
"learning_rate": 2.9581618788927657e-05,
|
| 275 |
+
"loss": 0.8838,
|
| 276 |
+
"step": 190
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.377541142303969,
|
| 280 |
+
"grad_norm": 0.9881988167762756,
|
| 281 |
+
"learning_rate": 2.9543274604287414e-05,
|
| 282 |
+
"loss": 0.8771,
|
| 283 |
+
"step": 195
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.3872216844143272,
|
| 287 |
+
"grad_norm": 0.8338304758071899,
|
| 288 |
+
"learning_rate": 2.950327658399756e-05,
|
| 289 |
+
"loss": 0.8609,
|
| 290 |
+
"step": 200
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.3969022265246854,
|
| 294 |
+
"grad_norm": 0.9100682735443115,
|
| 295 |
+
"learning_rate": 2.9461629276562717e-05,
|
| 296 |
+
"loss": 0.8169,
|
| 297 |
+
"step": 205
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.40658276863504356,
|
| 301 |
+
"grad_norm": 1.0720361471176147,
|
| 302 |
+
"learning_rate": 2.941833741804157e-05,
|
| 303 |
+
"loss": 0.8149,
|
| 304 |
+
"step": 210
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.41626331074540174,
|
| 308 |
+
"grad_norm": 0.9578617811203003,
|
| 309 |
+
"learning_rate": 2.9373405931508237e-05,
|
| 310 |
+
"loss": 0.8855,
|
| 311 |
+
"step": 215
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.4259438528557599,
|
| 315 |
+
"grad_norm": 0.9943941831588745,
|
| 316 |
+
"learning_rate": 2.9326839926492473e-05,
|
| 317 |
+
"loss": 0.799,
|
| 318 |
+
"step": 220
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.4356243949661181,
|
| 322 |
+
"grad_norm": 0.9589488506317139,
|
| 323 |
+
"learning_rate": 2.9278644698398585e-05,
|
| 324 |
+
"loss": 0.7855,
|
| 325 |
+
"step": 225
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.4453049370764763,
|
| 329 |
+
"grad_norm": 0.9750145077705383,
|
| 330 |
+
"learning_rate": 2.922882572790329e-05,
|
| 331 |
+
"loss": 0.7451,
|
| 332 |
+
"step": 230
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.45498547918683446,
|
| 336 |
+
"grad_norm": 1.1122719049453735,
|
| 337 |
+
"learning_rate": 2.917738868033243e-05,
|
| 338 |
+
"loss": 0.7813,
|
| 339 |
+
"step": 235
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.46466602129719264,
|
| 343 |
+
"grad_norm": 0.9726570248603821,
|
| 344 |
+
"learning_rate": 2.912433940501673e-05,
|
| 345 |
+
"loss": 0.7538,
|
| 346 |
+
"step": 240
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.4743465634075508,
|
| 350 |
+
"grad_norm": 0.9562707543373108,
|
| 351 |
+
"learning_rate": 2.906968393462661e-05,
|
| 352 |
+
"loss": 0.745,
|
| 353 |
+
"step": 245
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.484027105517909,
|
| 357 |
+
"grad_norm": 0.9341024160385132,
|
| 358 |
+
"learning_rate": 2.9013428484486202e-05,
|
| 359 |
+
"loss": 0.7205,
|
| 360 |
+
"step": 250
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.4937076476282672,
|
| 364 |
+
"grad_norm": 1.0728899240493774,
|
| 365 |
+
"learning_rate": 2.89555794518665e-05,
|
| 366 |
+
"loss": 0.7173,
|
| 367 |
+
"step": 255
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.5033881897386253,
|
| 371 |
+
"grad_norm": 1.091996669769287,
|
| 372 |
+
"learning_rate": 2.8896143415257916e-05,
|
| 373 |
+
"loss": 0.6832,
|
| 374 |
+
"step": 260
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.5130687318489835,
|
| 378 |
+
"grad_norm": 0.940743088722229,
|
| 379 |
+
"learning_rate": 2.883512713362216e-05,
|
| 380 |
+
"loss": 0.7173,
|
| 381 |
+
"step": 265
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.5227492739593417,
|
| 385 |
+
"grad_norm": 0.9621837735176086,
|
| 386 |
+
"learning_rate": 2.8772537545623626e-05,
|
| 387 |
+
"loss": 0.7261,
|
| 388 |
+
"step": 270
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.5324298160696999,
|
| 392 |
+
"grad_norm": 1.0028799772262573,
|
| 393 |
+
"learning_rate": 2.870838176884036e-05,
|
| 394 |
+
"loss": 0.6776,
|
| 395 |
+
"step": 275
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.542110358180058,
|
| 399 |
+
"grad_norm": 1.0846943855285645,
|
| 400 |
+
"learning_rate": 2.8642667098954637e-05,
|
| 401 |
+
"loss": 0.6937,
|
| 402 |
+
"step": 280
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.5517909002904162,
|
| 406 |
+
"grad_norm": 1.256654977798462,
|
| 407 |
+
"learning_rate": 2.857540100892332e-05,
|
| 408 |
+
"loss": 0.6865,
|
| 409 |
+
"step": 285
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.5614714424007744,
|
| 413 |
+
"grad_norm": 1.0469144582748413,
|
| 414 |
+
"learning_rate": 2.8506591148128046e-05,
|
| 415 |
+
"loss": 0.6662,
|
| 416 |
+
"step": 290
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.5711519845111326,
|
| 420 |
+
"grad_norm": 1.1145750284194946,
|
| 421 |
+
"learning_rate": 2.8436245341505348e-05,
|
| 422 |
+
"loss": 0.6901,
|
| 423 |
+
"step": 295
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.5808325266214908,
|
| 427 |
+
"grad_norm": 0.9869698286056519,
|
| 428 |
+
"learning_rate": 2.8364371588656832e-05,
|
| 429 |
+
"loss": 0.615,
|
| 430 |
+
"step": 300
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.590513068731849,
|
| 434 |
+
"grad_norm": 1.132925271987915,
|
| 435 |
+
"learning_rate": 2.829097806293946e-05,
|
| 436 |
+
"loss": 0.6539,
|
| 437 |
+
"step": 305
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.6001936108422071,
|
| 441 |
+
"grad_norm": 1.0004526376724243,
|
| 442 |
+
"learning_rate": 2.821607311053609e-05,
|
| 443 |
+
"loss": 0.5814,
|
| 444 |
+
"step": 310
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.6098741529525653,
|
| 448 |
+
"grad_norm": 1.0933210849761963,
|
| 449 |
+
"learning_rate": 2.813966524950638e-05,
|
| 450 |
+
"loss": 0.6049,
|
| 451 |
+
"step": 315
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.6195546950629235,
|
| 455 |
+
"grad_norm": 1.2509098052978516,
|
| 456 |
+
"learning_rate": 2.806176316881811e-05,
|
| 457 |
+
"loss": 0.5684,
|
| 458 |
+
"step": 320
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.6292352371732817,
|
| 462 |
+
"grad_norm": 1.1069066524505615,
|
| 463 |
+
"learning_rate": 2.798237572735909e-05,
|
| 464 |
+
"loss": 0.6273,
|
| 465 |
+
"step": 325
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.6389157792836399,
|
| 469 |
+
"grad_norm": 1.0906236171722412,
|
| 470 |
+
"learning_rate": 2.790151195292977e-05,
|
| 471 |
+
"loss": 0.5819,
|
| 472 |
+
"step": 330
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.648596321393998,
|
| 476 |
+
"grad_norm": 1.2983148097991943,
|
| 477 |
+
"learning_rate": 2.781918104121657e-05,
|
| 478 |
+
"loss": 0.5535,
|
| 479 |
+
"step": 335
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.6582768635043562,
|
| 483 |
+
"grad_norm": 1.031111478805542,
|
| 484 |
+
"learning_rate": 2.7735392354746198e-05,
|
| 485 |
+
"loss": 0.4973,
|
| 486 |
+
"step": 340
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.6679574056147144,
|
| 490 |
+
"grad_norm": 1.2123416662216187,
|
| 491 |
+
"learning_rate": 2.765015542182094e-05,
|
| 492 |
+
"loss": 0.574,
|
| 493 |
+
"step": 345
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.6776379477250726,
|
| 497 |
+
"grad_norm": 1.1910861730575562,
|
| 498 |
+
"learning_rate": 2.7563479935435137e-05,
|
| 499 |
+
"loss": 0.5954,
|
| 500 |
+
"step": 350
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.6873184898354308,
|
| 504 |
+
"grad_norm": 1.1290500164031982,
|
| 505 |
+
"learning_rate": 2.747537575217289e-05,
|
| 506 |
+
"loss": 0.5541,
|
| 507 |
+
"step": 355
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.6969990319457889,
|
| 511 |
+
"grad_norm": 1.444022297859192,
|
| 512 |
+
"learning_rate": 2.7385852891087212e-05,
|
| 513 |
+
"loss": 0.4998,
|
| 514 |
+
"step": 360
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.7066795740561471,
|
| 518 |
+
"grad_norm": 1.2342149019241333,
|
| 519 |
+
"learning_rate": 2.7294921532560652e-05,
|
| 520 |
+
"loss": 0.5216,
|
| 521 |
+
