Upload folder using huggingface_hub
Browse files- 107_128_e3_3e-5/adapter_config.json +39 -0
- 107_128_e3_3e-5/adapter_model.safetensors +3 -0
- 107_128_e3_3e-5/added_tokens.json +9 -0
- 107_128_e3_3e-5/all_results.json +9 -0
- 107_128_e3_3e-5/chat_template.jinja +62 -0
- 107_128_e3_3e-5/config.json +32 -0
- 107_128_e3_3e-5/merges.txt +0 -0
- 107_128_e3_3e-5/special_tokens_map.json +33 -0
- 107_128_e3_3e-5/tokenizer.json +0 -0
- 107_128_e3_3e-5/tokenizer_config.json +234 -0
- 107_128_e3_3e-5/train_results.json +9 -0
- 107_128_e3_3e-5/trainer_state.json +1723 -0
- 107_128_e3_3e-5/training_args.bin +3 -0
- 107_128_e3_3e-5/vocab.json +0 -0
107_128_e3_3e-5/adapter_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "ibm-granite/granite-3.3-8b-instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 256,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.05,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 128,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"k_proj",
|
| 28 |
+
"o_proj",
|
| 29 |
+
"up_proj",
|
| 30 |
+
"down_proj",
|
| 31 |
+
"gate_proj",
|
| 32 |
+
"q_proj",
|
| 33 |
+
"v_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
+
"use_dora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
107_128_e3_3e-5/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:080bd7140f55aeffdf37a0b4d574b7e8361b2a919cceccc0d209bfe7a9fc04c6
|
| 3 |
+
size 791751704
|
107_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 |
+
}
|
107_128_e3_3e-5/all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 1.7520698214297108e+18,
|
| 4 |
+
"train_loss": 0.538740111408091,
|
| 5 |
+
"train_runtime": 824.1982,
|
| 6 |
+
"train_samples": 12813,
|
| 7 |
+
"train_samples_per_second": 46.638,
|
| 8 |
+
"train_steps_per_second": 1.46
|
| 9 |
+
}
|
107_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 %}
|
107_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 |
+
}
|
107_128_e3_3e-5/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
107_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 |
+
}
|
107_128_e3_3e-5/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
107_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 |
+
}
|
107_128_e3_3e-5/train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 1.7520698214297108e+18,
|
| 4 |
+
"train_loss": 0.538740111408091,
|
| 5 |
+
"train_runtime": 824.1982,
|
| 6 |
+
"train_samples": 12813,
|
| 7 |
+
"train_samples_per_second": 46.638,
|
| 8 |
+
"train_steps_per_second": 1.46
|
| 9 |
+
}
|
107_128_e3_3e-5/trainer_state.json
ADDED
|
@@ -0,0 +1,1723 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 1203,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.012484394506866416,
|
| 14 |
+
"grad_norm": 3.259528398513794,
|
| 15 |
+
"learning_rate": 1.9672131147540985e-06,
|
| 16 |
+
"loss": 1.4491,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.024968789013732832,
|
| 21 |
+
"grad_norm": 2.3043220043182373,
|
| 22 |
+
"learning_rate": 4.426229508196722e-06,
|
| 23 |
+
"loss": 1.452,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.03745318352059925,
|
| 28 |
+
"grad_norm": 0.9013122916221619,
|
| 29 |
+
"learning_rate": 6.885245901639345e-06,
|
| 30 |
+
"loss": 1.3781,
|
| 31 |
+
"step": 15
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.049937578027465665,
|
| 35 |
+
"grad_norm": 0.5503786206245422,
|
| 36 |
+
"learning_rate": 9.344262295081968e-06,
|
| 37 |
+
"loss": 1.2929,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.062421972534332085,
|
| 42 |
+
"grad_norm": 0.4774400293827057,
|
| 43 |
+
"learning_rate": 1.180327868852459e-05,
|
| 44 |
+
"loss": 1.2416,
|
| 45 |
+
"step": 25
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.0749063670411985,
|
| 49 |
+
"grad_norm": 0.4003322422504425,
|
| 50 |
+
"learning_rate": 1.4262295081967213e-05,
|
| 51 |
+
"loss": 1.3229,
|
| 52 |
+
"step": 30
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.08739076154806492,
|
| 56 |
+
"grad_norm": 0.49404653906822205,
|
| 57 |
+
"learning_rate": 1.6721311475409834e-05,
|
| 58 |
+
"loss": 1.2255,
|
| 59 |
+
"step": 35
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.09987515605493133,
|
| 63 |
+
"grad_norm": 0.3782234191894531,
|
| 64 |
+
"learning_rate": 1.9180327868852462e-05,
|
| 65 |
+
"loss": 1.251,
|
| 66 |
+
"step": 40
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.11235955056179775,
|
| 70 |
+
"grad_norm": 0.39610394835472107,
|
| 71 |
+
"learning_rate": 2.1639344262295084e-05,
|
| 72 |
+
"loss": 1.2573,
|
| 73 |
+
"step": 45
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.12484394506866417,
|
| 77 |
+
"grad_norm": 0.3563311994075775,
|
| 78 |
+
"learning_rate": 2.4098360655737705e-05,
|
| 79 |
+
"loss": 1.2099,
|
| 80 |
+
"step": 50
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.1373283395755306,
|
| 84 |
+
"grad_norm": 0.4278824031352997,
|
| 85 |
+
"learning_rate": 2.6557377049180327e-05,
|
| 86 |
+
"loss": 1.2081,
|
| 87 |
+
"step": 55
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.149812734082397,
|
| 91 |
+
"grad_norm": 0.37753868103027344,
|
| 92 |
+
"learning_rate": 2.901639344262295e-05,
|
| 93 |
+
"loss": 1.1443,
|
| 94 |
+
"step": 60
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.16229712858926343,
|
| 98 |
+
"grad_norm": 0.37719282507896423,
|
| 99 |
+
"learning_rate": 2.999948917887945e-05,
|
| 100 |
+
"loss": 1.1569,
|
| 101 |
+
"step": 65
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.17478152309612985,
|
| 105 |
+
"grad_norm": 0.4125896990299225,
|
| 106 |
+
"learning_rate": 2.9996367620247847e-05,
|
| 107 |
+
"loss": 1.1306,
|
| 108 |
+
"step": 70
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.18726591760299627,
|
| 112 |
+
"grad_norm": 0.3757750391960144,
|
| 113 |
+
"learning_rate": 2.999040888235128e-05,
|
| 114 |
+
"loss": 1.1255,
|
| 115 |
+
"step": 75
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.19975031210986266,
|
| 119 |
+
"grad_norm": 0.4374464750289917,
|
| 120 |
+
"learning_rate": 2.998161409252991e-05,
|
| 121 |
+
"loss": 1.0668,
|
| 122 |
+
"step": 80
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.21223470661672908,
|
| 126 |
+
"grad_norm": 0.41650235652923584,
|
| 127 |
+
"learning_rate": 2.9969984914679688e-05,
|
| 128 |
+
