Upload folder using huggingface_hub
Browse files- instruct/136_128_e3_3e-5/adapter_config.json +39 -0
- instruct/136_128_e3_3e-5/adapter_model.safetensors +3 -0
- instruct/136_128_e3_3e-5/added_tokens.json +9 -0
- instruct/136_128_e3_3e-5/all_results.json +9 -0
- instruct/136_128_e3_3e-5/chat_template.jinja +62 -0
- instruct/136_128_e3_3e-5/config.json +32 -0
- instruct/136_128_e3_3e-5/merges.txt +0 -0
- instruct/136_128_e3_3e-5/special_tokens_map.json +33 -0
- instruct/136_128_e3_3e-5/tokenizer.json +0 -0
- instruct/136_128_e3_3e-5/tokenizer_config.json +234 -0
- instruct/136_128_e3_3e-5/train_results.json +9 -0
- instruct/136_128_e3_3e-5/trainer_state.json +2248 -0
- instruct/136_128_e3_3e-5/training_args.bin +3 -0
- instruct/136_128_e3_3e-5/vocab.json +0 -0
instruct/136_128_e3_3e-5/adapter_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "ibm-granite/granite-3.3-8b-instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 256,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.05,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 128,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"down_proj",
|
| 28 |
+
"k_proj",
|
| 29 |
+
"v_proj",
|
| 30 |
+
"q_proj",
|
| 31 |
+
"gate_proj",
|
| 32 |
+
"o_proj",
|
| 33 |
+
"up_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
+
"use_dora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
instruct/136_128_e3_3e-5/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e330bc3a58c810321366c5e2f3f37f4cf9bcb43f2a3843b47564767e4f2f4c5
|
| 3 |
+
size 791751704
|
instruct/136_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/136_128_e3_3e-5/all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 2.0726363014414991e+18,
|
| 4 |
+
"train_loss": 0.36312728373307845,
|
| 5 |
+
"train_runtime": 985.9967,
|
| 6 |
+
"train_samples": 16827,
|
| 7 |
+
"train_samples_per_second": 51.198,
|
| 8 |
+
"train_steps_per_second": 1.6
|
| 9 |
+
}
|
instruct/136_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/136_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/136_128_e3_3e-5/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
instruct/136_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/136_128_e3_3e-5/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
instruct/136_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/136_128_e3_3e-5/train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 2.0726363014414991e+18,
|
| 4 |
+
"train_loss": 0.36312728373307845,
|
| 5 |
+
"train_runtime": 985.9967,
|
| 6 |
+
"train_samples": 16827,
|
| 7 |
+
"train_samples_per_second": 51.198,
|
| 8 |
+
"train_steps_per_second": 1.6
|
| 9 |
+
}
|
instruct/136_128_e3_3e-5/trainer_state.json
ADDED
|
@@ -0,0 +1,2248 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 1578,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.009505703422053232,
|
| 14 |
+
"grad_norm": 2.5604145526885986,
|
| 15 |
+
"learning_rate": 1.518987341772152e-06,
|
| 16 |
+
"loss": 1.5814,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.019011406844106463,
|
| 21 |
+
"grad_norm": 2.2293221950531006,
|
| 22 |
+
"learning_rate": 3.4177215189873417e-06,
|
| 23 |
+
"loss": 1.5624,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.028517110266159697,
|
| 28 |
+
"grad_norm": 1.093841552734375,
|
| 29 |
+
"learning_rate": 5.3164556962025316e-06,
|
| 30 |
+
"loss": 1.4797,
|
| 31 |
+
"step": 15
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.03802281368821293,
|
| 35 |
+
"grad_norm": 0.6079933643341064,
|
| 36 |
+
"learning_rate": 7.215189873417722e-06,
|
| 37 |
+
"loss": 1.4787,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.04752851711026616,
|
| 42 |
+
"grad_norm": 0.5419549345970154,
|
| 43 |
+
"learning_rate": 9.113924050632912e-06,
|
| 44 |
+
"loss": 1.3978,
|
| 45 |
+
"step": 25
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.057034220532319393,
|
| 49 |
+
"grad_norm": 0.6234089732170105,
|
| 50 |
+
"learning_rate": 1.1012658227848103e-05,
|
| 51 |
+
"loss": 1.3898,
|
| 52 |
+
"step": 30
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.06653992395437262,
|
| 56 |
+
"grad_norm": 0.464495450258255,
|
| 57 |
+
"learning_rate": 1.2911392405063291e-05,
|
| 58 |
+
"loss": 1.3622,
|
| 59 |
+
"step": 35
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.07604562737642585,
|
| 63 |
+
"grad_norm": 0.41255953907966614,
|
| 64 |
+
"learning_rate": 1.4810126582278482e-05,
|
| 65 |
+
"loss": 1.3831,
|
| 66 |
+
"step": 40
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.08555133079847908,
|
| 70 |
+
"grad_norm": 0.4105514585971832,
|
| 71 |
+
"learning_rate": 1.670886075949367e-05,
|
| 72 |
+
"loss": 1.4216,
|
| 73 |
+
"step": 45
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.09505703422053231,
|
| 77 |
+
"grad_norm": 0.4833674430847168,
|
| 78 |
+
"learning_rate": 1.860759493670886e-05,
|
| 79 |
+
"loss": 1.337,
|
| 80 |
+
"step": 50
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.10456273764258556,
|
| 84 |
+
"grad_norm": 0.3686533570289612,
|
| 85 |
+
"learning_rate": 2.050632911392405e-05,
|
| 86 |
+
"loss": 1.3121,
|
| 87 |
+
"step": 55
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.11406844106463879,
|
| 91 |
+
"grad_norm": 0.42876163125038147,
|
| 92 |
+
"learning_rate": 2.240506329113924e-05,
|
| 93 |
+
"loss": 1.3605,
|
| 94 |
+
"step": 60
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.12357414448669202,
|
| 98 |
+
"grad_norm": 0.43886029720306396,
|
| 99 |
+
"learning_rate": 2.430379746835443e-05,
|
| 100 |
+
"loss": 1.3119,
|
| 101 |
+
"step": 65
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.13307984790874525,
|
| 105 |
+
"grad_norm": 0.4192378520965576,
|
| 106 |
+
"learning_rate": 2.620253164556962e-05,
|
| 107 |
+
"loss": 1.2838,
|
| 108 |
+
"step": 70
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.14258555133079848,
|
| 112 |
+
"grad_norm": 0.43422406911849976,
|
| 113 |
+
"learning_rate": 2.8101265822784812e-05,
|
| 114 |
+
"loss": 1.2827,
|
| 115 |
+
"step": 75
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.1520912547528517,
|
| 119 |
+
"grad_norm": 0.5291144847869873,
|
| 120 |
+
"learning_rate": 3e-05,
|
| 121 |
+
"loss": 1.2943,
|
| 122 |
+
"step": 80
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.16159695817490494,
|
| 126 |
+
"grad_norm": 0.4798138439655304,
|
| 127 |
+
"learning_rate": 2.9999176442782448e-05,
|
| 128 |
+
"loss": 1.2078,
|
| 129 |
+
"step": 85
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.17110266159695817,
|
| 133 |
+
"grad_norm": 0.4653783440589905,
|
| 134 |
+
"learning_rate": 2.999670586156266e-05,
|
| 135 |
+
"loss": 1.2387,
|
| 136 |
+
"step": 90
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.1806083650190114,
|
| 140 |
+
"grad_norm": 0.5787487626075745,
|
| 141 |
+
"learning_rate": 2.9992588527629303e-05,
|
| 142 |
+
"loss": 1.1873,
|
| 143 |
+
"step": 95
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.19011406844106463,
|
| 147 |
+
"grad_norm": 0.5955005288124084,
|
| 148 |
+
"learning_rate": 2.998682489309705e-05,
|
| 149 |
+
"loss": 1.1697,
|
| 150 |
+
"step": 100
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.19961977186311788,
|
| 154 |
+
"grad_norm": 0.5041700601577759,
|
| 155 |
+
"learning_rate": 2.9979415590856944e-05,
|
| 156 |
+
"loss": 1.1786,
|
| 157 |
+
"step": 105
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.20912547528517111,
|
| 161 |
+
"grad_norm": 0.5608066916465759,
|
| 162 |
+
"learning_rate": 2.9970361434506903e-05,
|
| 163 |
+
"loss": 1.1388,
|
| 164 |
+
"step": 110
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.21863117870722434,
|
| 168 |
+
"grad_norm": 0.5853084921836853,
|
| 169 |
+
"learning_rate": 2.9959663418262358e-05,
|
| 170 |
+
"loss": 1.1181,
|
| 171 |
+
"step": 115
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.22813688212927757,
|
| 175 |
+
"grad_norm": 0.5741764307022095,
|
| 176 |
+
"learning_rate": 2.9947322716847114e-05,
|
| 177 |
+
"loss": 1.0925,
|
| 178 |
+
"step": 120
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.2376425855513308,
|
| 182 |
+
"grad_norm": 0.623802661895752,
|
| 183 |
+
"learning_rate": 2.9933340685364335e-05,
|
| 184 |
+
"loss": 1.0602,
|
| 185 |
+
"step": 125
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.24714828897338403,
|
| 189 |
+
"grad_norm": 0.6625247597694397,
|
| 190 |
+
"learning_rate": 2.9917718859147743e-05,
|
| 191 |
+
"loss": 1.0856,
|
| 192 |
+
"step": 130
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.25665399239543724,
|
| 196 |
+
"grad_norm": 0.6497186422348022,
|
| 197 |
+
"learning_rate": 2.990045895359304e-05,
|
| 198 |
+
"loss": 1.1132,
|
| 199 |
+
"step": 135
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.2661596958174905,
|
| 203 |
+
"grad_norm": 0.6561116576194763,
|
| 204 |
+
"learning_rate": 2.9881562863969535e-05,
|
| 205 |
+
"loss": 1.0569,
|
| 206 |
+
"step": 140
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.27566539923954375,
|
| 210 |
+
"grad_norm": 0.7474815845489502,
|
| 211 |
+
"learning_rate": 2.986103266521201e-05,
|
| 212 |
+
"loss": 1.0606,
|
| 213 |
+
"step": 145
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.28517110266159695,
|
| 217 |
+
"grad_norm": 0.7578780055046082,
|
| 218 |
+
"learning_rate": 2.983887061169293e-05,
|
| 219 |
+
"loss": 1.0108,
|
| 220 |
+
"step": 150
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.2946768060836502,
