Upload folder using huggingface_hub
Browse files- 103_128_e3_3e-5/adapter_config.json +39 -0
- 103_128_e3_3e-5/adapter_model.safetensors +3 -0
- 103_128_e3_3e-5/added_tokens.json +9 -0
- 103_128_e3_3e-5/all_results.json +9 -0
- 103_128_e3_3e-5/chat_template.jinja +62 -0
- 103_128_e3_3e-5/config.json +32 -0
- 103_128_e3_3e-5/merges.txt +0 -0
- 103_128_e3_3e-5/special_tokens_map.json +33 -0
- 103_128_e3_3e-5/tokenizer.json +0 -0
- 103_128_e3_3e-5/tokenizer_config.json +234 -0
- 103_128_e3_3e-5/train_results.json +9 -0
- 103_128_e3_3e-5/trainer_state.json +1926 -0
- 103_128_e3_3e-5/training_args.bin +3 -0
- 103_128_e3_3e-5/vocab.json +0 -0
103_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 |
+
"o_proj",
|
| 28 |
+
"q_proj",
|
| 29 |
+
"k_proj",
|
| 30 |
+
"up_proj",
|
| 31 |
+
"down_proj",
|
| 32 |
+
"v_proj",
|
| 33 |
+
"gate_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
+
"use_dora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
103_128_e3_3e-5/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd82ff8088b20ea042079c435c1b5ac550fdee0311d066e7f204f89291a89b09
|
| 3 |
+
size 791751704
|
103_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 |
+
}
|
103_128_e3_3e-5/all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 1.8647534585071534e+18,
|
| 4 |
+
"train_loss": 0.5871922652988675,
|
| 5 |
+
"train_runtime": 872.6809,
|
| 6 |
+
"train_samples": 14358,
|
| 7 |
+
"train_samples_per_second": 49.358,
|
| 8 |
+
"train_steps_per_second": 1.544
|
| 9 |
+
}
|
103_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 %}
|
103_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 |
+
}
|
103_128_e3_3e-5/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
103_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 |
+
}
|
103_128_e3_3e-5/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
103_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 |
+
}
|
103_128_e3_3e-5/train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 1.8647534585071534e+18,
|
| 4 |
+
"train_loss": 0.5871922652988675,
|
| 5 |
+
"train_runtime": 872.6809,
|
| 6 |
+
"train_samples": 14358,
|
| 7 |
+
"train_samples_per_second": 49.358,
|
| 8 |
+
"train_steps_per_second": 1.544
|
| 9 |
+
}
|
103_128_e3_3e-5/trainer_state.json
ADDED
|
@@ -0,0 +1,1926 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 1347,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.011135857461024499,
|
| 14 |
+
"grad_norm": 3.011831760406494,
|
| 15 |
+
"learning_rate": 1.7647058823529412e-06,
|
| 16 |
+
"loss": 1.5551,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.022271714922048998,
|
| 21 |
+
"grad_norm": 2.884472370147705,
|
| 22 |
+
"learning_rate": 3.970588235294118e-06,
|
| 23 |
+
"loss": 1.6148,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.0334075723830735,
|
| 28 |
+
"grad_norm": 1.1130396127700806,
|
| 29 |
+
"learning_rate": 6.176470588235294e-06,
|
| 30 |
+
"loss": 1.4765,
|
| 31 |
+
"step": 15
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.044543429844097995,
|
| 35 |
+
"grad_norm": 0.5881382822990417,
|
| 36 |
+
"learning_rate": 8.382352941176472e-06,
|
| 37 |
+
"loss": 1.4146,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.0556792873051225,
|
| 42 |
+
"grad_norm": 0.43582701683044434,
|
| 43 |
+
"learning_rate": 1.0588235294117648e-05,
|
| 44 |
+
"loss": 1.4031,
|
| 45 |
+
"step": 25
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.066815144766147,
|
| 49 |
+
"grad_norm": 0.5293598771095276,
|
| 50 |
+
"learning_rate": 1.2794117647058824e-05,
|
| 51 |
+
"loss": 1.4041,
|
| 52 |
+
"step": 30
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.0779510022271715,
|
| 56 |
+
"grad_norm": 0.4321681559085846,
|
| 57 |
+
"learning_rate": 1.5e-05,
|
| 58 |
+
"loss": 1.3638,
|
| 59 |
+
"step": 35
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.08908685968819599,
|
| 63 |
+
"grad_norm": 0.35817426443099976,
|
| 64 |
+
"learning_rate": 1.7205882352941175e-05,
|
| 65 |
+
"loss": 1.2377,
|
| 66 |
+
"step": 40
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.10022271714922049,
|
| 70 |
+
"grad_norm": 0.37552395462989807,
|
| 71 |
+
"learning_rate": 1.9411764705882355e-05,
|
| 72 |
+
"loss": 1.2719,
|
| 73 |
+
"step": 45
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.111358574610245,
|
| 77 |
+
"grad_norm": 0.4484923481941223,
|
| 78 |
+
"learning_rate": 2.161764705882353e-05,
|
| 79 |
+
"loss": 1.2796,
|
| 80 |
+
"step": 50
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.12249443207126949,
|
| 84 |
+
"grad_norm": 0.43503645062446594,
|
| 85 |
+
"learning_rate": 2.3823529411764704e-05,
|
| 86 |
+
"loss": 1.3049,
|
| 87 |
+
"step": 55
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.133630289532294,
|
| 91 |
+
"grad_norm": 0.3340904116630554,
|
| 92 |
+
"learning_rate": 2.6029411764705883e-05,
|
| 93 |
+
"loss": 1.2598,
|
| 94 |
+
"step": 60
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.1447661469933185,
|
| 98 |
+
"grad_norm": 0.44583529233932495,
|
| 99 |
+
"learning_rate": 2.823529411764706e-05,
|
| 100 |
+
"loss": 1.2634,
|
| 101 |
+
"step": 65
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.155902004454343,
|
| 105 |
+
"grad_norm": 0.4122629463672638,
|
| 106 |
+
"learning_rate": 2.999995474988352e-05,
|
| 107 |
+
"loss": 1.2614,
|
| 108 |
+
"step": 70
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.16703786191536749,
|
| 112 |
+
"grad_norm": 0.3926136791706085,
|
| 113 |
+
"learning_rate": 2.9998371024472586e-05,
|
| 114 |
+
"loss": 1.1996,
|
| 115 |
+
"step": 75
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.17817371937639198,
|
| 119 |
+
"grad_norm": 0.42907795310020447,
|
| 120 |
+
"learning_rate": 2.9994525066240027e-05,
|
| 121 |
+
"loss": 1.2446,
|
| 122 |
+
"step": 80
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.18930957683741648,
|
| 126 |
+
"grad_norm": 0.40913739800453186,
|
| 127 |
+
"learning_rate": 2.998841745527904e-05,
|
| 128 |
+
"loss": 1.1798,
|
| 129 |
+
"step": 85
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.20044543429844097,
|
| 133 |
+
"grad_norm": 0.4026980698108673,
|
| 134 |
+
"learning_rate": 2.9980049112812197e-05,
|
| 135 |
+
"loss": 1.1895,
|
| 136 |
+
"step": 90
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.21158129175946547,
|
| 140 |
+
"grad_norm": 0.44694283604621887,
|
| 141 |
+
"learning_rate": 2.9969421301052503e-05,
|
| 142 |
+
"loss": 1.1622,
|
| 143 |
+
"step": 95
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.22271714922049,
|
| 147 |
+
"grad_norm": 0.4653894305229187,
|
| 148 |
+
"learning_rate": 2.9956535623013017e-05,
|
| 149 |
+
"loss": 1.1896,
|
| 150 |
+
"step": 100
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.23385300668151449,
|
| 154 |
+
"grad_norm": 0.4920363426208496,
|
| 155 |
+
"learning_rate": 2.9941394022265062e-05,
|
| 156 |
+
"loss": 1.1189,
|
| 157 |
+
"step": 105
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.24498886414253898,
|
| 161 |
+
"grad_norm": 0.4969410300254822,
|
| 162 |
+
"learning_rate": 2.9923998782645068e-05,
|
| 163 |
+
"loss": 1.1711,
|
| 164 |
+
"step": 110
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.2561247216035635,
|
| 168 |
+
"grad_norm": 0.544940710067749,
|
| 169 |
+
"learning_rate": 2.990435252791011e-05,
|
| 170 |
+
"loss": 1.1603,
|
| 171 |
+
"step": 115
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.267260579064588,
|
| 175 |
+
"grad_norm": 0.5352882146835327,
|
| 176 |
+
"learning_rate": 2.9882458221342136e-05,
|
| 177 |
+
"loss": 1.1264,
|
| 178 |
+
"step": 120
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.27839643652561247,
|
| 182 |
+
"grad_norm": 0.4591788947582245,
|
| 183 |
+
"learning_rate": 2.9858319165301055e-05,
|
| 184 |
+
"loss": 1.1157,
|
| 185 |
+
"step": 125
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.289532293986637,
|
| 189 |
+
"grad_norm": 0.4337748885154724,
|
| 190 |
+
"learning_rate": 2.983193900072658e-05,
|
| 191 |
+
"loss": 1.0741,
|
| 192 |
+
"step": 130