"step": 365
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.7163601161665053,
|
| 525 |
+
"grad_norm": 1.122484803199768,
|
| 526 |
+
"learning_rate": 2.720259201714763e-05,
|
| 527 |
+
"loss": 0.5275,
|
| 528 |
+
"step": 370
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.7260406582768635,
|
| 532 |
+
"grad_norm": 1.0921597480773926,
|
| 533 |
+
"learning_rate": 2.7108874844398508e-05,
|
| 534 |
+
"loss": 0.4735,
|
| 535 |
+
"step": 375
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.7357212003872217,
|
| 539 |
+
"grad_norm": 1.0548079013824463,
|
| 540 |
+
"learning_rate": 2.7013780671665595e-05,
|
| 541 |
+
"loss": 0.5154,
|
| 542 |
+
"step": 380
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.7454017424975798,
|
| 546 |
+
"grad_norm": 1.1719199419021606,
|
| 547 |
+
"learning_rate": 2.6917320312891232e-05,
|
| 548 |
+
"loss": 0.5148,
|
| 549 |
+
"step": 385
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.755082284607938,
|
| 553 |
+
"grad_norm": 1.2420458793640137,
|
| 554 |
+
"learning_rate": 2.6819504737378024e-05,
|
| 555 |
+
"loss": 0.5132,
|
| 556 |
+
"step": 390
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.7647628267182962,
|
| 560 |
+
"grad_norm": 1.1030137538909912,
|
| 561 |
+
"learning_rate": 2.6720345068541464e-05,
|
| 562 |
+
"loss": 0.4968,
|
| 563 |
+
"step": 395
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.7744433688286544,
|
| 567 |
+
"grad_norm": 1.213926911354065,
|
| 568 |
+
"learning_rate": 2.661985258264495e-05,
|
| 569 |
+
"loss": 0.4562,
|
| 570 |
+
"step": 400
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.7841239109390126,
|
| 574 |
+
"grad_norm": 1.185013771057129,
|
| 575 |
+
"learning_rate": 2.6518038707517524e-05,
|
| 576 |
+
"loss": 0.4773,
|
| 577 |
+
"step": 405
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.7938044530493708,
|
| 581 |
+
"grad_norm": 1.246468424797058,
|
| 582 |
+
"learning_rate": 2.6414915021254267e-05,
|
| 583 |
+
"loss": 0.419,
|
| 584 |
+
"step": 410
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.8034849951597289,
|
| 588 |
+
"grad_norm": 1.1366288661956787,
|
| 589 |
+
"learning_rate": 2.6310493250899696e-05,
|
| 590 |
+
"loss": 0.4803,
|
| 591 |
+
"step": 415
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.8131655372700871,
|
| 595 |
+
"grad_norm": 1.1719627380371094,
|
| 596 |
+
"learning_rate": 2.6204785271114175e-05,
|
| 597 |
+
"loss": 0.4811,
|
| 598 |
+
"step": 420
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.8228460793804453,
|
| 602 |
+
"grad_norm": 1.2611087560653687,
|
| 603 |
+
"learning_rate": 2.6097803102823526e-05,
|
| 604 |
+
"loss": 0.4355,
|
| 605 |
+
"step": 425
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.8325266214908035,
|
| 609 |
+
"grad_norm": 1.2296397686004639,
|
| 610 |
+
"learning_rate": 2.598955891185208e-05,
|
| 611 |
+
"loss": 0.4454,
|
| 612 |
+
"step": 430
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.8422071636011617,
|
| 616 |
+
"grad_norm": 1.3506165742874146,
|
| 617 |
+
"learning_rate": 2.588006500753914e-05,
|
| 618 |
+
"loss": 0.3936,
|
| 619 |
+
"step": 435
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.8518877057115198,
|
| 623 |
+
"grad_norm": 1.1522878408432007,
|
| 624 |
+
"learning_rate": 2.576933384133924e-05,
|
| 625 |
+
"loss": 0.4067,
|
| 626 |
+
"step": 440
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.861568247821878,
|
| 630 |
+
"grad_norm": 1.2492619752883911,
|
| 631 |
+
"learning_rate": 2.5657378005406143e-05,
|
| 632 |
+
"loss": 0.4197,
|
| 633 |
+
"step": 445
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.8712487899322362,
|
| 637 |
+
"grad_norm": 1.1224294900894165,
|
| 638 |
+
"learning_rate": 2.5544210231160925e-05,
|
| 639 |
+
"loss": 0.4367,
|
| 640 |
+
"step": 450
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.8809293320425944,
|
| 644 |
+
"grad_norm": 1.2644156217575073,
|
| 645 |
+
"learning_rate": 2.542984338784414e-05,
|
| 646 |
+
"loss": 0.4088,
|
| 647 |
+
"step": 455
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.8906098741529526,
|
| 651 |
+
"grad_norm": 1.1783829927444458,
|
| 652 |
+
"learning_rate": 2.5314290481052378e-05,
|
| 653 |
+
"loss": 0.4556,
|
| 654 |
+
"step": 460
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.9002904162633107,
|
| 658 |
+
"grad_norm": 1.1985176801681519,
|
| 659 |
+
"learning_rate": 2.5197564651259292e-05,
|
| 660 |
+
"loss": 0.4281,
|
| 661 |
+
"step": 465
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.9099709583736689,
|
| 665 |
+
"grad_norm": 1.300177812576294,
|
| 666 |
+
"learning_rate": 2.507967917232127e-05,
|
| 667 |
+
"loss": 0.3923,
|
| 668 |
+
"step": 470
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.9196515004840271,
|
| 672 |
+
"grad_norm": 1.383947491645813,
|
| 673 |
+
"learning_rate": 2.4960647449967962e-05,
|
| 674 |
+
"loss": 0.4202,
|
| 675 |
+
"step": 475
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.9293320425943853,
|
| 679 |
+
"grad_norm": 1.2635477781295776,
|
| 680 |
+
"learning_rate": 2.4840483020277814e-05,
|
| 681 |
+
"loss": 0.4364,
|
| 682 |
+
"step": 480
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.9390125847047435,
|
| 686 |
+
"grad_norm": 1.1635620594024658,
|
| 687 |
+
"learning_rate": 2.471919954813876e-05,
|
| 688 |
+
"loss": 0.3902,
|
| 689 |
+
"step": 485
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.9486931268151017,
|
| 693 |
+
"grad_norm": 1.205683946609497,
|
| 694 |
+
"learning_rate": 2.4596810825694272e-05,
|
| 695 |
+
"loss": 0.3769,
|
| 696 |
+
"step": 490
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.9583736689254598,
|
| 700 |
+
"grad_norm": 1.163185954093933,
|
| 701 |
+
"learning_rate": 2.447333077077495e-05,
|
| 702 |
+
"loss": 0.3673,
|
| 703 |
+
"step": 495
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.968054211035818,
|
| 707 |
+
"grad_norm": 1.1635117530822754,
|
| 708 |
+
"learning_rate": 2.4348773425315805e-05,
|
| 709 |
+
"loss": 0.3854,
|
| 710 |
+
"step": 500
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.9777347531461762,
|
| 714 |
+
"grad_norm": 1.2384796142578125,
|
| 715 |
+
"learning_rate": 2.4223152953759435e-05,
|
| 716 |
+
"loss": 0.3955,
|
| 717 |
+
"step": 505
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.9874152952565344,
|
| 721 |
+
"grad_norm": 1.4900280237197876,
|
| 722 |
+
"learning_rate": 2.4096483641445277e-05,
|
| 723 |
+
"loss": 0.3516,
|
| 724 |
+
"step": 510
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.9970958373668926,
|
| 728 |
+
"grad_norm": 1.1215156316757202,
|
| 729 |
+
"learning_rate": 2.3968779892985084e-05,
|
| 730 |
+
"loss": 0.3465,
|
| 731 |
+
"step": 515
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.0058083252662149,
|
| 735 |
+
"grad_norm": 1.3642420768737793,
|
| 736 |
+
"learning_rate": 2.3840056230624888e-05,
|
| 737 |
+
"loss": 0.2815,
|
| 738 |
+
"step": 520
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.0154888673765732,
|
| 742 |
+
"grad_norm": 1.1887036561965942,
|
| 743 |
+
"learning_rate": 2.3710327292593528e-05,
|
| 744 |
+
"loss": 0.2545,
|
| 745 |
+
"step": 525
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.0251694094869312,
|
| 749 |
+
"grad_norm": 1.1791625022888184,
|
| 750 |
+
"learning_rate": 2.3579607831438023e-05,
|
| 751 |
+
"loss": 0.3239,
|
| 752 |
+
"step": 530
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.0348499515972895,
|
| 756 |
+
"grad_norm": 1.1845959424972534,
|
| 757 |
+
"learning_rate": 2.344791271234596e-05,
|
| 758 |
+
"loss": 0.2679,
|
| 759 |
+
"step": 535
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.0445304937076476,
|
| 763 |
+
"grad_norm": 1.1946723461151123,
|
| 764 |
+
"learning_rate": 2.3315256911455007e-05,
|
| 765 |
+
"loss": 0.3076,
|
| 766 |
+
"step": 540
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.054211035818006,
