Upload folder using huggingface_hub
Browse files- instruct/12_128_e3_3e-5/adapter_config.json +39 -0
- instruct/12_128_e3_3e-5/adapter_model.safetensors +3 -0
- instruct/12_128_e3_3e-5/added_tokens.json +9 -0
- instruct/12_128_e3_3e-5/all_results.json +9 -0
- instruct/12_128_e3_3e-5/chat_template.jinja +62 -0
- instruct/12_128_e3_3e-5/config.json +32 -0
- instruct/12_128_e3_3e-5/merges.txt +0 -0
- instruct/12_128_e3_3e-5/special_tokens_map.json +33 -0
- instruct/12_128_e3_3e-5/tokenizer.json +0 -0
- instruct/12_128_e3_3e-5/tokenizer_config.json +234 -0
- instruct/12_128_e3_3e-5/train_results.json +9 -0
- instruct/12_128_e3_3e-5/trainer_state.json +2276 -0
- instruct/12_128_e3_3e-5/training_args.bin +3 -0
- instruct/12_128_e3_3e-5/vocab.json +0 -0
instruct/12_128_e3_3e-5/adapter_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "ibm-granite/granite-3.3-8b-instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 256,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.05,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 128,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"k_proj",
|
| 28 |
+
"q_proj",
|
| 29 |
+
"up_proj",
|
| 30 |
+
"down_proj",
|
| 31 |
+
"v_proj",
|
| 32 |
+
"o_proj",
|
| 33 |
+
"gate_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
+
"use_dora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
instruct/12_128_e3_3e-5/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e247ec697ab43df592aa8e8ff6e38c3d08fc0cfcefd406dbcb60ef580ac4f2fe
|
| 3 |
+
size 791751704
|
instruct/12_128_e3_3e-5/added_tokens.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|end_of_cite|>": 49156,
|
| 3 |
+
"<|end_of_plugin|>": 49158,
|
| 4 |
+
"<|end_of_role|>": 49153,
|
| 5 |
+
"<|start_of_cite|>": 49155,
|
| 6 |
+
"<|start_of_plugin|>": 49157,
|
| 7 |
+
"<|start_of_role|>": 49152,
|
| 8 |
+
"<|tool_call|>": 49154
|
| 9 |
+
}
|
instruct/12_128_e3_3e-5/all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 2.0415991178298655e+18,
|
| 4 |
+
"train_loss": 0.36059863125452574,
|
| 5 |
+
"train_runtime": 988.9937,
|
| 6 |
+
"train_samples": 17017,
|
| 7 |
+
"train_samples_per_second": 51.619,
|
| 8 |
+
"train_steps_per_second": 1.614
|
| 9 |
+
}
|
instruct/12_128_e3_3e-5/chat_template.jinja
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{# Alias tools -> available_tools #}
|
| 2 |
+
{%- if tools and not available_tools -%}
|
| 3 |
+
{%- set available_tools = tools -%}
|
| 4 |
+
{%- endif -%}
|
| 5 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 6 |
+
{%- set system_message = messages[0]['content'] %}
|
| 7 |
+
{%- set loop_messages = messages[1:] %}
|
| 8 |
+
{%- else %}
|
| 9 |
+
{%- set system_message = "Knowledge Cutoff Date: April 2024.
|
| 10 |
+
Today's Date: " + strftime_now('%B %d, %Y') + ".
|
| 11 |
+
You are Granite, developed by IBM." %}
|
| 12 |
+
{%- if available_tools and documents %}
|
| 13 |
+
{%- set system_message = system_message + " You are a helpful assistant with access to the following tools. When a tool is required to answer the user's query, respond only with <|tool_call|> followed by a JSON list of tools used. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request.
|
| 14 |
+
Write the response to the user's input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data." %}
|
| 15 |
+
{%- elif available_tools %}
|
| 16 |
+
{%- set system_message = system_message + " You are a helpful assistant with access to the following tools. When a tool is required to answer the user's query, respond only with <|tool_call|> followed by a JSON list of tools used. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request." %}
|
| 17 |
+
{%- elif documents %}
|
| 18 |
+
{%- set system_message = system_message + " Write the response to the user's input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data." %}
|
| 19 |
+
{%- elif thinking %}
|
| 20 |
+
{%- set system_message = system_message + " You are a helpful AI assistant.
|
| 21 |
+
Respond to every user query in a comprehensive and detailed way. You can write down your thoughts and reasoning process before responding. In the thought process, engage in a comprehensive cycle of analysis, summarization, exploration, reassessment, reflection, backtracing, and iteration to develop well-considered thinking process. In the response section, based on various attempts, explorations, and reflections from the thoughts section, systematically present the final solution that you deem correct. The response should summarize the thought process. Write your thoughts between <think></think> and write your response between <response></response> for each user query." %}
|
| 22 |
+
{%- else %}
|
| 23 |
+
{%- set system_message = system_message + " You are a helpful AI assistant." %}
|
| 24 |
+
{%- endif %}
|
| 25 |
+
{%- if 'citations' in controls and documents %}
|
| 26 |
+
{%- set system_message = system_message + '
|
| 27 |
+
Use the symbols <|start_of_cite|> and <|end_of_cite|> to indicate when a fact comes from a document in the search result, e.g <|start_of_cite|> {document_id: 1}my fact <|end_of_cite|> for a fact from document 1. Afterwards, list all the citations with their corresponding documents in an ordered list.' %}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{%- if 'hallucinations' in controls and documents %}
|
| 30 |
+
{%- set system_message = system_message + '
|
| 31 |
+
Finally, after the response is written, include a numbered list of sentences from the response with a corresponding risk value that are hallucinated and not based in the documents.' %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{%- set loop_messages = messages %}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{{- '<|start_of_role|>system<|end_of_role|>' + system_message + '<|end_of_text|>
|
| 36 |
+
' }}
|
| 37 |
+
{%- if available_tools %}
|
| 38 |
+
{{- '<|start_of_role|>available_tools<|end_of_role|>' }}
|
| 39 |
+
{{- available_tools | tojson(indent=4) }}
|
| 40 |
+
{{- '<|end_of_text|>
|
| 41 |
+
' }}
|
| 42 |
+
{%- endif %}
|
| 43 |
+
{%- if documents %}
|
| 44 |
+
{%- for document in documents %}
|
| 45 |
+
{{- '<|start_of_role|>document {"document_id": "' + document['doc_id'] | string + '"}<|end_of_role|>
|
| 46 |
+
' }}
|
| 47 |
+
{{- document['text'] }}
|
| 48 |
+
{{- '<|end_of_text|>
|
| 49 |
+
' }}
|
| 50 |
+
{%- endfor %}
|
| 51 |
+
{%- endif %}
|
| 52 |
+
{%- for message in loop_messages %}
|
| 53 |
+
{{- '<|start_of_role|>' + message['role'] + '<|end_of_role|>' + message['content'] + '<|end_of_text|>
|
| 54 |
+
' }}
|
| 55 |
+
{%- if loop.last and add_generation_prompt %}
|
| 56 |
+
{{- '<|start_of_role|>assistant' }}
|
| 57 |
+
{%- if controls %}
|
| 58 |
+
{{- ' ' + controls | tojson()}}
|
| 59 |
+
{%- endif %}
|
| 60 |
+
{{- '<|end_of_role|>' }}
|
| 61 |
+
{%- endif %}
|
| 62 |
+
{%- endfor %}
|
instruct/12_128_e3_3e-5/config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"GraniteForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"attention_multiplier": 0.0078125,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"embedding_multiplier": 12.0,
|
| 10 |
+
"eos_token_id": 0,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 4096,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 12800,
|
| 15 |
+
"logits_scaling": 16.0,
|
| 16 |
+
"max_position_embeddings": 131072,
|
| 17 |
+
"mlp_bias": false,
|
| 18 |
+
"model_type": "granite",
|
| 19 |
+
"num_attention_heads": 32,
|
| 20 |
+
"num_hidden_layers": 40,
|
| 21 |
+
"num_key_value_heads": 8,
|
| 22 |
+
"pad_token_id": 0,
|
| 23 |
+
"residual_multiplier": 0.22,
|
| 24 |
+
"rms_norm_eps": 1e-05,
|
| 25 |
+
"rope_scaling": null,
|
| 26 |
+
"rope_theta": 10000000.0,
|
| 27 |
+
"tie_word_embeddings": true,
|
| 28 |
+
"torch_dtype": "bfloat16",
|
| 29 |
+
"transformers_version": "4.52.4",
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 49159
|
| 32 |
+
}
|
instruct/12_128_e3_3e-5/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
instruct/12_128_e3_3e-5/special_tokens_map.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|start_of_role|>",
|
| 4 |
+
"<|end_of_role|>",
|
| 5 |
+
"<|tool_call|>",
|
| 6 |
+
"<|start_of_cite|>",
|
| 7 |
+
"<|end_of_cite|>",
|
| 8 |
+
"<|start_of_plugin|>",
|
| 9 |
+
"<|end_of_plugin|>"
|
| 10 |
+
],
|
| 11 |
+
"bos_token": {
|
| 12 |
+
"content": "<|end_of_text|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false
|
| 17 |
+
},
|
| 18 |
+
"eos_token": {
|
| 19 |
+
"content": "<|end_of_text|>",
|
| 20 |
+
"lstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
+
"rstrip": false,
|
| 23 |
+
"single_word": false
|
| 24 |
+
},
|
| 25 |
+
"pad_token": "<|end_of_plugin|>",
|
| 26 |
+
"unk_token": {
|
| 27 |
+
"content": "<|end_of_text|>",
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"normalized": false,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"single_word": false
|
| 32 |
+
}
|
| 33 |
+
}
|
instruct/12_128_e3_3e-5/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
instruct/12_128_e3_3e-5/tokenizer_config.json
ADDED
|
@@ -0,0 +1,234 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<|end_of_text|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<fim_prefix>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "<fim_middle>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"3": {
|
| 30 |
+
"content": "<fim_suffix>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"4": {
|
| 38 |
+
"content": "<fim_pad>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"5": {
|
| 46 |
+
"content": "<filename>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"6": {
|
| 54 |
+
"content": "<gh_stars>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"7": {
|
| 62 |
+
"content": "<issue_start>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"8": {
|
| 70 |
+
"content": "<issue_comment>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"9": {
|
| 78 |
+
"content": "<issue_closed>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"10": {
|
| 86 |
+
"content": "<jupyter_start>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"11": {
|
| 94 |
+
"content": "<jupyter_text>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"12": {
|
| 102 |
+
"content": "<jupyter_code>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"13": {
|
| 110 |
+
"content": "<jupyter_output>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"14": {
|
| 118 |
+
"content": "<empty_output>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": true
|
| 124 |
+
},
|
| 125 |
+
"15": {
|
| 126 |
+
"content": "<commit_before>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": true
|
| 132 |
+
},
|
| 133 |
+
"16": {
|
| 134 |
+
"content": "<commit_msg>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": true
|
| 140 |
+
},
|
| 141 |