"loss": 1.1363,
|
| 129 |
+
"step": 85
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.2247191011235955,
|
| 133 |
+
"grad_norm": 0.45344486832618713,
|
| 134 |
+
"learning_rate": 2.995552354893755e-05,
|
| 135 |
+
"loss": 1.1203,
|
| 136 |
+
"step": 90
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.23720349563046192,
|
| 140 |
+
"grad_norm": 0.46486198902130127,
|
| 141 |
+
"learning_rate": 2.993823273126517e-05,
|
| 142 |
+
"loss": 1.117,
|
| 143 |
+
"step": 95
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.24968789013732834,
|
| 147 |
+
"grad_norm": 0.43523311614990234,
|
| 148 |
+
"learning_rate": 2.9918115732931336e-05,
|
| 149 |
+
"loss": 1.0992,
|
| 150 |
+
"step": 100
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.26217228464419473,
|
| 154 |
+
"grad_norm": 0.4960132837295532,
|
| 155 |
+
"learning_rate": 2.9895176359893063e-05,
|
| 156 |
+
"loss": 1.0442,
|
| 157 |
+
"step": 105
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.2746566791510612,
|
| 161 |
+
"grad_norm": 0.43662625551223755,
|
| 162 |
+
"learning_rate": 2.9869418952075534e-05,
|
| 163 |
+
"loss": 1.0876,
|
| 164 |
+
"step": 110
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.28714107365792757,
|
| 168 |
+
"grad_norm": 0.4467952847480774,
|
| 169 |
+
"learning_rate": 2.9840848382551035e-05,
|
| 170 |
+
"loss": 1.1113,
|
| 171 |
+
"step": 115
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.299625468164794,
|
| 175 |
+
"grad_norm": 0.4758909344673157,
|
| 176 |
+
"learning_rate": 2.9809470056617005e-05,
|
| 177 |
+
"loss": 1.0464,
|
| 178 |
+
"step": 120
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.3121098626716604,
|
| 182 |
+
"grad_norm": 0.5345353484153748,
|
| 183 |
+
"learning_rate": 2.977528991077339e-05,
|
| 184 |
+
"loss": 1.0053,
|
| 185 |
+
"step": 125
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.32459425717852686,
|
| 189 |
+
"grad_norm": 0.5077415704727173,
|
| 190 |
+
"learning_rate": 2.9738314411599538e-05,
|
| 191 |
+
"loss": 0.9939,
|
| 192 |
+
"step": 130
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.33707865168539325,
|
| 196 |
+
"grad_norm": 0.45568081736564636,
|
| 197 |
+
"learning_rate": 2.9698550554530767e-05,
|
| 198 |
+
"loss": 1.0413,
|
| 199 |
+
"step": 135
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.3495630461922597,
|
| 203 |
+
"grad_norm": 0.5219548344612122,
|
| 204 |
+
"learning_rate": 2.9656005862534862e-05,
|
| 205 |
+
"loss": 0.9719,
|
| 206 |
+
"step": 140
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.3620474406991261,
|
| 210 |
+
"grad_norm": 0.543969452381134,
|
| 211 |
+
"learning_rate": 2.961068838468885e-05,
|
| 212 |
+
"loss": 1.0827,
|
| 213 |
+
"step": 145
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.37453183520599254,
|
| 217 |
+
"grad_norm": 0.5370684862136841,
|
| 218 |
+
"learning_rate": 2.9562606694656155e-05,
|
| 219 |
+
"loss": 0.9832,
|
| 220 |
+
"step": 150
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.38701622971285893,
|
| 224 |
+
"grad_norm": 0.5677061676979065,
|
| 225 |
+
"learning_rate": 2.951176988906453e-05,
|
| 226 |
+
"loss": 0.974,
|
| 227 |
+
"step": 155
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.3995006242197253,
|
| 231 |
+
"grad_norm": 0.5067345499992371,
|
| 232 |
+
"learning_rate": 2.945818758578508e-05,
|
| 233 |
+
"loss": 0.9829,
|
| 234 |
+
"step": 160
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.41198501872659177,
|
| 238 |
+
"grad_norm": 0.6304710507392883,
|
| 239 |
+
"learning_rate": 2.940186992211262e-05,
|
| 240 |
+
"loss": 1.03,
|
| 241 |
+
"step": 165
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.42446941323345816,
|
| 245 |
+
"grad_norm": 0.6881770491600037,
|
| 246 |
+
"learning_rate": 2.934282755284781e-05,
|
| 247 |
+
"loss": 0.9199,
|
| 248 |
+
"step": 170
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.4369538077403246,
|
| 252 |
+
"grad_norm": 0.5799649357795715,
|
| 253 |
+
"learning_rate": 2.9281071648281363e-05,
|
| 254 |
+
"loss": 0.9676,
|
| 255 |
+
"step": 175
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.449438202247191,
|
| 259 |
+
"grad_norm": 0.5652274489402771,
|
| 260 |
+
"learning_rate": 2.92166138920807e-05,
|
| 261 |
+
"loss": 0.9113,
|
| 262 |
+
"step": 180
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.46192259675405745,
|
| 266 |
+
"grad_norm": 0.6180217862129211,
|
| 267 |
+
"learning_rate": 2.9149466479079537e-05,
|
| 268 |
+
"loss": 0.882,
|
| 269 |
+
"step": 185
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.47440699126092384,
|
| 273 |
+
"grad_norm": 0.6467666029930115,
|
| 274 |
+
"learning_rate": 2.90796421129707e-05,
|
| 275 |
+
"loss": 0.94,
|
| 276 |
+
"step": 190
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.4868913857677903,
|
| 280 |
+
"grad_norm": 0.6313362121582031,
|
| 281 |
+
"learning_rate": 2.9007154003902728e-05,
|
| 282 |
+
"loss": 0.9095,
|
| 283 |
+
"step": 195
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.4993757802746567,
|
| 287 |
+
"grad_norm": 0.7488819360733032,
|
| 288 |
+
"learning_rate": 2.8932015865980608e-05,
|
| 289 |
+
"loss": 0.8728,
|
| 290 |
+
"step": 200
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.5118601747815231,
|
| 294 |
+
"grad_norm": 0.7012350559234619,
|
| 295 |
+
"learning_rate": 2.8854241914671196e-05,
|
| 296 |
+
"loss": 0.8859,
|
| 297 |
+
"step": 205
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.5243445692883895,
|
| 301 |
+
"grad_norm": 0.6681339144706726,
|
| 302 |
+
"learning_rate": 2.8773846864113788e-05,
|
| 303 |
+
"loss": 0.8792,
|
| 304 |
+
"step": 210
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.5368289637952559,
|
| 308 |
+
"grad_norm": 0.6512778997421265,
|
| 309 |
+
"learning_rate": 2.8690845924336318e-05,
|
| 310 |
+
"loss": 0.8814,
|
| 311 |
+
"step": 215
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.5493133583021224,
|
| 315 |
+
"grad_norm": 0.8134379386901855,
|
| 316 |
+
"learning_rate": 2.860525479837776e-05,
|
| 317 |
+
"loss": 0.8476,
|
| 318 |
+
"step": 220
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.5617977528089888,
|
| 322 |
+
"grad_norm": 0.7582933306694031,
|
| 323 |
+
"learning_rate": 2.8517089679317278e-05,
|
| 324 |
+
"loss": 0.8498,