|
| 224 |
+
"grad_norm": 0.7403013706207275,
|
| 225 |
+
"learning_rate": 2.981507913697484e-05,
|
| 226 |
+
"loss": 1.0373,
|
| 227 |
+
"step": 155
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.3041825095057034,
|
| 231 |
+
"grad_norm": 0.7570089101791382,
|
| 232 |
+
"learning_rate": 2.9789660853543176e-05,
|
| 233 |
+
"loss": 1.0252,
|
| 234 |
+
"step": 160
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.31368821292775667,
|
| 238 |
+
"grad_norm": 0.8064972758293152,
|
| 239 |
+
"learning_rate": 2.9762618552519366e-05,
|
| 240 |
+
"loss": 1.0349,
|
| 241 |
+
"step": 165
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.3231939163498099,
|
| 245 |
+
"grad_norm": 0.818407416343689,
|
| 246 |
+
"learning_rate": 2.973395520335437e-05,
|
| 247 |
+
"loss": 1.0016,
|
| 248 |
+
"step": 170
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.33269961977186313,
|
| 252 |
+
"grad_norm": 0.8063826560974121,
|
| 253 |
+
"learning_rate": 2.9703673953502598e-05,
|
| 254 |
+
"loss": 0.9779,
|
| 255 |
+
"step": 175
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.34220532319391633,
|
| 259 |
+
"grad_norm": 0.7921943664550781,
|
| 260 |
+
"learning_rate": 2.967177812807631e-05,
|
| 261 |
+
"loss": 0.9516,
|
| 262 |
+
"step": 180
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.3517110266159696,
|
| 266 |
+
"grad_norm": 0.778381884098053,
|
| 267 |
+
"learning_rate": 2.9638271229480458e-05,
|
| 268 |
+
"loss": 0.9739,
|
| 269 |
+
"step": 185
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.3612167300380228,
|
| 273 |
+
"grad_norm": 0.8687506914138794,
|
| 274 |
+
"learning_rate": 2.9603156937028142e-05,
|
| 275 |
+
"loss": 0.9281,
|
| 276 |
+
"step": 190
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.37072243346007605,
|
| 280 |
+
"grad_norm": 0.8581569790840149,
|
| 281 |
+
"learning_rate": 2.9566439106536554e-05,
|
| 282 |
+
"loss": 0.933,
|
| 283 |
+
"step": 195
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.38022813688212925,
|
| 287 |
+
"grad_norm": 0.8881865739822388,
|
| 288 |
+
"learning_rate": 2.9528121769903604e-05,
|
| 289 |
+
"loss": 0.8949,
|
| 290 |
+
"step": 200
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.3897338403041825,
|
| 294 |
+
"grad_norm": 0.9205732941627502,
|
| 295 |
+
"learning_rate": 2.948820913466518e-05,
|
| 296 |
+
"loss": 0.8979,
|
| 297 |
+
"step": 205
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.39923954372623577,
|
| 301 |
+
"grad_norm": 0.9295692443847656,
|
| 302 |
+
"learning_rate": 2.944670558353312e-05,
|
| 303 |
+
"loss": 0.8696,
|
| 304 |
+
"step": 210
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.40874524714828897,
|
| 308 |
+
"grad_norm": 1.090277075767517,
|
| 309 |
+
"learning_rate": 2.9403615673913977e-05,
|
| 310 |
+
"loss": 0.8519,
|
| 311 |
+
"step": 215
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.41825095057034223,
|
| 315 |
+
"grad_norm": 0.9070485234260559,
|
| 316 |
+
"learning_rate": 2.9358944137408553e-05,
|
| 317 |
+
"loss": 0.8102,
|
| 318 |
+
"step": 220
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.42775665399239543,
|
| 322 |
+
"grad_norm": 0.9800488352775574,
|
| 323 |
+
"learning_rate": 2.931269587929236e-05,
|
| 324 |
+
"loss": 0.8416,
|
| 325 |
+
"step": 225
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.4372623574144487,
|
| 329 |
+
"grad_norm": 0.9660536050796509,
|
| 330 |
+
"learning_rate": 2.9264875977976966e-05,
|
| 331 |
+
"loss": 0.7891,
|
| 332 |
+
"step": 230
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.4467680608365019,
|
| 336 |
+
"grad_norm": 0.9573851227760315,
|
| 337 |
+
"learning_rate": 2.9215489684452354e-05,
|
| 338 |
+
"loss": 0.7854,
|
| 339 |
+
"step": 235
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.45627376425855515,
|
| 343 |
+
"grad_norm": 1.0426607131958008,
|
| 344 |
+
"learning_rate": 2.9164542421710325e-05,
|
| 345 |
+
"loss": 0.8348,
|
| 346 |
+
"step": 240
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.46577946768060835,
|
| 350 |
+
"grad_norm": 1.036786437034607,
|
| 351 |
+
"learning_rate": 2.9112039784148993e-05,
|
| 352 |
+
"loss": 0.7667,
|
| 353 |
+
"step": 245
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.4752851711026616,
|
| 357 |
+
"grad_norm": 1.1910680532455444,
|
| 358 |
+
"learning_rate": 2.905798753695852e-05,
|
| 359 |
+
"loss": 0.7364,
|
| 360 |
+
"step": 250
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.4847908745247148,
|
| 364 |
+
"grad_norm": 0.982923150062561,
|
| 365 |
+
"learning_rate": 2.9002391615488008e-05,
|
| 366 |
+
"loss": 0.7656,
|
| 367 |
+
"step": 255
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.49429657794676807,
|
| 371 |
+
"grad_norm": 1.0457642078399658,
|
| 372 |
+
"learning_rate": 2.894525812459377e-05,
|
| 373 |
+
"loss": 0.762,
|
| 374 |
+
"step": 260
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.5038022813688213,
|
| 378 |
+
"grad_norm": 1.0140658617019653,
|
| 379 |
+
"learning_rate": 2.888659333796898e-05,
|
| 380 |
+
"loss": 0.7302,
|
| 381 |
+
"step": 265
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.5133079847908745,
|
| 385 |
+
"grad_norm": 1.1099199056625366,
|
| 386 |
+
"learning_rate": 2.882640369745477e-05,
|
| 387 |
+
"loss": 0.7289,
|
| 388 |
+
"step": 270
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.5228136882129277,
|
| 392 |
+
"grad_norm": 1.125267744064331,
|
| 393 |
+
"learning_rate": 2.876469581233285e-05,
|
| 394 |
+
"loss": 0.7525,
|
| 395 |
+
"step": 275
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.532319391634981,
|
| 399 |
+
"grad_norm": 1.023065447807312,
|
| 400 |
+
"learning_rate": 2.870147645859978e-05,
|
| 401 |
+
"loss": 0.6652,
|
| 402 |
+
"step": 280
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.5418250950570342,
|
| 406 |
+
"grad_norm": 1.0743114948272705,
|
| 407 |
+
"learning_rate": 2.863675257822289e-05,
|
| 408 |
+
"loss": 0.7274,
|
| 409 |
+
"step": 285
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.5513307984790875,
|
| 413 |
+
"grad_norm": 1.0767483711242676,
|
| 414 |
+
"learning_rate": 2.8570531278378044e-05,
|
| 415 |
+
"loss": 0.7068,
|
| 416 |
+
"step": 290
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.5608365019011406,
|
| 420 |
+
"grad_norm": 1.0350711345672607,
|
| 421 |
+
"learning_rate": 2.8502819830669148e-05,
|
| 422 |
+
"loss": 0.7092,
|
| 423 |
+
"step": 295
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.5703422053231939,
|
| 427 |
+
"grad_norm": 1.1286636590957642,
|
| 428 |
+
"learning_rate": 2.843362567032974e-05,
|
| 429 |
+
"loss": 0.6888,
|
| 430 |
+
"step": 300
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.5798479087452472,
|
| 434 |
+
"grad_norm": 1.1008257865905762,
|
| 435 |
+
"learning_rate": 2.8362956395406512e-05,
|
| 436 |
+
"loss": 0.6785,
|
| 437 |
+
"step": 305
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.5893536121673004,
|
| 441 |
+
"grad_norm": 1.3177601099014282,
|
| 442 |
+
"learning_rate": 2.8290819765924984e-05,
|
| 443 |
+
"loss": 0.6728,
|
| 444 |
+
"step": 310
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.5988593155893536,
|
| 448 |
+
"grad_norm": 1.1282750368118286,
|
| 449 |
+
"learning_rate": 2.8217223703037398e-05,
|
| 450 |
+
"loss": 0.6544,
|
| 451 |
+
"step": 315
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.6083650190114068,
|
| 455 |
+
"grad_norm": 1.0715219974517822,
|
| 456 |
+
"learning_rate": 2.8142176288152935e-05,
|
| 457 |
+
"loss": 0.6139,
|
| 458 |
+
"step": 320
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.6178707224334601,
|
| 462 |
+
"grad_norm": 1.2381781339645386,
|
| 463 |
+
"learning_rate": 2.8065685762050274e-05,
|
| 464 |
+
"loss": 0.6064,
|
| 465 |
+
"step": 325
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.6273764258555133,
|
| 469 |
+
"grad_norm": 1.0476949214935303,
|
| 470 |
+
"learning_rate": 2.7987760523972735e-05,
|
| 471 |
+
"loss": 0.6164,
|
| 472 |
+
"step": 330
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.6368821292775665,
|
| 476 |
+
"grad_norm": 1.0898168087005615,
|
| 477 |
+
"learning_rate": 2.7908409130705952e-05,
|
| 478 |
+
"loss": 0.6173,
|
| 479 |
+
"step": 335
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.6463878326996197,
|
| 483 |
+
"grad_norm": 1.184018850326538,
|
| 484 |
+
"learning_rate": 2.7827640295638274e-05,
|
| 485 |
+
"loss": 0.6334,
|
| 486 |
+
"step": 340
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.655893536121673,
|
| 490 |
+
"grad_norm": 1.2060376405715942,
|
| 491 |
+
"learning_rate": 2.7745462887803984e-05,
|
| 492 |
+
"loss": 0.6024,
|
| 493 |
+
"step": 345
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.6653992395437263,
|
| 497 |
+
"grad_norm": 1.2812397480010986,
|
| 498 |
+
"learning_rate": 2.7661885930909385e-05,
|
| 499 |
+
"loss": 0.5963,
|
| 500 |
+
"step": 350
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.6749049429657795,
|
| 504 |
+
"grad_norm": 1.123320460319519,
|
| 505 |
+
"learning_rate": 2.7576918602341957e-05,
|
| 506 |
+
"loss": 0.6084,
|
| 507 |
+
"step": 355
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.6844106463878327,
|
| 511 |
+
"grad_norm": 1.2154338359832764,
|
| 512 |
+
"learning_rate": 2.7490570232162595e-05,
|
| 513 |
+
"loss": 0.5511,
|
| 514 |
+
"step": 360
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.6939163498098859,
|
| 518 |
+