|
| 770 |
+
"grad_norm": 1.2731225490570068,
|
| 771 |
+
"learning_rate": 2.3181655514149913e-05,
|
| 772 |
+
"loss": 0.3044,
|
| 773 |
+
"step": 545
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.063891577928364,
|
| 777 |
+
"grad_norm": 1.0046724081039429,
|
| 778 |
+
"learning_rate": 2.3047123713346955e-05,
|
| 779 |
+
"loss": 0.2585,
|
| 780 |
+
"step": 550
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.0735721200387223,
|
| 784 |
+
"grad_norm": 1.3609782457351685,
|
| 785 |
+
"learning_rate": 2.291167680776629e-05,
|
| 786 |
+
"loss": 0.282,
|
| 787 |
+
"step": 555
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.0832526621490803,
|
| 791 |
+
"grad_norm": 1.2548587322235107,
|
| 792 |
+
"learning_rate": 2.2775330200192165e-05,
|
| 793 |
+
"loss": 0.27,
|
| 794 |
+
"step": 560
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.0929332042594386,
|
| 798 |
+
"grad_norm": 1.231648325920105,
|
| 799 |
+
"learning_rate": 2.2638099395721365e-05,
|
| 800 |
+
"loss": 0.2503,
|
| 801 |
+
"step": 565
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.1026137463697967,
|
| 805 |
+
"grad_norm": 1.1396890878677368,
|
| 806 |
+
"learning_rate": 2.25e-05,
|
| 807 |
+
"loss": 0.2463,
|
| 808 |
+
"step": 570
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.112294288480155,
|
| 812 |
+
"grad_norm": 1.371836543083191,
|
| 813 |
+
"learning_rate": 2.2361047717448843e-05,
|
| 814 |
+
"loss": 0.2785,
|
| 815 |
+
"step": 575
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.121974830590513,
|
| 819 |
+
"grad_norm": 1.199236512184143,
|
| 820 |
+
"learning_rate": 2.222125834947745e-05,
|
| 821 |
+
"loss": 0.2866,
|
| 822 |
+
"step": 580
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.1316553727008714,
|
| 826 |
+
"grad_norm": 1.1279804706573486,
|
| 827 |
+
"learning_rate": 2.2080647792687295e-05,
|
| 828 |
+
"loss": 0.2342,
|
| 829 |
+
"step": 585
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.1413359148112294,
|
| 833 |
+
"grad_norm": 1.1763415336608887,
|
| 834 |
+
"learning_rate": 2.193923203706396e-05,
|
| 835 |
+
"loss": 0.2745,
|
| 836 |
+
"step": 590
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.1510164569215875,
|
| 840 |
+
"grad_norm": 1.2062084674835205,
|
| 841 |
+
"learning_rate": 2.1797027164158853e-05,
|
| 842 |
+
"loss": 0.2657,
|
| 843 |
+
"step": 595
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.1606969990319458,
|
| 847 |
+
"grad_norm": 1.436498761177063,
|
| 848 |
+
"learning_rate": 2.1654049345260404e-05,
|
| 849 |
+
"loss": 0.2564,
|
| 850 |
+
"step": 600
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.170377541142304,
|
| 854 |
+
"grad_norm": 1.1157000064849854,
|
| 855 |
+
"learning_rate": 2.151031483955511e-05,
|
| 856 |
+
"loss": 0.2498,
|
| 857 |
+
"step": 605
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.1800580832526621,
|
| 861 |
+
"grad_norm": 1.280535340309143,
|
| 862 |
+
"learning_rate": 2.136583999227855e-05,
|
| 863 |
+
"loss": 0.2427,
|
| 864 |
+
"step": 610
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.1897386253630202,
|
| 868 |
+
"grad_norm": 1.3744301795959473,
|
| 869 |
+
"learning_rate": 2.122064123285666e-05,
|
| 870 |
+
"loss": 0.2452,
|
| 871 |
+
"step": 615
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.1994191674733785,
|
| 875 |
+
"grad_norm": 1.1136362552642822,
|
| 876 |
+
"learning_rate": 2.1074735073037383e-05,
|
| 877 |
+
"loss": 0.2344,
|
| 878 |
+
"step": 620
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.2090997095837368,
|
| 882 |
+
"grad_norm": 1.187138319015503,
|
| 883 |
+
"learning_rate": 2.0928138105013e-05,
|
| 884 |
+
"loss": 0.2443,
|
| 885 |
+
"step": 625
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.2187802516940949,
|
| 889 |
+
"grad_norm": 1.3247230052947998,
|
| 890 |
+
"learning_rate": 2.0780866999533298e-05,
|
| 891 |
+
"loss": 0.2707,
|
| 892 |
+
"step": 630
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 1.228460793804453,
|
| 896 |
+
"grad_norm": 1.205047369003296,
|
| 897 |
+
"learning_rate": 2.0632938504009765e-05,
|
| 898 |
+
"loss": 0.2618,
|
| 899 |
+
"step": 635
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 1.2381413359148112,
|
| 903 |
+
"grad_norm": 0.9527857303619385,
|
| 904 |
+
"learning_rate": 2.048436944061115e-05,
|
| 905 |
+
"loss": 0.2766,
|
| 906 |
+
"step": 640
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.2478218780251695,
|
| 910 |
+
"grad_norm": 1.2868491411209106,
|
| 911 |
+
"learning_rate": 2.033517670435045e-05,
|
| 912 |
+
"loss": 0.2356,
|
| 913 |
+
"step": 645
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.2575024201355276,
|
| 917 |
+
"grad_norm": 1.2020649909973145,
|
| 918 |
+
"learning_rate": 2.018537726116365e-05,
|
| 919 |
+
"loss": 0.2272,
|
| 920 |
+
"step": 650
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.2671829622458857,
|
| 924 |
+
"grad_norm": 1.1579198837280273,
|
| 925 |
+
"learning_rate": 2.0034988145980376e-05,
|
| 926 |
+
"loss": 0.214,
|
| 927 |
+
"step": 655
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.276863504356244,
|
| 931 |
+
"grad_norm": 1.280042052268982,
|
| 932 |
+
"learning_rate": 1.988402646078672e-05,
|
| 933 |
+
"loss": 0.2269,
|
| 934 |
+
"step": 660
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.2865440464666023,
|
| 938 |
+
"grad_norm": 1.0474588871002197,
|
| 939 |
+
"learning_rate": 1.973250937268042e-05,
|
| 940 |
+
"loss": 0.1988,
|
| 941 |
+
"step": 665
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.2962245885769603,
|
| 945 |
+
"grad_norm": 1.1829776763916016,
|
| 946 |
+
"learning_rate": 1.9580454111918684e-05,
|
| 947 |
+
"loss": 0.2201,
|
| 948 |
+
"step": 670
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 1.3059051306873184,
|
| 952 |
+
"grad_norm": 1.1204521656036377,
|
| 953 |
+
"learning_rate": 1.9427877969958744e-05,
|
| 954 |
+
"loss": 0.2273,
|
| 955 |
+
"step": 675
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.3155856727976767,
|
| 959 |
+
"grad_norm": 1.1652275323867798,
|
| 960 |
+
"learning_rate": 1.9274798297491532e-05,
|
| 961 |
+
"loss": 0.2352,
|
| 962 |
+
"step": 680
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.325266214908035,
|
| 966 |
+
"grad_norm": 1.1074024438858032,
|
| 967 |
+
"learning_rate": 1.9121232502468594e-05,
|
| 968 |
+
"loss": 0.2423,
|
| 969 |
+
"step": 685
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.334946757018393,
|
| 973 |
+
"grad_norm": 1.2995609045028687,
|
| 974 |
+
"learning_rate": 1.896719804812247e-05,
|
| 975 |
+
"loss": 0.1961,
|
| 976 |
+
"step": 690
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.3446272991287511,
|
| 980 |
+
"grad_norm": 1.088392734527588,
|
| 981 |
+
"learning_rate": 1.8812712450980826e-05,
|
| 982 |
+
"loss": 0.2025,
|
| 983 |
+
"step": 695
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.3543078412391094,
|
| 987 |
+
"grad_norm": 1.0325970649719238,
|
| 988 |
+
"learning_rate": 1.8657793278874482e-05,
|
| 989 |
+
"loss": 0.175,
|
| 990 |
+
"step": 700
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.3639883833494677,
|
| 994 |
+
"grad_norm": 1.0761932134628296,
|
| 995 |
+
"learning_rate": 1.850245814893965e-05,
|
| 996 |
+
"loss": 0.185,
|
| 997 |
+
"step": 705
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 1.3736689254598258,
|
| 1001 |
+
"grad_norm": 1.0386158227920532,
|
| 1002 |
+
"learning_rate": 1.8346724725614536e-05,
|
| 1003 |
+
"loss": 0.2387,
|
| 1004 |
+
"step": 710
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.3833494675701838,
|
| 1008 |
+
"grad_norm": 1.1490120887756348,
|
| 1009 |
+
"learning_rate": 1.819061071863056e-05,
|
| 1010 |
+
"loss": 0.2068,
|
| 1011 |
+
"step": 715
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 1.3930300096805421,
|
| 1015 |
+
"grad_norm": 1.108993411064148,
|
| 1016 |
+
"learning_rate": 1.803413388099847e-05,