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.30066815144766146,
|
| 196 |
+
"grad_norm": 0.5300671458244324,
|
| 197 |
+
"learning_rate": 2.9803321706589098e-05,
|
| 198 |
+
"loss": 1.0989,
|
| 199 |
+
"step": 135
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.311804008908686,
|
| 203 |
+
"grad_norm": 0.4856047034263611,
|
| 204 |
+
"learning_rate": 2.97724715992895e-05,
|
| 205 |
+
"loss": 1.0914,
|
| 206 |
+
"step": 140
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.32293986636971045,
|
| 210 |
+
"grad_norm": 0.5013135075569153,
|
| 211 |
+
"learning_rate": 2.973939333200814e-05,
|
| 212 |
+
"loss": 1.0931,
|
| 213 |
+
"step": 145
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.33407572383073497,
|
| 217 |
+
"grad_norm": 0.45660150051116943,
|
| 218 |
+
"learning_rate": 2.970409189400296e-05,
|
| 219 |
+
"loss": 1.0634,
|
| 220 |
+
"step": 150
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.34521158129175944,
|
| 224 |
+
"grad_norm": 0.5180467367172241,
|
| 225 |
+
"learning_rate": 2.9666572609856995e-05,
|
| 226 |
+
"loss": 1.0562,
|
| 227 |
+
"step": 155
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.35634743875278396,
|
| 231 |
+
"grad_norm": 0.5715084075927734,
|
| 232 |
+
"learning_rate": 2.9626841138675205e-05,
|
| 233 |
+
"loss": 1.0093,
|
| 234 |
+
"step": 160
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.3674832962138085,
|
| 238 |
+
"grad_norm": 0.6340333819389343,
|
| 239 |
+
"learning_rate": 2.9584903473230948e-05,
|
| 240 |
+
"loss": 1.0338,
|
| 241 |
+
"step": 165
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.37861915367483295,
|
| 245 |
+
"grad_norm": 0.5650427937507629,
|
| 246 |
+
"learning_rate": 2.9540765939062045e-05,
|
| 247 |
+
"loss": 0.9952,
|
| 248 |
+
"step": 170
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.3897550111358575,
|
| 252 |
+
"grad_norm": 0.6139913201332092,
|
| 253 |
+
"learning_rate": 2.94944351935167e-05,
|
| 254 |
+
"loss": 0.9877,
|
| 255 |
+
"step": 175
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.40089086859688194,
|
| 259 |
+
"grad_norm": 0.5496277809143066,
|
| 260 |
+
"learning_rate": 2.9445918224749372e-05,
|
| 261 |
+
"loss": 0.9474,
|
| 262 |
+
"step": 180
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.41202672605790647,
|
| 266 |
+
"grad_norm": 0.6407635807991028,
|
| 267 |
+
"learning_rate": 2.9395222350666713e-05,
|
| 268 |
+
"loss": 1.0235,
|
| 269 |
+
"step": 185
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.42316258351893093,
|
| 273 |
+
"grad_norm": 0.6844958662986755,
|
| 274 |
+
"learning_rate": 2.9342355217823808e-05,
|
| 275 |
+
"loss": 1.0227,
|
| 276 |
+
"step": 190
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.43429844097995546,
|
| 280 |
+
"grad_norm": 0.6006965041160583,
|
| 281 |
+
"learning_rate": 2.928732480027084e-05,
|
| 282 |
+
"loss": 1.0427,
|
| 283 |
+
"step": 195
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.44543429844098,
|
| 287 |
+
"grad_norm": 0.5823552012443542,
|
| 288 |
+
"learning_rate": 2.923013939835032e-05,
|
| 289 |
+
"loss": 0.9506,
|
| 290 |
+
"step": 200
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.45657015590200445,
|
| 294 |
+
"grad_norm": 0.6315293312072754,
|
| 295 |
+
"learning_rate": 2.9170807637445173e-05,
|
| 296 |
+
"loss": 0.9763,
|
| 297 |
+
"step": 205
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.46770601336302897,
|
| 301 |
+
"grad_norm": 0.715202808380127,
|
| 302 |
+
"learning_rate": 2.910933846667771e-05,
|
| 303 |
+
"loss": 1.0043,
|
| 304 |
+
"step": 210
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.47884187082405344,
|
| 308 |
+
"grad_norm": 0.593745768070221,
|
| 309 |
+
"learning_rate": 2.904574115755985e-05,
|
| 310 |
+
"loss": 0.9347,
|
| 311 |
+
"step": 215
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.48997772828507796,
|
| 315 |
+
"grad_norm": 0.7218592762947083,
|
| 316 |
+
"learning_rate": 2.898002530259465e-05,
|
| 317 |
+
"loss": 0.963,
|
| 318 |
+
"step": 220
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.5011135857461024,
|
| 322 |
+
"grad_norm": 0.6377033591270447,
|
| 323 |
+
"learning_rate": 2.8912200813829484e-05,
|
| 324 |
+
"loss": 0.9311,
|
| 325 |
+
"step": 225
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.512249443207127,
|
| 329 |
+
"grad_norm": 0.6982869505882263,
|
| 330 |
+
"learning_rate": 2.884227792136096e-05,
|
| 331 |
+
"loss": 0.9053,
|
| 332 |
+
"step": 230
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.5233853006681515,
|
| 336 |
+
"grad_norm": 0.7429744601249695,
|
| 337 |
+
"learning_rate": 2.8770267171791913e-05,
|
| 338 |
+
"loss": 0.9385,
|
| 339 |
+
"step": 235
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.534521158129176,
|
| 343 |
+
"grad_norm": 0.6968746185302734,
|
| 344 |
+
"learning_rate": 2.8696179426640627e-05,
|
| 345 |
+
"loss": 0.9427,
|
| 346 |
+
"step": 240
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.5456570155902004,
|
| 350 |
+
"grad_norm": 0.6877008080482483,
|
| 351 |
+
"learning_rate": 2.8620025860702587e-05,
|
| 352 |
+
"loss": 0.968,
|
| 353 |
+
"step": 245
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.5567928730512249,
|
| 357 |
+
"grad_norm": 0.7620334625244141,
|
| 358 |
+
"learning_rate": 2.8541817960364954e-05,
|
| 359 |
+
"loss": 0.8913,
|
| 360 |
+
"step": 250
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.5679287305122495,
|
| 364 |
+
"grad_norm": 0.7203275561332703,
|
| 365 |
+
"learning_rate": 2.8461567521874053e-05,
|
| 366 |
+
"loss": 0.8793,
|
| 367 |
+
"step": 255
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.579064587973274,
|
| 371 |
+
"grad_norm": 0.6845876574516296,
|
| 372 |
+
"learning_rate": 2.8379286649556116e-05,
|
| 373 |
+
"loss": 0.8848,
|
| 374 |
+
"step": 260
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.5902004454342984,
|
| 378 |
+
"grad_norm": 0.778755784034729,
|
| 379 |
+
"learning_rate": 2.8294987753991576e-05,
|
| 380 |
+
"loss": 0.8693,
|
| 381 |
+
"step": 265
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.6013363028953229,
|
| 385 |
+
"grad_norm": 0.7565673589706421,
|
| 386 |
+
"learning_rate": 2.820868355014315e-05,
|
| 387 |
+
"loss": 0.8966,
|
| 388 |
+
"step": 270
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.6124721603563474,
|
| 392 |
+
"grad_norm": 0.7945839166641235,
|
| 393 |
+
"learning_rate": 2.8120387055438015e-05,
|
| 394 |
+
"loss": 0.8838,
|
| 395 |
+
"step": 275
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.623608017817372,
|
| 399 |
+
"grad_norm": 0.7651553153991699,
|
| 400 |
+
"learning_rate": 2.8030111587804366e-05,
|
| 401 |
+
"loss": 0.9187,
|
| 402 |
+
"step": 280
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.6347438752783965,
|
| 406 |
+
"grad_norm": 0.7515232563018799,
|
| 407 |
+
"learning_rate": 2.793787076366265e-05,
|
| 408 |
+
"loss": 0.8738,
|
| 409 |
+
"step": 285
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.6458797327394209,
|
| 413 |
+
"grad_norm": 0.7491884827613831,
|
| 414 |
+
"learning_rate": 2.7843678495871772e-05,
|
| 415 |
+
"loss": 0.812,
|
| 416 |
+
"step": 290
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.6570155902004454,
|
| 420 |
+
"grad_norm": 0.7611950635910034,
|
| 421 |
+
"learning_rate": 2.7747548991630592e-05,
|
| 422 |
+
"loss": 0.8474,
|
| 423 |
+
"step": 295
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.6681514476614699,
|
| 427 |
+
"grad_norm": 0.8440566062927246,
|
| 428 |
+
"learning_rate": 2.764949675033503e-05,
|
| 429 |
+
"loss": 0.8555,
|
| 430 |
+
"step": 300
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.6792873051224945,
|
| 434 |
+
"grad_norm": 0.7965632677078247,
|
| 435 |
+
"learning_rate": 2.754953656139109e-05,
|
| 436 |
+
"loss": 0.7757,
|
| 437 |
+
"step": 305
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.6904231625835189,
|
| 441 |
+
"grad_norm": 0.7886831164360046,
|
| 442 |
+
"learning_rate": 2.744768350198415e-05,
|
| 443 |
+
"loss": 0.8333,
|
| 444 |
+
"step": 310