"grad_norm": 1.1865524053573608,
|
| 519 |
+
"learning_rate": 2.74028503020811e-05,
|
| 520 |
+
"loss": 0.5686,
|
| 521 |
+
"step": 365
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.7034220532319392,
|
| 525 |
+
"grad_norm": 1.0821212530136108,
|
| 526 |
+
"learning_rate": 2.7313768444415004e-05,
|
| 527 |
+
"loss": 0.5546,
|
| 528 |
+
"step": 370
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.7129277566539924,
|
| 532 |
+
"grad_norm": 1.3064649105072021,
|
| 533 |
+
"learning_rate": 2.722333444103189e-05,
|
| 534 |
+
"loss": 0.5584,
|
| 535 |
+
"step": 375
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.7224334600760456,
|
| 539 |
+
"grad_norm": 1.183626413345337,
|
| 540 |
+
"learning_rate": 2.7131558222275243e-05,
|
| 541 |
+
"loss": 0.6334,
|
| 542 |
+
"step": 380
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.7319391634980988,
|
| 546 |
+
"grad_norm": 1.184539556503296,
|
| 547 |
+
"learning_rate": 2.7038449865874053e-05,
|
| 548 |
+
"loss": 0.5729,
|
| 549 |
+
"step": 385
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.7414448669201521,
|
| 553 |
+
"grad_norm": 1.0619412660598755,
|
| 554 |
+
"learning_rate": 2.694401959583618e-05,
|
| 555 |
+
"loss": 0.5618,
|
| 556 |
+
"step": 390
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.7509505703422054,
|
| 560 |
+
"grad_norm": 1.1095987558364868,
|
| 561 |
+
"learning_rate": 2.684827778132567e-05,
|
| 562 |
+
"loss": 0.5192,
|
| 563 |
+
"step": 395
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.7604562737642585,
|
| 567 |
+
"grad_norm": 1.3031337261199951,
|
| 568 |
+
"learning_rate": 2.675123493552418e-05,
|
| 569 |
+
"loss": 0.5109,
|
| 570 |
+
"step": 400
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.7699619771863118,
|
| 574 |
+
"grad_norm": 1.2062933444976807,
|
| 575 |
+
"learning_rate": 2.6652901714476516e-05,
|
| 576 |
+
"loss": 0.5546,
|
| 577 |
+
"step": 405
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.779467680608365,
|
| 581 |
+
"grad_norm": 1.3904153108596802,
|
| 582 |
+
"learning_rate": 2.6553288915920533e-05,
|
| 583 |
+
"loss": 0.4918,
|
| 584 |
+
"step": 410
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.7889733840304183,
|
| 588 |
+
"grad_norm": 1.036934494972229,
|
| 589 |
+
"learning_rate": 2.6452407478101472e-05,
|
| 590 |
+
"loss": 0.4929,
|
| 591 |
+
"step": 415
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.7984790874524715,
|
| 595 |
+
"grad_norm": 1.259943962097168,
|
| 596 |
+
"learning_rate": 2.6350268478570813e-05,
|
| 597 |
+
"loss": 0.5479,
|
| 598 |
+
"step": 420
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.8079847908745247,
|
| 602 |
+
"grad_norm": 1.2847987413406372,
|
| 603 |
+
"learning_rate": 2.6246883132969934e-05,
|
| 604 |
+
"loss": 0.4988,
|
| 605 |
+
"step": 425
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.8174904942965779,
|
| 609 |
+
"grad_norm": 1.3519943952560425,
|
| 610 |
+
"learning_rate": 2.6142262793798507e-05,
|
| 611 |
+
"loss": 0.5018,
|
| 612 |
+
"step": 430
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.8269961977186312,
|
| 616 |
+
"grad_norm": 1.215004563331604,
|
| 617 |
+
"learning_rate": 2.6036418949167922e-05,
|
| 618 |
+
"loss": 0.4708,
|
| 619 |
+
"step": 435
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.8365019011406845,
|
| 623 |
+
"grad_norm": 1.2391618490219116,
|
| 624 |
+
"learning_rate": 2.5929363221539802e-05,
|
| 625 |
+
"loss": 0.4731,
|
| 626 |
+
"step": 440
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.8460076045627376,
|
| 630 |
+
"grad_norm": 1.5271750688552856,
|
| 631 |
+
"learning_rate": 2.582110736644977e-05,
|
| 632 |
+
"loss": 0.4865,
|
| 633 |
+
"step": 445
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.8555133079847909,
|
| 637 |
+
"grad_norm": 1.2682982683181763,
|
| 638 |
+
"learning_rate": 2.5711663271216597e-05,
|
| 639 |
+
"loss": 0.4942,
|
| 640 |
+
"step": 450
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.8650190114068441,
|
| 644 |
+
"grad_norm": 1.301849126815796,
|
| 645 |
+
"learning_rate": 2.5601042953636895e-05,
|
| 646 |
+
"loss": 0.4378,
|
| 647 |
+
"step": 455
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.8745247148288974,
|
| 651 |
+
"grad_norm": 1.3602726459503174,
|
| 652 |
+
"learning_rate": 2.5489258560665455e-05,
|
| 653 |
+
"loss": 0.4301,
|
| 654 |
+
"step": 460
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.8840304182509505,
|
| 658 |
+
"grad_norm": 1.2645303010940552,
|
| 659 |
+
"learning_rate": 2.5376322367081433e-05,
|
| 660 |
+
"loss": 0.4077,
|
| 661 |
+
"step": 465
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.8935361216730038,
|
| 665 |
+
"grad_norm": 1.1444551944732666,
|
| 666 |
+
"learning_rate": 2.5262246774140466e-05,
|
| 667 |
+
"loss": 0.3965,
|
| 668 |
+
"step": 470
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.903041825095057,
|
| 672 |
+
"grad_norm": 1.3566426038742065,
|
| 673 |
+
"learning_rate": 2.5147044308212947e-05,
|
| 674 |
+
"loss": 0.4157,
|
| 675 |
+
"step": 475
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.9125475285171103,
|
| 679 |
+
"grad_norm": 1.2055705785751343,
|
| 680 |
+
"learning_rate": 2.503072761940852e-05,
|
| 681 |
+
"loss": 0.4587,
|
| 682 |
+
"step": 480
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.9220532319391636,
|
| 686 |
+
"grad_norm": 1.3660587072372437,
|
| 687 |
+
"learning_rate": 2.4913309480186988e-05,
|
| 688 |
+
"loss": 0.4237,
|
| 689 |
+
"step": 485
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.9315589353612167,
|
| 693 |
+
"grad_norm": 1.135892391204834,
|
| 694 |
+
"learning_rate": 2.4794802783955827e-05,
|
| 695 |
+
"loss": 0.4187,
|
| 696 |
+
"step": 490
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.94106463878327,
|
| 700 |
+
"grad_norm": 1.2711762189865112,
|
| 701 |
+
"learning_rate": 2.4675220543654374e-05,
|
| 702 |
+
"loss": 0.3989,
|
| 703 |
+
"step": 495
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.9505703422053232,
|
| 707 |
+
"grad_norm": 1.258678913116455,
|
| 708 |
+
"learning_rate": 2.45545758903249e-05,
|
| 709 |
+
"loss": 0.3739,
|
| 710 |
+
"step": 500
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.9600760456273765,
|
| 714 |
+
"grad_norm": 1.2297592163085938,
|
| 715 |
+
"learning_rate": 2.4432882071670746e-05,
|
| 716 |
+
"loss": 0.4084,
|
| 717 |
+
"step": 505
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.9695817490494296,
|
| 721 |
+
"grad_norm": 1.2128267288208008,
|
| 722 |
+
"learning_rate": 2.43101524506016e-05,
|
| 723 |
+
"loss": 0.4066,
|
| 724 |
+
"step": 510
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.9790874524714829,
|
| 728 |
+
"grad_norm": 1.3045459985733032,
|
| 729 |
+
"learning_rate": 2.418640050376616e-05,
|
| 730 |
+
"loss": 0.4137,
|
| 731 |
+
"step": 515
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.9885931558935361,
|
| 735 |
+
"grad_norm": 1.5434411764144897,
|
| 736 |
+
"learning_rate": 2.40616398200723e-05,
|
| 737 |
+
"loss": 0.3745,
|
| 738 |
+
"step": 520
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.9980988593155894,
|
| 742 |
+
"grad_norm": 1.29697585105896,
|
| 743 |
+
"learning_rate": 2.3935884099194875e-05,
|
| 744 |
+
"loss": 0.3808,
|
| 745 |
+
"step": 525
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.0076045627376427,
|
| 749 |
+
"grad_norm": 1.249290943145752,
|
| 750 |
+
"learning_rate": 2.3809147150071444e-05,
|
| 751 |
+
"loss": 0.3344,
|
| 752 |
+
"step": 530
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.0171102661596958,
|
| 756 |
+
"grad_norm": 1.3798565864562988,
|
| 757 |
+
"learning_rate": 2.368144288938589e-05,
|
| 758 |
+
"loss": 0.337,
|
| 759 |
+
"step": 535
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.026615969581749,
|
| 763 |
+
"grad_norm": 1.0569286346435547,
|
| 764 |
+
"learning_rate": 2.3552785340040294e-05,
|
| 765 |
+
"loss": 0.3107,
|
| 766 |
+
"step": 540
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.0361216730038023,
|
| 770 |
+
"grad_norm": 1.0867054462432861,
|
| 771 |
+
"learning_rate": 2.3423188629615107e-05,
|
| 772 |
+
"loss": 0.3457,
|
| 773 |
+
"step": 545
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.0456273764258555,
|
| 777 |
+
"grad_norm": 1.2050837278366089,
|
| 778 |
+
"learning_rate": 2.3292666988817818e-05,
|
| 779 |
+
"loss": 0.3055,
|
| 780 |
+
"step": 550
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.0551330798479088,
|
| 784 |
+
"grad_norm": 1.3146299123764038,
|
| 785 |
+
"learning_rate": 2.316123474992035e-05,
|
| 786 |
+
"loss": 0.3246,
|
| 787 |
+
"step": 555
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.064638783269962,
|
| 791 |
+
"grad_norm": 1.2243584394454956,
|
| 792 |
+
"learning_rate": 2.3028906345185224e-05,
|
| 793 |
+
"loss": 0.2944,
|
| 794 |
+
"step": 560
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.0741444866920151,
|
| 798 |
+
"grad_norm": 1.147451400756836,
|
| 799 |
+
"learning_rate": 2.2895696305280812e-05,
|
| 800 |
+
"loss": 0.2943,
|
| 801 |
+
"step": 565
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.0836501901140685,
|
| 805 |
+
"grad_norm": 1.1949355602264404,
|
| 806 |
+
"learning_rate": 2.2761619257685757e-05,
|
| 807 |
+
"loss": 0.2924,
|
| 808 |
+
"step": 570
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.0931558935361216,
|
| 812 |
+
"grad_norm": 1.129530906677246,
|
| 813 |
+