|
| 1017 |
+
"loss": 0.179,
|
| 1018 |
+
"step": 720
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.4027105517909004,
|
| 1022 |
+
"grad_norm": 1.114526391029358,
|
| 1023 |
+
"learning_rate": 1.7877312006989447e-05,
|
| 1024 |
+
"loss": 0.1856,
|
| 1025 |
+
"step": 725
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 1.4123910939012585,
|
| 1029 |
+
"grad_norm": 1.197409749031067,
|
| 1030 |
+
"learning_rate": 1.772016293011163e-05,
|
| 1031 |
+
"loss": 0.1885,
|
| 1032 |
+
"step": 730
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 1.4220716360116166,
|
| 1036 |
+
"grad_norm": 1.244173288345337,
|
| 1037 |
+
"learning_rate": 1.7562704521082084e-05,
|
| 1038 |
+
"loss": 0.181,
|
| 1039 |
+
"step": 735
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 1.4317521781219749,
|
| 1043 |
+
"grad_norm": 1.1902437210083008,
|
| 1044 |
+
"learning_rate": 1.7404954685794582e-05,
|
| 1045 |
+
"loss": 0.1979,
|
| 1046 |
+
"step": 740
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.441432720232333,
|
| 1050 |
+
"grad_norm": 1.2063813209533691,
|
| 1051 |
+
"learning_rate": 1.724693136328337e-05,
|
| 1052 |
+
"loss": 0.1774,
|
| 1053 |
+
"step": 745
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 1.4511132623426912,
|
| 1057 |
+
"grad_norm": 1.2083414793014526,
|
| 1058 |
+
"learning_rate": 1.708865252368321e-05,
|
| 1059 |
+
"loss": 0.181,
|
| 1060 |
+
"step": 750
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 1.4607938044530493,
|
| 1064 |
+
"grad_norm": 0.9992215633392334,
|
| 1065 |
+
"learning_rate": 1.693013616618578e-05,
|
| 1066 |
+
"loss": 0.1757,
|
| 1067 |
+
"step": 755
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 1.4704743465634076,
|
| 1071 |
+
"grad_norm": 1.1482878923416138,
|
| 1072 |
+
"learning_rate": 1.6771400316992902e-05,
|
| 1073 |
+
"loss": 0.1978,
|
| 1074 |
+
"step": 760
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.4801548886737657,
|
| 1078 |
+
"grad_norm": 1.2638379335403442,
|
| 1079 |
+
"learning_rate": 1.661246302726661e-05,
|
| 1080 |
+
"loss": 0.1742,
|
| 1081 |
+
"step": 765
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 1.489835430784124,
|
| 1085 |
+
"grad_norm": 1.1536481380462646,
|
| 1086 |
+
"learning_rate": 1.645334237107638e-05,
|
| 1087 |
+
"loss": 0.1938,
|
| 1088 |
+
"step": 770
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 1.499515972894482,
|
| 1092 |
+
"grad_norm": 1.0423345565795898,
|
| 1093 |
+
"learning_rate": 1.6294056443343824e-05,
|
| 1094 |
+
"loss": 0.1452,
|
| 1095 |
+
"step": 775
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 1.5091965150048403,
|
| 1099 |
+
"grad_norm": 1.4653370380401611,
|
| 1100 |
+
"learning_rate": 1.6134623357784927e-05,
|
| 1101 |
+
"loss": 0.1753,
|
| 1102 |
+
"step": 780
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 1.5188770571151986,
|
| 1106 |
+
"grad_norm": 1.1847798824310303,
|
| 1107 |
+
"learning_rate": 1.5975061244850214e-05,
|
| 1108 |
+
"loss": 0.1554,
|
| 1109 |
+
"step": 785
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 1.5285575992255567,
|
| 1113 |
+
"grad_norm": 1.3937023878097534,
|
| 1114 |
+
"learning_rate": 1.5815388249662973e-05,
|
| 1115 |
+
"loss": 0.1517,
|
| 1116 |
+
"step": 790
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 1.5382381413359147,
|
| 1120 |
+
"grad_norm": 1.4321658611297607,
|
| 1121 |
+
"learning_rate": 1.5655622529955823e-05,
|
| 1122 |
+
"loss": 0.1645,
|
| 1123 |
+
"step": 795
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 1.547918683446273,
|
| 1127 |
+
"grad_norm": 1.2445905208587646,
|
| 1128 |
+
"learning_rate": 1.549578225400586e-05,
|
| 1129 |
+
"loss": 0.1636,
|
| 1130 |
+
"step": 800
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 1.5575992255566313,
|
| 1134 |
+
"grad_norm": 1.068450927734375,
|
| 1135 |
+
"learning_rate": 1.533588559856857e-05,
|
| 1136 |
+
"loss": 0.1764,
|
| 1137 |
+
"step": 805
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 1.5672797676669894,
|
| 1141 |
+
"grad_norm": 1.0307741165161133,
|
| 1142 |
+
"learning_rate": 1.5175950746810843e-05,
|
| 1143 |
+
"loss": 0.1601,
|
| 1144 |
+
"step": 810
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 1.5769603097773475,
|
| 1148 |
+
"grad_norm": 1.140405297279358,
|
| 1149 |
+
"learning_rate": 1.5015995886243164e-05,
|
| 1150 |
+
"loss": 0.1509,
|
| 1151 |
+
"step": 815
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.5866408518877058,
|
| 1155 |
+
"grad_norm": 1.0222396850585938,
|
| 1156 |
+
"learning_rate": 1.4856039206651385e-05,
|
| 1157 |
+
"loss": 0.1437,
|
| 1158 |
+
"step": 820
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 1.596321393998064,
|
| 1162 |
+
"grad_norm": 1.1660407781600952,
|
| 1163 |
+
"learning_rate": 1.469609889802823e-05,
|
| 1164 |
+
"loss": 0.1769,
|
| 1165 |
+
"step": 825
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 1.6060019361084221,
|
| 1169 |
+
"grad_norm": 1.0608596801757812,
|
| 1170 |
+
"learning_rate": 1.4536193148504733e-05,
|
| 1171 |
+
"loss": 0.1725,
|
| 1172 |
+
"step": 830
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 1.6156824782187802,
|
| 1176 |
+
"grad_norm": 0.8545246720314026,
|
| 1177 |
+
"learning_rate": 1.4376340142281926e-05,
|
| 1178 |
+
"loss": 0.138,
|
| 1179 |
+
"step": 835
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 1.6253630203291385,
|
| 1183 |
+
"grad_norm": 1.0420597791671753,
|
| 1184 |
+
"learning_rate": 1.4216558057562984e-05,
|
| 1185 |
+
"loss": 0.1621,
|
| 1186 |
+
"step": 840
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 1.6350435624394968,
|
| 1190 |
+
"grad_norm": 0.9588462710380554,
|
| 1191 |
+
"learning_rate": 1.4056865064485984e-05,
|
| 1192 |
+
"loss": 0.1556,
|
| 1193 |
+
"step": 845
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 1.6447241045498546,
|
| 1197 |
+
"grad_norm": 0.8879302144050598,
|
| 1198 |
+
"learning_rate": 1.3897279323057679e-05,
|
| 1199 |
+
"loss": 0.1521,
|
| 1200 |
+
"step": 850
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 1.654404646660213,
|
| 1204 |
+
"grad_norm": 1.1756333112716675,
|
| 1205 |
+
"learning_rate": 1.3737818981088347e-05,
|
| 1206 |
+
"loss": 0.128,
|
| 1207 |
+
"step": 855
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 1.6640851887705712,
|
| 1211 |
+
"grad_norm": 1.2112951278686523,
|
| 1212 |
+
"learning_rate": 1.3578502172128063e-05,
|
| 1213 |
+
"loss": 0.1524,
|
| 1214 |
+
"step": 860
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 1.6737657308809293,
|
| 1218 |
+
"grad_norm": 0.9899519681930542,
|
| 1219 |
+
"learning_rate": 1.3419347013404578e-05,
|
| 1220 |
+
"loss": 0.1288,
|
| 1221 |
+
"step": 865
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 1.6834462729912874,
|
| 1225 |
+
"grad_norm": 1.134343147277832,
|
| 1226 |
+
"learning_rate": 1.3260371603763055e-05,
|
| 1227 |
+
"loss": 0.1277,
|
| 1228 |
+
"step": 870
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 1.6931268151016456,
|
| 1232 |
+
"grad_norm": 1.2117475271224976,
|
| 1233 |
+
"learning_rate": 1.3101594021607923e-05,
|
| 1234 |
+
"loss": 0.1537,
|
| 1235 |
+
"step": 875
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 1.702807357212004,
|
| 1239 |
+
"grad_norm": 0.9401290416717529,
|
| 1240 |
+
"learning_rate": 1.2943032322846995e-05,
|
| 1241 |
+
"loss": 0.1325,
|
| 1242 |
+
"step": 880
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 1.712487899322362,
|
| 1246 |
+
"grad_norm": 0.9358014464378357,
|
| 1247 |
+
"learning_rate": 1.278470453883822e-05,
|
| 1248 |
+
"loss": 0.1434,
|
| 1249 |
+
"step": 885
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 1.72216844143272,
|
| 1253 |
+
"grad_norm": 0.8018755912780762,
|
| 1254 |
+
"learning_rate": 1.2626628674339169e-05,
|
| 1255 |
+
"loss": 0.1332,
|
| 1256 |
+
"step": 890
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 1.7318489835430784,