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.7015590200445434,
|
| 448 |
+
"grad_norm": 0.8007385730743408,
|
| 449 |
+
"learning_rate": 2.734395293480484e-05,
|
| 450 |
+
"loss": 0.8825,
|
| 451 |
+
"step": 315
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.7126948775055679,
|
| 455 |
+
"grad_norm": 0.849041223526001,
|
| 456 |
+
"learning_rate": 2.7238360505731847e-05,
|
| 457 |
+
"loss": 0.8348,
|
| 458 |
+
"step": 320
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.7238307349665924,
|
| 462 |
+
"grad_norm": 0.849378228187561,
|
| 463 |
+
"learning_rate": 2.7130922141472037e-05,
|
| 464 |
+
"loss": 0.8643,
|
| 465 |
+
"step": 325
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.734966592427617,
|
| 469 |
+
"grad_norm": 0.8217678666114807,
|
| 470 |
+
"learning_rate": 2.7021654047158204e-05,
|
| 471 |
+
"loss": 0.7699,
|
| 472 |
+
"step": 330
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.7461024498886414,
|
| 476 |
+
"grad_norm": 0.8490059971809387,
|
| 477 |
+
"learning_rate": 2.6910572703904782e-05,
|
| 478 |
+
"loss": 0.7826,
|
| 479 |
+
"step": 335
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.7572383073496659,
|
| 483 |
+
"grad_norm": 0.8670004606246948,
|
| 484 |
+
"learning_rate": 2.679769486632199e-05,
|
| 485 |
+
"loss": 0.833,
|
| 486 |
+
"step": 340
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.7683741648106904,
|
| 490 |
+
"grad_norm": 0.8972408175468445,
|
| 491 |
+
"learning_rate": 2.6683037559988728e-05,
|
| 492 |
+
"loss": 0.7801,
|
| 493 |
+
"step": 345
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.779510022271715,
|
| 497 |
+
"grad_norm": 0.9939659237861633,
|
| 498 |
+
"learning_rate": 2.656661807888453e-05,
|
| 499 |
+
"loss": 0.797,
|
| 500 |
+
"step": 350
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.7906458797327395,
|
| 504 |
+
"grad_norm": 0.8599905967712402,
|
| 505 |
+
"learning_rate": 2.6448453982781104e-05,
|
| 506 |
+
"loss": 0.7599,
|
| 507 |
+
"step": 355
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.8017817371937639,
|
| 511 |
+
"grad_norm": 0.8295682668685913,
|
| 512 |
+
"learning_rate": 2.632856309459376e-05,
|
| 513 |
+
"loss": 0.7896,
|
| 514 |
+
"step": 360
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.8129175946547884,
|
| 518 |
+
"grad_norm": 0.8687642216682434,
|
| 519 |
+
"learning_rate": 2.6206963497693145e-05,
|
| 520 |
+
"loss": 0.7733,
|
| 521 |
+
"step": 365
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.8240534521158129,
|
| 525 |
+
"grad_norm": 0.8289012908935547,
|
| 526 |
+
"learning_rate": 2.608367353317768e-05,
|
| 527 |
+
"loss": 0.7059,
|
| 528 |
+
"step": 370
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.8351893095768375,
|
| 532 |
+
"grad_norm": 0.8974064588546753,
|
| 533 |
+
"learning_rate": 2.5958711797107158e-05,
|
| 534 |
+
"loss": 0.8048,
|
| 535 |
+
"step": 375
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.8463251670378619,
|
| 539 |
+
"grad_norm": 0.9098872542381287,
|
| 540 |
+
"learning_rate": 2.5832097137697848e-05,
|
| 541 |
+
"loss": 0.7732,
|
| 542 |
+
"step": 380
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.8574610244988864,
|
| 546 |
+
"grad_norm": 0.8924546241760254,
|
| 547 |
+
"learning_rate": 2.5703848652479594e-05,
|
| 548 |
+
"loss": 0.708,
|
| 549 |
+
"step": 385
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.8685968819599109,
|
| 553 |
+
"grad_norm": 0.8143579959869385,
|
| 554 |
+
"learning_rate": 2.5573985685415292e-05,
|
| 555 |
+
"loss": 0.7073,
|
| 556 |
+
"step": 390
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.8797327394209354,
|
| 560 |
+
"grad_norm": 0.8222923278808594,
|
| 561 |
+
"learning_rate": 2.54425278239832e-05,
|
| 562 |
+
"loss": 0.7977,
|
| 563 |
+
"step": 395
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.89086859688196,
|
| 567 |
+
"grad_norm": 1.00271475315094,
|
| 568 |
+
"learning_rate": 2.5309494896222528e-05,
|
| 569 |
+
"loss": 0.7791,
|
| 570 |
+
"step": 400
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.9020044543429844,
|
| 574 |
+
"grad_norm": 0.816573977470398,
|
| 575 |
+
"learning_rate": 2.517490696774274e-05,
|
| 576 |
+
"loss": 0.7193,
|
| 577 |
+
"step": 405
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.9131403118040089,
|
| 581 |
+
"grad_norm": 1.043613076210022,
|
| 582 |
+
"learning_rate": 2.5038784338697018e-05,
|
| 583 |
+
"loss": 0.7649,
|
| 584 |
+
"step": 410
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.9242761692650334,
|
| 588 |
+
"grad_norm": 0.8600007891654968,
|
| 589 |
+
"learning_rate": 2.490114754072034e-05,
|
| 590 |
+
"loss": 0.7203,
|
| 591 |
+
"step": 415
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.9354120267260579,
|
| 595 |
+
"grad_norm": 0.9310862421989441,
|
| 596 |
+
"learning_rate": 2.4762017333832667e-05,
|
| 597 |
+
"loss": 0.7367,
|
| 598 |
+
"step": 420
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.9465478841870824,
|
| 602 |
+
"grad_norm": 0.9194145798683167,
|
| 603 |
+
"learning_rate": 2.4621414703307664e-05,
|
| 604 |
+
"loss": 0.6963,
|
| 605 |
+
"step": 425
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.9576837416481069,
|
| 609 |
+
"grad_norm": 1.0241931676864624,
|
| 610 |
+
"learning_rate": 2.4479360856507457e-05,
|
| 611 |
+
"loss": 0.7544,
|
| 612 |
+
"step": 430
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.9688195991091314,
|
| 616 |
+
"grad_norm": 0.8260948657989502,
|
| 617 |
+
"learning_rate": 2.433587721968388e-05,
|
| 618 |
+
"loss": 0.6925,
|
| 619 |
+
"step": 435
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.9799554565701559,
|
| 623 |
+
"grad_norm": 0.8787631392478943,
|
| 624 |
+
"learning_rate": 2.419098543474671e-05,
|
| 625 |
+
"loss": 0.6855,
|
| 626 |
+
"step": 440
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.9910913140311804,
|
| 630 |
+
"grad_norm": 1.0173147916793823,
|
| 631 |
+
"learning_rate": 2.4044707355999392e-05,
|
| 632 |
+
"loss": 0.6934,
|
| 633 |
+
"step": 445
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.0022271714922049,
|
| 637 |
+
"grad_norm": 0.9487058520317078,
|
| 638 |
+
"learning_rate": 2.3897065046842694e-05,
|
| 639 |
+
"loss": 0.6721,
|
| 640 |
+
"step": 450
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.0133630289532294,
|
| 644 |
+
"grad_norm": 1.0052411556243896,
|
| 645 |
+
"learning_rate": 2.3748080776446855e-05,
|
| 646 |
+
"loss": 0.5926,
|
| 647 |
+
"step": 455
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.024498886414254,
|
| 651 |
+
"grad_norm": 0.9942535161972046,
|
| 652 |
+
"learning_rate": 2.359777701639268e-05,
|
| 653 |
+
"loss": 0.6376,
|
| 654 |
+
"step": 460
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.0356347438752784,
|
| 658 |
+
"grad_norm": 0.9476110935211182,
|
| 659 |
+
"learning_rate": 2.3446176437282104e-05,
|
| 660 |
+
"loss": 0.5885,
|
| 661 |
+
"step": 465
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.046770601336303,
|
| 665 |
+
"grad_norm": 0.9419899582862854,
|
| 666 |
+
"learning_rate": 2.329330190531875e-05,
|
| 667 |
+
"loss": 0.6666,
|
| 668 |
+
"step": 470
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.0579064587973275,
|
| 672 |
+
"grad_norm": 0.936540961265564,
|
| 673 |
+
"learning_rate": 2.313917647885897e-05,
|
| 674 |
+
"loss": 0.6452,
|
| 675 |
+
"step": 475
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.069042316258352,
|
| 679 |
+
"grad_norm": 1.0330755710601807,
|
| 680 |
+
"learning_rate": 2.2983823404933917e-05,
|
| 681 |
+
"loss": 0.5251,
|
| 682 |
+
"step": 480
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.0801781737193763,
|
| 686 |
+
"grad_norm": 0.9818919897079468,
|
| 687 |
+
"learning_rate": 2.2827266115743133e-05,
|
| 688 |
+
"loss": 0.5767,
|
| 689 |
+
"step": 485
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.0913140311804008,
|
| 693 |
+
"grad_norm": 1.0238152742385864,
|
| 694 |
+
"learning_rate": 2.266952822512026e-05,
|
| 695 |
+
"loss": 0.5583,
|
| 696 |
+
"step": 490