"learning_rate": 2.2626689925082772e-05,
|
| 814 |
+
"loss": 0.2966,
|
| 815 |
+
"step": 575
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.102661596958175,
|
| 819 |
+
"grad_norm": 1.1324480772018433,
|
| 820 |
+
"learning_rate": 2.2490923123741937e-05,
|
| 821 |
+
"loss": 0.3043,
|
| 822 |
+
"step": 580
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.1121673003802282,
|
| 826 |
+
"grad_norm": 1.389204978942871,
|
| 827 |
+
"learning_rate": 2.235433376189381e-05,
|
| 828 |
+
"loss": 0.3117,
|
| 829 |
+
"step": 585
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.1216730038022813,
|
| 833 |
+
"grad_norm": 1.093299150466919,
|
| 834 |
+
"learning_rate": 2.2216936838092368e-05,
|
| 835 |
+
"loss": 0.275,
|
| 836 |
+
"step": 590
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.1311787072243347,
|
| 840 |
+
"grad_norm": 1.3970575332641602,
|
| 841 |
+
"learning_rate": 2.207874743956804e-05,
|
| 842 |
+
"loss": 0.2728,
|
| 843 |
+
"step": 595
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.1406844106463878,
|
| 847 |
+
"grad_norm": 1.2366869449615479,
|
| 848 |
+
"learning_rate": 2.1939780740571034e-05,
|
| 849 |
+
"loss": 0.2887,
|
| 850 |
+
"step": 600
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.1501901140684412,
|
| 854 |
+
"grad_norm": 1.3439961671829224,
|
| 855 |
+
"learning_rate": 2.1800052000705084e-05,
|
| 856 |
+
"loss": 0.2834,
|
| 857 |
+
"step": 605
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.1596958174904943,
|
| 861 |
+
"grad_norm": 1.2513900995254517,
|
| 862 |
+
"learning_rate": 2.1659576563251807e-05,
|
| 863 |
+
"loss": 0.2549,
|
| 864 |
+
"step": 610
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.1692015209125475,
|
| 868 |
+
"grad_norm": 1.1543340682983398,
|
| 869 |
+
"learning_rate": 2.1518369853485935e-05,
|
| 870 |
+
"loss": 0.2317,
|
| 871 |
+
"step": 615
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.1787072243346008,
|
| 875 |
+
"grad_norm": 1.1417486667633057,
|
| 876 |
+
"learning_rate": 2.1376447376981462e-05,
|
| 877 |
+
"loss": 0.2582,
|
| 878 |
+
"step": 620
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.188212927756654,
|
| 882 |
+
"grad_norm": 1.1724592447280884,
|
| 883 |
+
"learning_rate": 2.123382471790903e-05,
|
| 884 |
+
"loss": 0.2709,
|
| 885 |
+
"step": 625
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.1977186311787071,
|
| 889 |
+
"grad_norm": 1.1819095611572266,
|
| 890 |
+
"learning_rate": 2.109051753732469e-05,
|
| 891 |
+
"loss": 0.2896,
|
| 892 |
+
"step": 630
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 1.2072243346007605,
|
| 896 |
+
"grad_norm": 1.1863148212432861,
|
| 897 |
+
"learning_rate": 2.0946541571450143e-05,
|
| 898 |
+
"loss": 0.2911,
|
| 899 |
+
"step": 635
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 1.2167300380228137,
|
| 903 |
+
"grad_norm": 1.1303791999816895,
|
| 904 |
+
"learning_rate": 2.080191262994485e-05,
|
| 905 |
+
"loss": 0.2314,
|
| 906 |
+
"step": 640
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.2262357414448668,
|
| 910 |
+
"grad_norm": 1.276293396949768,
|
| 911 |
+
"learning_rate": 2.0656646594169957e-05,
|
| 912 |
+
"loss": 0.2585,
|
| 913 |
+
"step": 645
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.2357414448669202,
|
| 917 |
+
"grad_norm": 1.1533775329589844,
|
| 918 |
+
"learning_rate": 2.0510759415444427e-05,
|
| 919 |
+
"loss": 0.2593,
|
| 920 |
+
"step": 650
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.2452471482889733,
|
| 924 |
+
"grad_norm": 1.2675774097442627,
|
| 925 |
+
"learning_rate": 2.036426711329346e-05,
|
| 926 |
+
"loss": 0.2423,
|
| 927 |
+
"step": 655
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.2547528517110267,
|
| 931 |
+
"grad_norm": 1.229582667350769,
|
| 932 |
+
"learning_rate": 2.0217185773689424e-05,
|
| 933 |
+
"loss": 0.2694,
|
| 934 |
+
"step": 660
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.2642585551330798,
|
| 938 |
+
"grad_norm": 1.307586908340454,
|
| 939 |
+
"learning_rate": 2.0069531547285493e-05,
|
| 940 |
+
"loss": 0.2314,
|
| 941 |
+
"step": 665
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.2737642585551332,
|
| 945 |
+
"grad_norm": 1.4162110090255737,
|
| 946 |
+
"learning_rate": 1.9921320647642177e-05,
|
| 947 |
+
"loss": 0.2291,
|
| 948 |
+
"step": 670
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 1.2832699619771863,
|
| 952 |
+
"grad_norm": 1.2408655881881714,
|
| 953 |
+
"learning_rate": 1.9772569349446962e-05,
|
| 954 |
+
"loss": 0.2267,
|
| 955 |
+
"step": 675
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.2927756653992395,
|
| 959 |
+
"grad_norm": 1.1572657823562622,
|
| 960 |
+
"learning_rate": 1.962329398672721e-05,
|
| 961 |
+
"loss": 0.2411,
|
| 962 |
+
"step": 680
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.3022813688212929,
|
| 966 |
+
"grad_norm": 1.2200615406036377,
|
| 967 |
+
"learning_rate": 1.9473510951056575e-05,
|
| 968 |
+
"loss": 0.2488,
|
| 969 |
+
"step": 685
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.311787072243346,
|
| 973 |
+
"grad_norm": 1.1246532201766968,
|
| 974 |
+
"learning_rate": 1.9323236689755073e-05,
|
| 975 |
+
"loss": 0.2123,
|
| 976 |
+
"step": 690
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.3212927756653992,
|
| 980 |
+
"grad_norm": 1.204129695892334,
|
| 981 |
+
"learning_rate": 1.9172487704083033e-05,
|
| 982 |
+
"loss": 0.2261,
|
| 983 |
+
"step": 695
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.3307984790874525,
|
| 987 |
+
"grad_norm": 1.0712982416152954,
|
| 988 |
+
"learning_rate": 1.9021280547429146e-05,
|
| 989 |
+
"loss": 0.2089,
|
| 990 |
+
"step": 700
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.3403041825095057,
|
| 994 |
+
"grad_norm": 1.149864673614502,
|
| 995 |
+
"learning_rate": 1.8869631823492768e-05,
|
| 996 |
+
"loss": 0.238,
|
| 997 |
+
"step": 705
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 1.3498098859315588,
|
| 1001 |
+
"grad_norm": 1.065934181213379,
|
| 1002 |
+
"learning_rate": 1.871755818446073e-05,
|
| 1003 |
+
"loss": 0.2338,
|
| 1004 |
+
"step": 710
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.3593155893536122,
|
| 1008 |
+
"grad_norm": 1.3242136240005493,
|
| 1009 |
+
"learning_rate": 1.8565076329178762e-05,
|
| 1010 |
+
"loss": 0.2181,
|
| 1011 |
+
"step": 715
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 1.3688212927756653,
|
| 1015 |
+
"grad_norm": 1.0688703060150146,
|
| 1016 |
+
"learning_rate": 1.8412203001317856e-05,
|
| 1017 |
+
"loss": 0.2143,
|
| 1018 |
+
"step": 720
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.3783269961977187,
|
| 1022 |
+
"grad_norm": 1.0195553302764893,
|
| 1023 |
+
"learning_rate": 1.8258954987535686e-05,
|
| 1024 |
+
"loss": 0.2035,
|
| 1025 |
+
"step": 725
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 1.3878326996197718,
|
| 1029 |
+
"grad_norm": 1.364370584487915,
|
| 1030 |
+
"learning_rate": 1.8105349115633297e-05,
|
| 1031 |
+
"loss": 0.239,
|
| 1032 |
+
"step": 730
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 1.3973384030418252,
|
| 1036 |
+
"grad_norm": 1.1326632499694824,
|
| 1037 |
+
"learning_rate": 1.7951402252707277e-05,
|
| 1038 |
+
"loss": 0.2306,
|
| 1039 |
+
"step": 735
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 1.4068441064638784,
|
| 1043 |
+
"grad_norm": 1.27006196975708,
|
| 1044 |
+
"learning_rate": 1.7797131303297644e-05,
|
| 1045 |
+
"loss": 0.2157,
|
| 1046 |
+
"step": 740
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.4163498098859315,
|
| 1050 |
+
"grad_norm": 1.1105040311813354,
|
| 1051 |
+
"learning_rate": 1.7642553207531577e-05,
|
| 1052 |
+
"loss": 0.2232,
|
| 1053 |
+
"step": 745
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 1.4258555133079849,
|
| 1057 |
+
"grad_norm": 1.3687723875045776,
|
| 1058 |
+
"learning_rate": 1.7487684939263266e-05,
|
| 1059 |
+
"loss": 0.196,
|
| 1060 |
+
"step": 750
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 1.435361216730038,
|
| 1064 |
+
"grad_norm": 1.2684054374694824,
|
| 1065 |
+
"learning_rate": 1.7332543504210058e-05,
|
| 1066 |
+
"loss": 0.1821,
|
| 1067 |
+
"step": 755
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 1.4448669201520912,
|
| 1071 |
+
"grad_norm": 1.137814998626709,
|
| 1072 |
+
"learning_rate": 1.7177145938085094e-05,
|
| 1073 |
+
"loss": 0.1992,
|
| 1074 |
+
"step": 760
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.4543726235741445,
|
| 1078 |
+
"grad_norm": 0.962353527545929,
|
| 1079 |
+
"learning_rate": 1.702150930472667e-05,
|
| 1080 |
+
"loss": 0.195,
|
| 1081 |
+
"step": 765
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 1.4638783269961977,
|
| 1085 |
+
"grad_norm": 1.1436002254486084,
|
| 1086 |
+
"learning_rate": 1.686565069422448e-05,
|
| 1087 |
+
"loss": 0.1935,
|
| 1088 |
+
"step": 770
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 1.4733840304182508,
|
| 1092 |
+
"grad_norm": 1.125365138053894,
|
| 1093 |
+
"learning_rate": 1.6709587221043e-05,
|
| 1094 |
+
"loss": 0.2145,
|
| 1095 |
+
"step": 775
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 1.4828897338403042,
|
| 1099 |
+
"grad_norm": 1.1643452644348145,
|
| 1100 |
+
"learning_rate": 1.65533360221422e-05,
|
| 1101 |
+
"loss": 0.1885,
|
| 1102 |
+
"step": 780
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 1.4923954372623573,
|
| 1106 |
+