|
| 325 |
+
"step": 225
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.5742821473158551,
|
| 329 |
+
"grad_norm": 0.7291813492774963,
|
| 330 |
+
"learning_rate": 2.8426367247210593e-05,
|
| 331 |
+
"loss": 0.8324,
|
| 332 |
+
"step": 230
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.5867665418227216,
|
| 336 |
+
"grad_norm": 0.7229104042053223,
|
| 337 |
+
"learning_rate": 2.8333104665934304e-05,
|
| 338 |
+
"loss": 0.8304,
|
| 339 |
+
"step": 235
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.599250936329588,
|
| 343 |
+
"grad_norm": 0.6971867680549622,
|
| 344 |
+
"learning_rate": 2.8237319579938628e-05,
|
| 345 |
+
"loss": 0.8614,
|
| 346 |
+
"step": 240
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.6117353308364545,
|
| 350 |
+
"grad_norm": 0.6570233702659607,
|
| 351 |
+
"learning_rate": 2.8139030110909205e-05,
|
| 352 |
+
"loss": 0.8276,
|
| 353 |
+
"step": 245
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.6242197253433208,
|
| 357 |
+
"grad_norm": 0.7193368077278137,
|
| 358 |
+
"learning_rate": 2.8038254854338664e-05,
|
| 359 |
+
"loss": 0.7518,
|
| 360 |
+
"step": 250
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.6367041198501873,
|
| 364 |
+
"grad_norm": 0.6586946845054626,
|
| 365 |
+
"learning_rate": 2.79350128760085e-05,
|
| 366 |
+
"loss": 0.805,
|
| 367 |
+
"step": 255
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.6491885143570537,
|
| 371 |
+
"grad_norm": 0.7007092237472534,
|
| 372 |
+
"learning_rate": 2.7829323708382027e-05,
|
| 373 |
+
"loss": 0.7817,
|
| 374 |
+
"step": 260
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.66167290886392,
|
| 378 |
+
"grad_norm": 0.6828142404556274,
|
| 379 |
+
"learning_rate": 2.7721207346908965e-05,
|
| 380 |
+
"loss": 0.8473,
|
| 381 |
+
"step": 265
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.6741573033707865,
|
| 385 |
+
"grad_norm": 0.7842512726783752,
|
| 386 |
+
"learning_rate": 2.7610684246242523e-05,
|
| 387 |
+
"loss": 0.7794,
|
| 388 |
+
"step": 270
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.686641697877653,
|
| 392 |
+
"grad_norm": 0.8085831999778748,
|
| 393 |
+
"learning_rate": 2.7497775316369534e-05,
|
| 394 |
+
"loss": 0.7876,
|
| 395 |
+
"step": 275
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.6991260923845194,
|
| 399 |
+
"grad_norm": 0.7807929515838623,
|
| 400 |
+
"learning_rate": 2.738250191865449e-05,
|
| 401 |
+
"loss": 0.7516,
|
| 402 |
+
"step": 280
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.7116104868913857,
|
| 406 |
+
"grad_norm": 0.8091070652008057,
|
| 407 |
+
"learning_rate": 2.7264885861798127e-05,
|
| 408 |
+
"loss": 0.7733,
|
| 409 |
+
"step": 285
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.7240948813982522,
|
| 413 |
+
"grad_norm": 0.727055549621582,
|
| 414 |
+
"learning_rate": 2.7144949397711465e-05,
|
| 415 |
+
"loss": 0.7735,
|
| 416 |
+
"step": 290
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.7365792759051186,
|
| 420 |
+
"grad_norm": 0.9584328532218933,
|
| 421 |
+
"learning_rate": 2.7022715217305905e-05,
|
| 422 |
+
"loss": 0.7699,
|
| 423 |
+
"step": 295
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.7490636704119851,
|
| 427 |
+
"grad_norm": 0.7299036383628845,
|
| 428 |
+
"learning_rate": 2.6898206446200323e-05,
|
| 429 |
+
"loss": 0.75,
|
| 430 |
+
"step": 300
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.7615480649188514,
|
| 434 |
+
"grad_norm": 0.9077457189559937,
|
| 435 |
+
"learning_rate": 2.6771446640345905e-05,
|
| 436 |
+
"loss": 0.7369,
|
| 437 |
+
"step": 305
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.7740324594257179,
|
| 441 |
+
"grad_norm": 0.795857846736908,
|
| 442 |
+
"learning_rate": 2.664245978156958e-05,
|
| 443 |
+
"loss": 0.7272,
|
| 444 |
+
"step": 310
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.7865168539325843,
|
| 448 |
+
"grad_norm": 0.7558704018592834,
|
| 449 |
+
"learning_rate": 2.6511270273036865e-05,
|
| 450 |
+
"loss": 0.7374,
|
| 451 |
+
"step": 315
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.7990012484394506,
|
| 455 |
+
"grad_norm": 0.8740859627723694,
|
| 456 |
+
"learning_rate": 2.6377902934635005e-05,
|
| 457 |
+
"loss": 0.7259,
|
| 458 |
+
"step": 320
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.8114856429463171,
|
| 462 |
+
"grad_norm": 0.9814260005950928,
|
| 463 |
+
"learning_rate": 2.6242382998277262e-05,
|
| 464 |
+
"loss": 0.6816,
|
| 465 |
+
"step": 325
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.8239700374531835,
|
| 469 |
+
"grad_norm": 0.8275319337844849,
|
| 470 |
+
"learning_rate": 2.6104736103129286e-05,
|
| 471 |
+
"loss": 0.6936,
|
| 472 |
+
"step": 330
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.83645443196005,
|
| 476 |
+
"grad_norm": 0.898194432258606,
|
| 477 |
+
"learning_rate": 2.5964988290758377e-05,
|
| 478 |
+
"loss": 0.6518,
|
| 479 |
+
"step": 335
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.8489388264669163,
|
| 483 |
+
"grad_norm": 0.8312516212463379,
|
| 484 |
+
"learning_rate": 2.5823166000206694e-05,
|
| 485 |
+
"loss": 0.7291,
|
| 486 |
+
"step": 340
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.8614232209737828,
|
| 490 |
+
"grad_norm": 0.8480665683746338,
|
| 491 |
+
"learning_rate": 2.567929606298918e-05,
|
| 492 |
+
"loss": 0.6855,
|
| 493 |
+
"step": 345
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.8739076154806492,
|
| 497 |
+
"grad_norm": 0.9153986573219299,
|
| 498 |
+
"learning_rate": 2.5533405698017323e-05,
|
| 499 |
+
"loss": 0.6904,
|
| 500 |
+
"step": 350
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.8863920099875156,
|
| 504 |
+
"grad_norm": 0.9200903177261353,
|
| 505 |
+
"learning_rate": 2.5385522506449537e-05,
|
| 506 |
+
"loss": 0.695,
|
| 507 |
+
"step": 355
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.898876404494382,
|
| 511 |
+
"grad_norm": 0.8653243184089661,
|
| 512 |
+
"learning_rate": 2.5235674466469306e-05,
|
| 513 |
+
"loss": 0.6664,
|
| 514 |
+
"step": 360
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.9113607990012484,
|
| 518 |
+
"grad_norm": 0.9044493436813354,
|
| 519 |
+
"learning_rate": 2.5083889927991928e-05,
|
| 520 |
+
"loss": 0.6409,
|
| 521 |
+
"step": 365