|
| 1260 |
+
"grad_norm": 0.9107668995857239,
|
| 1261 |
+
"learning_rate": 1.2468822705459568e-05,
|
| 1262 |
+
"loss": 0.1461,
|
| 1263 |
+
"step": 895
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 1.7415295256534367,
|
| 1267 |
+
"grad_norm": 0.9294764995574951,
|
| 1268 |
+
"learning_rate": 1.2311304577617084e-05,
|
| 1269 |
+
"loss": 0.1392,
|
| 1270 |
+
"step": 900
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 1.7512100677637947,
|
| 1274 |
+
"grad_norm": 1.0142641067504883,
|
| 1275 |
+
"learning_rate": 1.2154092203496617e-05,
|
| 1276 |
+
"loss": 0.1319,
|
| 1277 |
+
"step": 905
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 1.7608906098741528,
|
| 1281 |
+
"grad_norm": 0.8471230268478394,
|
| 1282 |
+
"learning_rate": 1.199720346101327e-05,
|
| 1283 |
+
"loss": 0.1303,
|
| 1284 |
+
"step": 910
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 1.770571151984511,
|
| 1288 |
+
"grad_norm": 1.002325415611267,
|
| 1289 |
+
"learning_rate": 1.1840656191279346e-05,
|
| 1290 |
+
"loss": 0.1233,
|
| 1291 |
+
"step": 915
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 1.7802516940948694,
|
| 1295 |
+
"grad_norm": 1.2102103233337402,
|
| 1296 |
+
"learning_rate": 1.1684468196575453e-05,
|
| 1297 |
+
"loss": 0.1391,
|
| 1298 |
+
"step": 920
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 1.7899322362052275,
|
| 1302 |
+
"grad_norm": 0.9681775569915771,
|
| 1303 |
+
"learning_rate": 1.1528657238326078e-05,
|
| 1304 |
+
"loss": 0.1371,
|
| 1305 |
+
"step": 925
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 1.7996127783155855,
|
| 1309 |
+
"grad_norm": 0.9048433303833008,
|
| 1310 |
+
"learning_rate": 1.137324103507979e-05,
|
| 1311 |
+
"loss": 0.1229,
|
| 1312 |
+
"step": 930
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 1.8092933204259438,
|
| 1316 |
+
"grad_norm": 1.2149651050567627,
|
| 1317 |
+
"learning_rate": 1.1218237260494305e-05,
|
| 1318 |
+
"loss": 0.1248,
|
| 1319 |
+
"step": 935
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 1.818973862536302,
|
| 1323 |
+
"grad_norm": 1.0637120008468628,
|
| 1324 |
+
"learning_rate": 1.1063663541326682e-05,
|
| 1325 |
+
"loss": 0.1118,
|
| 1326 |
+
"step": 940
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 1.8286544046466602,
|
| 1330 |
+
"grad_norm": 0.9652562141418457,
|
| 1331 |
+
"learning_rate": 1.090953745542882e-05,
|
| 1332 |
+
"loss": 0.1249,
|
| 1333 |
+
"step": 945
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 1.8383349467570183,
|
| 1337 |
+
"grad_norm": 1.018527865409851,
|
| 1338 |
+
"learning_rate": 1.0755876529748562e-05,
|
| 1339 |
+
"loss": 0.1132,
|
| 1340 |
+
"step": 950
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 1.8480154888673765,
|
| 1344 |
+
"grad_norm": 0.9471136927604675,
|
| 1345 |
+
"learning_rate": 1.060269823833654e-05,
|
| 1346 |
+
"loss": 0.1158,
|
| 1347 |
+
"step": 955
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 1.8576960309777348,
|
| 1351 |
+
"grad_norm": 0.9643023014068604,
|
| 1352 |
+
"learning_rate": 1.0450020000359076e-05,
|
| 1353 |
+
"loss": 0.1125,
|
| 1354 |
+
"step": 960
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 1.867376573088093,
|
| 1358 |
+
"grad_norm": 0.7923740744590759,
|
| 1359 |
+
"learning_rate": 1.029785917811728e-05,
|
| 1360 |
+
"loss": 0.1009,
|
| 1361 |
+
"step": 965
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 1.877057115198451,
|
| 1365 |
+
"grad_norm": 0.8744542002677917,
|
| 1366 |
+
"learning_rate": 1.0146233075072657e-05,
|
| 1367 |
+
"loss": 0.1092,
|
| 1368 |
+
"step": 970
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 1.8867376573088093,
|
| 1372 |
+
"grad_norm": 1.0112791061401367,
|
| 1373 |
+
"learning_rate": 9.995158933879397e-06,
|
| 1374 |
+
"loss": 0.1287,
|
| 1375 |
+
"step": 975
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 1.8964181994191676,
|
| 1379 |
+
"grad_norm": 1.4026895761489868,
|
| 1380 |
+
"learning_rate": 9.84465393442353e-06,
|
| 1381 |
+
"loss": 0.1105,
|
| 1382 |
+
"step": 980
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 1.9060987415295256,
|
| 1386 |
+
"grad_norm": 1.0406018495559692,
|
| 1387 |
+
"learning_rate": 9.694735191869315e-06,
|
| 1388 |
+
"loss": 0.1164,
|
| 1389 |
+
"step": 985
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 1.9157792836398837,
|
| 1393 |
+
"grad_norm": 0.7971872091293335,
|
| 1394 |
+
"learning_rate": 9.54541975471289e-06,
|
| 1395 |
+
"loss": 0.109,
|
| 1396 |
+
"step": 990
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 1.925459825750242,
|
| 1400 |
+
"grad_norm": 1.0442346334457397,
|
| 1401 |
+
"learning_rate": 9.396724602843564e-06,
|
| 1402 |
+
"loss": 0.112,
|
| 1403 |
+
"step": 995
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 1.9351403678606003,
|
| 1407 |
+
"grad_norm": 0.9047033190727234,
|
| 1408 |
+
"learning_rate": 9.248666645612897e-06,
|
| 1409 |
+
"loss": 0.1041,
|
| 1410 |
+
"step": 1000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 1.9448209099709584,
|
| 1414 |
+
"grad_norm": 1.1186202764511108,
|
| 1415 |
+
"learning_rate": 9.101262719911796e-06,
|
| 1416 |
+
"loss": 0.0933,
|
| 1417 |
+
"step": 1005
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 1.9545014520813164,
|
| 1421 |
+
"grad_norm": 1.0027741193771362,
|
| 1422 |
+
"learning_rate": 8.954529588255838e-06,
|
| 1423 |
+
"loss": 0.1042,
|
| 1424 |
+
"step": 1010
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 1.9641819941916747,
|
| 1428 |
+
"grad_norm": 0.9105640053749084,
|
| 1429 |
+
"learning_rate": 8.808483936879091e-06,
|
| 1430 |
+
"loss": 0.0957,
|
| 1431 |
+
"step": 1015
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 1.973862536302033,
|
| 1435 |
+
"grad_norm": 0.9466278553009033,
|
| 1436 |
+
"learning_rate": 8.663142373836572e-06,
|
| 1437 |
+
"loss": 0.1094,
|
| 1438 |
+
"step": 1020
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 1.983543078412391,
|
| 1442 |
+
"grad_norm": 1.0125550031661987,
|
| 1443 |
+
"learning_rate": 8.518521427115604e-06,
|
| 1444 |
+
"loss": 0.0959,
|
| 1445 |
+
"step": 1025
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 1.9932236205227492,
|
| 1449 |
+
"grad_norm": 0.8532976508140564,
|
| 1450 |
+
"learning_rate": 8.374637542756286e-06,
|
| 1451 |
+
"loss": 0.1037,
|
| 1452 |
+
"step": 1030
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 2.0019361084220715,
|
| 1456 |
+
"grad_norm": 0.6454092860221863,
|
| 1457 |
+
"learning_rate": 8.231507082981288e-06,
|
| 1458 |
+
"loss": 0.0892,
|
| 1459 |
+
"step": 1035
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 2.0116166505324298,
|
| 1463 |
+
"grad_norm": 0.7566469311714172,
|
| 1464 |
+
"learning_rate": 8.089146324335161e-06,
|
| 1465 |
+
"loss": 0.0757,
|
| 1466 |
+
"step": 1040
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 2.021297192642788,
|
| 1470 |
+
"grad_norm": 0.8712649345397949,
|
| 1471 |
+
"learning_rate": 7.947571455833376e-06,
|
| 1472 |
+
"loss": 0.0841,
|
| 1473 |
+
"step": 1045
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 2.0309777347531464,
|
| 1477 |
+
"grad_norm": 0.6450208425521851,
|
| 1478 |
+
"learning_rate": 7.806798577121374e-06,
|
| 1479 |
+
"loss": 0.0795,
|
| 1480 |
+
"step": 1050
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 2.040658276863504,
|
| 1484 |
+
"grad_norm": 0.7852831482887268,
|
| 1485 |
+
"learning_rate": 7.666843696643723e-06,
|
| 1486 |
+
"loss": 0.0837,
|
| 1487 |
+
"step": 1055
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 2.0503388189738625,
|
| 1491 |
+
"grad_norm": 0.8889209628105164,
|
| 1492 |
+
"learning_rate": 7.527722729823668e-06,
|
| 1493 |
+
"loss": 0.075,
|
| 1494 |
+
"step": 1060
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 2.060019361084221,
|
| 1498 |
+
"grad_norm": 0.7815482020378113,
|
| 1499 |
+