"grad_norm": 1.2016589641571045,
|
| 1107 |
+
"learning_rate": 1.6396914255095753e-05,
|
| 1108 |
+
"loss": 0.2,
|
| 1109 |
+
"step": 785
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 1.5019011406844105,
|
| 1113 |
+
"grad_norm": 1.0389260053634644,
|
| 1114 |
+
"learning_rate": 1.624033909620703e-05,
|
| 1115 |
+
"loss": 0.1772,
|
| 1116 |
+
"step": 790
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 1.5114068441064639,
|
| 1120 |
+
"grad_norm": 1.0926350355148315,
|
| 1121 |
+
"learning_rate": 1.6083627738622986e-05,
|
| 1122 |
+
"loss": 0.1765,
|
| 1123 |
+
"step": 795
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 1.5209125475285172,
|
| 1127 |
+
"grad_norm": 1.0132405757904053,
|
| 1128 |
+
"learning_rate": 1.5926797390446244e-05,
|
| 1129 |
+
"loss": 0.1854,
|
| 1130 |
+
"step": 800
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 1.5304182509505704,
|
| 1134 |
+
"grad_norm": 1.1432725191116333,
|
| 1135 |
+
"learning_rate": 1.5769865272845484e-05,
|
| 1136 |
+
"loss": 0.2032,
|
| 1137 |
+
"step": 805
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 1.5399239543726235,
|
| 1141 |
+
"grad_norm": 1.4454073905944824,
|
| 1142 |
+
"learning_rate": 1.561284861816446e-05,
|
| 1143 |
+
"loss": 0.1753,
|
| 1144 |
+
"step": 810
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 1.549429657794677,
|
| 1148 |
+
"grad_norm": 1.158607840538025,
|
| 1149 |
+
"learning_rate": 1.5455764668029732e-05,
|
| 1150 |
+
"loss": 0.1722,
|
| 1151 |
+
"step": 815
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.55893536121673,
|
| 1155 |
+
"grad_norm": 0.9735372066497803,
|
| 1156 |
+
"learning_rate": 1.5298630671457422e-05,
|
| 1157 |
+
"loss": 0.1706,
|
| 1158 |
+
"step": 820
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 1.5684410646387832,
|
| 1162 |
+
"grad_norm": 1.1664737462997437,
|
| 1163 |
+
"learning_rate": 1.5141463882959134e-05,
|
| 1164 |
+
"loss": 0.1668,
|
| 1165 |
+
"step": 825
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 1.5779467680608366,
|
| 1169 |
+
"grad_norm": 1.1877906322479248,
|
| 1170 |
+
"learning_rate": 1.4984281560647267e-05,
|
| 1171 |
+
"loss": 0.1598,
|
| 1172 |
+
"step": 830
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 1.5874524714828897,
|
| 1176 |
+
"grad_norm": 1.0138477087020874,
|
| 1177 |
+
"learning_rate": 1.4827100964339957e-05,
|
| 1178 |
+
"loss": 0.1571,
|
| 1179 |
+
"step": 835
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 1.5969581749049429,
|
| 1183 |
+
"grad_norm": 1.0953423976898193,
|
| 1184 |
+
"learning_rate": 1.4669939353665808e-05,
|
| 1185 |
+
"loss": 0.1478,
|
| 1186 |
+
"step": 840
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 1.6064638783269962,
|
| 1190 |
+
"grad_norm": 1.1865073442459106,
|
| 1191 |
+
"learning_rate": 1.4512813986168666e-05,
|
| 1192 |
+
"loss": 0.1942,
|
| 1193 |
+
"step": 845
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 1.6159695817490496,
|
| 1197 |
+
"grad_norm": 1.1958262920379639,
|
| 1198 |
+
"learning_rate": 1.4355742115412583e-05,
|
| 1199 |
+
"loss": 0.1689,
|
| 1200 |
+
"step": 850
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 1.6254752851711025,
|
| 1204 |
+
"grad_norm": 1.1214553117752075,
|
| 1205 |
+
"learning_rate": 1.4198740989087277e-05,
|
| 1206 |
+
"loss": 0.1656,
|
| 1207 |
+
"step": 855
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 1.6349809885931559,
|
| 1211 |
+
"grad_norm": 1.0260697603225708,
|
| 1212 |
+
"learning_rate": 1.4041827847114183e-05,
|
| 1213 |
+
"loss": 0.1505,
|
| 1214 |
+
"step": 860
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 1.6444866920152093,
|
| 1218 |
+
"grad_norm": 1.0690749883651733,
|
| 1219 |
+
"learning_rate": 1.3885019919753377e-05,
|
| 1220 |
+
"loss": 0.1499,
|
| 1221 |
+
"step": 865
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 1.6539923954372624,
|
| 1225 |
+
"grad_norm": 1.1591182947158813,
|
| 1226 |
+
"learning_rate": 1.3728334425711571e-05,
|
| 1227 |
+
"loss": 0.142,
|
| 1228 |
+
"step": 870
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 1.6634980988593155,
|
| 1232 |
+
"grad_norm": 1.1139787435531616,
|
| 1233 |
+
"learning_rate": 1.3571788570251364e-05,
|
| 1234 |
+
"loss": 0.1631,
|
| 1235 |
+
"step": 875
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 1.673003802281369,
|
| 1239 |
+
"grad_norm": 1.1159265041351318,
|
| 1240 |
+
"learning_rate": 1.3415399543301983e-05,
|
| 1241 |
+
"loss": 0.159,
|
| 1242 |
+
"step": 880
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 1.682509505703422,
|
| 1246 |
+
"grad_norm": 1.2559670209884644,
|
| 1247 |
+
"learning_rate": 1.3259184517571674e-05,
|
| 1248 |
+
"loss": 0.1428,
|
| 1249 |
+
"step": 885
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 1.6920152091254752,
|
| 1253 |
+
"grad_norm": 1.1505334377288818,
|
| 1254 |
+
"learning_rate": 1.3103160646662029e-05,
|
| 1255 |
+
"loss": 0.1722,
|
| 1256 |
+
"step": 890
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 1.7015209125475286,
|
| 1260 |
+
"grad_norm": 1.1908087730407715,
|
| 1261 |
+
"learning_rate": 1.294734506318438e-05,
|
| 1262 |
+
"loss": 0.1461,
|
| 1263 |
+
"step": 895
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 1.7110266159695817,
|
| 1267 |
+
"grad_norm": 0.9099418520927429,
|
| 1268 |
+
"learning_rate": 1.2791754876878513e-05,
|
| 1269 |
+
"loss": 0.132,
|
| 1270 |
+
"step": 900
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 1.7205323193916349,
|
| 1274 |
+
"grad_norm": 1.0939401388168335,
|
| 1275 |
+
"learning_rate": 1.263640717273388e-05,
|
| 1276 |
+
"loss": 0.1496,
|
| 1277 |
+
"step": 905
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 1.7300380228136882,
|
| 1281 |
+
"grad_norm": 0.9969981908798218,
|
| 1282 |
+
"learning_rate": 1.2481319009113548e-05,
|
| 1283 |
+
"loss": 0.1389,
|
| 1284 |
+
"step": 910
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 1.7395437262357416,
|
| 1288 |
+
"grad_norm": 0.9727360606193542,
|
| 1289 |
+
"learning_rate": 1.2326507415881051e-05,
|
| 1290 |
+
"loss": 0.1347,
|
| 1291 |
+
"step": 915
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 1.7490494296577945,
|
| 1295 |
+
"grad_norm": 1.2379605770111084,
|
| 1296 |
+
"learning_rate": 1.2171989392530383e-05,
|
| 1297 |
+
"loss": 0.1625,
|
| 1298 |
+
"step": 920
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 1.758555133079848,
|
| 1302 |
+
"grad_norm": 1.298364520072937,
|
| 1303 |
+
"learning_rate": 1.2017781906319326e-05,
|
| 1304 |
+
"loss": 0.1357,
|
| 1305 |
+
"step": 925
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 1.7680608365019013,
|
| 1309 |
+
"grad_norm": 0.9068416953086853,
|
| 1310 |
+
"learning_rate": 1.1863901890406316e-05,
|
| 1311 |
+
"loss": 0.13,
|
| 1312 |
+
"step": 930
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 1.7775665399239544,
|
| 1316 |
+
"grad_norm": 1.0278451442718506,
|
| 1317 |
+
"learning_rate": 1.1710366241991054e-05,
|
| 1318 |
+
"loss": 0.1354,
|
| 1319 |
+
"step": 935
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 1.7870722433460076,
|
| 1323 |
+
"grad_norm": 0.9125218987464905,
|
| 1324 |
+
"learning_rate": 1.1557191820459061e-05,
|
| 1325 |
+
"loss": 0.1361,
|
| 1326 |
+
"step": 940
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 1.796577946768061,
|
| 1330 |
+
"grad_norm": 1.138777732849121,
|
| 1331 |
+
"learning_rate": 1.140439544553039e-05,
|
| 1332 |
+
"loss": 0.1345,
|
| 1333 |
+
"step": 945
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 1.806083650190114,
|
| 1337 |
+
"grad_norm": 1.219953179359436,
|
| 1338 |
+
"learning_rate": 1.1251993895412692e-05,
|
| 1339 |
+
"loss": 0.1342,
|
| 1340 |
+
"step": 950
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 1.8155893536121672,
|
| 1344 |
+
"grad_norm": 0.9787817001342773,
|
| 1345 |
+
"learning_rate": 1.1100003904958839e-05,
|
| 1346 |
+
"loss": 0.1206,
|
| 1347 |
+
"step": 955
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 1.8250950570342206,
|
| 1351 |
+
"grad_norm": 1.0593589544296265,
|
| 1352 |
+
"learning_rate": 1.0948442163829318e-05,
|
| 1353 |
+
"loss": 0.1268,
|
| 1354 |
+
"step": 960
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 1.8346007604562737,
|
| 1358 |
+
"grad_norm": 0.9782788753509521,
|
| 1359 |
+
"learning_rate": 1.0797325314659571e-05,
|
| 1360 |
+
"loss": 0.1429,
|
| 1361 |
+
"step": 965
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 1.8441064638783269,
|
| 1365 |
+
"grad_norm": 0.9805053472518921,
|
| 1366 |
+
"learning_rate": 1.064666995123251e-05,
|
| 1367 |
+
"loss": 0.1313,
|
| 1368 |
+
"step": 970
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 1.8536121673003803,
|
| 1372 |
+
"grad_norm": 0.9250869750976562,
|
| 1373 |
+
"learning_rate": 1.049649261665639e-05,
|
| 1374 |
+
"loss": 0.1427,
|
| 1375 |
+
"step": 975
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 1.8631178707224336,
|
| 1379 |
+
"grad_norm": 0.9160425662994385,
|
| 1380 |
+
"learning_rate": 1.0346809801548247e-05,
|
| 1381 |
+
"loss": 0.1299,
|
| 1382 |
+
"step": 980
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 1.8726235741444865,
|
| 1386 |
+
"grad_norm": 1.075844168663025,
|
| 1387 |
+
"learning_rate": 1.019763794222311e-05,
|
| 1388 |
+
"loss": 0.1123,
|
| 1389 |
+
"step": 985
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 1.88212927756654,
|
| 1393 |
+
"grad_norm": 0.9277103543281555,
|