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.9238451935081149,
|
| 525 |
+
"grad_norm": 0.8836537003517151,
|
| 526 |
+
"learning_rate": 2.4930197607300992e-05,
|
| 527 |
+
"loss": 0.6552,
|
| 528 |
+
"step": 370
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.9363295880149812,
|
| 532 |
+
"grad_norm": 0.9393295645713806,
|
| 533 |
+
"learning_rate": 2.477462658161549e-05,
|
| 534 |
+
"loss": 0.6787,
|
| 535 |
+
"step": 375
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.9488139825218477,
|
| 539 |
+
"grad_norm": 0.896806001663208,
|
| 540 |
+
"learning_rate": 2.4617206283588693e-05,
|
| 541 |
+
"loss": 0.6296,
|
| 542 |
+
"step": 380
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.9612983770287141,
|
| 546 |
+
"grad_norm": 0.8710506558418274,
|
| 547 |
+
"learning_rate": 2.4457966495739706e-05,
|
| 548 |
+
"loss": 0.6183,
|
| 549 |
+
"step": 385
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.9737827715355806,
|
| 553 |
+
"grad_norm": 0.9796684384346008,
|
| 554 |
+
"learning_rate": 2.4296937344818946e-05,
|
| 555 |
+
"loss": 0.6261,
|
| 556 |
+
"step": 390
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.9862671660424469,
|
| 560 |
+
"grad_norm": 0.8438889980316162,
|
| 561 |
+
"learning_rate": 2.4134149296108377e-05,
|
| 562 |
+
"loss": 0.6551,
|
| 563 |
+
"step": 395
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.9987515605493134,
|
| 567 |
+
"grad_norm": 0.959943950176239,
|
| 568 |
+
"learning_rate": 2.396963314765777e-05,
|
| 569 |
+
"loss": 0.6044,
|
| 570 |
+
"step": 400
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.0099875156054932,
|
| 574 |
+
"grad_norm": 0.8981118202209473,
|
| 575 |
+
"learning_rate": 2.3803420024457993e-05,
|
| 576 |
+
"loss": 0.5931,
|
| 577 |
+
"step": 405
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.0224719101123596,
|
| 581 |
+
"grad_norm": 0.9474178552627563,
|
| 582 |
+
"learning_rate": 2.3635541372552415e-05,
|
| 583 |
+
"loss": 0.5419,
|
| 584 |
+
"step": 410
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.034956304619226,
|
| 588 |
+
"grad_norm": 0.8506945371627808,
|
| 589 |
+
"learning_rate": 2.3466028953087627e-05,
|
| 590 |
+
"loss": 0.5106,
|
| 591 |
+
"step": 415
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.0474406991260923,
|
| 595 |
+
"grad_norm": 0.9398747682571411,
|
| 596 |
+
"learning_rate": 2.329491483630449e-05,
|
| 597 |
+
"loss": 0.5307,
|
| 598 |
+
"step": 420
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.0599250936329587,
|
| 602 |
+
"grad_norm": 0.8924016952514648,
|
| 603 |
+
"learning_rate": 2.3122231395470747e-05,
|
| 604 |
+
"loss": 0.5419,
|
| 605 |
+
"step": 425
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.0724094881398252,
|
| 609 |
+
"grad_norm": 0.892546534538269,
|
| 610 |
+
"learning_rate": 2.2948011300756274e-05,
|
| 611 |
+
"loss": 0.5773,
|
| 612 |
+
"step": 430
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.0848938826466916,
|
| 616 |
+
"grad_norm": 1.0284653902053833,
|
| 617 |
+
"learning_rate": 2.2772287513052186e-05,
|
| 618 |
+
"loss": 0.5111,
|
| 619 |
+
"step": 435
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.097378277153558,
|
| 623 |
+
"grad_norm": 0.8848852515220642,
|
| 624 |
+
"learning_rate": 2.259509327773493e-05,
|
| 625 |
+
"loss": 0.5341,
|
| 626 |
+
"step": 440
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.1098626716604245,
|
| 630 |
+
"grad_norm": 0.9534015655517578,
|
| 631 |
+
"learning_rate": 2.241646211837655e-05,
|
| 632 |
+
"loss": 0.532,
|
| 633 |
+
"step": 445
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.122347066167291,
|
| 637 |
+
"grad_norm": 1.067837119102478,
|
| 638 |
+
"learning_rate": 2.223642783040233e-05,
|
| 639 |
+
"loss": 0.5261,
|
| 640 |
+
"step": 450
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.1348314606741572,
|
| 644 |
+
"grad_norm": 0.9914408326148987,
|
| 645 |
+
"learning_rate": 2.2055024474696986e-05,
|
| 646 |
+
"loss": 0.4906,
|
| 647 |
+
"step": 455
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.1473158551810236,
|
| 651 |
+
"grad_norm": 0.9797998666763306,
|
| 652 |
+
"learning_rate": 2.1872286371160682e-05,
|
| 653 |
+
"loss": 0.5344,
|
| 654 |
+
"step": 460
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.15980024968789,
|
| 658 |
+
"grad_norm": 0.9411128163337708,
|
| 659 |
+
"learning_rate": 2.168824809221598e-05,
|
| 660 |
+
"loss": 0.4845,
|
| 661 |
+
"step": 465
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.1722846441947565,
|
| 665 |
+
"grad_norm": 0.827637791633606,
|
| 666 |
+
"learning_rate": 2.150294445626705e-05,
|
| 667 |
+
"loss": 0.569,
|
| 668 |
+
"step": 470
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.184769038701623,
|
| 672 |
+
"grad_norm": 1.013363242149353,
|
| 673 |
+
"learning_rate": 2.131641052111236e-05,
|
| 674 |
+
"loss": 0.5259,
|
| 675 |
+
"step": 475
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.1972534332084894,
|
| 679 |
+
"grad_norm": 1.0870174169540405,
|
| 680 |
+
"learning_rate": 2.112868157731202e-05,
|
| 681 |
+
"loss": 0.5108,
|
| 682 |
+
"step": 480
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.2097378277153559,
|
| 686 |
+
"grad_norm": 1.0271228551864624,
|
| 687 |
+
"learning_rate": 2.0939793141511145e-05,
|
| 688 |
+
"loss": 0.5053,
|
| 689 |
+
"step": 485
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.2222222222222223,
|
| 693 |
+
"grad_norm": 0.9361982941627502,
|
| 694 |
+
"learning_rate": 2.074978094972042e-05,
|
| 695 |
+
"loss": 0.5098,
|
| 696 |
+
"step": 490
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.2347066167290885,
|
| 700 |
+
"grad_norm": 1.0290281772613525,
|
| 701 |
+
"learning_rate": 2.055868095055515e-05,
|
| 702 |
+
"loss": 0.4834,
|
| 703 |
+
"step": 495
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.247191011235955,
|
| 707 |
+
"grad_norm": 1.1110929250717163,
|
| 708 |
+
"learning_rate": 2.036652929843412e-05,
|
| 709 |
+
"loss": 0.5214,
|
| 710 |
+
"step": 500
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.2596754057428214,
|
| 714 |
+
"grad_norm": 0.9082972407341003,
|
| 715 |
+
"learning_rate": 2.0173362346739495e-05,
|
| 716 |
+
"loss": 0.4584,
|
| 717 |
+
"step": 505