+
"17": {
|
| 142 |
+
"content": "<commit_after>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": true
|
| 148 |
+
},
|
| 149 |
+
"18": {
|
| 150 |
+
"content": "<reponame>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": true
|
| 156 |
+
},
|
| 157 |
+
"49152": {
|
| 158 |
+
"content": "<|start_of_role|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": true
|
| 164 |
+
},
|
| 165 |
+
"49153": {
|
| 166 |
+
"content": "<|end_of_role|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": true
|
| 172 |
+
},
|
| 173 |
+
"49154": {
|
| 174 |
+
"content": "<|tool_call|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": true
|
| 180 |
+
},
|
| 181 |
+
"49155": {
|
| 182 |
+
"content": "<|start_of_cite|>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": true
|
| 188 |
+
},
|
| 189 |
+
"49156": {
|
| 190 |
+
"content": "<|end_of_cite|>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": true
|
| 196 |
+
},
|
| 197 |
+
"49157": {
|
| 198 |
+
"content": "<|start_of_plugin|>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": true
|
| 204 |
+
},
|
| 205 |
+
"49158": {
|
| 206 |
+
"content": "<|end_of_plugin|>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": true
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|start_of_role|>",
|
| 216 |
+
"<|end_of_role|>",
|
| 217 |
+
"<|tool_call|>",
|
| 218 |
+
"<|start_of_cite|>",
|
| 219 |
+
"<|end_of_cite|>",
|
| 220 |
+
"<|start_of_plugin|>",
|
| 221 |
+
"<|end_of_plugin|>"
|
| 222 |
+
],
|
| 223 |
+
"bos_token": "<|end_of_text|>",
|
| 224 |
+
"clean_up_tokenization_spaces": true,
|
| 225 |
+
"eos_token": "<|end_of_text|>",
|
| 226 |
+
"errors": "replace",
|
| 227 |
+
"extra_special_tokens": {},
|
| 228 |
+
"model_max_length": 8192,
|
| 229 |
+
"pad_token": "<|end_of_plugin|>",
|
| 230 |
+
"padding_side": "left",
|
| 231 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 232 |
+
"unk_token": "<|end_of_text|>",
|
| 233 |
+
"vocab_size": 49152
|
| 234 |
+
}
|
instruct/12_128_e3_3e-5/train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 2.0415991178298655e+18,
|
| 4 |
+
"train_loss": 0.36059863125452574,
|
| 5 |
+
"train_runtime": 988.9937,
|
| 6 |
+
"train_samples": 17017,
|
| 7 |
+
"train_samples_per_second": 51.619,
|
| 8 |
+
"train_steps_per_second": 1.614
|
| 9 |
+
}
|
instruct/12_128_e3_3e-5/trainer_state.json
ADDED
|
@@ -0,0 +1,2276 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 1596,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.009398496240601503,
|
| 14 |
+
"grad_norm": 2.502014398574829,
|
| 15 |
+
"learning_rate": 1.5e-06,
|
| 16 |
+
"loss": 1.5469,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.018796992481203006,
|
| 21 |
+
"grad_norm": 2.0200090408325195,
|
| 22 |
+
"learning_rate": 3.3750000000000003e-06,
|
| 23 |
+
"loss": 1.5636,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.02819548872180451,
|
| 28 |
+
"grad_norm": 1.2822911739349365,
|
| 29 |
+
"learning_rate": 5.25e-06,
|
| 30 |
+
"loss": 1.4923,
|
| 31 |
+
"step": 15
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.03759398496240601,
|
| 35 |
+
"grad_norm": 0.7315253019332886,
|
| 36 |
+
"learning_rate": 7.1249999999999995e-06,
|
| 37 |
+
"loss": 1.4596,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.046992481203007516,
|
| 42 |
+
"grad_norm": 0.5335997343063354,
|
| 43 |
+
"learning_rate": 9e-06,
|
| 44 |
+
"loss": 1.3887,
|
| 45 |
+
"step": 25
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.05639097744360902,
|
| 49 |
+
"grad_norm": 0.6000903248786926,
|
| 50 |
+
"learning_rate": 1.0875e-05,
|
| 51 |
+
"loss": 1.415,
|
| 52 |
+
"step": 30
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.06578947368421052,
|
| 56 |
+
"grad_norm": 0.4487023651599884,
|
| 57 |
+
"learning_rate": 1.275e-05,
|
| 58 |
+
"loss": 1.38,
|
| 59 |
+
"step": 35
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.07518796992481203,
|
| 63 |
+
"grad_norm": 0.41073116660118103,
|
| 64 |
+
"learning_rate": 1.4625e-05,
|
| 65 |
+
"loss": 1.3887,
|
| 66 |
+
"step": 40
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.08458646616541353,
|
| 70 |
+
"grad_norm": 0.4798469841480255,
|
| 71 |
+
"learning_rate": 1.65e-05,
|
| 72 |
+
"loss": 1.3778,
|
| 73 |
+
"step": 45
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.09398496240601503,
|
| 77 |
+
"grad_norm": 0.42918503284454346,
|
| 78 |
+
"learning_rate": 1.8375000000000003e-05,
|
| 79 |
+
"loss": 1.4056,
|
| 80 |
+
"step": 50
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.10338345864661654,
|
| 84 |
+
"grad_norm": 0.5621869564056396,
|
| 85 |
+
"learning_rate": 2.025e-05,
|
| 86 |
+
"loss": 1.3789,
|
| 87 |
+
"step": 55
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.11278195488721804,
|
| 91 |
+
"grad_norm": 0.3957989513874054,
|
| 92 |
+
"learning_rate": 2.2125000000000002e-05,
|
| 93 |
+
"loss": 1.2872,
|
| 94 |
+
"step": 60
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.12218045112781954,
|
| 98 |
+
"grad_norm": 0.4491111636161804,
|
| 99 |
+
"learning_rate": 2.4e-05,
|
| 100 |
+
"loss": 1.332,
|
| 101 |
+
"step": 65
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.13157894736842105,
|
| 105 |
+
"grad_norm": 0.378256618976593,
|
| 106 |
+
"learning_rate": 2.5875000000000002e-05,
|
| 107 |
+
"loss": 1.2599,
|
| 108 |
+
"step": 70
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.14097744360902256,
|
| 112 |
+
"grad_norm": 0.4281750023365021,
|
| 113 |
+
"learning_rate": 2.7750000000000004e-05,
|
| 114 |
+
"loss": 1.3005,
|
| 115 |
+
"step": 75
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.15037593984962405,
|
| 119 |
+
"grad_norm": 0.4786468744277954,
|
| 120 |
+
"learning_rate": 2.9625000000000002e-05,
|
| 121 |
+
"loss": 1.2266,
|
| 122 |
+
"step": 80
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.15977443609022557,
|
| 126 |
+
"grad_norm": 0.46316206455230713,
|
| 127 |
+
"learning_rate": 2.999948467631686e-05,
|
| 128 |
+
"loss": 1.2327,
|
| 129 |
+
"step": 85
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.16917293233082706,
|
| 133 |
+
"grad_norm": 0.5043375492095947,
|
| 134 |
+
"learning_rate": 2.999739123453822e-05,
|
| 135 |
+
"loss": 1.2683,
|
| 136 |
+
"step": 90
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.17857142857142858,
|
| 140 |
+
"grad_norm": 0.5216848850250244,
|
| 141 |
+
"learning_rate": 2.99936876915103e-05,
|
| 142 |
+
"loss": 1.1855,
|
| 143 |
+
"step": 95
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.18796992481203006,
|
| 147 |
+
"grad_norm": 0.5720008611679077,
|
| 148 |
+
"learning_rate": 2.9988374444840858e-05,
|
| 149 |
+
"loss": 1.1781,
|
| 150 |
+
"step": 100
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.19736842105263158,
|
| 154 |
+
"grad_norm": 0.5401681661605835,
|
| 155 |
+
"learning_rate": 2.9981452064953454e-05,
|
| 156 |
+
"loss": 1.1784,
|
| 157 |
+
"step": 105
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.20676691729323307,
|
| 161 |
+
"grad_norm": 0.5164614915847778,
|
| 162 |
+
"learning_rate": 2.997292129502616e-05,
|
| 163 |
+
"loss": 1.1571,
|
| 164 |
+
"step": 110
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.2161654135338346,
|
| 168 |
+
"grad_norm": 0.5654135942459106,
|
| 169 |
+
"learning_rate": 2.9962783050911824e-05,
|
| 170 |
+
"loss": 1.1502,
|
| 171 |
+
"step": 115
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.22556390977443608,
|
| 175 |
+
"grad_norm": 0.6060947179794312,
|
| 176 |
+
"learning_rate": 2.9951038421039704e-05,
|
| 177 |
+
"loss": 1.1131,
|
| 178 |
+
"step": 120
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.2349624060150376,
|
| 182 |
+
"grad_norm": 0.5892205834388733,
|
| 183 |
+
"learning_rate": 2.9937688666298648e-05,
|
| 184 |
+
"loss": 1.0911,
|
| 185 |
+
"step": 125
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.24436090225563908,
|
| 189 |
+
"grad_norm": 0.5846742987632751,
|
| 190 |
+
"learning_rate": 2.9922735219901693e-05,
|
| 191 |
+
"loss": 1.0838,
|
| 192 |
+
"step": 130
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.25375939849624063,
|
| 196 |
+
"grad_norm": 0.711112916469574,
|
| 197 |
+
"learning_rate": 2.990617968723223e-05,
|
| 198 |
+
"loss": 1.0234,
|
| 199 |
+
"step": 135
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.2631578947368421,
|
| 203 |
+
"grad_norm": 0.631570041179657,
|
| 204 |
+
"learning_rate": 2.9888023845671632e-05,
|
| 205 |
+
"loss": 1.1093,
|
| 206 |
+
"step": 140
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.2725563909774436,
|
| 210 |
+
"grad_norm": 0.6685044765472412,
|
| 211 |
+
"learning_rate": 2.9868269644408445e-05,
|
| 212 |
+
"loss": 1.0641,
|
| 213 |
+
"step": 145
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.2819548872180451,
|
| 217 |
+
"grad_norm": 0.7012262940406799,
|
| 218 |
+
"learning_rate": 2.984691920422911e-05,
|
| 219 |
+
"loss": 1.0143,
|
| 220 |
+
"step": 150
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.29135338345864664,
|
| 224 |
+
"grad_norm": 0.8340694308280945,
|
| 225 |
+
"learning_rate": 2.9823974817290317e-05,
|
| 226 |
+
"loss": 0.99,
|
| 227 |
+
"step": 155
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.3007518796992481,
|
| 231 |
+
"grad_norm": 0.8734436631202698,
|
| 232 |
+
"learning_rate": 2.9799438946872865e-05,
|
| 233 |
+
"loss": 0.9719,
|
| 234 |
+
"step": 160
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.3101503759398496,
|
| 238 |
+
"grad_norm": 0.8449086546897888,
|
| 239 |
+
"learning_rate": 2.9773314227117265e-05,
|
| 240 |
+
"loss": 0.9679,
|
| 241 |
+
"step": 165
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.31954887218045114,
|
| 245 |
+
"grad_norm": 0.8639029860496521,
|
| 246 |
+
"learning_rate": 2.9745603462740886e-05,
|
| 247 |
+
"loss": 0.9634,
|
| 248 |
+
"step": 170
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.32894736842105265,
|
| 252 |
+
"grad_norm": 0.7578688263893127,
|
| 253 |
+
"learning_rate": 2.97163096287369e-05,
|
| 254 |
+
"loss": 0.9581,
|
| 255 |
+
"step": 175
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.3383458646616541,
|
| 259 |
+
"grad_norm": 0.7792065739631653,
|
| 260 |
+
"learning_rate": 2.9685435870054843e-05,
|
| 261 |
+
"loss": 0.9393,
|
| 262 |
+
"step": 180
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.34774436090225563,
|
| 266 |
+
"grad_norm": 1.0152794122695923,
|
| 267 |
+
"learning_rate": 2.9652985501263013e-05,
|
| 268 |
+
"loss": 0.8903,
|
| 269 |
+
"step": 185
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.35714285714285715,
|
| 273 |
+
"grad_norm": 0.8871893882751465,
|
| 274 |
+
"learning_rate": 2.9618962006192595e-05,
|
| 275 |
+
"loss": 0.9388,
|
| 276 |
+
"step": 190
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.36654135338345867,
|
| 280 |
+
"grad_norm": 0.8481462597846985,
|
| 281 |