| 1394 |
+
"learning_rate": 1.0048993418889176e-05,
|
| 1395 |
+
"loss": 0.1175,
|
| 1396 |
+
"step": 990
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 1.8916349809885933,
|
| 1400 |
+
"grad_norm": 0.9449766278266907,
|
| 1401 |
+
"learning_rate": 9.90089255384911e-06,
|
| 1402 |
+
"loss": 0.1295,
|
| 1403 |
+
"step": 995
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 1.9011406844106464,
|
| 1407 |
+
"grad_norm": 0.8973495960235596,
|
| 1408 |
+
"learning_rate": 9.753351609707754e-06,
|
| 1409 |
+
"loss": 0.13,
|
| 1410 |
+
"step": 1000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 1.9106463878326996,
|
| 1414 |
+
"grad_norm": 1.0114878416061401,
|
| 1415 |
+
"learning_rate": 9.606386787586371e-06,
|
| 1416 |
+
"loss": 0.111,
|
| 1417 |
+
"step": 1005
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 1.920152091254753,
|
| 1421 |
+
"grad_norm": 0.99404376745224,
|
| 1422 |
+
"learning_rate": 9.460014225343625e-06,
|
| 1423 |
+
"loss": 0.115,
|
| 1424 |
+
"step": 1010
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 1.929657794676806,
|
| 1428 |
+
"grad_norm": 0.9833143949508667,
|
| 1429 |
+
"learning_rate": 9.314249995803519e-06,
|
| 1430 |
+
"loss": 0.1195,
|
| 1431 |
+
"step": 1015
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 1.9391634980988592,
|
| 1435 |
+
"grad_norm": 0.9722551703453064,
|
| 1436 |
+
"learning_rate": 9.169110104990505e-06,
|
| 1437 |
+
"loss": 0.124,
|
| 1438 |
+
"step": 1020
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 1.9486692015209126,
|
| 1442 |
+
"grad_norm": 0.8894194960594177,
|
| 1443 |
+
"learning_rate": 9.024610490371862e-06,
|
| 1444 |
+
"loss": 0.1096,
|
| 1445 |
+
"step": 1025
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 1.9581749049429658,
|
| 1449 |
+
"grad_norm": 0.9732495546340942,
|
| 1450 |
+
"learning_rate": 8.88076701910766e-06,
|
| 1451 |
+
"loss": 0.117,
|
| 1452 |
+
"step": 1030
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 1.967680608365019,
|
| 1456 |
+
"grad_norm": 0.8335443139076233,
|
| 1457 |
+
"learning_rate": 8.737595486308433e-06,
|
| 1458 |
+
"loss": 0.1073,
|
| 1459 |
+
"step": 1035
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 1.9771863117870723,
|
| 1463 |
+
"grad_norm": 0.8418932557106018,
|
| 1464 |
+
"learning_rate": 8.595111613300735e-06,
|
| 1465 |
+
"loss": 0.1107,
|
| 1466 |
+
"step": 1040
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 1.9866920152091256,
|
| 1470 |
+
"grad_norm": 0.8937597870826721,
|
| 1471 |
+
"learning_rate": 8.453331045900835e-06,
|
| 1472 |
+
"loss": 0.1079,
|
| 1473 |
+
"step": 1045
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 1.9961977186311786,
|
| 1477 |
+
"grad_norm": 0.8126094937324524,
|
| 1478 |
+
"learning_rate": 8.312269352696674e-06,
|
| 1479 |
+
"loss": 0.1001,
|
| 1480 |
+
"step": 1050
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 2.005703422053232,
|
| 1484 |
+
"grad_norm": 0.73410964012146,
|
| 1485 |
+
"learning_rate": 8.171942023338328e-06,
|
| 1486 |
+
"loss": 0.0906,
|
| 1487 |
+
"step": 1055
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 2.0152091254752853,
|
| 1491 |
+
"grad_norm": 0.9089372754096985,
|
| 1492 |
+
"learning_rate": 8.032364466837124e-06,
|
| 1493 |
+
"loss": 0.0882,
|
| 1494 |
+
"step": 1060
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 2.0247148288973382,
|
| 1498 |
+
"grad_norm": 0.743759274482727,
|
| 1499 |
+
"learning_rate": 7.893552009873601e-06,
|
| 1500 |
+
"loss": 0.0952,
|
| 1501 |
+
"step": 1065
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 2.0342205323193916,
|
| 1505 |
+
"grad_norm": 0.7030158042907715,
|
| 1506 |
+
"learning_rate": 7.755519895114533e-06,
|
| 1507 |
+
"loss": 0.084,
|
| 1508 |
+
"step": 1070
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 2.043726235741445,
|
| 1512 |
+
"grad_norm": 0.7420192360877991,
|
| 1513 |
+
"learning_rate": 7.61828327953917e-06,
|
| 1514 |
+
"loss": 0.0838,
|
| 1515 |
+
"step": 1075
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 2.053231939163498,
|
| 1519 |
+
"grad_norm": 0.8167407512664795,
|
| 1520 |
+
"learning_rate": 7.481857232774882e-06,
|
| 1521 |
+
"loss": 0.0787,
|
| 1522 |
+
"step": 1080
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 2.0627376425855513,
|
| 1526 |
+
"grad_norm": 0.8695756793022156,
|
| 1527 |
+
"learning_rate": 7.346256735442396e-06,
|
| 1528 |
+
"loss": 0.0868,
|
| 1529 |
+
"step": 1085
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 2.0722433460076046,
|
| 1533 |
+
"grad_norm": 0.8835598230361938,
|
| 1534 |
+
"learning_rate": 7.21149667751082e-06,
|
| 1535 |
+
"loss": 0.0867,
|
| 1536 |
+
"step": 1090
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 2.081749049429658,
|
| 1540 |
+
"grad_norm": 0.859008252620697,
|
| 1541 |
+
"learning_rate": 7.077591856662598e-06,
|
| 1542 |
+
"loss": 0.0717,
|
| 1543 |
+
"step": 1095
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 2.091254752851711,
|
| 1547 |
+
"grad_norm": 0.8529567718505859,
|
| 1548 |
+
"learning_rate": 6.944556976668619e-06,
|
| 1549 |
+
"loss": 0.0794,
|
| 1550 |
+
"step": 1100
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 2.1007604562737643,
|
| 1554 |
+
"grad_norm": 0.764645516872406,
|
| 1555 |
+
"learning_rate": 6.812406645773632e-06,
|
| 1556 |
+
"loss": 0.0904,
|
| 1557 |
+
"step": 1105
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 2.1102661596958177,
|
| 1561 |
+
"grad_norm": 0.80103999376297,
|
| 1562 |
+
"learning_rate": 6.6811553750921395e-06,
|
| 1563 |
+
"loss": 0.0882,
|
| 1564 |
+
"step": 1110
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 2.1197718631178706,
|
| 1568 |
+
"grad_norm": 0.6383639574050903,
|
| 1569 |
+
"learning_rate": 6.5508175770149905e-06,
|
| 1570 |
+
"loss": 0.0828,
|
| 1571 |
+
"step": 1115
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 2.129277566539924,
|
| 1575 |
+
"grad_norm": 0.7766659259796143,
|
| 1576 |
+
"learning_rate": 6.421407563626753e-06,
|
| 1577 |
+
"loss": 0.0775,
|
| 1578 |
+
"step": 1120
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 2.1387832699619773,
|
| 1582 |
+
"grad_norm": 0.8435718417167664,
|
| 1583 |
+
"learning_rate": 6.292939545134172e-06,
|
| 1584 |
+
"loss": 0.0768,
|
| 1585 |
+
"step": 1125
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 2.1482889733840302,
|
| 1589 |
+
"grad_norm": 0.799665629863739,
|
| 1590 |
+
"learning_rate": 6.165427628305758e-06,
|
| 1591 |
+
"loss": 0.0805,
|
| 1592 |
+
"step": 1130
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 2.1577946768060836,
|
| 1596 |
+
"grad_norm": 0.8663192987442017,
|
| 1597 |
+
"learning_rate": 6.038885814922769e-06,
|
| 1598 |
+
"loss": 0.0799,
|
| 1599 |
+
"step": 1135
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 2.167300380228137,
|
| 1603 |
+
"grad_norm": 0.7893325686454773,
|
| 1604 |
+
"learning_rate": 5.913328000241704e-06,
|
| 1605 |
+
"loss": 0.087,
|
| 1606 |
+
"step": 1140
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 2.17680608365019,
|
| 1610 |
+
"grad_norm": 0.7125917077064514,
|
| 1611 |
+
"learning_rate": 5.788767971468493e-06,
|
| 1612 |
+
"loss": 0.0825,
|
| 1613 |
+
"step": 1145
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 2.1863117870722433,
|
| 1617 |
+
"grad_norm": 0.8277238607406616,
|
| 1618 |
+
"learning_rate": 5.665219406244569e-06,
|
| 1619 |
+
"loss": 0.0817,
|
| 1620 |
+
"step": 1150
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 2.1958174904942966,
|
| 1624 |
+
"grad_norm": 0.8407533764839172,
|
| 1625 |
+
"learning_rate": 5.542695871144943e-06,
|
| 1626 |
+
"loss": 0.0861,
|
| 1627 |
+
"step": 1155
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 2.20532319391635,
|
| 1631 |
+
"grad_norm": 0.7299392819404602,
|
| 1632 |
+
"learning_rate": 5.421210820188503e-06,
|
| 1633 |
+
"loss": 0.0767,
|
| 1634 |
+
"step": 1160
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 2.214828897338403,
|
| 1638 |
+
"grad_norm": 0.8483830094337463,
|
| 1639 |
+
"learning_rate": 5.300777593360649e-06,
|
| 1640 |
+
"loss": 0.0786,
|
| 1641 |
+
"step": 1165
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 2.2243346007604563,
|
| 1645 |
+
"grad_norm": 0.8090299367904663,
|
| 1646 |
+
"learning_rate": 5.181409415148482e-06,
|
| 1647 |
+
"loss": 0.0729,
|
| 1648 |
+
"step": 1170
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 2.2338403041825097,
|
| 1652 |
+
"grad_norm": 0.7625455856323242,
|
| 1653 |
+
"learning_rate": 5.0631193930886295e-06,
|
| 1654 |
+
"loss": 0.0789,
|
| 1655 |
+
"step": 1175
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 2.2433460076045626,
|
| 1659 |
+
"grad_norm": 0.8784281015396118,
|
| 1660 |
+
"learning_rate": 4.945920516327942e-06,
|
| 1661 |
+
"loss": 0.081,
|
| 1662 |
+
"step": 1180
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 2.252851711026616,
|
| 1666 |
+
"grad_norm": 0.843019962310791,
|
| 1667 |
+
"learning_rate": 4.829825654197206e-06,
|
| 1668 |
+
"loss": 0.081,
|
| 1669 |
+
"step": 1185
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 2.2623574144486693,
|
| 1673 |
+
"grad_norm": 0.7855110168457031,
|
| 1674 |
+
"learning_rate": 4.7148475547979665e-06,
|
| 1675 |
+
"loss": 0.0773,
|
| 1676 |
+
"step": 1190
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 2.2718631178707223,
|
| 1680 |
+
"grad_norm": 0.8021001219749451,
|
| 1681 |
+
"learning_rate": 4.60099884360271e-06,