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.2721598002496879,
|
| 721 |
+
"grad_norm": 1.3379322290420532,
|
| 722 |
+
"learning_rate": 1.9979216640939074e-05,
|
| 723 |
+
"loss": 0.5024,
|
| 724 |
+
"step": 510
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.2846441947565543,
|
| 728 |
+
"grad_norm": 0.9891626834869385,
|
| 729 |
+
"learning_rate": 1.9784128911672223e-05,
|
| 730 |
+
"loss": 0.4738,
|
| 731 |
+
"step": 515
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.2971285892634208,
|
| 735 |
+
"grad_norm": 0.9586921334266663,
|
| 736 |
+
"learning_rate": 1.9588136067800767e-05,
|
| 737 |
+
"loss": 0.4933,
|
| 738 |
+
"step": 520
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.309612983770287,
|
| 742 |
+
"grad_norm": 1.0176736116409302,
|
| 743 |
+
"learning_rate": 1.9391275189426156e-05,
|
| 744 |
+
"loss": 0.4884,
|
| 745 |
+
"step": 525
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.3220973782771535,
|
| 749 |
+
"grad_norm": 1.0128319263458252,
|
| 750 |
+
"learning_rate": 1.9193583520874236e-05,
|
| 751 |
+
"loss": 0.4839,
|
| 752 |
+
"step": 530
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.33458177278402,
|
| 756 |
+
"grad_norm": 1.1018482446670532,
|
| 757 |
+
"learning_rate": 1.899509846364896e-05,
|
| 758 |
+
"loss": 0.4753,
|
| 759 |
+
"step": 535
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.3470661672908864,
|
| 763 |
+
"grad_norm": 1.0179154872894287,
|
| 764 |
+
"learning_rate": 1.8795857569356367e-05,
|
| 765 |
+
"loss": 0.4752,
|
| 766 |
+
"step": 540
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.3595505617977528,
|
| 770 |
+
"grad_norm": 0.9641721844673157,
|
| 771 |
+
"learning_rate": 1.8595898532600125e-05,
|
| 772 |
+
"loss": 0.4705,
|
| 773 |
+
"step": 545
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.3720349563046192,
|
| 777 |
+
"grad_norm": 1.093848466873169,
|
| 778 |
+
"learning_rate": 1.8395259183850078e-05,
|
| 779 |
+
"loss": 0.47,
|
| 780 |
+
"step": 550
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.3845193508114857,
|
| 784 |
+
"grad_norm": 1.1060792207717896,
|
| 785 |
+
"learning_rate": 1.819397748228503e-05,
|
| 786 |
+
"loss": 0.4006,
|
| 787 |
+
"step": 555
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.3970037453183521,
|
| 791 |
+
"grad_norm": 0.9817847609519958,
|
| 792 |
+
"learning_rate": 1.799209150861123e-05,
|
| 793 |
+
"loss": 0.4237,
|
| 794 |
+
"step": 560
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.4094881398252186,
|
| 798 |
+
"grad_norm": 1.0256028175354004,
|
| 799 |
+
"learning_rate": 1.778963945785783e-05,
|
| 800 |
+
"loss": 0.4873,
|
| 801 |
+
"step": 565
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.4219725343320848,
|
| 805 |
+
"grad_norm": 1.0990488529205322,
|
| 806 |
+
"learning_rate": 1.7586659632150717e-05,
|
| 807 |
+
"loss": 0.4299,
|
| 808 |
+
"step": 570
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.4344569288389513,
|
| 812 |
+
"grad_norm": 1.008880853652954,
|
| 813 |
+
"learning_rate": 1.7383190433466115e-05,
|
| 814 |
+
"loss": 0.4575,
|
| 815 |
+
"step": 575
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.4469413233458177,
|
| 819 |
+
"grad_norm": 1.0123085975646973,
|
| 820 |
+
"learning_rate": 1.717927035636525e-05,
|
| 821 |
+
"loss": 0.4616,
|
| 822 |
+
"step": 580
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.4594257178526842,
|
| 826 |
+
"grad_norm": 1.0933775901794434,
|
| 827 |
+
"learning_rate": 1.6974937980711538e-05,
|
| 828 |
+
"loss": 0.4114,
|
| 829 |
+
"step": 585
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.4719101123595506,
|
| 833 |
+
"grad_norm": 0.9162276983261108,
|
| 834 |
+
"learning_rate": 1.6770231964371604e-05,
|
| 835 |
+
"loss": 0.4581,
|
| 836 |
+
"step": 590
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.484394506866417,
|
| 840 |
+
"grad_norm": 1.0059937238693237,
|
| 841 |
+
"learning_rate": 1.6565191035901567e-05,
|
| 842 |
+
"loss": 0.4008,
|
| 843 |
+
"step": 595
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.4968789013732833,
|
| 847 |
+
"grad_norm": 1.0753304958343506,
|
| 848 |
+
"learning_rate": 1.6359853987219936e-05,
|
| 849 |
+
"loss": 0.4368,
|
| 850 |
+
"step": 600
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.5093632958801497,
|
| 854 |
+
"grad_norm": 1.083181381225586,
|
| 855 |
+
"learning_rate": 1.6154259666268544e-05,
|
| 856 |
+
"loss": 0.4044,
|
| 857 |
+
"step": 605
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.5218476903870162,
|
| 861 |
+
"grad_norm": 1.318939447402954,
|
| 862 |
+
"learning_rate": 1.5948446969662827e-05,
|
| 863 |
+
"loss": 0.4179,
|
| 864 |
+
"step": 610
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.5343320848938826,
|
| 868 |
+
"grad_norm": 1.0248621702194214,
|
| 869 |
+
"learning_rate": 1.5742454835332964e-05,
|
| 870 |
+
"loss": 0.4067,
|
| 871 |
+
"step": 615
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.546816479400749,
|
| 875 |
+
"grad_norm": 1.0350463390350342,
|
| 876 |
+
"learning_rate": 1.553632223515715e-05,
|
| 877 |
+
"loss": 0.4143,
|
| 878 |
+
"step": 620
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.5593008739076155,
|
| 882 |
+
"grad_norm": 1.081904411315918,
|
| 883 |
+
"learning_rate": 1.5330088167588465e-05,
|
| 884 |
+
"loss": 0.411,
|
| 885 |
+
"step": 625
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.571785268414482,
|
| 889 |
+
"grad_norm": 0.9879482984542847,
|
| 890 |
+
"learning_rate": 1.5123791650276726e-05,
|
| 891 |
+
"loss": 0.4196,
|
| 892 |
+
"step": 630
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 1.5842696629213484,
|
| 896 |
+
"grad_norm": 1.0490570068359375,
|
| 897 |
+
"learning_rate": 1.491747171268667e-05,
|
| 898 |
+
"loss": 0.3653,
|
| 899 |
+
"step": 635
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 1.5967540574282149,
|
| 903 |
+
"grad_norm": 0.9883170127868652,
|
| 904 |
+
"learning_rate": 1.4711167388713959e-05,
|
| 905 |
+
"loss": 0.4398,
|
| 906 |
+
"step": 640
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.6092384519350813,
|
| 910 |
+
"grad_norm": 1.0209392309188843,
|
| 911 |
+
"learning_rate": 1.4504917709300286e-05,
|
| 912 |
+
"loss": 0.3899,
|
| 913 |
+
"step": 645
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.6217228464419475,