+
"learning_rate": 2.9583369037563655e-05,
|
| 282 |
+
"loss": 0.8553,
|
| 283 |
+
"step": 195
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.37593984962406013,
|
| 287 |
+
"grad_norm": 0.9429571628570557,
|
| 288 |
+
"learning_rate": 2.9546210416592988e-05,
|
| 289 |
+
"loss": 0.9058,
|
| 290 |
+
"step": 200
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.38533834586466165,
|
| 294 |
+
"grad_norm": 0.9846692085266113,
|
| 295 |
+
"learning_rate": 2.9507490132583873e-05,
|
| 296 |
+
"loss": 0.8096,
|
| 297 |
+
"step": 205
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.39473684210526316,
|
| 301 |
+
"grad_norm": 0.980230987071991,
|
| 302 |
+
"learning_rate": 2.946721234249779e-05,
|
| 303 |
+
"loss": 0.87,
|
| 304 |
+
"step": 210
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.4041353383458647,
|
| 308 |
+
"grad_norm": 1.0099208354949951,
|
| 309 |
+
"learning_rate": 2.9425381370508138e-05,
|
| 310 |
+
"loss": 0.8291,
|
| 311 |
+
"step": 215
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.41353383458646614,
|
| 315 |
+
"grad_norm": 0.939041256904602,
|
| 316 |
+
"learning_rate": 2.9382001707535976e-05,
|
| 317 |
+
"loss": 0.8555,
|
| 318 |
+
"step": 220
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.42293233082706766,
|
| 322 |
+
"grad_norm": 1.0197454690933228,
|
| 323 |
+
"learning_rate": 2.9337078010767914e-05,
|
| 324 |
+
"loss": 0.8518,
|
| 325 |
+
"step": 225
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.4323308270676692,
|
| 329 |
+
"grad_norm": 1.0676138401031494,
|
| 330 |
+
"learning_rate": 2.9290615103156095e-05,
|
| 331 |
+
"loss": 0.836,
|
| 332 |
+
"step": 230
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.4417293233082707,
|
| 336 |
+
"grad_norm": 1.1104499101638794,
|
| 337 |
+
"learning_rate": 2.924261797290043e-05,
|
| 338 |
+
"loss": 0.8404,
|
| 339 |
+
"step": 235
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.45112781954887216,
|
| 343 |
+
"grad_norm": 0.8881465196609497,
|
| 344 |
+
"learning_rate": 2.9193091772913064e-05,
|
| 345 |
+
"loss": 0.8172,
|
| 346 |
+
"step": 240
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.4605263157894737,
|
| 350 |
+
"grad_norm": 1.028106927871704,
|
| 351 |
+
"learning_rate": 2.9142041820265163e-05,
|
| 352 |
+
"loss": 0.7831,
|
| 353 |
+
"step": 245
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.4699248120300752,
|
| 357 |
+
"grad_norm": 0.9798471331596375,
|
| 358 |
+
"learning_rate": 2.908947359561607e-05,
|
| 359 |
+
"loss": 0.7552,
|
| 360 |
+
"step": 250
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.4793233082706767,
|
| 364 |
+
"grad_norm": 1.0129481554031372,
|
| 365 |
+
"learning_rate": 2.9035392742624943e-05,
|
| 366 |
+
"loss": 0.7903,
|
| 367 |
+
"step": 255
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.48872180451127817,
|
| 371 |
+
"grad_norm": 1.1476976871490479,
|
| 372 |
+
"learning_rate": 2.8979805067344808e-05,
|
| 373 |
+
"loss": 0.7736,
|
| 374 |
+
"step": 260
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.4981203007518797,
|
| 378 |
+
"grad_norm": 1.058274269104004,
|
| 379 |
+
"learning_rate": 2.8922716537599273e-05,
|
| 380 |
+
"loss": 0.7195,
|
| 381 |
+
"step": 265
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.5075187969924813,
|
| 385 |
+
"grad_norm": 1.0607396364212036,
|
| 386 |
+
"learning_rate": 2.8864133282341818e-05,
|
| 387 |
+
"loss": 0.7259,
|
| 388 |
+
"step": 270
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.5169172932330827,
|
| 392 |
+
"grad_norm": 1.0076299905776978,
|
| 393 |
+
"learning_rate": 2.8804061590997775e-05,
|
| 394 |
+
"loss": 0.7034,
|
| 395 |
+
"step": 275
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.5263157894736842,
|
| 399 |
+
"grad_norm": 0.9910840392112732,
|
| 400 |
+
"learning_rate": 2.874250791278913e-05,
|
| 401 |
+
"loss": 0.6738,
|
| 402 |
+
"step": 280
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.5357142857142857,
|
| 406 |
+
"grad_norm": 1.1556156873703003,
|
| 407 |
+
"learning_rate": 2.8679478856042137e-05,
|
| 408 |
+
"loss": 0.6827,
|
| 409 |
+
"step": 285
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.5451127819548872,
|
| 413 |
+
"grad_norm": 0.9208582043647766,
|
| 414 |
+
"learning_rate": 2.8614981187477845e-05,
|
| 415 |
+
"loss": 0.7085,
|
| 416 |
+
"step": 290
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.5545112781954887,
|
| 420 |
+
"grad_norm": 1.012955904006958,
|
| 421 |
+
"learning_rate": 2.8549021831485645e-05,
|
| 422 |
+
"loss": 0.6869,
|
| 423 |
+
"step": 295
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.5639097744360902,
|
| 427 |
+
"grad_norm": 1.103227972984314,
|
| 428 |
+
"learning_rate": 2.8481607869379873e-05,
|
| 429 |
+
"loss": 0.6031,
|
| 430 |
+
"step": 300
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.5733082706766918,
|
| 434 |
+
"grad_norm": 1.2159794569015503,
|
| 435 |
+
"learning_rate": 2.8412746538639556e-05,
|
| 436 |
+
"loss": 0.7008,
|
| 437 |
+
"step": 305
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.5827067669172933,
|
| 441 |
+
"grad_norm": 1.063978672027588,
|
| 442 |
+
"learning_rate": 2.8342445232131427e-05,
|
| 443 |
+
"loss": 0.665,
|
| 444 |
+
"step": 310
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.5921052631578947,
|
| 448 |
+
"grad_norm": 1.1001124382019043,
|
| 449 |
+
"learning_rate": 2.8270711497316208e-05,
|
| 450 |
+
"loss": 0.6327,
|
| 451 |
+
"step": 315
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.6015037593984962,
|
| 455 |
+
"grad_norm": 1.1076452732086182,
|
| 456 |
+
"learning_rate": 2.8197553035438365e-05,
|
| 457 |
+
"loss": 0.6637,
|
| 458 |
+
"step": 320
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.6109022556390977,
|
| 462 |
+
"grad_norm": 1.1827822923660278,
|
| 463 |
+
"learning_rate": 2.8122977700699263e-05,
|
| 464 |
+
"loss": 0.6087,
|
| 465 |
+
"step": 325
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.6203007518796992,
|
| 469 |
+
"grad_norm": 1.1983767747879028,
|
| 470 |
+
"learning_rate": 2.8046993499413982e-05,
|
| 471 |
+
"loss": 0.5684,
|
| 472 |
+
"step": 330
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.6296992481203008,
|
| 476 |
+
"grad_norm": 1.2548726797103882,
|
| 477 |
+
"learning_rate": 2.796960858915177e-05,
|
| 478 |
+
"loss": 0.6433,
|
| 479 |
+
"step": 335
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.6390977443609023,
|
| 483 |
+
"grad_norm": 1.2525805234909058,
|
| 484 |
+
"learning_rate": 2.7890831277860243e-05,
|
| 485 |
+
"loss": 0.6509,
|
| 486 |
+
"step": 340
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.6484962406015038,
|
| 490 |
+
"grad_norm": 1.1672039031982422,
|
| 491 |
+
"learning_rate": 2.781067002297344e-05,
|
| 492 |
+
"loss": 0.6039,
|
| 493 |
+
"step": 345
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.6578947368421053,
|
| 497 |
+
"grad_norm": 1.2225556373596191,
|
| 498 |
+
"learning_rate": 2.7729133430503884e-05,
|
| 499 |
+
"loss": 0.622,
|
| 500 |
+
"step": 350
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.6672932330827067,
|
| 504 |
+
"grad_norm": 1.2113149166107178,
|
| 505 |
+
"learning_rate": 2.7646230254118617e-05,
|
| 506 |
+
"loss": 0.6003,
|
| 507 |
+
"step": 355
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.6766917293233082,
|
| 511 |
+
"grad_norm": 1.285935640335083,
|
| 512 |
+
"learning_rate": 2.756196939419943e-05,
|
| 513 |
+
"loss": 0.5416,
|
| 514 |
+
"step": 360
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.6860902255639098,
|
| 518 |
+
"grad_norm": 1.180495023727417,
|
| 519 |
+
"learning_rate": 2.747635989688733e-05,
|
| 520 |
+
"loss": 0.604,
|
| 521 |
+
"step": 365
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.6954887218045113,
|
| 525 |
+
"grad_norm": 1.1116900444030762,
|
| 526 |
+
"learning_rate": 2.738941095311135e-05,
|
| 527 |
+
"loss": 0.556,
|
| 528 |
+
"step": 370
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.7048872180451128,
|
| 532 |
+
"grad_norm": 1.1285786628723145,
|
| 533 |
+
"learning_rate": 2.730113189760183e-05,
|
| 534 |
+
"loss": 0.6079,
|
| 535 |
+
"step": 375
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.7142857142857143,
|
| 539 |
+
"grad_norm": 1.2646759748458862,
|
| 540 |
+
"learning_rate": 2.721153220788826e-05,
|
| 541 |
+
"loss": 0.5678,
|
| 542 |
+
"step": 380
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.7236842105263158,
|
| 546 |
+
"grad_norm": 1.1523957252502441,
|
| 547 |
+
"learning_rate": 2.7120621503281756e-05,
|
| 548 |
+
"loss": 0.5305,
|
| 549 |
+
"step": 385
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.7330827067669173,
|
| 553 |
+
"grad_norm": 1.3809316158294678,
|
| 554 |
+
"learning_rate": 2.7028409543842378e-05,
|
| 555 |
+
"loss": 0.561,
|
| 556 |
+
"step": 390
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.7424812030075187,
|
| 560 |
+
"grad_norm": 1.1742485761642456,
|
| 561 |
+
"learning_rate": 2.6934906229331262e-05,
|
| 562 |
+
"loss": 0.5361,
|
| 563 |
+
"step": 395
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.7518796992481203,
|
| 567 |
+
"grad_norm": 1.324890375137329,
|
| 568 |
+
"learning_rate": 2.6840121598147845e-05,
|
| 569 |
+
"loss": 0.5614,
|
| 570 |
+
"step": 400
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.7612781954887218,
|
| 574 |
+
"grad_norm": 1.161738395690918,
|
| 575 |
+
"learning_rate": 2.6744065826252103e-05,
|
| 576 |
+
"loss": 0.5056,
|
| 577 |
+
"step": 405
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.7706766917293233,
|
| 581 |
+
"grad_norm": 1.1795762777328491,
|
| 582 |
+
"learning_rate": 2.6646749226072105e-05,
|
| 583 |
+
"loss": 0.4927,
|
| 584 |
+
"step": 410
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.7800751879699248,
|
| 588 |
+
"grad_norm": 1.2287588119506836,
|
| 589 |
+
"learning_rate": 2.6548182245396885e-05,
|
| 590 |
+
"loss": 0.5048,
|
| 591 |
+
"step": 415
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.7894736842105263,
|
| 595 |
+
"grad_norm": 1.1695654392242432,
|
| 596 |
+
"learning_rate": 2.6448375466254745e-05,
|
| 597 |
+
"loss": 0.5191,
|
| 598 |
+
"step": 420
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.7988721804511278,
|
| 602 |
+
"grad_norm": 1.2173978090286255,
|
| 603 |
+
"learning_rate": 2.6347339603777236e-05,
|
| 604 |
+
"loss": 0.505,
|
| 605 |
+
"step": 425
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.8082706766917294,
|
| 609 |
+
"grad_norm": 1.170729160308838,
|
| 610 |
+
"learning_rate": 2.624508550504874e-05,
|
| 611 |
+
"loss": 0.4839,
|
| 612 |
+
"step": 430
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.8176691729323309,
|
| 616 |
+
"grad_norm": 1.1502288579940796,
|
| 617 |
+
"learning_rate": 2.614162414794198e-05,
|
| 618 |
+
"loss": 0.4501,
|
| 619 |
+
"step": 435