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.1024498886414253,
|
| 700 |
+
"grad_norm": 0.9279976487159729,
|
| 701 |
+
"learning_rate": 2.251063352497127e-05,
|
| 702 |
+
"loss": 0.5625,
|
| 703 |
+
"step": 495
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.1135857461024499,
|
| 707 |
+
"grad_norm": 0.97560715675354,
|
| 708 |
+
"learning_rate": 2.235060598168594e-05,
|
| 709 |
+
"loss": 0.5558,
|
| 710 |
+
"step": 500
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.1247216035634744,
|
| 714 |
+
"grad_norm": 0.9987034797668457,
|
| 715 |
+
"learning_rate": 2.218946973252292e-05,
|
| 716 |
+
"loss": 0.5277,
|
| 717 |
+
"step": 505
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.135857461024499,
|
| 721 |
+
"grad_norm": 1.062520980834961,
|
| 722 |
+
"learning_rate": 2.202724908196908e-05,
|
| 723 |
+
"loss": 0.5563,
|
| 724 |
+
"step": 510
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.1469933184855234,
|
| 728 |
+
"grad_norm": 0.9421431422233582,
|
| 729 |
+
"learning_rate": 2.186396849807361e-05,
|
| 730 |
+
"loss": 0.563,
|
| 731 |
+
"step": 515
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.158129175946548,
|
| 735 |
+
"grad_norm": 1.0231684446334839,
|
| 736 |
+
"learning_rate": 2.1699652608757467e-05,
|
| 737 |
+
"loss": 0.5659,
|
| 738 |
+
"step": 520
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.1692650334075725,
|
| 742 |
+
"grad_norm": 1.0898637771606445,
|
| 743 |
+
"learning_rate": 2.1534326198098685e-05,
|
| 744 |
+
"loss": 0.5159,
|
| 745 |
+
"step": 525
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.1804008908685968,
|
| 749 |
+
"grad_norm": 0.8799867033958435,
|
| 750 |
+
"learning_rate": 2.1368014202594158e-05,
|
| 751 |
+
"loss": 0.6001,
|
| 752 |
+
"step": 530
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.1915367483296213,
|
| 756 |
+
"grad_norm": 1.0832245349884033,
|
| 757 |
+
"learning_rate": 2.1200741707398425e-05,
|
| 758 |
+
"loss": 0.5639,
|
| 759 |
+
"step": 535
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.2026726057906458,
|
| 763 |
+
"grad_norm": 0.9998000264167786,
|
| 764 |
+
"learning_rate": 2.1032533942540004e-05,
|
| 765 |
+
"loss": 0.5241,
|
| 766 |
+
"step": 540
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.2138084632516704,
|
| 770 |
+
"grad_norm": 1.0483994483947754,
|
| 771 |
+
"learning_rate": 2.086341627911592e-05,
|
| 772 |
+
"loss": 0.6003,
|
| 773 |
+
"step": 545
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.2249443207126949,
|
| 777 |
+
"grad_norm": 0.9831916093826294,
|
| 778 |
+
"learning_rate": 2.0693414225464943e-05,
|
| 779 |
+
"loss": 0.5326,
|
| 780 |
+
"step": 550
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.2360801781737194,
|
| 784 |
+
"grad_norm": 1.0163428783416748,
|
| 785 |
+
"learning_rate": 2.0522553423320084e-05,
|
| 786 |
+
"loss": 0.5244,
|
| 787 |
+
"step": 555
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.247216035634744,
|
| 791 |
+
"grad_norm": 1.1133408546447754,
|
| 792 |
+
"learning_rate": 2.035085964394103e-05,
|
| 793 |
+
"loss": 0.5196,
|
| 794 |
+
"step": 560
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.2583518930957684,
|
| 798 |
+
"grad_norm": 1.1191511154174805,
|
| 799 |
+
"learning_rate": 2.0178358784226997e-05,
|
| 800 |
+
"loss": 0.5535,
|
| 801 |
+
"step": 565
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.269487750556793,
|
| 805 |
+
"grad_norm": 1.1303200721740723,
|
| 806 |
+
"learning_rate": 2.000507686281069e-05,
|
| 807 |
+
"loss": 0.5907,
|
| 808 |
+
"step": 570
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.2806236080178173,
|
| 812 |
+
"grad_norm": 0.9778265953063965,
|
| 813 |
+
"learning_rate": 1.9831040016133816e-05,
|
| 814 |
+
"loss": 0.5489,
|
| 815 |
+
"step": 575
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.2917594654788418,
|
| 819 |
+
"grad_norm": 1.1150294542312622,
|
| 820 |
+
"learning_rate": 1.965627449450488e-05,
|
| 821 |
+
"loss": 0.5182,
|
| 822 |
+
"step": 580
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.3028953229398663,
|
| 826 |
+
"grad_norm": 1.0767874717712402,
|
| 827 |
+
"learning_rate": 1.9480806658139858e-05,
|
| 828 |
+
"loss": 0.5336,
|
| 829 |
+
"step": 585
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.3140311804008908,
|
| 833 |
+
"grad_norm": 1.0775963068008423,
|
| 834 |
+
"learning_rate": 1.9304662973186146e-05,
|
| 835 |
+
"loss": 0.5839,
|
| 836 |
+
"step": 590
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.3251670378619154,
|
| 840 |
+
"grad_norm": 1.0338784456253052,
|
| 841 |
+
"learning_rate": 1.9127870007730702e-05,
|
| 842 |
+
"loss": 0.5252,
|
| 843 |
+
"step": 595
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.3363028953229399,
|
| 847 |
+
"grad_norm": 1.2222623825073242,
|
| 848 |
+
"learning_rate": 1.8950454427792684e-05,
|
| 849 |
+
"loss": 0.5342,
|
| 850 |
+
"step": 600
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.3474387527839644,
|
| 854 |
+
"grad_norm": 1.0011582374572754,
|
| 855 |
+
"learning_rate": 1.8772442993301373e-05,
|
| 856 |
+
"loss": 0.4945,
|
| 857 |
+
"step": 605
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.358574610244989,
|
| 861 |
+
"grad_norm": 1.046838402748108,
|
| 862 |
+
"learning_rate": 1.8593862554059932e-05,
|
| 863 |
+
"loss": 0.4783,
|
| 864 |
+
"step": 610
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.3697104677060135,
|
| 868 |
+
"grad_norm": 1.07161545753479,
|
| 869 |
+
"learning_rate": 1.8414740045695582e-05,
|
| 870 |
+
"loss": 0.5064,
|
| 871 |
+
"step": 615
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.3808463251670378,
|
| 875 |
+
"grad_norm": 0.9844891428947449,
|
| 876 |
+
"learning_rate": 1.8235102485596887e-05,
|
| 877 |
+
"loss": 0.4781,
|
| 878 |
+
"step": 620
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.3919821826280623,
|
| 882 |
+
"grad_norm": 0.9671491384506226,
|
| 883 |
+
"learning_rate": 1.8054976968838603e-05,
|
| 884 |
+
"loss": 0.524,
|
| 885 |
+
"step": 625
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.4031180400890868,
|
| 889 |
+
"grad_norm": 1.0659390687942505,
|
| 890 |
+
"learning_rate": 1.787439066409495e-05,
|
| 891 |
+
"loss": 0.4946,
|
| 892 |
+
"step": 630
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 1.4142538975501113,
|
| 896 |
+
"grad_norm": 1.1342428922653198,
|
| 897 |
+
"learning_rate": 1.7693370809541663e-05,
|
| 898 |
+
"loss": 0.5177,
|
| 899 |
+
"step": 635
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 1.4253897550111359,
|
| 903 |
+
"grad_norm": 1.0668096542358398,
|
| 904 |
+
"learning_rate": 1.751194470874762e-05,
|
| 905 |
+
"loss": 0.4795,
|
| 906 |
+
"step": 640
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.4365256124721604,
|
| 910 |
+
"grad_norm": 1.043365716934204,
|
| 911 |
+
"learning_rate": 1.7330139726556594e-05,
|
| 912 |
+
"loss": 0.4877,
|
| 913 |
+
"step": 645
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.447661469933185,
|
| 917 |
+
"grad_norm": 1.1115537881851196,
|
| 918 |
+
"learning_rate": 1.714798328495976e-05,
|
| 919 |
+
"loss": 0.4432,
|
| 920 |
+
"step": 650
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.4587973273942094,
|
| 924 |
+
"grad_norm": 1.2205064296722412,
|
| 925 |
+
"learning_rate": 1.6965502858959575e-05,
|
| 926 |
+
"loss": 0.4549,
|
| 927 |
+
"step": 655
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.469933184855234,
|
| 931 |
+
"grad_norm": 1.1843407154083252,
|
| 932 |
+
"learning_rate": 1.678272597242569e-05,
|
| 933 |
+
"loss": 0.5061,
|
| 934 |
+
"step": 660
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.4810690423162582,
|
| 938 |
+
"grad_norm": 1.0663741827011108,
|
| 939 |
+
"learning_rate": 1.659968019394347e-05,
|
| 940 |
+
"loss": 0.5286,
|
| 941 |
+
"step": 665
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.492204899777283,
|
| 945 |
+
"grad_norm": 1.1001248359680176,
|
| 946 |
+
"learning_rate": 1.6416393132655726e-05,
|
| 947 |
+
"loss": 0.5048,
|
| 948 |
+
"step": 670