|
| 917 |
+
"grad_norm": 0.8898019194602966,
|
| 918 |
+
"learning_rate": 1.4298761695049081e-05,
|
| 919 |
+
"loss": 0.4236,
|
| 920 |
+
"step": 650
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.634207240948814,
|
| 924 |
+
"grad_norm": 1.047666072845459,
|
| 925 |
+
"learning_rate": 1.4092738348843166e-05,
|
| 926 |
+
"loss": 0.3864,
|
| 927 |
+
"step": 655
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.6466916354556804,
|
| 931 |
+
"grad_norm": 1.146623134613037,
|
| 932 |
+
"learning_rate": 1.3886886648465745e-05,
|
| 933 |
+
"loss": 0.412,
|
| 934 |
+
"step": 660
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.6591760299625467,
|
| 938 |
+
"grad_norm": 0.9214068651199341,
|
| 939 |
+
"learning_rate": 1.3681245539226157e-05,
|
| 940 |
+
"loss": 0.3998,
|
| 941 |
+
"step": 665
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.671660424469413,
|
| 945 |
+
"grad_norm": 1.0148948431015015,
|
| 946 |
+
"learning_rate": 1.3475853926591778e-05,
|
| 947 |
+
"loss": 0.4485,
|
| 948 |
+
"step": 670
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 1.6841448189762795,
|
| 952 |
+
"grad_norm": 1.0182747840881348,
|
| 953 |
+
"learning_rate": 1.327075066882744e-05,
|
| 954 |
+
"loss": 0.4063,
|
| 955 |
+
"step": 675
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.696629213483146,
|
| 959 |
+
"grad_norm": 1.0928360223770142,
|
| 960 |
+
"learning_rate": 1.3065974569643808e-05,
|
| 961 |
+
"loss": 0.4025,
|
| 962 |
+
"step": 680
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.7091136079900124,
|
| 966 |
+
"grad_norm": 1.0240341424942017,
|
| 967 |
+
"learning_rate": 1.286156437085605e-05,
|
| 968 |
+
"loss": 0.428,
|
| 969 |
+
"step": 685
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.7215980024968789,
|
| 973 |
+
"grad_norm": 1.1378248929977417,
|
| 974 |
+
"learning_rate": 1.2657558745054238e-05,
|
| 975 |
+
"loss": 0.3549,
|
| 976 |
+
"step": 690
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.7340823970037453,
|
| 980 |
+
"grad_norm": 1.0845273733139038,
|
| 981 |
+
"learning_rate": 1.2453996288286837e-05,
|
| 982 |
+
"loss": 0.3901,
|
| 983 |
+
"step": 695
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.7465667915106118,
|
| 987 |
+
"grad_norm": 1.2057894468307495,
|
| 988 |
+
"learning_rate": 1.2250915512758673e-05,
|
| 989 |
+
"loss": 0.3645,
|
| 990 |
+
"step": 700
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.7590511860174782,
|
| 994 |
+
"grad_norm": 1.113541603088379,
|
| 995 |
+
"learning_rate": 1.2048354839544777e-05,
|
| 996 |
+
"loss": 0.389,
|
| 997 |
+
"step": 705
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 1.7715355805243447,
|
| 1001 |
+
"grad_norm": 1.1122398376464844,
|
| 1002 |
+
"learning_rate": 1.1846352591321438e-05,
|
| 1003 |
+
"loss": 0.3674,
|
| 1004 |
+
"step": 710
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.7840199750312111,
|
| 1008 |
+
"grad_norm": 1.1806241273880005,
|
| 1009 |
+
"learning_rate": 1.1644946985115921e-05,
|
| 1010 |
+
"loss": 0.3591,
|
| 1011 |
+
"step": 715
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 1.7965043695380774,
|
| 1015 |
+
"grad_norm": 1.2145330905914307,
|
| 1016 |
+
"learning_rate": 1.1444176125076126e-05,
|
| 1017 |
+
"loss": 0.3375,
|
| 1018 |
+
"step": 720
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.8089887640449438,
|
| 1022 |
+
"grad_norm": 1.2138397693634033,
|
| 1023 |
+
"learning_rate": 1.1244077995261626e-05,
|
| 1024 |
+
"loss": 0.3499,
|
| 1025 |
+
"step": 725
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 1.8214731585518102,
|
| 1029 |
+
"grad_norm": 1.0844088792800903,
|
| 1030 |
+
"learning_rate": 1.1044690452457432e-05,
|
| 1031 |
+
"loss": 0.3817,
|
| 1032 |
+
"step": 730
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 1.8339575530586767,
|
| 1036 |
+
"grad_norm": 1.0201855897903442,
|
| 1037 |
+
"learning_rate": 1.0846051219011807e-05,
|
| 1038 |
+
"loss": 0.3698,
|
| 1039 |
+
"step": 735
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 1.846441947565543,
|
| 1043 |
+
"grad_norm": 1.1144471168518066,
|
| 1044 |
+
"learning_rate": 1.0648197875699552e-05,
|
| 1045 |
+
"loss": 0.3621,
|
| 1046 |
+
"step": 740
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.8589263420724094,
|
| 1050 |
+
"grad_norm": 0.9572870135307312,
|
| 1051 |
+
"learning_rate": 1.0451167854612055e-05,
|
| 1052 |
+
"loss": 0.3612,
|
| 1053 |
+
"step": 745
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 1.8714107365792758,
|
| 1057 |
+
"grad_norm": 1.090131163597107,
|
| 1058 |
+
"learning_rate": 1.0254998432075452e-05,
|
| 1059 |
+
"loss": 0.3734,
|
| 1060 |
+
"step": 750
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 1.8838951310861423,
|
| 1064 |
+
"grad_norm": 1.003427505493164,
|
| 1065 |
+
"learning_rate": 1.0059726721598307e-05,
|
| 1066 |
+
"loss": 0.3694,
|
| 1067 |
+
"step": 755
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 1.8963795255930087,
|
| 1071 |
+
"grad_norm": 1.1181766986846924,
|
| 1072 |
+
"learning_rate": 9.865389666850046e-06,
|
| 1073 |
+
"loss": 0.3435,
|
| 1074 |
+
"step": 760
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.9088639200998752,
|
| 1078 |
+
"grad_norm": 1.0437352657318115,
|
| 1079 |
+
"learning_rate": 9.672024034671558e-06,
|
| 1080 |
+
"loss": 0.3794,
|
| 1081 |
+
"step": 765
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 1.9213483146067416,
|
| 1085 |
+
"grad_norm": 1.0181244611740112,
|
| 1086 |
+
"learning_rate": 9.479666408119223e-06,
|
| 1087 |
+
"loss": 0.3535,
|
| 1088 |
+
"step": 770
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 1.933832709113608,
|
| 1092 |
+
"grad_norm": 0.9547065496444702,
|
| 1093 |
+
"learning_rate": 9.288353179543733e-06,
|
| 1094 |
+
"loss": 0.3047,
|
| 1095 |
+
"step": 775
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 1.9463171036204745,
|
| 1099 |
+
"grad_norm": 1.0332533121109009,
|
| 1100 |
+
"learning_rate": 9.098120543704974e-06,
|
| 1101 |
+
"loss": 0.3494,
|
| 1102 |
+
"step": 780
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 1.958801498127341,
|
| 1106 |
+
"grad_norm": 1.180931568145752,
|
| 1107 |
+
"learning_rate": 8.909004490924311e-06,
|
| 1108 |
+
"loss": 0.3781,
|
| 1109 |
+