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.8270676691729323,
|
| 623 |
+
"grad_norm": 1.3801743984222412,
|
| 624 |
+
"learning_rate": 2.6036966639939438e-05,
|
| 625 |
+
"loss": 0.4682,
|
| 626 |
+
"step": 440
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.8364661654135338,
|
| 630 |
+
"grad_norm": 1.235448956489563,
|
| 631 |
+
"learning_rate": 2.5931124216940854e-05,
|
| 632 |
+
"loss": 0.4795,
|
| 633 |
+
"step": 445
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.8458646616541353,
|
| 637 |
+
"grad_norm": 1.4729183912277222,
|
| 638 |
+
"learning_rate": 2.5824108242056976e-05,
|
| 639 |
+
"loss": 0.4714,
|
| 640 |
+
"step": 450
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.8552631578947368,
|
| 644 |
+
"grad_norm": 1.2395603656768799,
|
| 645 |
+
"learning_rate": 2.5715930204389617e-05,
|
| 646 |
+
"loss": 0.4653,
|
| 647 |
+
"step": 455
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.8646616541353384,
|
| 651 |
+
"grad_norm": 1.1458605527877808,
|
| 652 |
+
"learning_rate": 2.5606601717798212e-05,
|
| 653 |
+
"loss": 0.4444,
|
| 654 |
+
"step": 460
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.8740601503759399,
|
| 658 |
+
"grad_norm": 1.2719547748565674,
|
| 659 |
+
"learning_rate": 2.549613451965295e-05,
|
| 660 |
+
"loss": 0.4349,
|
| 661 |
+
"step": 465
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.8834586466165414,
|
| 665 |
+
"grad_norm": 1.2125513553619385,
|
| 666 |
+
"learning_rate": 2.538454046957468e-05,
|
| 667 |
+
"loss": 0.4706,
|
| 668 |
+
"step": 470
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.8928571428571429,
|
| 672 |
+
"grad_norm": 1.3109755516052246,
|
| 673 |
+
"learning_rate": 2.5271831548161667e-05,
|
| 674 |
+
"loss": 0.4087,
|
| 675 |
+
"step": 475
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.9022556390977443,
|
| 679 |
+
"grad_norm": 1.2260974645614624,
|
| 680 |
+
"learning_rate": 2.5158019855703377e-05,
|
| 681 |
+
"loss": 0.4173,
|
| 682 |
+
"step": 480
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.9116541353383458,
|
| 686 |
+
"grad_norm": 1.4752731323242188,
|
| 687 |
+
"learning_rate": 2.5043117610881402e-05,
|
| 688 |
+
"loss": 0.4099,
|
| 689 |
+
"step": 485
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.9210526315789473,
|
| 693 |
+
"grad_norm": 1.258771300315857,
|
| 694 |
+
"learning_rate": 2.4927137149457685e-05,
|
| 695 |
+
"loss": 0.412,
|
| 696 |
+
"step": 490
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.9304511278195489,
|
| 700 |
+
"grad_norm": 1.2981860637664795,
|
| 701 |
+
"learning_rate": 2.4810090922950143e-05,
|
| 702 |
+
"loss": 0.406,
|
| 703 |
+
"step": 495
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.9398496240601504,
|
| 707 |
+
"grad_norm": 1.2472333908081055,
|
| 708 |
+
"learning_rate": 2.4691991497295922e-05,
|
| 709 |
+
"loss": 0.4052,
|
| 710 |
+
"step": 500
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.9492481203007519,
|
| 714 |
+
"grad_norm": 1.4154011011123657,
|
| 715 |
+
"learning_rate": 2.457285155150231e-05,
|
| 716 |
+
"loss": 0.3895,
|
| 717 |
+
"step": 505
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.9586466165413534,
|
| 721 |
+
"grad_norm": 1.2483034133911133,
|
| 722 |
+
"learning_rate": 2.4452683876285546e-05,
|
| 723 |
+
"loss": 0.4271,
|
| 724 |
+
"step": 510
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.9680451127819549,
|
| 728 |
+
"grad_norm": 1.471336007118225,
|
| 729 |
+
"learning_rate": 2.433150137269762e-05,
|
| 730 |
+
"loss": 0.4334,
|
| 731 |
+
"step": 515
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.9774436090225563,
|
| 735 |
+
"grad_norm": 1.2480738162994385,
|
| 736 |
+
"learning_rate": 2.420931705074122e-05,
|
| 737 |
+
"loss": 0.3566,
|
| 738 |
+
"step": 520
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.9868421052631579,
|
| 742 |
+
"grad_norm": 1.4982995986938477,
|
| 743 |
+
"learning_rate": 2.408614402797302e-05,
|
| 744 |
+
"loss": 0.4002,
|
| 745 |
+
"step": 525
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.9962406015037594,
|
| 749 |
+
"grad_norm": 1.1962337493896484,
|
| 750 |
+
"learning_rate": 2.3961995528095385e-05,
|
| 751 |
+
"loss": 0.3889,
|
| 752 |
+
"step": 530
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.005639097744361,
|
| 756 |
+
"grad_norm": 1.140385389328003,
|
| 757 |
+
"learning_rate": 2.3836884879536676e-05,
|
| 758 |
+
"loss": 0.3202,
|
| 759 |
+
"step": 535
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.0150375939849625,
|
| 763 |
+
"grad_norm": 1.1931862831115723,
|
| 764 |
+
"learning_rate": 2.371082551402034e-05,
|
| 765 |
+
"loss": 0.3586,
|
| 766 |
+
"step": 540
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.0244360902255638,
|
| 770 |
+
"grad_norm": 1.0671947002410889,
|
| 771 |
+
"learning_rate": 2.3583830965122904e-05,
|
| 772 |
+
"loss": 0.3112,
|
| 773 |
+
"step": 545
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.0338345864661653,
|
| 777 |
+
"grad_norm": 1.3327282667160034,
|
| 778 |
+
"learning_rate": 2.345591486682101e-05,
|
| 779 |
+
"loss": 0.3376,
|
| 780 |
+
"step": 550
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.0432330827067668,
|
| 784 |
+
"grad_norm": 1.3870916366577148,
|
| 785 |
+
"learning_rate": 2.3327090952027704e-05,
|
| 786 |
+
"loss": 0.3209,
|
| 787 |
+
"step": 555
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.0526315789473684,
|
| 791 |
+
"grad_norm": 1.2349412441253662,
|
| 792 |
+
"learning_rate": 2.3197373051118074e-05,
|
| 793 |
+
"loss": 0.2813,
|
| 794 |
+
"step": 560
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.0620300751879699,
|
| 798 |
+
"grad_norm": 1.1286367177963257,
|
| 799 |
+
"learning_rate": 2.3066775090444446e-05,
|
| 800 |
+
"loss": 0.2833,
|
| 801 |
+
"step": 565
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.0714285714285714,
|
| 805 |
+
"grad_norm": 1.31594979763031,
|
| 806 |
+
"learning_rate": 2.2935311090841265e-05,
|
| 807 |
+
"loss": 0.295,
|
| 808 |
+
"step": 570
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.080827067669173,
|
| 812 |
+
"grad_norm": 1.274774432182312,
|
| 813 |
+
"learning_rate": 2.2802995166119846e-05,
|
| 814 |
+
"loss": 0.2885,
|
| 815 |
+
"step": 575
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.0902255639097744,
|
| 819 |
+
"grad_norm": 1.1666953563690186,
|
| 820 |
+
"learning_rate": 2.266984152155311e-05,
|
| 821 |
+
"loss": 0.34,
|
| 822 |
+
"step": 580
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.099624060150376,
|
| 826 |
+
"grad_norm": 1.193224310874939,
|
| 827 |
+
"learning_rate": 2.2535864452350543e-05,
|
| 828 |
+
"loss": 0.2888,
|
| 829 |
+
"step": 585
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.1090225563909775,
|
| 833 |
+
"grad_norm": 1.3207679986953735,
|
| 834 |
+
"learning_rate": 2.2401078342123483e-05,
|
| 835 |
+
"loss": 0.2788,
|
| 836 |
+
"step": 590
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.118421052631579,
|
| 840 |
+
"grad_norm": 1.2950669527053833,
|
| 841 |
+
"learning_rate": 2.2265497661340893e-05,
|
| 842 |
+
"loss": 0.3238,
|
| 843 |
+
"step": 595
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.1278195488721805,
|
| 847 |
+
"grad_norm": 1.1799949407577515,
|
| 848 |
+
"learning_rate": 2.212913696577585e-05,
|
| 849 |
+
"loss": 0.303,
|
| 850 |
+
"step": 600
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.137218045112782,
|
| 854 |
+
"grad_norm": 1.327563762664795,
|
| 855 |
+
"learning_rate": 2.1992010894942845e-05,
|
| 856 |
+
"loss": 0.2545,
|
| 857 |
+
"step": 605
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.1466165413533835,
|
| 861 |
+
"grad_norm": 1.3011080026626587,
|
| 862 |
+
"learning_rate": 2.1854134170526094e-05,
|
| 863 |
+
"loss": 0.2662,
|
| 864 |
+
"step": 610
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.156015037593985,
|
| 868 |
+
"grad_norm": 1.568489909172058,
|
| 869 |
+
"learning_rate": 2.1715521594799065e-05,
|
| 870 |
+
"loss": 0.2689,
|
| 871 |
+
"step": 615
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.1654135338345863,
|
| 875 |
+
"grad_norm": 1.2697765827178955,
|
| 876 |
+
"learning_rate": 2.15761880490353e-05,
|
| 877 |
+
"loss": 0.2719,
|
| 878 |
+
"step": 620
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.1748120300751879,
|
| 882 |
+
"grad_norm": 1.260827898979187,
|
| 883 |
+
"learning_rate": 2.1436148491910773e-05,
|
| 884 |
+
"loss": 0.2451,
|
| 885 |
+
"step": 625
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.1842105263157894,
|
| 889 |
+
"grad_norm": 1.2346687316894531,
|
| 890 |
+
"learning_rate": 2.1295417957897982e-05,
|
| 891 |
+
"loss": 0.2639,
|
| 892 |
+
"step": 630
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 1.193609022556391,
|
| 896 |
+
"grad_norm": 1.3587771654129028,
|
| 897 |
+
"learning_rate": 2.1154011555651822e-05,
|
| 898 |
+
"loss": 0.2428,
|
| 899 |
+
"step": 635
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 1.2030075187969924,
|
| 903 |
+
"grad_norm": 1.3083690404891968,
|
| 904 |
+
"learning_rate": 2.1011944466387577e-05,
|
| 905 |
+
"loss": 0.2329,
|
| 906 |
+
"step": 640
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.212406015037594,
|
| 910 |
+
"grad_norm": 1.4359098672866821,
|
| 911 |
+
"learning_rate": 2.086923194225105e-05,
|
| 912 |
+
"loss": 0.2309,
|
| 913 |
+
"step": 645
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.2218045112781954,
|
| 917 |
+
"grad_norm": 1.353179931640625,
|
| 918 |
+
"learning_rate": 2.0725889304681143e-05,
|
| 919 |
+
"loss": 0.2491,
|
| 920 |
+
"step": 650
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.231203007518797,
|
| 924 |
+
"grad_norm": 1.1572445631027222,
|
| 925 |
+
"learning_rate": 2.0581931942764945e-05,
|
| 926 |
+
"loss": 0.2541,
|
| 927 |
+
"step": 655
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.2406015037593985,
|
| 931 |
+
"grad_norm": 1.3108141422271729,
|
| 932 |
+
"learning_rate": 2.043737531158559e-05,
|
| 933 |
+
"loss": 0.2584,
|
| 934 |
+
"step": 660
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.25,
|
| 938 |
+
"grad_norm": 1.0516366958618164,
|
| 939 |
+
"learning_rate": 2.0292234930563e-05,
|
| 940 |
+
"loss": 0.262,
|
| 941 |
+
"step": 665
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.2593984962406015,
|
| 945 |
+
"grad_norm": 1.211906909942627,
|
| 946 |
+
"learning_rate": 2.014652638178777e-05,
|
| 947 |
+
"loss": 0.226,
|
| 948 |
+
"step": 670
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 1.268796992481203,
|
| 952 |
+
"grad_norm": 1.2837917804718018,
|
| 953 |
+
"learning_rate": 2.0000265308348273e-05,
|
| 954 |
+
"loss": 0.2544,
|
| 955 |
+
"step": 675
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.2781954887218046,
|
| 959 |
+
"grad_norm": 1.1363428831100464,
|
| 960 |
+