|
| 1682 |
+
"loss": 0.0823,
|
| 1683 |
+
"step": 1195
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 2.2813688212927756,
|
| 1687 |
+
"grad_norm": 0.7722094058990479,
|
| 1688 |
+
"learning_rate": 4.488292022068475e-06,
|
| 1689 |
+
"loss": 0.0792,
|
| 1690 |
+
"step": 1200
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 2.290874524714829,
|
| 1694 |
+
"grad_norm": 0.6311149597167969,
|
| 1695 |
+
"learning_rate": 4.3767394662641106e-06,
|
| 1696 |
+
"loss": 0.0766,
|
| 1697 |
+
"step": 1205
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 2.3003802281368824,
|
| 1701 |
+
"grad_norm": 0.8658928871154785,
|
| 1702 |
+
"learning_rate": 4.266353425511277e-06,
|
| 1703 |
+
"loss": 0.0775,
|
| 1704 |
+
"step": 1210
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 2.3098859315589353,
|
| 1708 |
+
"grad_norm": 0.755916178226471,
|
| 1709 |
+
"learning_rate": 4.157146021039383e-06,
|
| 1710 |
+
"loss": 0.0785,
|
| 1711 |
+
"step": 1215
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 2.3193916349809887,
|
| 1715 |
+
"grad_norm": 0.587697446346283,
|
| 1716 |
+
"learning_rate": 4.049129244654584e-06,
|
| 1717 |
+
"loss": 0.0705,
|
| 1718 |
+
"step": 1220
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 2.328897338403042,
|
| 1722 |
+
"grad_norm": 0.7521547079086304,
|
| 1723 |
+
"learning_rate": 3.942314957422994e-06,
|
| 1724 |
+
"loss": 0.0723,
|
| 1725 |
+
"step": 1225
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 2.338403041825095,
|
| 1729 |
+
"grad_norm": 0.6250755786895752,
|
| 1730 |
+
"learning_rate": 3.836714888368234e-06,
|
| 1731 |
+
"loss": 0.0698,
|
| 1732 |
+
"step": 1230
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 2.3479087452471483,
|
| 1736 |
+
"grad_norm": 0.6285881996154785,
|
| 1737 |
+
"learning_rate": 3.732340633183507e-06,
|
| 1738 |
+
"loss": 0.0752,
|
| 1739 |
+
"step": 1235
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 2.3574144486692017,
|
| 1743 |
+
"grad_norm": 0.6878852844238281,
|
| 1744 |
+
"learning_rate": 3.629203652958309e-06,
|
| 1745 |
+
"loss": 0.0637,
|
| 1746 |
+
"step": 1240
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 2.3669201520912546,
|
| 1750 |
+
"grad_norm": 0.8017040491104126,
|
| 1751 |
+
"learning_rate": 3.5273152729198973e-06,
|
| 1752 |
+
"loss": 0.0738,
|
| 1753 |
+
"step": 1245
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 2.376425855513308,
|
| 1757 |
+
"grad_norm": 0.7701224088668823,
|
| 1758 |
+
"learning_rate": 3.426686681189711e-06,
|
| 1759 |
+
"loss": 0.0721,
|
| 1760 |
+
"step": 1250
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 2.3859315589353614,
|
| 1764 |
+
"grad_norm": 0.6260634064674377,
|
| 1765 |
+
"learning_rate": 3.3273289275548154e-06,
|
| 1766 |
+
"loss": 0.0673,
|
| 1767 |
+
"step": 1255
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 2.3954372623574143,
|
| 1771 |
+
"grad_norm": 0.6028752326965332,
|
| 1772 |
+
"learning_rate": 3.2292529222545608e-06,
|
| 1773 |
+
"loss": 0.0732,
|
| 1774 |
+
"step": 1260
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 2.4049429657794676,
|
| 1778 |
+
"grad_norm": 0.6564818024635315,
|
| 1779 |
+
"learning_rate": 3.132469434782553e-06,
|
| 1780 |
+
"loss": 0.0677,
|
| 1781 |
+
"step": 1265
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 2.414448669201521,
|
| 1785 |
+
"grad_norm": 0.8518382906913757,
|
| 1786 |
+
"learning_rate": 3.036989092704079e-06,
|
| 1787 |
+
"loss": 0.073,
|
| 1788 |
+
"step": 1270
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 2.423954372623574,
|
| 1792 |
+
"grad_norm": 0.7608246803283691,
|
| 1793 |
+
"learning_rate": 2.9428223804891114e-06,
|
| 1794 |
+
"loss": 0.0818,
|
| 1795 |
+
"step": 1275
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 2.4334600760456273,
|
| 1799 |
+
"grad_norm": 0.7186647653579712,
|
| 1800 |
+
"learning_rate": 2.8499796383610625e-06,
|
| 1801 |
+
"loss": 0.0683,
|
| 1802 |
+
"step": 1280
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 2.4429657794676807,
|
| 1806 |
+
"grad_norm": 0.6510358452796936,
|
| 1807 |
+
"learning_rate": 2.758471061161309e-06,
|
| 1808 |
+
"loss": 0.0782,
|
| 1809 |
+
"step": 1285
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 2.4524714828897336,
|
| 1813 |
+
"grad_norm": 0.6423006653785706,
|
| 1814 |
+
"learning_rate": 2.6683066972297488e-06,
|
| 1815 |
+
"loss": 0.0754,
|
| 1816 |
+
"step": 1290
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 2.461977186311787,
|
| 1820 |
+
"grad_norm": 0.7106276154518127,
|
| 1821 |
+
"learning_rate": 2.579496447301404e-06,
|
| 1822 |
+
"loss": 0.0665,
|
| 1823 |
+
"step": 1295
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 2.4714828897338403,
|
| 1827 |
+
"grad_norm": 0.6568664908409119,
|
| 1828 |
+
"learning_rate": 2.492050063419252e-06,
|
| 1829 |
+
"loss": 0.0713,
|
| 1830 |
+
"step": 1300
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 2.4809885931558937,
|
| 1834 |
+
"grad_norm": 0.7260980010032654,
|
| 1835 |
+
"learning_rate": 2.405977147863372e-06,
|
| 1836 |
+
"loss": 0.081,
|
| 1837 |
+
"step": 1305
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 2.4904942965779466,
|
| 1841 |
+
"grad_norm": 0.6391762495040894,
|
| 1842 |
+
"learning_rate": 2.3212871520965432e-06,
|
| 1843 |
+
"loss": 0.0768,
|
| 1844 |
+
"step": 1310
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 2.5,
|
| 1848 |
+
"grad_norm": 0.652922511100769,
|
| 1849 |
+
"learning_rate": 2.2379893757264007e-06,
|
| 1850 |
+
"loss": 0.069,
|
| 1851 |
+
"step": 1315
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 2.5095057034220534,
|
| 1855 |
+
"grad_norm": 0.5948718190193176,
|
| 1856 |
+
"learning_rate": 2.1560929654842697e-06,
|
| 1857 |
+
"loss": 0.0692,
|
| 1858 |
+
"step": 1320
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 2.5190114068441067,
|
| 1862 |
+
"grad_norm": 0.7025821208953857,
|
| 1863 |
+
"learning_rate": 2.0756069142207846e-06,
|
| 1864 |
+
"loss": 0.069,
|
| 1865 |
+
"step": 1325
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 2.5285171102661597,
|
| 1869 |
+
"grad_norm": 0.6770378947257996,
|
| 1870 |
+
"learning_rate": 1.996540059918396e-06,
|
| 1871 |
+
"loss": 0.0703,
|
| 1872 |
+
"step": 1330
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 2.538022813688213,
|
| 1876 |
+
"grad_norm": 0.6679671406745911,
|
| 1877 |
+
"learning_rate": 1.918901084720916e-06,
|
| 1878 |
+
"loss": 0.0664,
|
| 1879 |
+
"step": 1335
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 2.5475285171102664,
|
| 1883 |
+
"grad_norm": 0.6371467709541321,
|
| 1884 |
+
"learning_rate": 1.8426985139801278e-06,
|
| 1885 |
+
"loss": 0.0728,
|
| 1886 |
+
"step": 1340
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 2.5570342205323193,
|
| 1890 |
+
"grad_norm": 0.5342304706573486,
|
| 1891 |
+
"learning_rate": 1.767940715319647e-06,
|
| 1892 |
+
"loss": 0.0608,
|
| 1893 |
+
"step": 1345
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 2.5665399239543727,
|
| 1897 |
+
"grad_norm": 0.5994696617126465,
|
| 1898 |
+
"learning_rate": 1.6946358977160936e-06,
|
| 1899 |
+
"loss": 0.0701,
|
| 1900 |
+
"step": 1350
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 2.576045627376426,
|
| 1904 |
+
"grad_norm": 0.8105832934379578,
|
| 1905 |
+
"learning_rate": 1.622792110597685e-06,
|
| 1906 |
+
"loss": 0.0616,
|
| 1907 |
+
"step": 1355
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 2.585551330798479,
|
| 1911 |
+
"grad_norm": 0.6744514107704163,
|
| 1912 |
+
"learning_rate": 1.5524172429603444e-06,
|
| 1913 |
+
"loss": 0.0672,
|
| 1914 |
+
"step": 1360
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 2.5950570342205324,
|
| 1918 |
+
"grad_norm": 0.6263822913169861,
|
| 1919 |
+
"learning_rate": 1.4835190225014255e-06,
|
| 1920 |
+
"loss": 0.0756,
|
| 1921 |
+
"step": 1365
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 2.6045627376425857,
|
| 1925 |
+
"grad_norm": 0.5048222541809082,
|
| 1926 |
+
"learning_rate": 1.416105014771163e-06,
|
| 1927 |
+
"loss": 0.0593,
|
| 1928 |
+
"step": 1370
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 2.6140684410646386,
|
| 1932 |
+
"grad_norm": 0.7641021013259888,
|
| 1933 |
+
"learning_rate": 1.3501826223419066e-06,
|
| 1934 |
+
"loss": 0.0726,
|
| 1935 |
+
"step": 1375
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 2.623574144486692,
|
| 1939 |
+
"grad_norm": 0.6130462288856506,
|
| 1940 |
+
"learning_rate": 1.285759083995266e-06,
|
| 1941 |
+
"loss": 0.0698,
|
| 1942 |
+
"step": 1380
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 2.6330798479087454,
|
| 1946 |
+
"grad_norm": 0.8435813784599304,
|
| 1947 |
+
"learning_rate": 1.222841473927238e-06,
|
| 1948 |
+
"loss": 0.0748,
|
| 1949 |
+
"step": 1385
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 2.6425855513307983,
|
| 1953 |
+
"grad_norm": 0.6960525512695312,
|
| 1954 |
+
"learning_rate": 1.1614367009714116e-06,
|
| 1955 |
+
"loss": 0.065,
|
| 1956 |
+
"step": 1390
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 2.6520912547528517,
|
| 1960 |
+
"grad_norm": 0.5265695452690125,
|
| 1961 |
+
"learning_rate": 1.1015515078403115e-06,
|
| 1962 |
+
"loss": 0.0644,
|
| 1963 |
+
"step": 1395
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 2.661596958174905,
|
| 1967 |
+
"grad_norm": 0.5959596633911133,
|
| 1968 |
+
"learning_rate": 1.04319247038501e-06,