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 1.5033407572383073,
|
| 952 |
+
"grad_norm": 1.0005817413330078,
|
| 953 |
+
"learning_rate": 1.6232892434098463e-05,
|
| 954 |
+
"loss": 0.457,
|
| 955 |
+
"step": 675
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.5144766146993318,
|
| 959 |
+
"grad_norm": 1.1287330389022827,
|
| 960 |
+
"learning_rate": 1.604920577603097e-05,
|
| 961 |
+
"loss": 0.4193,
|
| 962 |
+
"step": 680
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.5256124721603563,
|
| 966 |
+
"grad_norm": 0.9753129482269287,
|
| 967 |
+
"learning_rate": 1.586536086426117e-05,
|
| 968 |
+
"loss": 0.4679,
|
| 969 |
+
"step": 685
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.5367483296213809,
|
| 973 |
+
"grad_norm": 1.0173906087875366,
|
| 974 |
+
"learning_rate": 1.5681385428466698e-05,
|
| 975 |
+
"loss": 0.4595,
|
| 976 |
+
"step": 690
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.5478841870824054,
|
| 980 |
+
"grad_norm": 1.0840353965759277,
|
| 981 |
+
"learning_rate": 1.549730721801237e-05,
|
| 982 |
+
"loss": 0.464,
|
| 983 |
+
"step": 695
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.5590200445434297,
|
| 987 |
+
"grad_norm": 1.0250458717346191,
|
| 988 |
+
"learning_rate": 1.5313153997764695e-05,
|
| 989 |
+
"loss": 0.4351,
|
| 990 |
+
"step": 700
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.5701559020044544,
|
| 994 |
+
"grad_norm": 1.27544105052948,
|
| 995 |
+
"learning_rate": 1.5128953543904062e-05,
|
| 996 |
+
"loss": 0.4491,
|
| 997 |
+
"step": 705
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 1.5812917594654787,
|
| 1001 |
+
"grad_norm": 1.168850064277649,
|
| 1002 |
+
"learning_rate": 1.4944733639735196e-05,
|
| 1003 |
+
"loss": 0.4642,
|
| 1004 |
+
"step": 710
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.5924276169265035,
|
| 1008 |
+
"grad_norm": 1.0681533813476562,
|
| 1009 |
+
"learning_rate": 1.476052207149654e-05,
|
| 1010 |
+
"loss": 0.4632,
|
| 1011 |
+
"step": 715
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 1.6035634743875278,
|
| 1015 |
+
"grad_norm": 1.124383807182312,
|
| 1016 |
+
"learning_rate": 1.4576346624169215e-05,
|
| 1017 |
+
"loss": 0.4405,
|
| 1018 |
+
"step": 720
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.6146993318485523,
|
| 1022 |
+
"grad_norm": 1.1282367706298828,
|
| 1023 |
+
"learning_rate": 1.4392235077286157e-05,
|
| 1024 |
+
"loss": 0.4432,
|
| 1025 |
+
"step": 725
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 1.6258351893095768,
|
| 1029 |
+
"grad_norm": 1.0083343982696533,
|
| 1030 |
+
"learning_rate": 1.4208215200742085e-05,
|
| 1031 |
+
"loss": 0.4518,
|
| 1032 |
+
"step": 730
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 1.6369710467706013,
|
| 1036 |
+
"grad_norm": 1.0625771284103394,
|
| 1037 |
+
"learning_rate": 1.4024314750604896e-05,
|
| 1038 |
+
"loss": 0.4841,
|
| 1039 |
+
"step": 735
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 1.6481069042316259,
|
| 1043 |
+
"grad_norm": 1.0268199443817139,
|
| 1044 |
+
"learning_rate": 1.3840561464929176e-05,
|
| 1045 |
+
"loss": 0.4911,
|
| 1046 |
+
"step": 740
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.6592427616926502,
|
| 1050 |
+
"grad_norm": 1.0973244905471802,
|
| 1051 |
+
"learning_rate": 1.3656983059572422e-05,
|
| 1052 |
+
"loss": 0.4134,
|
| 1053 |
+
"step": 745
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 1.670378619153675,
|
| 1057 |
+
"grad_norm": 1.032193899154663,
|
| 1058 |
+
"learning_rate": 1.3473607224014588e-05,
|
| 1059 |
+
"loss": 0.4277,
|
| 1060 |
+
"step": 750
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 1.6815144766146992,
|
| 1064 |
+
"grad_norm": 1.064208984375,
|
| 1065 |
+
"learning_rate": 1.3290461617181657e-05,
|
| 1066 |
+
"loss": 0.4178,
|
| 1067 |
+
"step": 755
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 1.692650334075724,
|
| 1071 |
+
"grad_norm": 1.0647375583648682,
|
| 1072 |
+
"learning_rate": 1.3107573863273763e-05,
|
| 1073 |
+
"loss": 0.4499,
|
| 1074 |
+
"step": 760
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.7037861915367483,
|
| 1078 |
+
"grad_norm": 1.296118140220642,
|
| 1079 |
+
"learning_rate": 1.2924971547598597e-05,
|
| 1080 |
+
"loss": 0.4543,
|
| 1081 |
+
"step": 765
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 1.7149220489977728,
|
| 1085 |
+
"grad_norm": 1.1239320039749146,
|
| 1086 |
+
"learning_rate": 1.2742682212410647e-05,
|
| 1087 |
+
"loss": 0.4068,
|
| 1088 |
+
"step": 770
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 1.7260579064587973,
|
| 1092 |
+
"grad_norm": 1.1447110176086426,
|
| 1093 |
+
"learning_rate": 1.256073335275699e-05,
|
| 1094 |
+
"loss": 0.4242,
|
| 1095 |
+
"step": 775
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 1.7371937639198218,
|
| 1099 |
+
"grad_norm": 1.1734458208084106,
|
| 1100 |
+
"learning_rate": 1.2379152412330096e-05,
|
| 1101 |
+
"loss": 0.446,
|
| 1102 |
+
"step": 780
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 1.7483296213808464,
|
| 1106 |
+
"grad_norm": 1.140526294708252,
|
| 1107 |
+
"learning_rate": 1.2197966779328497e-05,
|
| 1108 |
+
"loss": 0.4118,
|
| 1109 |
+
"step": 785
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 1.7594654788418709,
|
| 1113 |
+
"grad_norm": 1.3425854444503784,
|
| 1114 |
+
"learning_rate": 1.201720378232575e-05,
|
| 1115 |
+
"loss": 0.4235,
|
| 1116 |
+
"step": 790
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 1.7706013363028954,
|
| 1120 |
+
"grad_norm": 1.1366854906082153,
|
| 1121 |
+
"learning_rate": 1.1836890686148418e-05,
|
| 1122 |
+
"loss": 0.3861,
|
| 1123 |
+
"step": 795
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 1.7817371937639197,
|
| 1127 |
+
"grad_norm": 1.1368030309677124,
|
| 1128 |
+
"learning_rate": 1.1657054687763678e-05,
|
| 1129 |
+
"loss": 0.431,
|
| 1130 |
+
"step": 800
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 1.7928730512249444,
|
| 1134 |
+
"grad_norm": 1.1710275411605835,
|
| 1135 |
+
"learning_rate": 1.1477722912177125e-05,
|
| 1136 |
+
"loss": 0.4114,
|
| 1137 |
+
"step": 805
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 1.8040089086859687,
|
| 1141 |
+
"grad_norm": 1.15105140209198,
|
| 1142 |
+
"learning_rate": 1.1298922408341483e-05,
|
| 1143 |
+
"loss": 0.4261,
|
| 1144 |
+
"step": 810
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 1.8151447661469933,
|
| 1148 |
+
"grad_norm": 1.104927659034729,
|
| 1149 |
+
"learning_rate": 1.1120680145076737e-05,
|
| 1150 |
+
"loss": 0.3925,
|
| 1151 |
+
"step": 815
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.8262806236080178,
|
| 1155 |
+
"grad_norm": 1.090867042541504,
|
| 1156 |
+
"learning_rate": 1.0943023007002382e-05,
|
| 1157 |
+
"loss": 0.4061,
|
| 1158 |
+
"step": 820
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 1.8374164810690423,
|
| 1162 |
+
"grad_norm": 1.1114544868469238,
|
| 1163 |
+
"learning_rate": 1.0765977790482395e-05,
|
| 1164 |
+
"loss": 0.3927,
|
| 1165 |
+
"step": 825
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 1.8485523385300668,
|
| 1169 |
+
"grad_norm": 1.142992377281189,
|
| 1170 |
+
"learning_rate": 1.058957119958343e-05,
|
| 1171 |
+
"loss": 0.4361,
|
| 1172 |
+
"step": 830
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 1.8596881959910914,
|
| 1176 |
+
"grad_norm": 1.3408854007720947,
|
| 1177 |
+
"learning_rate": 1.041382984204704e-05,
|
| 1178 |
+
"loss": 0.4013,
|
| 1179 |
+
"step": 835
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 1.8708240534521159,
|
| 1183 |
+
"grad_norm": 1.1359509229660034,
|
| 1184 |
+
"learning_rate": 1.0238780225276355e-05,
|
| 1185 |
+
"loss": 0.4172,
|
| 1186 |
+
"step": 840
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 1.8819599109131402,
|
| 1190 |
+
"grad_norm": 1.19562566280365,
|
| 1191 |
+
"learning_rate": 1.0064448752337946e-05,
|
| 1192 |
+
"loss": 0.4145,
|
| 1193 |
+
"step": 845
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 1.893095768374165,
|
| 1197 |
+