"learning_rate": 1.9853467412651235e-05,
|
| 961 |
+
"loss": 0.2386,
|
| 962 |
+
"step": 680
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.287593984962406,
|
| 966 |
+
"grad_norm": 1.3048768043518066,
|
| 967 |
+
"learning_rate": 1.970614845473596e-05,
|
| 968 |
+
"loss": 0.2479,
|
| 969 |
+
"step": 685
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.2969924812030076,
|
| 973 |
+
"grad_norm": 1.232675313949585,
|
| 974 |
+
"learning_rate": 1.9558324250582335e-05,
|
| 975 |
+
"loss": 0.237,
|
| 976 |
+
"step": 690
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.306390977443609,
|
| 980 |
+
"grad_norm": 1.1638017892837524,
|
| 981 |
+
"learning_rate": 1.941001067041286e-05,
|
| 982 |
+
"loss": 0.2307,
|
| 983 |
+
"step": 695
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.3157894736842106,
|
| 987 |
+
"grad_norm": 1.0934059619903564,
|
| 988 |
+
"learning_rate": 1.926122363698883e-05,
|
| 989 |
+
"loss": 0.2282,
|
| 990 |
+
"step": 700
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.3251879699248121,
|
| 994 |
+
"grad_norm": 1.7193068265914917,
|
| 995 |
+
"learning_rate": 1.91119791239009e-05,
|
| 996 |
+
"loss": 0.2133,
|
| 997 |
+
"step": 705
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 1.3345864661654137,
|
| 1001 |
+
"grad_norm": 1.1320679187774658,
|
| 1002 |
+
"learning_rate": 1.8962293153854164e-05,
|
| 1003 |
+
"loss": 0.2297,
|
| 1004 |
+
"step": 710
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.3439849624060152,
|
| 1008 |
+
"grad_norm": 1.2152717113494873,
|
| 1009 |
+
"learning_rate": 1.8812181796947988e-05,
|
| 1010 |
+
"loss": 0.2106,
|
| 1011 |
+
"step": 715
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 1.3533834586466165,
|
| 1015 |
+
"grad_norm": 1.231295108795166,
|
| 1016 |
+
"learning_rate": 1.8661661168950745e-05,
|
| 1017 |
+
"loss": 0.2395,
|
| 1018 |
+
"step": 720
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.362781954887218,
|
| 1022 |
+
"grad_norm": 1.0955288410186768,
|
| 1023 |
+
"learning_rate": 1.8510747429569633e-05,
|
| 1024 |
+
"loss": 0.2355,
|
| 1025 |
+
"step": 725
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 1.3721804511278195,
|
| 1029 |
+
"grad_norm": 1.0871318578720093,
|
| 1030 |
+
"learning_rate": 1.835945678071581e-05,
|
| 1031 |
+
"loss": 0.2428,
|
| 1032 |
+
"step": 730
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 1.381578947368421,
|
| 1036 |
+
"grad_norm": 1.29008150100708,
|
| 1037 |
+
"learning_rate": 1.8207805464764958e-05,
|
| 1038 |
+
"loss": 0.2168,
|
| 1039 |
+
"step": 735
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 1.3909774436090225,
|
| 1043 |
+
"grad_norm": 1.2296003103256226,
|
| 1044 |
+
"learning_rate": 1.8055809762813537e-05,
|
| 1045 |
+
"loss": 0.2093,
|
| 1046 |
+
"step": 740
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.400375939849624,
|
| 1050 |
+
"grad_norm": 1.2095301151275635,
|
| 1051 |
+
"learning_rate": 1.790348599293085e-05,
|
| 1052 |
+
"loss": 0.1981,
|
| 1053 |
+
"step": 745
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 1.4097744360902256,
|
| 1057 |
+
"grad_norm": 1.045202374458313,
|
| 1058 |
+
"learning_rate": 1.7750850508407172e-05,
|
| 1059 |
+
"loss": 0.2143,
|
| 1060 |
+
"step": 750
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 1.419172932330827,
|
| 1064 |
+
"grad_norm": 1.2133156061172485,
|
| 1065 |
+
"learning_rate": 1.7597919695998067e-05,
|
| 1066 |
+
"loss": 0.1857,
|
| 1067 |
+
"step": 755
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 1.4285714285714286,
|
| 1071 |
+
"grad_norm": 1.293715476989746,
|
| 1072 |
+
"learning_rate": 1.7444709974165143e-05,
|
| 1073 |
+
"loss": 0.2074,
|
| 1074 |
+
"step": 760
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.4379699248120301,
|
| 1078 |
+
"grad_norm": 1.0929676294326782,
|
| 1079 |
+
"learning_rate": 1.729123779131336e-05,
|
| 1080 |
+
"loss": 0.1796,
|
| 1081 |
+
"step": 765
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 1.4473684210526316,
|
| 1085 |
+
"grad_norm": 1.2607976198196411,
|
| 1086 |
+
"learning_rate": 1.7137519624025193e-05,
|
| 1087 |
+
"loss": 0.1813,
|
| 1088 |
+
"step": 770
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 1.4567669172932332,
|
| 1092 |
+
"grad_norm": 1.0812962055206299,
|
| 1093 |
+
"learning_rate": 1.6983571975291667e-05,
|
| 1094 |
+
"loss": 0.1881,
|
| 1095 |
+
"step": 775
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 1.4661654135338344,
|
| 1099 |
+
"grad_norm": 1.092307448387146,
|
| 1100 |
+
"learning_rate": 1.682941137274068e-05,
|
| 1101 |
+
"loss": 0.1872,
|
| 1102 |
+
"step": 780
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 1.475563909774436,
|
| 1106 |
+
"grad_norm": 1.804694414138794,
|
| 1107 |
+
"learning_rate": 1.6675054366862553e-05,
|
| 1108 |
+
"loss": 0.2035,
|
| 1109 |
+
"step": 785
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 1.4849624060150375,
|
| 1113 |
+
"grad_norm": 1.174047827720642,
|
| 1114 |
+
"learning_rate": 1.6520517529233265e-05,
|
| 1115 |
+
"loss": 0.1928,
|
| 1116 |
+
"step": 790
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 1.494360902255639,
|
| 1120 |
+
"grad_norm": 1.1136754751205444,
|
| 1121 |
+
"learning_rate": 1.6365817450735273e-05,
|
| 1122 |
+
"loss": 0.1903,
|
| 1123 |
+
"step": 795
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 1.5037593984962405,
|
| 1127 |
+
"grad_norm": 1.1049115657806396,
|
| 1128 |
+
"learning_rate": 1.6210970739776386e-05,
|
| 1129 |
+
"loss": 0.1856,
|
| 1130 |
+
"step": 800
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 1.513157894736842,
|
| 1134 |
+
"grad_norm": 1.2019330263137817,
|
| 1135 |
+
"learning_rate": 1.605599402050669e-05,
|
| 1136 |
+
"loss": 0.1805,
|
| 1137 |
+
"step": 805
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 1.5225563909774436,
|
| 1141 |
+
"grad_norm": 1.2262581586837769,
|
| 1142 |
+
"learning_rate": 1.5900903931033795e-05,
|
| 1143 |
+
"loss": 0.1851,
|
| 1144 |
+
"step": 810
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 1.531954887218045,
|
| 1148 |
+
"grad_norm": 1.0285981893539429,
|
| 1149 |
+
"learning_rate": 1.574571712163661e-05,
|
| 1150 |
+
"loss": 0.2051,
|
| 1151 |
+
"step": 815
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.5413533834586466,
|
| 1155 |
+
"grad_norm": 1.1294852495193481,
|
| 1156 |
+
"learning_rate": 1.559045025297775e-05,
|
| 1157 |
+
"loss": 0.1817,
|
| 1158 |
+
"step": 820
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 1.550751879699248,
|
| 1162 |
+
"grad_norm": 1.038309097290039,
|
| 1163 |
+
"learning_rate": 1.5435119994314924e-05,
|
| 1164 |
+
"loss": 0.1748,
|
| 1165 |
+
"step": 825
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 1.5601503759398496,
|
| 1169 |
+
"grad_norm": 1.0437440872192383,
|
| 1170 |
+
"learning_rate": 1.5279743021711284e-05,
|
| 1171 |
+
"loss": 0.1768,
|
| 1172 |
+
"step": 830
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 1.5695488721804511,
|
| 1176 |
+
"grad_norm": 1.1250826120376587,
|
| 1177 |
+
"learning_rate": 1.5124336016245149e-05,
|
| 1178 |
+
"loss": 0.1727,
|
| 1179 |
+
"step": 835
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 1.5789473684210527,
|
| 1183 |
+
"grad_norm": 1.0569233894348145,
|
| 1184 |
+
"learning_rate": 1.4968915662219128e-05,
|
| 1185 |
+
"loss": 0.1636,
|
| 1186 |
+
"step": 840
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 1.5883458646616542,
|
| 1190 |
+
"grad_norm": 1.0236541032791138,
|
| 1191 |
+
"learning_rate": 1.4813498645368903e-05,
|
| 1192 |
+
"loss": 0.1836,
|
| 1193 |
+
"step": 845
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 1.5977443609022557,
|
| 1197 |
+
"grad_norm": 1.0962340831756592,
|
| 1198 |
+
"learning_rate": 1.4658101651071892e-05,
|
| 1199 |
+
"loss": 0.1648,
|
| 1200 |
+
"step": 850
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 1.6071428571428572,
|
| 1204 |
+
"grad_norm": 1.1532505750656128,
|
| 1205 |
+
"learning_rate": 1.4502741362555917e-05,
|
| 1206 |
+
"loss": 0.1644,
|
| 1207 |
+
"step": 855
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 1.6165413533834587,
|
| 1211 |
+
"grad_norm": 1.4584366083145142,
|
| 1212 |
+
"learning_rate": 1.4347434459108116e-05,
|
| 1213 |
+
"loss": 0.1696,
|
| 1214 |
+
"step": 860
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 1.6259398496240602,
|
| 1218 |
+
"grad_norm": 1.0582867860794067,
|
| 1219 |
+
"learning_rate": 1.4192197614284248e-05,
|
| 1220 |
+
"loss": 0.1779,
|
| 1221 |
+
"step": 865
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 1.6353383458646618,
|
| 1225 |
+
"grad_norm": 1.1785125732421875,
|
| 1226 |
+
"learning_rate": 1.4037047494118694e-05,
|
| 1227 |
+
"loss": 0.1793,
|
| 1228 |
+
"step": 870
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 1.6447368421052633,
|
| 1232 |
+
"grad_norm": 1.038996696472168,
|
| 1233 |
+
"learning_rate": 1.388200075533518e-05,
|
| 1234 |
+
"loss": 0.1548,
|
| 1235 |
+
"step": 875
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 1.6541353383458648,
|
| 1239 |
+
"grad_norm": 1.4645986557006836,
|
| 1240 |
+
"learning_rate": 1.3727074043558517e-05,
|
| 1241 |
+
"loss": 0.1695,
|
| 1242 |
+
"step": 880
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 1.6635338345864663,
|
| 1246 |
+
"grad_norm": 1.1247239112854004,
|
| 1247 |
+
"learning_rate": 1.3572283991527582e-05,
|
| 1248 |
+
"loss": 0.1708,
|
| 1249 |
+
"step": 885
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 1.6729323308270678,
|
| 1253 |
+
"grad_norm": 1.0306785106658936,
|
| 1254 |
+
"learning_rate": 1.3417647217309632e-05,
|
| 1255 |
+
"loss": 0.1476,
|
| 1256 |
+
"step": 890
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 1.6823308270676691,
|
| 1260 |
+
"grad_norm": 1.0363950729370117,
|
| 1261 |
+
"learning_rate": 1.3263180322516205e-05,
|
| 1262 |
+
"loss": 0.1491,
|
| 1263 |
+
"step": 895
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 1.6917293233082706,
|
| 1267 |
+
"grad_norm": 0.8831355571746826,
|
| 1268 |
+
"learning_rate": 1.3108899890520786e-05,
|
| 1269 |
+
"loss": 0.1467,
|
| 1270 |
+
"step": 900
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 1.7011278195488722,
|
| 1274 |
+
"grad_norm": 1.2344099283218384,
|
| 1275 |
+
"learning_rate": 1.295482248467846e-05,
|
| 1276 |
+
"loss": 0.1594,
|
| 1277 |
+
"step": 905
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 1.7105263157894737,
|
| 1281 |
+
"grad_norm": 1.039624810218811,
|
| 1282 |
+
"learning_rate": 1.2800964646547674e-05,
|
| 1283 |
+
"loss": 0.1437,
|
| 1284 |
+
"step": 910
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 1.7199248120300752,
|
| 1288 |
+
"grad_norm": 0.8950397372245789,
|
| 1289 |
+
"learning_rate": 1.2647342894114357e-05,
|
| 1290 |
+
"loss": 0.1331,
|
| 1291 |
+
"step": 915