"step": 785
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 1.9712858926342074,
|
| 1113 |
+
"grad_norm": 1.1013957262039185,
|
| 1114 |
+
"learning_rate": 8.721040800275527e-06,
|
| 1115 |
+
"loss": 0.3722,
|
| 1116 |
+
"step": 790
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 1.9837702871410736,
|
| 1120 |
+
"grad_norm": 1.2435911893844604,
|
| 1121 |
+
"learning_rate": 8.534265032815759e-06,
|
| 1122 |
+
"loss": 0.3065,
|
| 1123 |
+
"step": 795
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 1.99625468164794,
|
| 1127 |
+
"grad_norm": 1.092275619506836,
|
| 1128 |
+
"learning_rate": 8.348712524857636e-06,
|
| 1129 |
+
"loss": 0.3505,
|
| 1130 |
+
"step": 800
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 2.00749063670412,
|
| 1134 |
+
"grad_norm": 1.0489857196807861,
|
| 1135 |
+
"learning_rate": 8.164418381283987e-06,
|
| 1136 |
+
"loss": 0.3031,
|
| 1137 |
+
"step": 805
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 2.0199750312109863,
|
| 1141 |
+
"grad_norm": 1.2991724014282227,
|
| 1142 |
+
"learning_rate": 7.9814174689063e-06,
|
| 1143 |
+
"loss": 0.277,
|
| 1144 |
+
"step": 810
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 2.0324594257178528,
|
| 1148 |
+
"grad_norm": 1.0748655796051025,
|
| 1149 |
+
"learning_rate": 7.799744409868235e-06,
|
| 1150 |
+
"loss": 0.2867,
|
| 1151 |
+
"step": 815
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 2.044943820224719,
|
| 1155 |
+
"grad_norm": 1.0463120937347412,
|
| 1156 |
+
"learning_rate": 7.619433575095407e-06,
|
| 1157 |
+
"loss": 0.2844,
|
| 1158 |
+
"step": 820
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 2.0574282147315857,
|
| 1162 |
+
"grad_norm": 1.0422537326812744,
|
| 1163 |
+
"learning_rate": 7.4405190777927405e-06,
|
| 1164 |
+
"loss": 0.2929,
|
| 1165 |
+
"step": 825
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 2.069912609238452,
|
| 1169 |
+
"grad_norm": 1.0519293546676636,
|
| 1170 |
+
"learning_rate": 7.263034766990533e-06,
|
| 1171 |
+
"loss": 0.2627,
|
| 1172 |
+
"step": 830
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 2.0823970037453186,
|
| 1176 |
+
"grad_norm": 1.1231743097305298,
|
| 1177 |
+
"learning_rate": 7.087014221140528e-06,
|
| 1178 |
+
"loss": 0.2958,
|
| 1179 |
+
"step": 835
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 2.0948813982521846,
|
| 1183 |
+
"grad_norm": 1.266548752784729,
|
| 1184 |
+
"learning_rate": 6.912490741763171e-06,
|
| 1185 |
+
"loss": 0.3061,
|
| 1186 |
+
"step": 840
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 2.107365792759051,
|
| 1190 |
+
"grad_norm": 1.1668893098831177,
|
| 1191 |
+
"learning_rate": 6.7394973471472535e-06,
|
| 1192 |
+
"loss": 0.274,
|
| 1193 |
+
"step": 845
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 2.1198501872659175,
|
| 1197 |
+
"grad_norm": 1.1760929822921753,
|
| 1198 |
+
"learning_rate": 6.568066766103152e-06,
|
| 1199 |
+
"loss": 0.2439,
|
| 1200 |
+
"step": 850
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 2.132334581772784,
|
| 1204 |
+
"grad_norm": 1.1019024848937988,
|
| 1205 |
+
"learning_rate": 6.398231431770829e-06,
|
| 1206 |
+
"loss": 0.2737,
|
| 1207 |
+
"step": 855
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 2.1448189762796503,
|
| 1211 |
+
"grad_norm": 1.1798478364944458,
|
| 1212 |
+
"learning_rate": 6.230023475483765e-06,
|
| 1213 |
+
"loss": 0.3055,
|
| 1214 |
+
"step": 860
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 2.157303370786517,
|
| 1218 |
+
"grad_norm": 1.0207715034484863,
|
| 1219 |
+
"learning_rate": 6.063474720690002e-06,
|
| 1220 |
+
"loss": 0.2653,
|
| 1221 |
+
"step": 865
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 2.1697877652933832,
|
| 1225 |
+
"grad_norm": 1.082462191581726,
|
| 1226 |
+
"learning_rate": 5.8986166769314284e-06,
|
| 1227 |
+
"loss": 0.2634,
|
| 1228 |
+
"step": 870
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 2.1822721598002497,
|
| 1232 |
+
"grad_norm": 1.2291069030761719,
|
| 1233 |
+
"learning_rate": 5.735480533882455e-06,
|
| 1234 |
+
"loss": 0.2681,
|
| 1235 |
+
"step": 875
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 2.194756554307116,
|
| 1239 |
+
"grad_norm": 0.9962201714515686,
|
| 1240 |
+
"learning_rate": 5.574097155449205e-06,
|
| 1241 |
+
"loss": 0.2597,
|
| 1242 |
+
"step": 880
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 2.2072409488139826,
|
| 1246 |
+
"grad_norm": 1.141408085823059,
|
| 1247 |
+
"learning_rate": 5.414497073930338e-06,
|
| 1248 |
+
"loss": 0.2782,
|
| 1249 |
+
"step": 885
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 2.219725343320849,
|
| 1253 |
+
"grad_norm": 1.2229342460632324,
|
| 1254 |
+
"learning_rate": 5.2567104842406144e-06,
|
| 1255 |
+
"loss": 0.2773,
|
| 1256 |
+
"step": 890
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 2.2322097378277155,
|
| 1260 |
+
"grad_norm": 0.9806187152862549,
|
| 1261 |
+
"learning_rate": 5.100767238198278e-06,
|
| 1262 |
+
"loss": 0.2764,
|
| 1263 |
+
"step": 895
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 2.244694132334582,
|
| 1267 |
+
"grad_norm": 1.1864205598831177,
|
| 1268 |
+
"learning_rate": 4.946696838877368e-06,
|
| 1269 |
+
"loss": 0.2589,
|
| 1270 |
+
"step": 900
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 2.2571785268414484,
|
| 1274 |
+
"grad_norm": 1.257620930671692,
|
| 1275 |
+
"learning_rate": 4.794528435025994e-06,
|
| 1276 |
+
"loss": 0.2939,
|
| 1277 |
+
"step": 905
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 2.2696629213483144,
|
| 1281 |
+
"grad_norm": 1.0354716777801514,
|
| 1282 |
+
"learning_rate": 4.6442908155516454e-06,
|
| 1283 |
+
"loss": 0.2617,
|
| 1284 |
+
"step": 910
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 2.2821473158551813,
|
| 1288 |
+
"grad_norm": 1.0254015922546387,
|
| 1289 |
+
"learning_rate": 4.496012404074604e-06,
|
| 1290 |
+
"loss": 0.2708,
|
| 1291 |
+
"step": 915
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 2.2946317103620473,
|
| 1295 |
+
"grad_norm": 1.1123079061508179,
|
| 1296 |
+
"learning_rate": 4.349721253550433e-06,
|
| 1297 |
+
"loss": 0.2642,
|
| 1298 |
+
"step": 920
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 2.3071161048689137,
|
| 1302 |
+