"learning_rate": 7.389451497253252e-06,
|
| 1500 |
+
"loss": 0.0666,
|
| 1501 |
+
"step": 1065
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 2.069699903194579,
|
| 1505 |
+
"grad_norm": 0.9109985828399658,
|
| 1506 |
+
"learning_rate": 7.25204572289424e-06,
|
| 1507 |
+
"loss": 0.0826,
|
| 1508 |
+
"step": 1070
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 2.079380445304937,
|
| 1512 |
+
"grad_norm": 0.6828309297561646,
|
| 1513 |
+
"learning_rate": 7.115521032289995e-06,
|
| 1514 |
+
"loss": 0.0805,
|
| 1515 |
+
"step": 1075
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 2.0890609874152952,
|
| 1519 |
+
"grad_norm": 0.8983790278434753,
|
| 1520 |
+
"learning_rate": 6.979892950788597e-06,
|
| 1521 |
+
"loss": 0.076,
|
| 1522 |
+
"step": 1080
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 2.0987415295256535,
|
| 1526 |
+
"grad_norm": 0.7680765986442566,
|
| 1527 |
+
"learning_rate": 6.845176901777313e-06,
|
| 1528 |
+
"loss": 0.0839,
|
| 1529 |
+
"step": 1085
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 2.108422071636012,
|
| 1533 |
+
"grad_norm": 0.8045234680175781,
|
| 1534 |
+
"learning_rate": 6.7113882049286605e-06,
|
| 1535 |
+
"loss": 0.0736,
|
| 1536 |
+
"step": 1090
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 2.1181026137463697,
|
| 1540 |
+
"grad_norm": 0.8118388056755066,
|
| 1541 |
+
"learning_rate": 6.578542074458311e-06,
|
| 1542 |
+
"loss": 0.0736,
|
| 1543 |
+
"step": 1095
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 2.127783155856728,
|
| 1547 |
+
"grad_norm": 0.9975394010543823,
|
| 1548 |
+
"learning_rate": 6.446653617394945e-06,
|
| 1549 |
+
"loss": 0.0808,
|
| 1550 |
+
"step": 1100
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 2.1374636979670862,
|
| 1554 |
+
"grad_norm": 0.7589239478111267,
|
| 1555 |
+
"learning_rate": 6.315737831862302e-06,
|
| 1556 |
+
"loss": 0.0817,
|
| 1557 |
+
"step": 1105
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 2.1471442400774445,
|
| 1561 |
+
"grad_norm": 0.72721266746521,
|
| 1562 |
+
"learning_rate": 6.18580960537361e-06,
|
| 1563 |
+
"loss": 0.0882,
|
| 1564 |
+
"step": 1110
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 2.1568247821878024,
|
| 1568 |
+
"grad_norm": 0.6363008618354797,
|
| 1569 |
+
"learning_rate": 6.056883713138637e-06,
|
| 1570 |
+
"loss": 0.0826,
|
| 1571 |
+
"step": 1115
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 2.1665053242981607,
|
| 1575 |
+
"grad_norm": 0.8117669820785522,
|
| 1576 |
+
"learning_rate": 5.928974816383446e-06,
|
| 1577 |
+
"loss": 0.076,
|
| 1578 |
+
"step": 1120
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 2.176185866408519,
|
| 1582 |
+
"grad_norm": 0.7908191084861755,
|
| 1583 |
+
"learning_rate": 5.802097460683168e-06,
|
| 1584 |
+
"loss": 0.0734,
|
| 1585 |
+
"step": 1125
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 2.1858664085188773,
|
| 1589 |
+
"grad_norm": 0.6734304428100586,
|
| 1590 |
+
"learning_rate": 5.676266074307891e-06,
|
| 1591 |
+
"loss": 0.0779,
|
| 1592 |
+
"step": 1130
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 2.195546950629235,
|
| 1596 |
+
"grad_norm": 0.9595420360565186,
|
| 1597 |
+
"learning_rate": 5.551494966581916e-06,
|
| 1598 |
+
"loss": 0.0746,
|
| 1599 |
+
"step": 1135
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 2.2052274927395934,
|
| 1603 |
+
"grad_norm": 0.8464432954788208,
|
| 1604 |
+
"learning_rate": 5.4277983262565e-06,
|
| 1605 |
+
"loss": 0.0749,
|
| 1606 |
+
"step": 1140
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 2.2149080348499517,
|
| 1610 |
+
"grad_norm": 0.8264310359954834,
|
| 1611 |
+
"learning_rate": 5.305190219896375e-06,
|
| 1612 |
+
"loss": 0.0787,
|
| 1613 |
+
"step": 1145
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 2.22458857696031,
|
| 1617 |
+
"grad_norm": 0.620573878288269,
|
| 1618 |
+
"learning_rate": 5.18368459028009e-06,
|
| 1619 |
+
"loss": 0.0782,
|
| 1620 |
+
"step": 1150
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 2.234269119070668,
|
| 1624 |
+
"grad_norm": 1.098819375038147,
|
| 1625 |
+
"learning_rate": 5.063295254814479e-06,
|
| 1626 |
+
"loss": 0.0635,
|
| 1627 |
+
"step": 1155
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 2.243949661181026,
|
| 1631 |
+
"grad_norm": 0.6919024586677551,
|
| 1632 |
+
"learning_rate": 4.944035903963371e-06,
|
| 1633 |
+
"loss": 0.0729,
|
| 1634 |
+
"step": 1160
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 2.2536302032913844,
|
| 1638 |
+
"grad_norm": 0.7214142084121704,
|
| 1639 |
+
"learning_rate": 4.825920099690708e-06,
|
| 1640 |
+
"loss": 0.0745,
|
| 1641 |
+
"step": 1165
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 2.2633107454017427,
|
| 1645 |
+
"grad_norm": 0.6879322528839111,
|
| 1646 |
+
"learning_rate": 4.708961273918344e-06,
|
| 1647 |
+
"loss": 0.0699,
|
| 1648 |
+
"step": 1170
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 2.2729912875121006,
|
| 1652 |
+
"grad_norm": 0.7095469236373901,
|
| 1653 |
+
"learning_rate": 4.5931727269985696e-06,
|
| 1654 |
+
"loss": 0.0808,
|
| 1655 |
+
"step": 1175
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 2.282671829622459,
|
| 1659 |
+
"grad_norm": 0.8471762537956238,
|
| 1660 |
+
"learning_rate": 4.478567626201602e-06,
|
| 1661 |
+
"loss": 0.0713,
|
| 1662 |
+
"step": 1180
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 2.292352371732817,
|
| 1666 |
+
"grad_norm": 0.7890109419822693,
|
| 1667 |
+
"learning_rate": 4.365159004218258e-06,
|
| 1668 |
+
"loss": 0.0731,
|
| 1669 |
+
"step": 1185
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 2.302032913843175,
|
| 1673 |
+
"grad_norm": 0.6397315859794617,
|
| 1674 |
+
"learning_rate": 4.25295975767788e-06,
|
| 1675 |
+
"loss": 0.0742,
|
| 1676 |
+
"step": 1190
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 2.3117134559535333,
|
| 1680 |
+
"grad_norm": 0.8097071051597595,
|
| 1681 |
+
"learning_rate": 4.1419826456817615e-06,
|
| 1682 |
+
"loss": 0.0682,
|
| 1683 |
+
"step": 1195
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 2.3213939980638916,
|
| 1687 |
+
"grad_norm": 0.6747831702232361,
|
| 1688 |
+
"learning_rate": 4.032240288352199e-06,
|
| 1689 |
+
"loss": 0.0723,
|
| 1690 |
+
"step": 1200
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 2.33107454017425,
|
| 1694 |
+
"grad_norm": 0.6692532896995544,
|
| 1695 |
+
"learning_rate": 3.923745165397363e-06,
|
| 1696 |
+
"loss": 0.0726,
|
| 1697 |
+
"step": 1205
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 2.340755082284608,
|
| 1701 |
+
"grad_norm": 0.5731667280197144,
|
| 1702 |
+
"learning_rate": 3.816509614692105e-06,
|
| 1703 |
+
"loss": 0.0746,
|
| 1704 |
+
"step": 1210
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 2.350435624394966,
|
| 1708 |
+
"grad_norm": 0.6692930459976196,
|
| 1709 |
+
"learning_rate": 3.7105458308749498e-06,
|
| 1710 |
+
"loss": 0.071,
|
| 1711 |
+
"step": 1215
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 2.3601161665053243,
|
| 1715 |
+
"grad_norm": 0.667002260684967,
|
| 1716 |
+
"learning_rate": 3.6058658639613146e-06,
|
| 1717 |
+
"loss": 0.0671,
|
| 1718 |
+
"step": 1220
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 2.3697967086156826,
|
| 1722 |
+
"grad_norm": 0.5717707276344299,
|
| 1723 |
+
"learning_rate": 3.5024816179732168e-06,
|
| 1724 |
+
"loss": 0.0649,
|
| 1725 |
+
"step": 1225
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 2.3794772507260404,
|
| 1729 |
+
"grad_norm": 0.8209498524665833,
|
| 1730 |
+
"learning_rate": 3.4004048495855642e-06,
|
| 1731 |
+
"loss": 0.0705,
|
| 1732 |
+
"step": 1230
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 2.3891577928363987,
|
| 1736 |
+
"grad_norm": 0.8030904531478882,
|
| 1737 |
+
"learning_rate": 3.299647166789215e-06,
|
| 1738 |
+
"loss": 0.0733,
|
| 1739 |
+
"step": 1235