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 1.7293233082706767,
|
| 1295 |
+
"grad_norm": 1.0810532569885254,
|
| 1296 |
+
"learning_rate": 1.2493973720018577e-05,
|
| 1297 |
+
"loss": 0.157,
|
| 1298 |
+
"step": 920
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 1.7387218045112782,
|
| 1302 |
+
"grad_norm": 1.3350157737731934,
|
| 1303 |
+
"learning_rate": 1.2340873589783888e-05,
|
| 1304 |
+
"loss": 0.1443,
|
| 1305 |
+
"step": 925
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 1.7481203007518797,
|
| 1309 |
+
"grad_norm": 1.0185054540634155,
|
| 1310 |
+
"learning_rate": 1.2188058940049651e-05,
|
| 1311 |
+
"loss": 0.1345,
|
| 1312 |
+
"step": 930
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 1.7575187969924813,
|
| 1316 |
+
"grad_norm": 1.1121907234191895,
|
| 1317 |
+
"learning_rate": 1.2035546176806386e-05,
|
| 1318 |
+
"loss": 0.1129,
|
| 1319 |
+
"step": 935
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 1.7669172932330826,
|
| 1323 |
+
"grad_norm": 1.2006617784500122,
|
| 1324 |
+
"learning_rate": 1.1883351673634457e-05,
|
| 1325 |
+
"loss": 0.1364,
|
| 1326 |
+
"step": 940
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 1.776315789473684,
|
| 1330 |
+
"grad_norm": 1.0103201866149902,
|
| 1331 |
+
"learning_rate": 1.1731491769946225e-05,
|
| 1332 |
+
"loss": 0.1416,
|
| 1333 |
+
"step": 945
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 1.7857142857142856,
|
| 1337 |
+
"grad_norm": 1.0189690589904785,
|
| 1338 |
+
"learning_rate": 1.157998276923187e-05,
|
| 1339 |
+
"loss": 0.1431,
|
| 1340 |
+
"step": 950
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 1.795112781954887,
|
| 1344 |
+
"grad_norm": 1.2393074035644531,
|
| 1345 |
+
"learning_rate": 1.1428840937309047e-05,
|
| 1346 |
+
"loss": 0.1282,
|
| 1347 |
+
"step": 955
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 1.8045112781954886,
|
| 1351 |
+
"grad_norm": 1.021828532218933,
|
| 1352 |
+
"learning_rate": 1.127808250057665e-05,
|
| 1353 |
+
"loss": 0.1403,
|
| 1354 |
+
"step": 960
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 1.8139097744360901,
|
| 1358 |
+
"grad_norm": 1.1605874300003052,
|
| 1359 |
+
"learning_rate": 1.1127723644272728e-05,
|
| 1360 |
+
"loss": 0.1423,
|
| 1361 |
+
"step": 965
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 1.8233082706766917,
|
| 1365 |
+
"grad_norm": 0.9515864253044128,
|
| 1366 |
+
"learning_rate": 1.0977780510736885e-05,
|
| 1367 |
+
"loss": 0.1321,
|
| 1368 |
+
"step": 970
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 1.8327067669172932,
|
| 1372 |
+
"grad_norm": 1.0644917488098145,
|
| 1373 |
+
"learning_rate": 1.0828269197677237e-05,
|
| 1374 |
+
"loss": 0.1259,
|
| 1375 |
+
"step": 975
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 1.8421052631578947,
|
| 1379 |
+
"grad_norm": 1.02317214012146,
|
| 1380 |
+
"learning_rate": 1.067920575644219e-05,
|
| 1381 |
+
"loss": 0.1383,
|
| 1382 |
+
"step": 980
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 1.8515037593984962,
|
| 1386 |
+
"grad_norm": 1.0989339351654053,
|
| 1387 |
+
"learning_rate": 1.0530606190297192e-05,
|
| 1388 |
+
"loss": 0.1262,
|
| 1389 |
+
"step": 985
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 1.8609022556390977,
|
| 1393 |
+
"grad_norm": 0.9936410784721375,
|
| 1394 |
+
"learning_rate": 1.0382486452706643e-05,
|
| 1395 |
+
"loss": 0.1206,
|
| 1396 |
+
"step": 990
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 1.8703007518796992,
|
| 1400 |
+
"grad_norm": 0.9912272095680237,
|
| 1401 |
+
"learning_rate": 1.0234862445621142e-05,
|
| 1402 |
+
"loss": 0.1201,
|
| 1403 |
+
"step": 995
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 1.8796992481203008,
|
| 1407 |
+
"grad_norm": 0.9345570206642151,
|
| 1408 |
+
"learning_rate": 1.0087750017770274e-05,
|
| 1409 |
+
"loss": 0.1234,
|
| 1410 |
+
"step": 1000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 1.8890977443609023,
|
| 1414 |
+
"grad_norm": 1.1206716299057007,
|
| 1415 |
+
"learning_rate": 9.941164962961124e-06,
|
| 1416 |
+
"loss": 0.1219,
|
| 1417 |
+
"step": 1005
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 1.8984962406015038,
|
| 1421 |
+
"grad_norm": 0.9936740398406982,
|
| 1422 |
+
"learning_rate": 9.795123018382661e-06,
|
| 1423 |
+
"loss": 0.1243,
|
| 1424 |
+
"step": 1010
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 1.9078947368421053,
|
| 1428 |
+
"grad_norm": 0.935027003288269,
|
| 1429 |
+
"learning_rate": 9.649639862916213e-06,
|
| 1430 |
+
"loss": 0.1192,
|
| 1431 |
+
"step": 1015
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 1.9172932330827068,
|
| 1435 |
+
"grad_norm": 0.939355194568634,
|
| 1436 |
+
"learning_rate": 9.5047311154522e-06,
|
| 1437 |
+
"loss": 0.1202,
|
| 1438 |
+
"step": 1020
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 1.9266917293233083,
|
| 1442 |
+
"grad_norm": 0.952413022518158,
|
| 1443 |
+
"learning_rate": 9.360412333213324e-06,
|
| 1444 |
+
"loss": 0.1108,
|
| 1445 |
+
"step": 1025
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 1.9360902255639099,
|
| 1449 |
+
"grad_norm": 0.9872532486915588,
|
| 1450 |
+
"learning_rate": 9.216699010084356e-06,
|
| 1451 |
+
"loss": 0.1135,
|
| 1452 |
+
"step": 1030
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 1.9454887218045114,
|
| 1456 |
+
"grad_norm": 0.8481807112693787,
|
| 1457 |
+
"learning_rate": 9.073606574948716e-06,
|
| 1458 |
+
"loss": 0.1151,
|
| 1459 |
+
"step": 1035
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 1.954887218045113,
|
| 1463 |
+
"grad_norm": 1.110603928565979,
|
| 1464 |
+
"learning_rate": 8.931150390032087e-06,
|
| 1465 |
+
"loss": 0.1186,
|
| 1466 |
+
"step": 1040
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 1.9642857142857144,
|
| 1470 |
+
"grad_norm": 1.1130671501159668,
|
| 1471 |
+
"learning_rate": 8.789345749253089e-06,
|
| 1472 |
+
"loss": 0.1239,
|
| 1473 |
+
"step": 1045
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 1.973684210526316,
|
| 1477 |
+
"grad_norm": 0.9827004075050354,
|
| 1478 |
+
"learning_rate": 8.648207876581394e-06,
|
| 1479 |
+
"loss": 0.112,
|
| 1480 |
+
"step": 1050
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 1.9830827067669174,
|
| 1484 |
+
"grad_norm": 1.004602074623108,
|
| 1485 |
+
"learning_rate": 8.50775192440329e-06,
|
| 1486 |
+
"loss": 0.1095,
|
| 1487 |
+
"step": 1055
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 1.9924812030075187,
|
| 1491 |
+
"grad_norm": 0.9740102291107178,
|
| 1492 |
+
"learning_rate": 8.367992971894906e-06,
|
| 1493 |
+
"loss": 0.107,
|
| 1494 |
+
"step": 1060
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 2.0018796992481205,
|
| 1498 |
+
"grad_norm": 0.6189488172531128,
|
| 1499 |
+
"learning_rate": 8.228946023403364e-06,
|
| 1500 |
+
"loss": 0.1023,
|
| 1501 |
+
"step": 1065
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 2.011278195488722,
|
| 1505 |
+
"grad_norm": 1.0207630395889282,
|
| 1506 |
+
"learning_rate": 8.09062600683593e-06,
|
| 1507 |
+
"loss": 0.0881,
|
| 1508 |
+
"step": 1070
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 2.0206766917293235,
|
| 1512 |
+
"grad_norm": 0.904458224773407,
|
| 1513 |
+
"learning_rate": 7.95304777205736e-06,
|
| 1514 |
+
"loss": 0.0882,
|
| 1515 |
+
"step": 1075
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 2.030075187969925,
|
| 1519 |
+
"grad_norm": 0.9616421461105347,
|
| 1520 |
+
"learning_rate": 7.816226089295627e-06,
|
| 1521 |
+
"loss": 0.091,
|
| 1522 |
+
"step": 1080
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 2.039473684210526,
|
| 1526 |
+
"grad_norm": 0.6990841627120972,
|
| 1527 |
+
"learning_rate": 7.680175647556236e-06,
|
| 1528 |
+
"loss": 0.0814,
|
| 1529 |
+
"step": 1085
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 2.0488721804511276,
|
| 1533 |
+
"grad_norm": 0.7550905346870422,
|
| 1534 |
+
"learning_rate": 7.54491105304521e-06,
|
| 1535 |
+
"loss": 0.0908,
|
| 1536 |
+
"step": 1090
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 2.058270676691729,
|
| 1540 |
+
"grad_norm": 0.8111321330070496,
|
| 1541 |
+
"learning_rate": 7.4104468276009995e-06,
|
| 1542 |
+
"loss": 0.0878,
|
| 1543 |
+
"step": 1095
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 2.0676691729323307,
|
| 1547 |
+
"grad_norm": 0.848985493183136,
|
| 1548 |
+
"learning_rate": 7.276797407135425e-06,
|
| 1549 |
+
"loss": 0.0927,
|
| 1550 |
+
"step": 1100
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 2.077067669172932,
|
| 1554 |
+
"grad_norm": 0.8092796802520752,
|
| 1555 |
+
"learning_rate": 7.143977140083848e-06,
|
| 1556 |
+
"loss": 0.0906,
|
| 1557 |
+
"step": 1105
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 2.0864661654135337,
|
| 1561 |
+
"grad_norm": 0.7931380867958069,
|
| 1562 |
+
"learning_rate": 7.012000285864764e-06,
|
| 1563 |
+
"loss": 0.0883,
|
| 1564 |
+
"step": 1110
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 2.095864661654135,
|
| 1568 |
+
"grad_norm": 0.7709981203079224,
|
| 1569 |
+
"learning_rate": 6.880881013348917e-06,
|
| 1570 |
+
"loss": 0.0732,
|
| 1571 |
+
"step": 1115
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 2.1052631578947367,
|
| 1575 |
+
"grad_norm": 0.7526527047157288,
|
| 1576 |
+
"learning_rate": 6.750633399338142e-06,
|
| 1577 |
+
"loss": 0.0803,
|
| 1578 |
+
"step": 1120
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 2.1146616541353382,
|
| 1582 |
+
"grad_norm": 0.7257946729660034,
|
| 1583 |
+
"learning_rate": 6.621271427054106e-06,
|
| 1584 |
+
"loss": 0.0762,
|
| 1585 |
+
"step": 1125
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 2.1240601503759398,
|
| 1589 |
+
"grad_norm": 0.9319130778312683,
|
| 1590 |
+
"learning_rate": 6.492808984637086e-06,
|
| 1591 |
+
"loss": 0.0914,
|
| 1592 |
+
"step": 1130
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 2.1334586466165413,
|
| 1596 |
+
"grad_norm": 0.8819976449012756,
|
| 1597 |
+
"learning_rate": 6.3652598636549365e-06,
|
| 1598 |
+
"loss": 0.0773,
|
| 1599 |
+
"step": 1135
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 2.142857142857143,
|
| 1603 |
+
"grad_norm": 0.7389273047447205,
|
| 1604 |
+
"learning_rate": 6.238637757622476e-06,
|
| 1605 |
+
"loss": 0.089,
|
| 1606 |
+
"step": 1140
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 2.1522556390977443,
|
| 1610 |
+
"grad_norm": 0.6320111155509949,
|
| 1611 |
+
"learning_rate": 6.112956260531351e-06,
|
| 1612 |
+
"loss": 0.0791,
|
| 1613 |
+
"step": 1145
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 2.161654135338346,
|
| 1617 |
+
"grad_norm": 0.6096066832542419,
|
| 1618 |
+
"learning_rate": 5.988228865390596e-06,
|
| 1619 |
+
"loss": 0.0769,
|
| 1620 |
+
"step": 1150
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 2.1710526315789473,
|