"grad_norm": 1.2395390272140503,
|
| 1198 |
+
"learning_rate": 9.890861717979369e-06,
|
| 1199 |
+
"loss": 0.4323,
|
| 1200 |
+
"step": 850
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 1.9042316258351892,
|
| 1204 |
+
"grad_norm": 1.1929833889007568,
|
| 1205 |
+
"learning_rate": 9.718045304663101e-06,
|
| 1206 |
+
"loss": 0.4293,
|
| 1207 |
+
"step": 855
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 1.9153674832962138,
|
| 1211 |
+
"grad_norm": 1.0412315130233765,
|
| 1212 |
+
"learning_rate": 9.546025578617383e-06,
|
| 1213 |
+
"loss": 0.4427,
|
| 1214 |
+
"step": 860
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 1.9265033407572383,
|
| 1218 |
+
"grad_norm": 1.2895293235778809,
|
| 1219 |
+
"learning_rate": 9.374828485904584e-06,
|
| 1220 |
+
"loss": 0.4163,
|
| 1221 |
+
"step": 865
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 1.9376391982182628,
|
| 1225 |
+
"grad_norm": 1.2366167306900024,
|
| 1226 |
+
"learning_rate": 9.204479848507753e-06,
|
| 1227 |
+
"loss": 0.3891,
|
| 1228 |
+
"step": 870
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 1.9487750556792873,
|
| 1232 |
+
"grad_norm": 1.2404311895370483,
|
| 1233 |
+
"learning_rate": 9.035005360435781e-06,
|
| 1234 |
+
"loss": 0.3843,
|
| 1235 |
+
"step": 875
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 1.9599109131403119,
|
| 1239 |
+
"grad_norm": 1.1814974546432495,
|
| 1240 |
+
"learning_rate": 8.866430583847973e-06,
|
| 1241 |
+
"loss": 0.3997,
|
| 1242 |
+
"step": 880
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 1.9710467706013364,
|
| 1246 |
+
"grad_norm": 1.1850112676620483,
|
| 1247 |
+
"learning_rate": 8.69878094519843e-06,
|
| 1248 |
+
"loss": 0.4245,
|
| 1249 |
+
"step": 885
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 1.9821826280623607,
|
| 1253 |
+
"grad_norm": 1.1383869647979736,
|
| 1254 |
+
"learning_rate": 8.53208173140094e-06,
|
| 1255 |
+
"loss": 0.3774,
|
| 1256 |
+
"step": 890
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 1.9933184855233854,
|
| 1260 |
+
"grad_norm": 1.219609022140503,
|
| 1261 |
+
"learning_rate": 8.366358086014915e-06,
|
| 1262 |
+
"loss": 0.4042,
|
| 1263 |
+
"step": 895
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 2.0044543429844097,
|
| 1267 |
+
"grad_norm": 1.0188366174697876,
|
| 1268 |
+
"learning_rate": 8.201635005452907e-06,
|
| 1269 |
+
"loss": 0.349,
|
| 1270 |
+
"step": 900
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 2.0155902004454345,
|
| 1274 |
+
"grad_norm": 1.1455644369125366,
|
| 1275 |
+
"learning_rate": 8.037937335210393e-06,
|
| 1276 |
+
"loss": 0.3467,
|
| 1277 |
+
"step": 905
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 2.0267260579064588,
|
| 1281 |
+
"grad_norm": 1.116882562637329,
|
| 1282 |
+
"learning_rate": 7.875289766118245e-06,
|
| 1283 |
+
"loss": 0.3506,
|
| 1284 |
+
"step": 910
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 2.0378619153674835,
|
| 1288 |
+
"grad_norm": 1.0602525472640991,
|
| 1289 |
+
"learning_rate": 7.713716830618596e-06,
|
| 1290 |
+
"loss": 0.2978,
|
| 1291 |
+
"step": 915
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 2.048997772828508,
|
| 1295 |
+
"grad_norm": 1.1811764240264893,
|
| 1296 |
+
"learning_rate": 7.553242899064551e-06,
|
| 1297 |
+
"loss": 0.3107,
|
| 1298 |
+
"step": 920
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 2.060133630289532,
|
| 1302 |
+
"grad_norm": 1.141510009765625,
|
| 1303 |
+
"learning_rate": 7.393892176044341e-06,
|
| 1304 |
+
"loss": 0.3219,
|
| 1305 |
+
"step": 925
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 2.071269487750557,
|
| 1309 |
+
"grad_norm": 1.0922493934631348,
|
| 1310 |
+
"learning_rate": 7.235688696730542e-06,
|
| 1311 |
+
"loss": 0.2954,
|
| 1312 |
+
"step": 930
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 2.082405345211581,
|
| 1316 |
+
"grad_norm": 1.16718590259552,
|
| 1317 |
+
"learning_rate": 7.078656323254758e-06,
|
| 1318 |
+
"loss": 0.3161,
|
| 1319 |
+
"step": 935
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 2.093541202672606,
|
| 1323 |
+
"grad_norm": 1.3747974634170532,
|
| 1324 |
+
"learning_rate": 6.922818741108489e-06,
|
| 1325 |
+
"loss": 0.3243,
|
| 1326 |
+
"step": 940
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 2.10467706013363,
|
| 1330 |
+
"grad_norm": 1.1849589347839355,
|
| 1331 |
+
"learning_rate": 6.76819945557059e-06,
|
| 1332 |
+
"loss": 0.3518,
|
| 1333 |
+
"step": 945
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 2.115812917594655,
|
| 1337 |
+
"grad_norm": 1.125738263130188,
|
| 1338 |
+
"learning_rate": 6.614821788161904e-06,
|
| 1339 |
+
"loss": 0.3212,
|
| 1340 |
+
"step": 950
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 2.1269487750556793,
|
| 1344 |
+
"grad_norm": 1.1123230457305908,
|
| 1345 |
+
"learning_rate": 6.462708873127657e-06,
|
| 1346 |
+
"loss": 0.2827,
|
| 1347 |
+
"step": 955
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 2.138084632516704,
|
| 1351 |
+
"grad_norm": 1.1810516119003296,
|
| 1352 |
+
"learning_rate": 6.311883653948077e-06,
|
| 1353 |
+
"loss": 0.3501,
|
| 1354 |
+
"step": 960
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 2.1492204899777283,
|
| 1358 |
+
"grad_norm": 1.0474131107330322,
|
| 1359 |
+
"learning_rate": 6.162368879877779e-06,
|
| 1360 |
+
"loss": 0.2767,
|
| 1361 |
+
"step": 965
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 2.1603563474387526,
|
| 1365 |
+
"grad_norm": 1.1583796739578247,
|
| 1366 |
+
"learning_rate": 6.014187102514433e-06,
|
| 1367 |
+
"loss": 0.286,
|
| 1368 |
+
"step": 970
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 2.1714922048997773,
|
| 1372 |
+
"grad_norm": 1.0514683723449707,
|
| 1373 |
+
"learning_rate": 5.867360672397303e-06,
|
| 1374 |
+
"loss": 0.291,
|
| 1375 |
+
"step": 975
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 2.1826280623608016,
|
| 1379 |
+
"grad_norm": 1.1558072566986084,
|
| 1380 |
+
"learning_rate": 5.7219117356360355e-06,
|
| 1381 |
+
"loss": 0.3227,
|
| 1382 |
+
"step": 980
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 2.1937639198218264,
|
| 1386 |
+
"grad_norm": 1.1098800897598267,
|
| 1387 |
+
"learning_rate": 5.577862230570326e-06,
|
| 1388 |
+
"loss": 0.2659,
|
| 1389 |
+
"step": 985
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 2.2048997772828507,
|
| 1393 |
+
"grad_norm": 1.2165024280548096,
|
| 1394 |
+
"learning_rate": 5.435233884460964e-06,
|
| 1395 |
+
"loss": 0.3292,
|
| 1396 |
+
"step": 990
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 2.2160356347438754,
|
| 1400 |
+
"grad_norm": 1.158936619758606,
|
| 1401 |
+
"learning_rate": 5.294048210212594e-06,
|
| 1402 |
+
"loss": 0.3069,
|
| 1403 |
+
"step": 995
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 2.2271714922048997,
|
| 1407 |
+
"grad_norm": 1.125988245010376,
|
| 1408 |
+
"learning_rate": 5.154326503128929e-06,
|
| 1409 |
+
"loss": 0.3007,
|
| 1410 |
+
"step": 1000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 2.2383073496659245,
|
| 1414 |
+
"grad_norm": 1.1055173873901367,
|
| 1415 |
+
"learning_rate": 5.016089837700739e-06,
|
| 1416 |
+
"loss": 0.3247,
|
| 1417 |
+
"step": 1005
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 2.249443207126949,
|
| 1421 |
+
"grad_norm": 1.3721768856048584,
|
| 1422 |
+
"learning_rate": 4.87935906442714e-06,
|
| 1423 |
+
"loss": 0.3397,
|
| 1424 |
+
"step": 1010
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 2.260579064587973,
|
| 1428 |
+
"grad_norm": 1.1548746824264526,
|
| 1429 |
+
"learning_rate": 4.744154806670651e-06,
|
| 1430 |
+
"loss": 0.3162,
|
| 1431 |
+
"step": 1015
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 2.271714922048998,
|
| 1435 |
+
"grad_norm": 1.2124496698379517,
|
| 1436 |
+
"learning_rate": 4.610497457546577e-06,
|
| 1437 |
+
"loss": 0.3251,
|
| 1438 |
+
"step": 1020
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 2.282850779510022,
|
| 1442 |
+
"grad_norm": 1.3251677751541138,
|
| 1443 |
+