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 2.398838334946757,
|
| 1743 |
+
"grad_norm": 0.6974596977233887,
|
| 1744 |
+
"learning_rate": 3.200220027570912e-06,
|
| 1745 |
+
"loss": 0.0753,
|
| 1746 |
+
"step": 1240
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 2.4085188770571153,
|
| 1750 |
+
"grad_norm": 0.7229620218276978,
|
| 1751 |
+
"learning_rate": 3.102134738610337e-06,
|
| 1752 |
+
"loss": 0.0667,
|
| 1753 |
+
"step": 1245
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 2.4181994191674736,
|
| 1757 |
+
"grad_norm": 0.6940773725509644,
|
| 1758 |
+
"learning_rate": 3.0054024539943125e-06,
|
| 1759 |
+
"loss": 0.0727,
|
| 1760 |
+
"step": 1250
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 2.4278799612778315,
|
| 1764 |
+
"grad_norm": 0.5743969082832336,
|
| 1765 |
+
"learning_rate": 2.9100341739483722e-06,
|
| 1766 |
+
"loss": 0.0638,
|
| 1767 |
+
"step": 1255
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 2.4375605033881897,
|
| 1771 |
+
"grad_norm": 0.6835336685180664,
|
| 1772 |
+
"learning_rate": 2.81604074358586e-06,
|
| 1773 |
+
"loss": 0.07,
|
| 1774 |
+
"step": 1260
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 2.447241045498548,
|
| 1778 |
+
"grad_norm": 0.6832726001739502,
|
| 1779 |
+
"learning_rate": 2.723432851674618e-06,
|
| 1780 |
+
"loss": 0.0753,
|
| 1781 |
+
"step": 1265
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 2.456921587608906,
|
| 1785 |
+
"grad_norm": 0.6815051436424255,
|
| 1786 |
+
"learning_rate": 2.6322210294215005e-06,
|
| 1787 |
+
"loss": 0.0705,
|
| 1788 |
+
"step": 1270
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 2.466602129719264,
|
| 1792 |
+
"grad_norm": 0.7195925712585449,
|
| 1793 |
+
"learning_rate": 2.542415649274752e-06,
|
| 1794 |
+
"loss": 0.0637,
|
| 1795 |
+
"step": 1275
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 2.4762826718296225,
|
| 1799 |
+
"grad_norm": 0.5729106068611145,
|
| 1800 |
+
"learning_rate": 2.4540269237445086e-06,
|
| 1801 |
+
"loss": 0.065,
|
| 1802 |
+
"step": 1280
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 2.4859632139399808,
|
| 1806 |
+
"grad_norm": 0.6054389476776123,
|
| 1807 |
+
"learning_rate": 2.367064904241422e-06,
|
| 1808 |
+
"loss": 0.0607,
|
| 1809 |
+
"step": 1285
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 2.495643756050339,
|
| 1813 |
+
"grad_norm": 0.7098192572593689,
|
| 1814 |
+
"learning_rate": 2.2815394799336457e-06,
|
| 1815 |
+
"loss": 0.0599,
|
| 1816 |
+
"step": 1290
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 2.505324298160697,
|
| 1820 |
+
"grad_norm": 0.6422216892242432,
|
| 1821 |
+
"learning_rate": 2.1974603766222456e-06,
|
| 1822 |
+
"loss": 0.073,
|
| 1823 |
+
"step": 1295
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 2.515004840271055,
|
| 1827 |
+
"grad_norm": 0.6374565362930298,
|
| 1828 |
+
"learning_rate": 2.1148371556352076e-06,
|
| 1829 |
+
"loss": 0.0657,
|
| 1830 |
+
"step": 1300
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 2.5246853823814135,
|
| 1834 |
+
"grad_norm": 0.6549335718154907,
|
| 1835 |
+
"learning_rate": 2.0336792127401273e-06,
|
| 1836 |
+
"loss": 0.066,
|
| 1837 |
+
"step": 1305
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 2.5343659244917713,
|
| 1841 |
+
"grad_norm": 0.5577257871627808,
|
| 1842 |
+
"learning_rate": 1.953995777075758e-06,
|
| 1843 |
+
"loss": 0.0668,
|
| 1844 |
+
"step": 1310
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 2.5440464666021296,
|
| 1848 |
+
"grad_norm": 0.6442563533782959,
|
| 1849 |
+
"learning_rate": 1.875795910102478e-06,
|
| 1850 |
+
"loss": 0.0775,
|
| 1851 |
+
"step": 1315
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 2.553727008712488,
|
| 1855 |
+
"grad_norm": 0.6345446705818176,
|
| 1856 |
+
"learning_rate": 1.799088504571843e-06,
|
| 1857 |
+
"loss": 0.0583,
|
| 1858 |
+
"step": 1320
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 2.563407550822846,
|
| 1862 |
+
"grad_norm": 0.49139729142189026,
|
| 1863 |
+
"learning_rate": 1.7238822835153e-06,
|
| 1864 |
+
"loss": 0.0582,
|
| 1865 |
+
"step": 1325
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 2.5730880929332045,
|
| 1869 |
+
"grad_norm": 0.5551604628562927,
|
| 1870 |
+
"learning_rate": 1.6501857992522485e-06,
|
| 1871 |
+
"loss": 0.0626,
|
| 1872 |
+
"step": 1330
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 2.5827686350435624,
|
| 1876 |
+
"grad_norm": 0.5181462168693542,
|
| 1877 |
+
"learning_rate": 1.5780074324174693e-06,
|
| 1878 |
+
"loss": 0.059,
|
| 1879 |
+
"step": 1335
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 2.5924491771539206,
|
| 1883 |
+
"grad_norm": 0.7382829189300537,
|
| 1884 |
+
"learning_rate": 1.5073553910080845e-06,
|
| 1885 |
+
"loss": 0.0608,
|
| 1886 |
+
"step": 1340
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 2.602129719264279,
|
| 1890 |
+
"grad_norm": 0.6327388882637024,
|
| 1891 |
+
"learning_rate": 1.4382377094501787e-06,
|
| 1892 |
+
"loss": 0.0645,
|
| 1893 |
+
"step": 1345
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 2.611810261374637,
|
| 1897 |
+
"grad_norm": 0.6324862837791443,
|
| 1898 |
+
"learning_rate": 1.3706622476851277e-06,
|
| 1899 |
+
"loss": 0.0681,
|
| 1900 |
+
"step": 1350
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 2.621490803484995,
|
| 1904 |
+
"grad_norm": 0.6399654150009155,
|
| 1905 |
+
"learning_rate": 1.3046366902757794e-06,
|
| 1906 |
+
"loss": 0.0685,
|
| 1907 |
+
"step": 1355
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 2.6311713455953534,
|
| 1911 |
+
"grad_norm": 0.6386643648147583,
|
| 1912 |
+
"learning_rate": 1.2401685455325789e-06,
|
| 1913 |
+
"loss": 0.0557,
|
| 1914 |
+
"step": 1360
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 2.6408518877057117,
|
| 1918 |
+
"grad_norm": 0.5728330016136169,
|
| 1919 |
+
"learning_rate": 1.17726514465974e-06,
|
| 1920 |
+
"loss": 0.0525,
|
| 1921 |
+
"step": 1365
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 2.65053242981607,
|
| 1925 |
+
"grad_norm": 0.7218917608261108,
|
| 1926 |
+
"learning_rate": 1.1159336409215448e-06,
|
| 1927 |
+
"loss": 0.065,
|
| 1928 |
+
"step": 1370
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 2.660212971926428,
|
| 1932 |
+
"grad_norm": 0.6826200485229492,
|
| 1933 |
+
"learning_rate": 1.0561810088289042e-06,
|
| 1934 |
+
"loss": 0.0645,
|
| 1935 |
+
"step": 1375
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 2.669893514036786,
|
| 1939 |
+
"grad_norm": 0.6935150623321533,
|
| 1940 |
+
"learning_rate": 9.980140433462093e-07,
|
| 1941 |
+
"loss": 0.062,
|
| 1942 |
+
"step": 1380
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 2.6795740561471444,
|
| 1946 |
+
"grad_norm": 0.5919090509414673,
|
| 1947 |
+
"learning_rate": 9.414393591186333e-07,
|
| 1948 |
+
"loss": 0.0646,
|
| 1949 |
+
"step": 1385
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 2.6892545982575022,
|
| 1953 |
+
"grad_norm": 0.36325803399086,
|
| 1954 |
+
"learning_rate": 8.864633897199182e-07,
|
| 1955 |
+
"loss": 0.0567,
|
| 1956 |
+
"step": 1390
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 2.6989351403678605,
|
| 1960 |
+
"grad_norm": 0.4311537742614746,
|
| 1961 |
+
"learning_rate": 8.330923869207702e-07,
|
| 1962 |
+
"loss": 0.051,
|
| 1963 |
+
"step": 1395
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 2.708615682478219,
|
| 1967 |
+
"grad_norm": 0.6049902439117432,
|
| 1968 |
+
"learning_rate": 7.813324199778999e-07,
|
| 1969 |
+
"loss": 0.0637,
|
| 1970 |
+
"step": 1400
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 2.718296224588577,
|
| 1974 |
+
"grad_norm": 0.5618370175361633,
|
| 1975 |
+
"learning_rate": 7.311893749438592e-07,
|
| 1976 |
+
"loss": 0.0618,
|
| 1977 |
+
"step": 1405
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 2.7279767666989354,
|
| 1981 |
+