|
| 1969 |
+
"loss": 0.0677,
|
| 1970 |
+
"step": 1400
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 2.671102661596958,
|
| 1974 |
+
"grad_norm": 0.6203439831733704,
|
| 1975 |
+
"learning_rate": 9.8636599687304e-07,
|
| 1976 |
+
"loss": 0.0694,
|
| 1977 |
+
"step": 1405
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 2.6806083650190113,
|
| 1981 |
+
"grad_norm": 0.6514430642127991,
|
| 1982 |
+
"learning_rate": 9.310783272847223e-07,
|
| 1983 |
+
"loss": 0.0713,
|
| 1984 |
+
"step": 1410
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 2.6901140684410647,
|
| 1988 |
+
"grad_norm": 0.6616337895393372,
|
| 1989 |
+
"learning_rate": 8.773355326279686e-07,
|
| 1990 |
+
"loss": 0.0787,
|
| 1991 |
+
"step": 1415
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 2.6996197718631176,
|
| 1995 |
+
"grad_norm": 0.5439194440841675,
|
| 1996 |
+
"learning_rate": 8.251435142716357e-07,
|
| 1997 |
+
"loss": 0.0728,
|
| 1998 |
+
"step": 1420
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 2.709125475285171,
|
| 2002 |
+
"grad_norm": 0.5798903107643127,
|
| 2003 |
+
"learning_rate": 7.745080032975144e-07,
|
| 2004 |
+
"loss": 0.0652,
|
| 2005 |
+
"step": 1425
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 2.7186311787072244,
|
| 2009 |
+
"grad_norm": 0.5315594673156738,
|
| 2010 |
+
"learning_rate": 7.254345598710044e-07,
|
| 2011 |
+
"loss": 0.0637,
|
| 2012 |
+
"step": 1430
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 2.7281368821292773,
|
| 2016 |
+
"grad_norm": 0.6243197321891785,
|
| 2017 |
+
"learning_rate": 6.779285726305762e-07,
|
| 2018 |
+
"loss": 0.0706,
|
| 2019 |
+
"step": 1435
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 2.7376425855513307,
|
| 2023 |
+
"grad_norm": 0.6620869636535645,
|
| 2024 |
+
"learning_rate": 6.319952580960559e-07,
|
| 2025 |
+
"loss": 0.0684,
|
| 2026 |
+
"step": 1440
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 2.747148288973384,
|
| 2030 |
+
"grad_norm": 0.5309165716171265,
|
| 2031 |
+
"learning_rate": 5.876396600958034e-07,
|
| 2032 |
+
"loss": 0.0615,
|
| 2033 |
+
"step": 1445
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 2.7566539923954374,
|
| 2037 |
+
"grad_norm": 0.45584654808044434,
|
| 2038 |
+
"learning_rate": 5.448666492128673e-07,
|
| 2039 |
+
"loss": 0.0667,
|
| 2040 |
+
"step": 1450
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 2.7661596958174908,
|
| 2044 |
+
"grad_norm": 0.4772530794143677,
|
| 2045 |
+
"learning_rate": 5.036809222501593e-07,
|
| 2046 |
+
"loss": 0.07,
|
| 2047 |
+
"step": 1455
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 2.7756653992395437,
|
| 2051 |
+
"grad_norm": 0.5844233632087708,
|
| 2052 |
+
"learning_rate": 4.6408700171470474e-07,
|
| 2053 |
+
"loss": 0.0628,
|
| 2054 |
+
"step": 1460
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 2.785171102661597,
|
| 2058 |
+
"grad_norm": 0.6680727601051331,
|
| 2059 |
+
"learning_rate": 4.2608923532104047e-07,
|
| 2060 |
+
"loss": 0.0726,
|
| 2061 |
+
"step": 1465
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 2.7946768060836504,
|
| 2065 |
+
"grad_norm": 0.5999226570129395,
|
| 2066 |
+
"learning_rate": 3.896917955138046e-07,
|
| 2067 |
+
"loss": 0.07,
|
| 2068 |
+
"step": 1470
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 2.8041825095057034,
|
| 2072 |
+
"grad_norm": 0.5890464782714844,
|
| 2073 |
+
"learning_rate": 3.5489867900956153e-07,
|
| 2074 |
+
"loss": 0.0644,
|
| 2075 |
+
"step": 1475
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 2.8136882129277567,
|
| 2079 |
+
"grad_norm": 0.5629656910896301,
|
| 2080 |
+
"learning_rate": 3.217137063579395e-07,
|
| 2081 |
+
"loss": 0.0697,
|
| 2082 |
+
"step": 1480
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 2.82319391634981,
|
| 2086 |
+
"grad_norm": 0.6490433216094971,
|
| 2087 |
+
"learning_rate": 2.901405215221081e-07,
|
| 2088 |
+
"loss": 0.0738,
|
| 2089 |
+
"step": 1485
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 2.832699619771863,
|
| 2093 |
+
"grad_norm": 0.6723814606666565,
|
| 2094 |
+
"learning_rate": 2.6018259147862986e-07,
|
| 2095 |
+
"loss": 0.0616,
|
| 2096 |
+
"step": 1490
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 2.8422053231939164,
|
| 2100 |
+
"grad_norm": 0.5256921052932739,
|
| 2101 |
+
"learning_rate": 2.3184320583677643e-07,
|
| 2102 |
+
"loss": 0.0598,
|
| 2103 |
+
"step": 1495
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 2.8517110266159698,
|
| 2107 |
+
"grad_norm": 0.5516988635063171,
|
| 2108 |
+
"learning_rate": 2.0512547647728918e-07,
|
| 2109 |
+
"loss": 0.0673,
|
| 2110 |
+
"step": 1500
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"epoch": 2.8612167300380227,
|
| 2114 |
+
"grad_norm": 0.6108591556549072,
|
| 2115 |
+
"learning_rate": 1.8003233721068434e-07,
|
| 2116 |
+
"loss": 0.07,
|
| 2117 |
+
"step": 1505
|
| 2118 |
+
},
|
| 2119 |
+
{
|
| 2120 |
+
"epoch": 2.870722433460076,
|
| 2121 |
+
"grad_norm": 0.5069841742515564,
|
| 2122 |
+
"learning_rate": 1.5656654345508892e-07,
|
| 2123 |
+
"loss": 0.0662,
|
| 2124 |
+
"step": 1510
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 2.8802281368821294,
|
| 2128 |
+
"grad_norm": 0.6191032528877258,
|
| 2129 |
+
"learning_rate": 1.347306719336777e-07,
|
| 2130 |
+
"loss": 0.0599,
|
| 2131 |
+
"step": 1515
|
| 2132 |
+
},
|
| 2133 |
+
{
|
| 2134 |
+
"epoch": 2.8897338403041823,
|
| 2135 |
+
"grad_norm": 0.6037904024124146,
|
| 2136 |
+
"learning_rate": 1.1452712039172808e-07,
|
| 2137 |
+
"loss": 0.0607,
|
| 2138 |
+
"step": 1520
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 2.8992395437262357,
|
| 2142 |
+
"grad_norm": 0.5701655149459839,
|
| 2143 |
+
"learning_rate": 9.595810733333543e-08,
|
| 2144 |
+
"loss": 0.064,
|
| 2145 |
+
"step": 1525
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 2.908745247148289,
|
| 2149 |
+
"grad_norm": 0.6150251030921936,
|
| 2150 |
+
"learning_rate": 7.902567177779319e-08,
|
| 2151 |
+
"loss": 0.0649,
|
| 2152 |
+
"step": 1530
|
| 2153 |
+
},
|
| 2154 |
+
{
|
| 2155 |
+
"epoch": 2.918250950570342,
|
| 2156 |
+
"grad_norm": 0.7660977840423584,
|
| 2157 |
+
"learning_rate": 6.373167303570515e-08,
|
| 2158 |
+
"loss": 0.072,
|
| 2159 |
+
"step": 1535
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 2.9277566539923954,
|
| 2163 |
+
"grad_norm": 0.6196973323822021,
|
| 2164 |
+
"learning_rate": 5.007779050481221e-08,
|
| 2165 |
+
"loss": 0.0683,
|
| 2166 |
+
"step": 1540
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 2.9372623574144487,
|
| 2170 |
+
"grad_norm": 0.527747392654419,
|
| 2171 |
+
"learning_rate": 3.806552348557812e-08,
|
| 2172 |
+
"loss": 0.053,
|
| 2173 |
+
"step": 1545
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 2.9467680608365017,
|
| 2177 |
+
"grad_norm": 0.5807064175605774,
|
| 2178 |
+
"learning_rate": 2.7696191016566287e-08,
|
| 2179 |
+
"loss": 0.0728,
|
| 2180 |
+
"step": 1550
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 2.956273764258555,
|
| 2184 |
+
"grad_norm": 0.5269973874092102,
|
| 2185 |
+
"learning_rate": 1.8970931729590525e-08,
|
| 2186 |
+
"loss": 0.051,
|
| 2187 |
+
"step": 1555
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 2.9657794676806084,
|
| 2191 |
+
"grad_norm": 0.6171160936355591,
|
| 2192 |
+
"learning_rate": 1.1890703724681817e-08,
|
| 2193 |
+
"loss": 0.0635,
|
| 2194 |
+
"step": 1560
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 2.9752851711026613,
|
| 2198 |
+
"grad_norm": 0.5301425457000732,
|
| 2199 |
+
"learning_rate": 6.456284464892437e-09,
|
| 2200 |
+
"loss": 0.0639,
|
| 2201 |
+
"step": 1565
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 2.9847908745247147,
|
| 2205 |
+
"grad_norm": 0.46173006296157837,
|
| 2206 |
+
"learning_rate": 2.6682706909159085e-09,
|
| 2207 |
+
"loss": 0.0581,
|
| 2208 |
+
"step": 1570
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 2.994296577946768,
|
| 2212 |
+
"grad_norm": 0.5762280821800232,
|
| 2213 |
+
"learning_rate": 5.270783555644254e-10,
|
| 2214 |
+
"loss": 0.068,
|
| 2215 |
+
"step": 1575
|
| 2216 |
+
},
|
| 2217 |
+
{
|
| 2218 |
+
"epoch": 3.0,
|
| 2219 |
+
"step": 1578,
|
| 2220 |
+
"total_flos": 2.0726363014414991e+18,
|
| 2221 |
+
"train_loss": 0.36312728373307845,
|
| 2222 |
+
"train_runtime": 985.9967,
|
| 2223 |
+
"train_samples_per_second": 51.198,
|
| 2224 |
+
"train_steps_per_second": 1.6
|
| 2225 |
+
}
|
| 2226 |
+
],
|
| 2227 |
+
"logging_steps": 5,
|
| 2228 |
+
"max_steps": 1578,
|
| 2229 |
+
"num_input_tokens_seen": 0,
|
| 2230 |
+
"num_train_epochs": 3,
|
| 2231 |
+
"save_steps": 20000,
|
| 2232 |
+
"stateful_callbacks": {
|
| 2233 |
+
"TrainerControl": {
|
| 2234 |
+
"args": {
|
| 2235 |
+
"should_epoch_stop": false,
|
| 2236 |
+
"should_evaluate": false,
|
| 2237 |
+
"should_log": false,
|
| 2238 |
+
"should_save": false,
|
| 2239 |
+
"should_training_stop": false
|
| 2240 |
+
},
|
| 2241 |
+
"attributes": {}
|
| 2242 |
+
}
|
| 2243 |
+
},
|
| 2244 |
+
"total_flos": 2.0726363014414991e+18,
|
| 2245 |
+
"train_batch_size": 2,
|
| 2246 |
+
"trial_name": null,
|
| 2247 |
+
"trial_params": null
|
| 2248 |
+
}
|
instruct/136_128_e3_3e-5/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:90d3eba4210dacbcb3f97b0c503d4d1579a9717fccb9c70b31301e4c5ba2fb2a
|
| 3 |
+
size 8273
|
instruct/136_128_e3_3e-5/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|