| 1624 |
+
"grad_norm": 0.7631605267524719,
|
| 1625 |
+
"learning_rate": 5.864468962778054e-06,
|
| 1626 |
+
"loss": 0.0743,
|
| 1627 |
+
"step": 1155
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 2.180451127819549,
|
| 1631 |
+
"grad_norm": 0.823680579662323,
|
| 1632 |
+
"learning_rate": 5.7416898394027766e-06,
|
| 1633 |
+
"loss": 0.0777,
|
| 1634 |
+
"step": 1160
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 2.1898496240601504,
|
| 1638 |
+
"grad_norm": 0.9240273237228394,
|
| 1639 |
+
"learning_rate": 5.619904676678565e-06,
|
| 1640 |
+
"loss": 0.0817,
|
| 1641 |
+
"step": 1165
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 2.199248120300752,
|
| 1645 |
+
"grad_norm": 0.6772187352180481,
|
| 1646 |
+
"learning_rate": 5.4991265493088545e-06,
|
| 1647 |
+
"loss": 0.0745,
|
| 1648 |
+
"step": 1170
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 2.2086466165413534,
|
| 1652 |
+
"grad_norm": 0.8896387219429016,
|
| 1653 |
+
"learning_rate": 5.3793684238830175e-06,
|
| 1654 |
+
"loss": 0.0874,
|
| 1655 |
+
"step": 1175
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 2.218045112781955,
|
| 1659 |
+
"grad_norm": 0.6756446361541748,
|
| 1660 |
+
"learning_rate": 5.260643157484284e-06,
|
| 1661 |
+
"loss": 0.0727,
|
| 1662 |
+
"step": 1180
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 2.2274436090225564,
|
| 1666 |
+
"grad_norm": 0.8986202478408813,
|
| 1667 |
+
"learning_rate": 5.142963496309428e-06,
|
| 1668 |
+
"loss": 0.0738,
|
| 1669 |
+
"step": 1185
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 2.236842105263158,
|
| 1673 |
+
"grad_norm": 0.6743974685668945,
|
| 1674 |
+
"learning_rate": 5.02634207430035e-06,
|
| 1675 |
+
"loss": 0.0848,
|
| 1676 |
+
"step": 1190
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 2.2462406015037595,
|
| 1680 |
+
"grad_norm": 0.7321045994758606,
|
| 1681 |
+
"learning_rate": 4.9107914117877e-06,
|
| 1682 |
+
"loss": 0.0757,
|
| 1683 |
+
"step": 1195
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 2.255639097744361,
|
| 1687 |
+
"grad_norm": 0.7953357100486755,
|
| 1688 |
+
"learning_rate": 4.796323914146734e-06,
|
| 1689 |
+
"loss": 0.081,
|
| 1690 |
+
"step": 1200
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 2.2650375939849625,
|
| 1694 |
+
"grad_norm": 0.7724120020866394,
|
| 1695 |
+
"learning_rate": 4.682951870465474e-06,
|
| 1696 |
+
"loss": 0.0826,
|
| 1697 |
+
"step": 1205
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 2.274436090225564,
|
| 1701 |
+
"grad_norm": 0.7581201195716858,
|
| 1702 |
+
"learning_rate": 4.570687452225367e-06,
|
| 1703 |
+
"loss": 0.0755,
|
| 1704 |
+
"step": 1210
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 2.2838345864661656,
|
| 1708 |
+
"grad_norm": 0.8605563640594482,
|
| 1709 |
+
"learning_rate": 4.459542711994568e-06,
|
| 1710 |
+
"loss": 0.0849,
|
| 1711 |
+
"step": 1215
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 2.293233082706767,
|
| 1715 |
+
"grad_norm": 0.748431384563446,
|
| 1716 |
+
"learning_rate": 4.349529582134008e-06,
|
| 1717 |
+
"loss": 0.076,
|
| 1718 |
+
"step": 1220
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 2.3026315789473686,
|
| 1722 |
+
"grad_norm": 0.7182886004447937,
|
| 1723 |
+
"learning_rate": 4.240659873516319e-06,
|
| 1724 |
+
"loss": 0.0833,
|
| 1725 |
+
"step": 1225
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 2.31203007518797,
|
| 1729 |
+
"grad_norm": 0.6337144374847412,
|
| 1730 |
+
"learning_rate": 4.132945274257862e-06,
|
| 1731 |
+
"loss": 0.0807,
|
| 1732 |
+
"step": 1230
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 2.3214285714285716,
|
| 1736 |
+
"grad_norm": 0.7233930230140686,
|
| 1737 |
+
"learning_rate": 4.026397348463898e-06,
|
| 1738 |
+
"loss": 0.0815,
|
| 1739 |
+
"step": 1235
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 2.3308270676691727,
|
| 1743 |
+
"grad_norm": 0.7005705237388611,
|
| 1744 |
+
"learning_rate": 3.921027534987075e-06,
|
| 1745 |
+
"loss": 0.0668,
|
| 1746 |
+
"step": 1240
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 2.340225563909774,
|
| 1750 |
+
"grad_norm": 0.7019994854927063,
|
| 1751 |
+
"learning_rate": 3.816847146199372e-06,
|
| 1752 |
+
"loss": 0.0742,
|
| 1753 |
+
"step": 1245
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 2.3496240601503757,
|
| 1757 |
+
"grad_norm": 0.6627863049507141,
|
| 1758 |
+
"learning_rate": 3.7138673667776056e-06,
|
| 1759 |
+
"loss": 0.0714,
|
| 1760 |
+
"step": 1250
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 2.3590225563909772,
|
| 1764 |
+
"grad_norm": 0.799941897392273,
|
| 1765 |
+
"learning_rate": 3.612099252502672e-06,
|
| 1766 |
+
"loss": 0.082,
|
| 1767 |
+
"step": 1255
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 2.3684210526315788,
|
| 1771 |
+
"grad_norm": 0.6937321424484253,
|
| 1772 |
+
"learning_rate": 3.5115537290726074e-06,
|
| 1773 |
+
"loss": 0.0732,
|
| 1774 |
+
"step": 1260
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 2.3778195488721803,
|
| 1778 |
+
"grad_norm": 0.9581036567687988,
|
| 1779 |
+
"learning_rate": 3.4122415909296157e-06,
|
| 1780 |
+
"loss": 0.0814,
|
| 1781 |
+
"step": 1265
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 2.387218045112782,
|
| 1785 |
+
"grad_norm": 0.6360145807266235,
|
| 1786 |
+
"learning_rate": 3.3141735001011908e-06,
|
| 1787 |
+
"loss": 0.068,
|
| 1788 |
+
"step": 1270
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 2.3966165413533833,
|
| 1792 |
+
"grad_norm": 0.694480836391449,
|
| 1793 |
+
"learning_rate": 3.217359985055462e-06,
|
| 1794 |
+
"loss": 0.0694,
|
| 1795 |
+
"step": 1275
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 2.406015037593985,
|
| 1799 |
+
"grad_norm": 0.716654360294342,
|
| 1800 |
+
"learning_rate": 3.1218114395708502e-06,
|
| 1801 |
+
"loss": 0.0733,
|
| 1802 |
+
"step": 1280
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 2.4154135338345863,
|
| 1806 |
+
"grad_norm": 0.7194705605506897,
|
| 1807 |
+
"learning_rate": 3.0275381216202334e-06,
|
| 1808 |
+
"loss": 0.0718,
|
| 1809 |
+
"step": 1285
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 2.424812030075188,
|
| 1813 |
+
"grad_norm": 0.6594160199165344,
|
| 1814 |
+
"learning_rate": 2.934550152269649e-06,
|
| 1815 |
+
"loss": 0.0707,
|
| 1816 |
+
"step": 1290
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 2.4342105263157894,
|
| 1820 |
+
"grad_norm": 0.9902744293212891,
|
| 1821 |
+
"learning_rate": 2.8428575145916946e-06,
|
| 1822 |
+
"loss": 0.0727,
|
| 1823 |
+
"step": 1295
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 2.443609022556391,
|
| 1827 |
+
"grad_norm": 0.8495991230010986,
|
| 1828 |
+
"learning_rate": 2.7524700525937884e-06,
|
| 1829 |
+
"loss": 0.0753,
|
| 1830 |
+
"step": 1300
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 2.4530075187969924,
|
| 1834 |
+
"grad_norm": 0.6580012440681458,
|
| 1835 |
+
"learning_rate": 2.6633974701613057e-06,
|
| 1836 |
+
"loss": 0.0765,
|
| 1837 |
+
"step": 1305
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 2.462406015037594,
|
| 1841 |
+
"grad_norm": 0.7875741720199585,
|
| 1842 |
+
"learning_rate": 2.575649330015794e-06,
|
| 1843 |
+
"loss": 0.0726,
|
| 1844 |
+
"step": 1310
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 2.4718045112781954,
|
| 1848 |
+
"grad_norm": 0.7627713680267334,
|
| 1849 |
+
"learning_rate": 2.489235052688314e-06,
|
| 1850 |
+
"loss": 0.0822,
|
| 1851 |
+
"step": 1315
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 2.481203007518797,
|
| 1855 |
+
"grad_norm": 0.6470919251441956,
|
| 1856 |
+
"learning_rate": 2.4041639155080854e-06,
|
| 1857 |
+
"loss": 0.0718,
|
| 1858 |
+
"step": 1320
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 2.4906015037593985,
|
| 1862 |
+
"grad_norm": 0.6367564797401428,
|
| 1863 |
+
"learning_rate": 2.320445051606474e-06,
|
| 1864 |
+
"loss": 0.0753,
|
| 1865 |
+
"step": 1325
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 2.5,
|
| 1869 |
+
"grad_norm": 0.6063794493675232,
|
| 1870 |
+
"learning_rate": 2.2380874489364657e-06,
|
| 1871 |
+
"loss": 0.0599,
|
| 1872 |
+
"step": 1330
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 2.5093984962406015,
|
| 1876 |
+
"grad_norm": 0.6223397254943848,
|
| 1877 |
+
"learning_rate": 2.157099949307741e-06,
|
| 1878 |
+
"loss": 0.0681,
|
| 1879 |
+
"step": 1335
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 2.518796992481203,
|
| 1883 |
+
"grad_norm": 0.640089213848114,
|
| 1884 |
+
"learning_rate": 2.0774912474374147e-06,
|
| 1885 |
+
"loss": 0.074,
|
| 1886 |
+
"step": 1340
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 2.5281954887218046,
|
| 1890 |
+
"grad_norm": 0.7845536470413208,
|
| 1891 |
+
"learning_rate": 1.9992698900165984e-06,
|
| 1892 |
+
"loss": 0.0673,
|
| 1893 |
+
"step": 1345
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 2.537593984962406,
|
| 1897 |
+
"grad_norm": 0.7514573931694031,
|
| 1898 |
+
"learning_rate": 1.922444274792831e-06,
|
| 1899 |
+
"loss": 0.065,
|
| 1900 |
+
"step": 1350
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 2.5469924812030076,
|
| 1904 |
+
"grad_norm": 0.6213982105255127,
|
| 1905 |
+
"learning_rate": 1.8470226496685055e-06,
|
| 1906 |
+
"loss": 0.0628,
|
| 1907 |
+
"step": 1355
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 2.556390977443609,
|
| 1911 |
+
"grad_norm": 0.6003556847572327,
|
| 1912 |
+
"learning_rate": 1.773013111815383e-06,
|
| 1913 |
+
"loss": 0.0705,
|
| 1914 |
+
"step": 1360
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 2.5657894736842106,
|
| 1918 |
+
"grad_norm": 0.7004033327102661,
|
| 1919 |
+
"learning_rate": 1.7004236068053025e-06,
|
| 1920 |
+
"loss": 0.064,
|
| 1921 |
+
"step": 1365
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 2.575187969924812,
|
| 1925 |
+
"grad_norm": 0.6858503818511963,
|
| 1926 |
+
"learning_rate": 1.6292619277571292e-06,
|
| 1927 |
+
"loss": 0.0639,
|
| 1928 |
+
"step": 1370
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 2.5845864661654137,
|
| 1932 |
+
"grad_norm": 0.5193300843238831,
|
| 1933 |
+
"learning_rate": 1.559535714500127e-06,
|
| 1934 |
+
"loss": 0.0591,
|
| 1935 |
+
"step": 1375
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 2.593984962406015,
|
| 1939 |
+
"grad_norm": 0.599259614944458,
|
| 1940 |
+
"learning_rate": 1.4912524527537307e-06,
|
| 1941 |
+
"loss": 0.0742,
|
| 1942 |
+
"step": 1380
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 2.6033834586466167,
|
| 1946 |
+
"grad_norm": 0.6666296124458313,
|
| 1947 |
+
"learning_rate": 1.4244194733239008e-06,
|
| 1948 |
+
"loss": 0.0714,
|
| 1949 |
+
"step": 1385
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 2.612781954887218,
|
| 1953 |
+
"grad_norm": 0.6025199294090271,
|
| 1954 |