"grad_norm": 0.5814527273178101,
|
| 1982 |
+
"learning_rate": 6.826689539976772e-07,
|
| 1983 |
+
"loss": 0.0632,
|
| 1984 |
+
"step": 1410
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 2.7376573088092933,
|
| 1988 |
+
"grad_norm": 0.4678923487663269,
|
| 1989 |
+
"learning_rate": 6.3577667479642e-07,
|
| 1990 |
+
"loss": 0.0562,
|
| 1991 |
+
"step": 1415
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 2.7473378509196515,
|
| 1995 |
+
"grad_norm": 0.5974392890930176,
|
| 1996 |
+
"learning_rate": 5.905178698477315e-07,
|
| 1997 |
+
"loss": 0.0651,
|
| 1998 |
+
"step": 1420
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 2.75701839303001,
|
| 2002 |
+
"grad_norm": 0.5679447054862976,
|
| 2003 |
+
"learning_rate": 5.468976859034397e-07,
|
| 2004 |
+
"loss": 0.0547,
|
| 2005 |
+
"step": 1425
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 2.7666989351403677,
|
| 2009 |
+
"grad_norm": 0.5908785462379456,
|
| 2010 |
+
"learning_rate": 5.049210833742618e-07,
|
| 2011 |
+
"loss": 0.0643,
|
| 2012 |
+
"step": 1430
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 2.776379477250726,
|
| 2016 |
+
"grad_norm": 0.6061670780181885,
|
| 2017 |
+
"learning_rate": 4.6459283576572696e-07,
|
| 2018 |
+
"loss": 0.0599,
|
| 2019 |
+
"step": 1435
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 2.7860600193610843,
|
| 2023 |
+
"grad_norm": 0.6512853503227234,
|
| 2024 |
+
"learning_rate": 4.2591752913533233e-07,
|
| 2025 |
+
"loss": 0.0581,
|
| 2026 |
+
"step": 1440
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 2.7957405614714426,
|
| 2030 |
+
"grad_norm": 0.48175665736198425,
|
| 2031 |
+
"learning_rate": 3.888995615710367e-07,
|
| 2032 |
+
"loss": 0.0603,
|
| 2033 |
+
"step": 1445
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 2.805421103581801,
|
| 2037 |
+
"grad_norm": 0.6186909675598145,
|
| 2038 |
+
"learning_rate": 3.53543142691104e-07,
|
| 2039 |
+
"loss": 0.0638,
|
| 2040 |
+
"step": 1450
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 2.8151016456921587,
|
| 2044 |
+
"grad_norm": 0.5678679943084717,
|
| 2045 |
+
"learning_rate": 3.198522931654047e-07,
|
| 2046 |
+
"loss": 0.0539,
|
| 2047 |
+
"step": 1455
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 2.824782187802517,
|
| 2051 |
+
"grad_norm": 0.6124197840690613,
|
| 2052 |
+
"learning_rate": 2.8783084425818453e-07,
|
| 2053 |
+
"loss": 0.0681,
|
| 2054 |
+
"step": 1460
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 2.8344627299128753,
|
| 2058 |
+
"grad_norm": 0.5437132716178894,
|
| 2059 |
+
"learning_rate": 2.574824373923834e-07,
|
| 2060 |
+
"loss": 0.0598,
|
| 2061 |
+
"step": 1465
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 2.844143272023233,
|
| 2065 |
+
"grad_norm": 0.6260445713996887,
|
| 2066 |
+
"learning_rate": 2.2881052373553312e-07,
|
| 2067 |
+
"loss": 0.0578,
|
| 2068 |
+
"step": 1470
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 2.8538238141335914,
|
| 2072 |
+
"grad_norm": 0.5867874622344971,
|
| 2073 |
+
"learning_rate": 2.018183638073112e-07,
|
| 2074 |
+
"loss": 0.0584,
|
| 2075 |
+
"step": 1475
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 2.8635043562439497,
|
| 2079 |
+
"grad_norm": 0.5346993207931519,
|
| 2080 |
+
"learning_rate": 1.7650902710874273e-07,
|
| 2081 |
+
"loss": 0.0565,
|
| 2082 |
+
"step": 1480
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 2.8731848983543076,
|
| 2086 |
+
"grad_norm": 0.5810688138008118,
|
| 2087 |
+
"learning_rate": 1.5288539177315598e-07,
|
| 2088 |
+
"loss": 0.0503,
|
| 2089 |
+
"step": 1485
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 2.882865440464666,
|
| 2093 |
+
"grad_norm": 0.4510127902030945,
|
| 2094 |
+
"learning_rate": 1.3095014423887275e-07,
|
| 2095 |
+
"loss": 0.0505,
|
| 2096 |
+
"step": 1490
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 2.892545982575024,
|
| 2100 |
+
"grad_norm": 0.49212077260017395,
|
| 2101 |
+
"learning_rate": 1.1070577894372769e-07,
|
| 2102 |
+
"loss": 0.0562,
|
| 2103 |
+
"step": 1495
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 2.9022265246853824,
|
| 2107 |
+
"grad_norm": 0.6030415296554565,
|
| 2108 |
+
"learning_rate": 9.215459804139347e-08,
|
| 2109 |
+
"loss": 0.0707,
|
| 2110 |
+
"step": 1500
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"epoch": 2.9119070667957407,
|
| 2114 |
+
"grad_norm": 0.5956991910934448,
|
| 2115 |
+
"learning_rate": 7.529871113958198e-08,
|
| 2116 |
+
"loss": 0.0616,
|
| 2117 |
+
"step": 1505
|
| 2118 |
+
},
|
| 2119 |
+
{
|
| 2120 |
+
"epoch": 2.9215876089060986,
|
| 2121 |
+
"grad_norm": 0.42999911308288574,
|
| 2122 |
+
"learning_rate": 6.014003506015275e-08,
|
| 2123 |
+
"loss": 0.0571,
|
| 2124 |
+
"step": 1510
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 2.931268151016457,
|
| 2128 |
+
"grad_norm": 0.5331460237503052,
|
| 2129 |
+
"learning_rate": 4.6680293621134127e-08,
|
| 2130 |
+
"loss": 0.055,
|
| 2131 |
+
"step": 1515
|
| 2132 |
+
},
|
| 2133 |
+
{
|
| 2134 |
+
"epoch": 2.940948693126815,
|
| 2135 |
+
"grad_norm": 0.622313916683197,
|
| 2136 |
+
"learning_rate": 3.4921017440683324e-08,
|
| 2137 |
+
"loss": 0.0664,
|
| 2138 |
+
"step": 1520
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 2.950629235237173,
|
| 2142 |
+
"grad_norm": 0.5072144269943237,
|
| 2143 |
+
"learning_rate": 2.4863543763040674e-08,
|
| 2144 |
+
"loss": 0.0566,
|
| 2145 |
+
"step": 1525
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 2.9603097773475313,
|
| 2149 |
+
"grad_norm": 0.5802115201950073,
|
| 2150 |
+
"learning_rate": 1.6509016306449632e-08,
|
| 2151 |
+
"loss": 0.0595,
|
| 2152 |
+
"step": 1530
|
| 2153 |
+
},
|
| 2154 |
+
{
|
| 2155 |
+
"epoch": 2.9699903194578896,
|
| 2156 |
+
"grad_norm": 0.6113269925117493,
|
| 2157 |
+
"learning_rate": 9.858385133102443e-09,
|
| 2158 |
+
"loss": 0.0635,
|
| 2159 |
+
"step": 1535
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 2.979670861568248,
|
| 2163 |
+
"grad_norm": 0.5206665396690369,
|
| 2164 |
+
"learning_rate": 4.912406541098258e-09,
|
| 2165 |
+
"loss": 0.0539,
|
| 2166 |
+
"step": 1540
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 2.989351403678606,
|
| 2170 |
+
"grad_norm": 0.5739409327507019,
|
| 2171 |
+
"learning_rate": 1.6716429784352504e-09,
|
| 2172 |
+
"loss": 0.0664,
|
| 2173 |
+
"step": 1545
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 2.999031945788964,
|
| 2177 |
+
"grad_norm": 0.6693248152732849,
|
| 2178 |
+
"learning_rate": 1.3646297905678397e-10,
|
| 2179 |
+
"loss": 0.0582,
|
| 2180 |
+
"step": 1550
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 3.0,
|
| 2184 |
+
"step": 1551,
|
| 2185 |
+
"total_flos": 1.9777146565039227e+18,
|
| 2186 |
+
"train_loss": 0.34789815965888576,
|
| 2187 |
+
"train_runtime": 958.473,
|
| 2188 |
+
"train_samples_per_second": 51.692,
|
| 2189 |
+
"train_steps_per_second": 1.618
|
| 2190 |
+
}
|
| 2191 |
+
],
|
| 2192 |
+
"logging_steps": 5,
|
| 2193 |
+
"max_steps": 1551,
|
| 2194 |
+
"num_input_tokens_seen": 0,
|
| 2195 |
+
"num_train_epochs": 3,
|
| 2196 |
+
"save_steps": 20000,
|
| 2197 |
+
"stateful_callbacks": {
|
| 2198 |
+
"TrainerControl": {
|
| 2199 |
+
"args": {
|
| 2200 |
+
"should_epoch_stop": false,
|
| 2201 |
+
"should_evaluate": false,
|
| 2202 |
+
"should_log": false,
|
| 2203 |
+
"should_save": false,
|
| 2204 |
+
"should_training_stop": false
|
| 2205 |
+
},
|
| 2206 |
+
"attributes": {}
|
| 2207 |
+
}
|
| 2208 |
+
},
|
| 2209 |
+
"total_flos": 1.9777146565039227e+18,
|
| 2210 |
+
"train_batch_size": 2,
|
| 2211 |
+
"trial_name": null,
|
| 2212 |
+
"trial_params": null
|
| 2213 |
+
}
|
instruct/132_128_e3_3e-5/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:21b6c6a4e5418ed34878981964102626a094d97368cc024663a23cd141f7fdf5
|
| 3 |
+
size 8273
|
instruct/132_128_e3_3e-5/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|