"learning_rate": 4.478407176847033e-06,
|
| 1444 |
+
"loss": 0.2898,
|
| 1445 |
+
"step": 1025
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 2.293986636971047,
|
| 1449 |
+
"grad_norm": 1.0971037149429321,
|
| 1450 |
+
"learning_rate": 4.3479038880002355e-06,
|
| 1451 |
+
"loss": 0.3067,
|
| 1452 |
+
"step": 1030
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 2.305122494432071,
|
| 1456 |
+
"grad_norm": 1.1671411991119385,
|
| 1457 |
+
"learning_rate": 4.219007275065402e-06,
|
| 1458 |
+
"loss": 0.3179,
|
| 1459 |
+
"step": 1035
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 2.316258351893096,
|
| 1463 |
+
"grad_norm": 1.182480812072754,
|
| 1464 |
+
"learning_rate": 4.09173677976376e-06,
|
| 1465 |
+
"loss": 0.2918,
|
| 1466 |
+
"step": 1040
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 2.3273942093541202,
|
| 1470 |
+
"grad_norm": 1.2389851808547974,
|
| 1471 |
+
"learning_rate": 3.96611159854612e-06,
|
| 1472 |
+
"loss": 0.2901,
|
| 1473 |
+
"step": 1045
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 2.338530066815145,
|
| 1477 |
+
"grad_norm": 1.1947388648986816,
|
| 1478 |
+
"learning_rate": 3.842150679697458e-06,
|
| 1479 |
+
"loss": 0.2938,
|
| 1480 |
+
"step": 1050
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 2.3496659242761693,
|
| 1484 |
+
"grad_norm": 1.1161694526672363,
|
| 1485 |
+
"learning_rate": 3.719872720478871e-06,
|
| 1486 |
+
"loss": 0.3066,
|
| 1487 |
+
"step": 1055
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 2.3608017817371936,
|
| 1491 |
+
"grad_norm": 1.2662599086761475,
|
| 1492 |
+
"learning_rate": 3.599296164307465e-06,
|
| 1493 |
+
"loss": 0.2832,
|
| 1494 |
+
"step": 1060
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 2.3719376391982183,
|
| 1498 |
+
"grad_norm": 1.140931487083435,
|
| 1499 |
+
"learning_rate": 3.4804391979744986e-06,
|
| 1500 |
+
"loss": 0.2678,
|
| 1501 |
+
"step": 1065
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 2.3830734966592426,
|
| 1505 |
+
"grad_norm": 1.323480486869812,
|
| 1506 |
+
"learning_rate": 3.3633197489022016e-06,
|
| 1507 |
+
"loss": 0.2866,
|
| 1508 |
+
"step": 1070
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 2.3942093541202674,
|
| 1512 |
+
"grad_norm": 1.1875169277191162,
|
| 1513 |
+
"learning_rate": 3.247955482439794e-06,
|
| 1514 |
+
"loss": 0.2629,
|
| 1515 |
+
"step": 1075
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 2.4053452115812917,
|
| 1519 |
+
"grad_norm": 1.0768179893493652,
|
| 1520 |
+
"learning_rate": 3.1343637991989554e-06,
|
| 1521 |
+
"loss": 0.2608,
|
| 1522 |
+
"step": 1080
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 2.4164810690423164,
|
| 1526 |
+
"grad_norm": 1.1807349920272827,
|
| 1527 |
+
"learning_rate": 3.022561832429262e-06,
|
| 1528 |
+
"loss": 0.307,
|
| 1529 |
+
"step": 1085
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 2.4276169265033407,
|
| 1533 |
+
"grad_norm": 1.1905728578567505,
|
| 1534 |
+
"learning_rate": 2.9125664454339655e-06,
|
| 1535 |
+
"loss": 0.2903,
|
| 1536 |
+
"step": 1090
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 2.4387527839643655,
|
| 1540 |
+
"grad_norm": 1.128546953201294,
|
| 1541 |
+
"learning_rate": 2.8043942290264447e-06,
|
| 1542 |
+
"loss": 0.2724,
|
| 1543 |
+
"step": 1095
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 2.4498886414253898,
|
| 1547 |
+
"grad_norm": 1.1763416528701782,
|
| 1548 |
+
"learning_rate": 2.698061499027788e-06,
|
| 1549 |
+
"loss": 0.2927,
|
| 1550 |
+
"step": 1100
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 2.461024498886414,
|
| 1554 |
+
"grad_norm": 1.3624482154846191,
|
| 1555 |
+
"learning_rate": 2.5935842938058613e-06,
|
| 1556 |
+
"loss": 0.2832,
|
| 1557 |
+
"step": 1105
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 2.472160356347439,
|
| 1561 |
+
"grad_norm": 1.0181281566619873,
|
| 1562 |
+
"learning_rate": 2.4909783718561995e-06,
|
| 1563 |
+
"loss": 0.288,
|
| 1564 |
+
"step": 1110
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 2.483296213808463,
|
| 1568 |
+
"grad_norm": 1.1647861003875732,
|
| 1569 |
+
"learning_rate": 2.390259209425114e-06,
|
| 1570 |
+
"loss": 0.2734,
|
| 1571 |
+
"step": 1115
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 2.494432071269488,
|
| 1575 |
+
"grad_norm": 1.3845289945602417,
|
| 1576 |
+
"learning_rate": 2.291441998175401e-06,
|
| 1577 |
+
"loss": 0.3119,
|
| 1578 |
+
"step": 1120
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 2.505567928730512,
|
| 1582 |
+
"grad_norm": 1.2042030096054077,
|
| 1583 |
+
"learning_rate": 2.1945416428949305e-06,
|
| 1584 |
+
"loss": 0.2807,
|
| 1585 |
+
"step": 1125
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 2.516703786191537,
|
| 1589 |
+
"grad_norm": 1.1011390686035156,
|
| 1590 |
+
"learning_rate": 2.0995727592485565e-06,
|
| 1591 |
+
"loss": 0.2545,
|
| 1592 |
+
"step": 1130
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 2.527839643652561,
|
| 1596 |
+
"grad_norm": 1.0278366804122925,
|
| 1597 |
+
"learning_rate": 2.0065496715735866e-06,
|
| 1598 |
+
"loss": 0.3028,
|
| 1599 |
+
"step": 1135
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 2.538975501113586,
|
| 1603 |
+
"grad_norm": 1.2590640783309937,
|
| 1604 |
+
"learning_rate": 1.9154864107192184e-06,
|
| 1605 |
+
"loss": 0.2708,
|
| 1606 |
+
"step": 1140
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 2.5501113585746102,
|
| 1610 |
+
"grad_norm": 1.215333104133606,
|
| 1611 |
+
"learning_rate": 1.8263967119302417e-06,
|
| 1612 |
+
"loss": 0.3113,
|
| 1613 |
+
"step": 1145
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 2.5612472160356345,
|
| 1617 |
+
"grad_norm": 1.1853814125061035,
|
| 1618 |
+
"learning_rate": 1.739294012775346e-06,
|
| 1619 |
+
"loss": 0.2933,
|
| 1620 |
+
"step": 1150
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 2.5723830734966593,
|
| 1624 |
+
"grad_norm": 1.0867751836776733,
|
| 1625 |
+
"learning_rate": 1.6541914511202666e-06,
|
| 1626 |
+
"loss": 0.3302,
|
| 1627 |
+
"step": 1155
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 2.5835189309576836,
|
| 1631 |
+
"grad_norm": 1.1324111223220825,
|
| 1632 |
+
"learning_rate": 1.5711018631462014e-06,
|
| 1633 |
+
"loss": 0.2963,
|
| 1634 |
+
"step": 1160
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 2.5946547884187083,
|
| 1638 |
+
"grad_norm": 1.2125216722488403,
|
| 1639 |
+
"learning_rate": 1.4900377814137083e-06,
|
| 1640 |
+
"loss": 0.2853,
|
| 1641 |
+
"step": 1165
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 2.6057906458797326,
|
| 1645 |
+
"grad_norm": 1.2052973508834839,
|
| 1646 |
+
"learning_rate": 1.4110114329723768e-06,
|
| 1647 |
+
"loss": 0.2968,
|
| 1648 |
+
"step": 1170
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 2.6169265033407574,
|
| 1652 |
+
"grad_norm": 1.1221556663513184,
|
| 1653 |
+
"learning_rate": 1.3340347375166145e-06,
|
| 1654 |
+
"loss": 0.2898,
|
| 1655 |
+
"step": 1175
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 2.6280623608017817,
|
| 1659 |
+
"grad_norm": 1.1094489097595215,
|
| 1660 |
+
"learning_rate": 1.259119305587777e-06,
|
| 1661 |
+
"loss": 0.2997,
|
| 1662 |
+
"step": 1180
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 2.6391982182628064,
|
| 1666 |
+
"grad_norm": 1.2124420404434204,
|
| 1667 |
+
"learning_rate": 1.1862764368229118e-06,
|
| 1668 |
+
"loss": 0.3035,
|
| 1669 |
+
"step": 1185
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 2.6503340757238307,
|
| 1673 |
+
"grad_norm": 1.0426665544509888,
|
| 1674 |
+
"learning_rate": 1.1155171182504276e-06,
|
| 1675 |
+
"loss": 0.2765,
|
| 1676 |
+
"step": 1190
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 2.661469933184855,
|
| 1680 |
+
"grad_norm": 1.1182564496994019,
|
| 1681 |
+
"learning_rate": 1.0468520226328966e-06,
|
| 1682 |
+
"loss": 0.2804,
|
| 1683 |
+
"step": 1195
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 2.6726057906458798,
|
| 1687 |
+
"grad_norm": 1.1782066822052002,
|
| 1688 |
+