+
"learning_rate": 1.3590439513160935e-06,
|
| 1955 |
+
"loss": 0.0719,
|
| 1956 |
+
"step": 1390
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 2.6221804511278197,
|
| 1960 |
+
"grad_norm": 0.4907478988170624,
|
| 1961 |
+
"learning_rate": 1.295132905364954e-06,
|
| 1962 |
+
"loss": 0.0635,
|
| 1963 |
+
"step": 1395
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 2.6315789473684212,
|
| 1967 |
+
"grad_norm": 0.7650317549705505,
|
| 1968 |
+
"learning_rate": 1.2326931968807908e-06,
|
| 1969 |
+
"loss": 0.0706,
|
| 1970 |
+
"step": 1400
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 2.6409774436090228,
|
| 1974 |
+
"grad_norm": 0.7375085949897766,
|
| 1975 |
+
"learning_rate": 1.171731529312966e-06,
|
| 1976 |
+
"loss": 0.0786,
|
| 1977 |
+
"step": 1405
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 2.6503759398496243,
|
| 1981 |
+
"grad_norm": 0.7329378128051758,
|
| 1982 |
+
"learning_rate": 1.1122544474302048e-06,
|
| 1983 |
+
"loss": 0.0714,
|
| 1984 |
+
"step": 1410
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 2.659774436090226,
|
| 1988 |
+
"grad_norm": 0.5412716865539551,
|
| 1989 |
+
"learning_rate": 1.0542683366179613e-06,
|
| 1990 |
+
"loss": 0.0607,
|
| 1991 |
+
"step": 1415
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 2.6691729323308273,
|
| 1995 |
+
"grad_norm": 0.7059949636459351,
|
| 1996 |
+
"learning_rate": 9.977794221928905e-07,
|
| 1997 |
+
"loss": 0.0736,
|
| 1998 |
+
"step": 1420
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 2.678571428571429,
|
| 2002 |
+
"grad_norm": 0.6849631071090698,
|
| 2003 |
+
"learning_rate": 9.427937687345145e-07,
|
| 2004 |
+
"loss": 0.0645,
|
| 2005 |
+
"step": 1425
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 2.6879699248120303,
|
| 2009 |
+
"grad_norm": 0.6165528297424316,
|
| 2010 |
+
"learning_rate": 8.893172794341159e-07,
|
| 2011 |
+
"loss": 0.074,
|
| 2012 |
+
"step": 1430
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 2.6973684210526314,
|
| 2016 |
+
"grad_norm": 0.5059214234352112,
|
| 2017 |
+
"learning_rate": 8.373556954610079e-07,
|
| 2018 |
+
"loss": 0.0654,
|
| 2019 |
+
"step": 1435
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 2.706766917293233,
|
| 2023 |
+
"grad_norm": 0.6148324608802795,
|
| 2024 |
+
"learning_rate": 7.869145953461443e-07,
|
| 2025 |
+
"loss": 0.0614,
|
| 2026 |
+
"step": 1440
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 2.7161654135338344,
|
| 2030 |
+
"grad_norm": 0.7251229882240295,
|
| 2031 |
+
"learning_rate": 7.379993943832269e-07,
|
| 2032 |
+
"loss": 0.0773,
|
| 2033 |
+
"step": 1445
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 2.725563909774436,
|
| 2037 |
+
"grad_norm": 0.6811131834983826,
|
| 2038 |
+
"learning_rate": 6.90615344047329e-07,
|
| 2039 |
+
"loss": 0.0742,
|
| 2040 |
+
"step": 1450
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 2.7349624060150375,
|
| 2044 |
+
"grad_norm": 0.6007992029190063,
|
| 2045 |
+
"learning_rate": 6.447675314310941e-07,
|
| 2046 |
+
"loss": 0.072,
|
| 2047 |
+
"step": 1455
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 2.744360902255639,
|
| 2051 |
+
"grad_norm": 0.6286112070083618,
|
| 2052 |
+
"learning_rate": 6.004608786985955e-07,
|
| 2053 |
+
"loss": 0.0744,
|
| 2054 |
+
"step": 1460
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 2.7537593984962405,
|
| 2058 |
+
"grad_norm": 0.5636522769927979,
|
| 2059 |
+
"learning_rate": 5.577001425569061e-07,
|
| 2060 |
+
"loss": 0.0603,
|
| 2061 |
+
"step": 1465
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 2.763157894736842,
|
| 2065 |
+
"grad_norm": 0.5101714134216309,
|
| 2066 |
+
"learning_rate": 5.164899137454149e-07,
|
| 2067 |
+
"loss": 0.062,
|
| 2068 |
+
"step": 1470
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 2.7725563909774436,
|
| 2072 |
+
"grad_norm": 0.6965596079826355,
|
| 2073 |
+
"learning_rate": 4.768346165429749e-07,
|
| 2074 |
+
"loss": 0.071,
|
| 2075 |
+
"step": 1475
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 2.781954887218045,
|
| 2079 |
+
"grad_norm": 0.6466209292411804,
|
| 2080 |
+
"learning_rate": 4.387385082929174e-07,
|
| 2081 |
+
"loss": 0.0635,
|
| 2082 |
+
"step": 1480
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 2.7913533834586466,
|
| 2086 |
+
"grad_norm": 0.5297590494155884,
|
| 2087 |
+
"learning_rate": 4.022056789459921e-07,
|
| 2088 |
+
"loss": 0.059,
|
| 2089 |
+
"step": 1485
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 2.800751879699248,
|
| 2093 |
+
"grad_norm": 0.5080699920654297,
|
| 2094 |
+
"learning_rate": 3.6724005062126534e-07,
|
| 2095 |
+
"loss": 0.0644,
|
| 2096 |
+
"step": 1490
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 2.8101503759398496,
|
| 2100 |
+
"grad_norm": 0.6745559573173523,
|
| 2101 |
+
"learning_rate": 3.3384537718506135e-07,
|
| 2102 |
+
"loss": 0.0687,
|
| 2103 |
+
"step": 1495
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 2.819548872180451,
|
| 2107 |
+
"grad_norm": 0.510647714138031,
|
| 2108 |
+
"learning_rate": 3.0202524384793706e-07,
|
| 2109 |
+
"loss": 0.0675,
|
| 2110 |
+
"step": 1500
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"epoch": 2.8289473684210527,
|
| 2114 |
+
"grad_norm": 0.5886790156364441,
|
| 2115 |
+
"learning_rate": 2.717830667797877e-07,
|
| 2116 |
+
"loss": 0.0607,
|
| 2117 |
+
"step": 1505
|
| 2118 |
+
},
|
| 2119 |
+
{
|
| 2120 |
+
"epoch": 2.838345864661654,
|
| 2121 |
+
"grad_norm": 0.537045419216156,
|
| 2122 |
+
"learning_rate": 2.431220927430905e-07,
|
| 2123 |
+
"loss": 0.0558,
|
| 2124 |
+
"step": 1510
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 2.8477443609022557,
|
| 2128 |
+
"grad_norm": 0.6089495420455933,
|
| 2129 |
+
"learning_rate": 2.1604539874433006e-07,
|
| 2130 |
+
"loss": 0.0585,
|
| 2131 |
+
"step": 1515
|
| 2132 |
+
},
|
| 2133 |
+
{
|
| 2134 |
+
"epoch": 2.857142857142857,
|
| 2135 |
+
"grad_norm": 0.7006784677505493,
|
| 2136 |
+
"learning_rate": 1.9055589170365762e-07,
|
| 2137 |
+
"loss": 0.0737,
|
| 2138 |
+
"step": 1520
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 2.8665413533834587,
|
| 2142 |
+
"grad_norm": 0.611802339553833,
|
| 2143 |
+
"learning_rate": 1.6665630814281575e-07,
|
| 2144 |
+
"loss": 0.0683,
|
| 2145 |
+
"step": 1525
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 2.8759398496240602,
|
| 2149 |
+
"grad_norm": 0.5512478351593018,
|
| 2150 |
+
"learning_rate": 1.4434921389133494e-07,
|
| 2151 |
+
"loss": 0.0656,
|
| 2152 |
+
"step": 1530
|
| 2153 |
+
},
|
| 2154 |
+
{
|
| 2155 |
+
"epoch": 2.8853383458646618,
|
| 2156 |
+
"grad_norm": 0.5502645373344421,
|
| 2157 |
+
"learning_rate": 1.2363700381107901e-07,
|
| 2158 |
+
"loss": 0.0612,
|
| 2159 |
+
"step": 1535
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 2.8947368421052633,
|
| 2163 |
+
"grad_norm": 0.5304490923881531,
|
| 2164 |
+
"learning_rate": 1.0452190153913243e-07,
|
| 2165 |
+
"loss": 0.0687,
|
| 2166 |
+
"step": 1540
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 2.904135338345865,
|
| 2170 |
+
"grad_norm": 0.6445665955543518,
|
| 2171 |
+
"learning_rate": 8.700595924907629e-08,
|
| 2172 |
+
"loss": 0.065,
|
| 2173 |
+
"step": 1545
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 2.9135338345864663,
|
| 2177 |
+
"grad_norm": 0.6678323149681091,
|
| 2178 |
+
"learning_rate": 7.10910574306628e-08,
|
| 2179 |
+
"loss": 0.0743,
|
| 2180 |
+
"step": 1550
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 2.922932330827068,
|
| 2184 |
+
"grad_norm": 0.7011875510215759,
|
| 2185 |
+
"learning_rate": 5.67789046879369e-08,
|
| 2186 |
+
"loss": 0.0697,
|
| 2187 |
+
"step": 1555
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 2.932330827067669,
|
| 2191 |
+
"grad_norm": 0.5663780570030212,
|
| 2192 |
+
"learning_rate": 4.4071037555796226e-08,
|
| 2193 |
+
"loss": 0.0626,
|
| 2194 |
+
"step": 1560
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 2.9417293233082704,
|
| 2198 |
+
"grad_norm": 0.48351287841796875,
|
| 2199 |
+
"learning_rate": 3.296882033503312e-08,
|
| 2200 |
+
"loss": 0.0598,
|
| 2201 |
+
"step": 1565
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 2.951127819548872,
|
| 2205 |
+
"grad_norm": 0.6389005184173584,
|
| 2206 |
+
"learning_rate": 2.3473444945863455e-08,
|
| 2207 |
+
"loss": 0.0671,
|
| 2208 |
+
"step": 1570
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 2.9605263157894735,
|
| 2212 |
+
"grad_norm": 0.6084789633750916,
|
| 2213 |
+
"learning_rate": 1.558593079996895e-08,
|
| 2214 |
+
"loss": 0.0668,
|
| 2215 |
+
"step": 1575
|
| 2216 |
+
},
|
| 2217 |
+
{
|
| 2218 |
+
"epoch": 2.969924812030075,
|
| 2219 |
+
"grad_norm": 0.5656338334083557,
|
| 2220 |
+
"learning_rate": 9.307124691044778e-09,
|
| 2221 |
+
"loss": 0.0579,
|
| 2222 |
+
"step": 1580
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 2.9793233082706765,
|
| 2226 |
+
"grad_norm": 0.575596809387207,
|
| 2227 |
+
"learning_rate": 4.63770070389724e-09,
|
| 2228 |
+
"loss": 0.0661,
|
| 2229 |
+
"step": 1585
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 2.988721804511278,
|
| 2233 |
+
"grad_norm": 0.6059058308601379,
|
| 2234 |
+
"learning_rate": 1.5781601420733483e-09,
|
| 2235 |
+
"loss": 0.0706,
|
| 2236 |
+
"step": 1590
|
| 2237 |
+
},
|
| 2238 |
+
{
|
| 2239 |
+
"epoch": 2.9981203007518795,
|
| 2240 |
+
"grad_norm": 0.5142336487770081,
|
| 2241 |
+
"learning_rate": 1.288314740371943e-10,
|
| 2242 |
+
"loss": 0.0739,
|
| 2243 |
+
"step": 1595
|
| 2244 |
+
},
|
| 2245 |
+
{
|
| 2246 |
+
"epoch": 3.0,
|
| 2247 |
+
"step": 1596,
|
| 2248 |
+
"total_flos": 2.0415991178298655e+18,
|
| 2249 |
+
"train_loss": 0.36059863125452574,
|
| 2250 |
+
"train_runtime": 988.9937,
|
| 2251 |
+
"train_samples_per_second": 51.619,
|
| 2252 |
+
"train_steps_per_second": 1.614
|
| 2253 |
+
}
|
| 2254 |
+
],
|
| 2255 |
+
"logging_steps": 5,
|
| 2256 |
+
"max_steps": 1596,
|
| 2257 |
+
"num_input_tokens_seen": 0,
|
| 2258 |
+
"num_train_epochs": 3,
|
| 2259 |
+
"save_steps": 20000,
|
| 2260 |
+
"stateful_callbacks": {
|
| 2261 |
+
"TrainerControl": {
|
| 2262 |
+
"args": {
|
| 2263 |
+
"should_epoch_stop": false,
|
| 2264 |
+
"should_evaluate": false,
|
| 2265 |
+
"should_log": false,
|
| 2266 |
+
"should_save": false,
|
| 2267 |
+
"should_training_stop": false
|
| 2268 |
+
},
|
| 2269 |
+
"attributes": {}
|
| 2270 |
+
}
|
| 2271 |
+
},
|
| 2272 |
+
"total_flos": 2.0415991178298655e+18,
|
| 2273 |
+
"train_batch_size": 2,
|
| 2274 |
+
"trial_name": null,
|
| 2275 |
+
"trial_params": null
|
| 2276 |
+
}
|
instruct/12_128_e3_3e-5/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a8154637e4c88b70cc4102a58d8c3026c5c563e0bd391a459b70475f191e00e
|
| 3 |
+
size 8273
|
instruct/12_128_e3_3e-5/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|