"learning_rate": 9.80291506857265e-07,
|
| 1689 |
+
"loss": 0.2753,
|
| 1690 |
+
"step": 1200
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 2.683741648106904,
|
| 1694 |
+
"grad_norm": 1.2433795928955078,
|
| 1695 |
+
"learning_rate": 9.158456103726881e-07,
|
| 1696 |
+
"loss": 0.2654,
|
| 1697 |
+
"step": 1205
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 2.694877505567929,
|
| 1701 |
+
"grad_norm": 1.1048508882522583,
|
| 1702 |
+
"learning_rate": 8.535240536762867e-07,
|
| 1703 |
+
"loss": 0.3038,
|
| 1704 |
+
"step": 1210
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 2.706013363028953,
|
| 1708 |
+
"grad_norm": 1.11650550365448,
|
| 1709 |
+
"learning_rate": 7.93336236846956e-07,
|
| 1710 |
+
"loss": 0.2919,
|
| 1711 |
+
"step": 1215
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 2.717149220489978,
|
| 1715 |
+
"grad_norm": 1.1663094758987427,
|
| 1716 |
+
"learning_rate": 7.352912381275617e-07,
|
| 1717 |
+
"loss": 0.283,
|
| 1718 |
+
"step": 1220
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 2.728285077951002,
|
| 1722 |
+
"grad_norm": 1.125610113143921,
|
| 1723 |
+
"learning_rate": 6.793978125556371e-07,
|
| 1724 |
+
"loss": 0.296,
|
| 1725 |
+
"step": 1225
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 2.739420935412027,
|
| 1729 |
+
"grad_norm": 1.1544047594070435,
|
| 1730 |
+
"learning_rate": 6.256643906428427e-07,
|
| 1731 |
+
"loss": 0.3075,
|
| 1732 |
+
"step": 1230
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 2.750556792873051,
|
| 1736 |
+
"grad_norm": 1.3158949613571167,
|
| 1737 |
+
"learning_rate": 5.740990771033849e-07,
|
| 1738 |
+
"loss": 0.3009,
|
| 1739 |
+
"step": 1235
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 2.7616926503340755,
|
| 1743 |
+
"grad_norm": 1.0194157361984253,
|
| 1744 |
+
"learning_rate": 5.247096496315523e-07,
|
| 1745 |
+
"loss": 0.2509,
|
| 1746 |
+
"step": 1240
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 2.7728285077951003,
|
| 1750 |
+
"grad_norm": 1.1348544359207153,
|
| 1751 |
+
"learning_rate": 4.775035577286141e-07,
|
| 1752 |
+
"loss": 0.2664,
|
| 1753 |
+
"step": 1245
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 2.7839643652561246,
|
| 1757 |
+
"grad_norm": 1.1943309307098389,
|
| 1758 |
+
"learning_rate": 4.3248792157916884e-07,
|
| 1759 |
+
"loss": 0.2869,
|
| 1760 |
+
"step": 1250
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 2.7951002227171493,
|
| 1764 |
+
"grad_norm": 1.198054313659668,
|
| 1765 |
+
"learning_rate": 3.896695309772219e-07,
|
| 1766 |
+
"loss": 0.2788,
|
| 1767 |
+
"step": 1255
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 2.8062360801781736,
|
| 1771 |
+
"grad_norm": 0.9976752400398254,
|
| 1772 |
+
"learning_rate": 3.490548443020447e-07,
|
| 1773 |
+
"loss": 0.2585,
|
| 1774 |
+
"step": 1260
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 2.8173719376391984,
|
| 1778 |
+
"grad_norm": 1.2706948518753052,
|
| 1779 |
+
"learning_rate": 3.106499875440605e-07,
|
| 1780 |
+
"loss": 0.2737,
|
| 1781 |
+
"step": 1265
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 2.8285077951002227,
|
| 1785 |
+
"grad_norm": 1.2077584266662598,
|
| 1786 |
+
"learning_rate": 2.7446075338084355e-07,
|
| 1787 |
+
"loss": 0.2795,
|
| 1788 |
+
"step": 1270
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 2.8396436525612474,
|
| 1792 |
+
"grad_norm": 1.199408769607544,
|
| 1793 |
+
"learning_rate": 2.404926003033947e-07,
|
| 1794 |
+
"loss": 0.3034,
|
| 1795 |
+
"step": 1275
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 2.8507795100222717,
|
| 1799 |
+
"grad_norm": 1.1135765314102173,
|
| 1800 |
+
"learning_rate": 2.0875065179283837e-07,
|
| 1801 |
+
"loss": 0.2342,
|
| 1802 |
+
"step": 1280
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 2.861915367483296,
|
| 1806 |
+
"grad_norm": 1.184799313545227,
|
| 1807 |
+
"learning_rate": 1.7923969554762386e-07,
|
| 1808 |
+
"loss": 0.2933,
|
| 1809 |
+
"step": 1285
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 2.8730512249443207,
|
| 1813 |
+
"grad_norm": 1.1362637281417847,
|
| 1814 |
+
"learning_rate": 1.519641827613999e-07,
|
| 1815 |
+
"loss": 0.2701,
|
| 1816 |
+
"step": 1290
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 2.884187082405345,
|
| 1820 |
+
"grad_norm": 1.1233021020889282,
|
| 1821 |
+
"learning_rate": 1.269282274516248e-07,
|
| 1822 |
+
"loss": 0.2376,
|
| 1823 |
+
"step": 1295
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 2.89532293986637,
|
| 1827 |
+
"grad_norm": 1.1383740901947021,
|
| 1828 |
+
"learning_rate": 1.0413560583904635e-07,
|
| 1829 |
+
"loss": 0.3145,
|
| 1830 |
+
"step": 1300
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 2.906458797327394,
|
| 1834 |
+
"grad_norm": 1.0466502904891968,
|
| 1835 |
+
"learning_rate": 8.358975577812067e-08,
|
| 1836 |
+
"loss": 0.2755,
|
| 1837 |
+
"step": 1305
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 2.917594654788419,
|
| 1841 |
+
"grad_norm": 1.015981912612915,
|
| 1842 |
+
"learning_rate": 6.529377623848198e-08,
|
| 1843 |
+
"loss": 0.3215,
|
| 1844 |
+
"step": 1310
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 2.928730512249443,
|
| 1848 |
+
"grad_norm": 1.1918387413024902,
|
| 1849 |
+
"learning_rate": 4.925042683751491e-08,
|
| 1850 |
+
"loss": 0.2658,
|
| 1851 |
+
"step": 1315
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 2.939866369710468,
|
| 1855 |
+
"grad_norm": 1.2517552375793457,
|
| 1856 |
+
"learning_rate": 3.5462127424117365e-08,
|
| 1857 |
+
"loss": 0.2583,
|
| 1858 |
+
"step": 1320
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 2.951002227171492,
|
| 1862 |
+
"grad_norm": 1.1709799766540527,
|
| 1863 |
+
"learning_rate": 2.3930957713709234e-08,
|
| 1864 |
+
"loss": 0.2584,
|
| 1865 |
+
"step": 1325
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 2.9621380846325165,
|
| 1869 |
+
"grad_norm": 1.159719705581665,
|
| 1870 |
+
"learning_rate": 1.4658656974544937e-08,
|
| 1871 |
+
"loss": 0.3151,
|
| 1872 |
+
"step": 1330
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 2.9732739420935412,
|
| 1876 |
+
"grad_norm": 1.0668970346450806,
|
| 1877 |
+
"learning_rate": 7.646623765374949e-09,
|
| 1878 |
+
"loss": 0.2389,
|
| 1879 |
+
"step": 1335
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 2.984409799554566,
|
| 1883 |
+
"grad_norm": 1.052242636680603,
|
| 1884 |
+
"learning_rate": 2.8959157245028735e-09,
|
| 1885 |
+
"loss": 0.2694,
|
| 1886 |
+
"step": 1340
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 2.9955456570155903,
|
| 1890 |
+
"grad_norm": 1.0957918167114258,
|
| 1891 |
+
"learning_rate": 4.0724941025638285e-10,
|
| 1892 |
+
"loss": 0.268,
|
| 1893 |
+
"step": 1345
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 3.0,
|
| 1897 |
+
"step": 1347,
|
| 1898 |
+
"total_flos": 1.8647534585071534e+18,
|
| 1899 |
+
"train_loss": 0.5871922652988675,
|
| 1900 |
+
"train_runtime": 872.6809,
|
| 1901 |
+
"train_samples_per_second": 49.358,
|
| 1902 |
+
"train_steps_per_second": 1.544
|
| 1903 |
+
}
|
| 1904 |
+
],
|
| 1905 |
+
"logging_steps": 5,
|
| 1906 |
+
"max_steps": 1347,
|
| 1907 |
+
"num_input_tokens_seen": 0,
|
| 1908 |
+
"num_train_epochs": 3,
|
| 1909 |
+
"save_steps": 20000,
|
| 1910 |
+
"stateful_callbacks": {
|
| 1911 |
+
"TrainerControl": {
|
| 1912 |
+
"args": {
|
| 1913 |
+
"should_epoch_stop": false,
|
| 1914 |
+
"should_evaluate": false,
|
| 1915 |
+
"should_log": false,
|
| 1916 |
+
"should_save": false,
|
| 1917 |
+
"should_training_stop": false
|
| 1918 |
+
},
|
| 1919 |
+
"attributes": {}
|
| 1920 |
+
}
|
| 1921 |
+
},
|
| 1922 |
+
"total_flos": 1.8647534585071534e+18,
|
| 1923 |
+
"train_batch_size": 2,
|
| 1924 |
+
"trial_name": null,
|
| 1925 |
+
"trial_params": null
|
| 1926 |
+
}
|
103_128_e3_3e-5/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d80d69bbf412c06f95e8804f12c51aef5548b7adca4e2f5eb064c455545ef790
|
| 3 |
+
size 8273
|
103_128_e3_3e-5/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|