"grad_norm": 1.0750259160995483,
|
| 1303 |
+
"learning_rate": 4.2054450409626185e-06,
|
| 1304 |
+
"loss": 0.2792,
|
| 1305 |
+
"step": 925
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 2.31960049937578,
|
| 1309 |
+
"grad_norm": 1.18399977684021,
|
| 1310 |
+
"learning_rate": 4.063211062086315e-06,
|
| 1311 |
+
"loss": 0.2653,
|
| 1312 |
+
"step": 930
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 2.3320848938826466,
|
| 1316 |
+
"grad_norm": 1.1210650205612183,
|
| 1317 |
+
"learning_rate": 3.9230462263242494e-06,
|
| 1318 |
+
"loss": 0.2568,
|
| 1319 |
+
"step": 935
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 2.344569288389513,
|
| 1323 |
+
"grad_norm": 1.2481412887573242,
|
| 1324 |
+
"learning_rate": 3.78497705161568e-06,
|
| 1325 |
+
"loss": 0.2626,
|
| 1326 |
+
"step": 940
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 2.3570536828963795,
|
| 1330 |
+
"grad_norm": 1.0726100206375122,
|
| 1331 |
+
"learning_rate": 3.64902965941945e-06,
|
| 1332 |
+
"loss": 0.2472,
|
| 1333 |
+
"step": 945
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 2.369538077403246,
|
| 1337 |
+
"grad_norm": 0.9773839116096497,
|
| 1338 |
+
"learning_rate": 3.515229769772045e-06,
|
| 1339 |
+
"loss": 0.2875,
|
| 1340 |
+
"step": 950
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 2.3820224719101124,
|
| 1344 |
+
"grad_norm": 0.9859097003936768,
|
| 1345 |
+
"learning_rate": 3.383602696421574e-06,
|
| 1346 |
+
"loss": 0.2826,
|
| 1347 |
+
"step": 955
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 2.394506866416979,
|
| 1351 |
+
"grad_norm": 1.1507136821746826,
|
| 1352 |
+
"learning_rate": 3.2541733420386495e-06,
|
| 1353 |
+
"loss": 0.2594,
|
| 1354 |
+
"step": 960
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 2.4069912609238453,
|
| 1358 |
+
"grad_norm": 1.1104159355163574,
|
| 1359 |
+
"learning_rate": 3.1269661935050188e-06,
|
| 1360 |
+
"loss": 0.2439,
|
| 1361 |
+
"step": 965
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 2.4194756554307117,
|
| 1365 |
+
"grad_norm": 1.1644476652145386,
|
| 1366 |
+
"learning_rate": 3.0020053172808617e-06,
|
| 1367 |
+
"loss": 0.2511,
|
| 1368 |
+
"step": 970
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 2.431960049937578,
|
| 1372 |
+
"grad_norm": 1.0530967712402344,
|
| 1373 |
+
"learning_rate": 2.8793143548516322e-06,
|
| 1374 |
+
"loss": 0.2488,
|
| 1375 |
+
"step": 975
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 2.4444444444444446,
|
| 1379 |
+
"grad_norm": 1.187363624572754,
|
| 1380 |
+
"learning_rate": 2.758916518255299e-06,
|
| 1381 |
+
"loss": 0.2529,
|
| 1382 |
+
"step": 980
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 2.4569288389513106,
|
| 1386 |
+
"grad_norm": 1.0086742639541626,
|
| 1387 |
+
"learning_rate": 2.640834585690834e-06,
|
| 1388 |
+
"loss": 0.2598,
|
| 1389 |
+
"step": 985
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 2.469413233458177,
|
| 1393 |
+
"grad_norm": 1.1733794212341309,
|
| 1394 |
+
"learning_rate": 2.5250908972087865e-06,
|
| 1395 |
+
"loss": 0.2488,
|
| 1396 |
+
"step": 990
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 2.4818976279650435,
|
| 1400 |
+
"grad_norm": 1.08202064037323,
|
| 1401 |
+
"learning_rate": 2.411707350484733e-06,
|
| 1402 |
+
"loss": 0.2546,
|
| 1403 |
+
"step": 995
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 2.49438202247191,
|
| 1407 |
+
"grad_norm": 1.0771207809448242,
|
| 1408 |
+
"learning_rate": 2.3007053966764417e-06,
|
| 1409 |
+
"loss": 0.2427,
|
| 1410 |
+
"step": 1000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 2.5068664169787764,
|
| 1414 |
+
"grad_norm": 0.9809816479682922,
|
| 1415 |
+
"learning_rate": 2.1921060363655e-06,
|
| 1416 |
+
"loss": 0.2426,
|
| 1417 |
+
"step": 1005
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 2.519350811485643,
|
| 1421 |
+
"grad_norm": 1.1476706266403198,
|
| 1422 |
+
"learning_rate": 2.0859298155841894e-06,
|
| 1423 |
+
"loss": 0.2726,
|
| 1424 |
+
"step": 1010
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 2.5318352059925093,
|
| 1428 |
+
"grad_norm": 0.9656662344932556,
|
| 1429 |
+
"learning_rate": 1.9821968219283655e-06,
|
| 1430 |
+
"loss": 0.2288,
|
| 1431 |
+
"step": 1015
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 2.5443196004993758,
|
| 1435 |
+
"grad_norm": 1.2177280187606812,
|
| 1436 |
+
"learning_rate": 1.880926680757059e-06,
|
| 1437 |
+
"loss": 0.2515,
|
| 1438 |
+
"step": 1020
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 2.5568039950062422,
|
| 1442 |
+
"grad_norm": 1.06821870803833,
|
| 1443 |
+
"learning_rate": 1.7821385514795297e-06,
|
| 1444 |
+
"loss": 0.2457,
|
| 1445 |
+
"step": 1025
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 2.5692883895131087,
|
| 1449 |
+
"grad_norm": 1.0444525480270386,
|
| 1450 |
+
"learning_rate": 1.685851123930487e-06,
|
| 1451 |
+
"loss": 0.2544,
|
| 1452 |
+
"step": 1030
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 2.581772784019975,
|
| 1456 |
+
"grad_norm": 1.096990942955017,
|
| 1457 |
+
"learning_rate": 1.5920826148341284e-06,
|
| 1458 |
+
"loss": 0.2555,
|
| 1459 |
+
"step": 1035
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 2.5942571785268416,
|
| 1463 |
+
"grad_norm": 1.0326865911483765,
|
| 1464 |
+
"learning_rate": 1.5008507643577008e-06,
|
| 1465 |
+
"loss": 0.2565,
|
| 1466 |
+
"step": 1040
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 2.606741573033708,
|
| 1470 |
+
"grad_norm": 0.9721912145614624,
|
| 1471 |
+
"learning_rate": 1.4121728327552253e-06,
|
| 1472 |
+
"loss": 0.2592,
|
| 1473 |
+
"step": 1045
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 2.619225967540574,
|
| 1477 |
+
"grad_norm": 1.0657060146331787,
|
| 1478 |
+
"learning_rate": 1.3260655971020024e-06,
|
| 1479 |
+
"loss": 0.2322,
|
| 1480 |
+
"step": 1050
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 2.631710362047441,
|
| 1484 |
+
"grad_norm": 1.0224922895431519,
|
| 1485 |
+
"learning_rate": 1.2425453481205418e-06,
|
| 1486 |
+
"loss": 0.255,
|
| 1487 |
+
"step": 1055
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 2.644194756554307,
|
| 1491 |
+
"grad_norm": 1.137595534324646,
|
| 1492 |
+
"learning_rate": 1.1616278870985015e-06,
|
| 1493 |
+
"loss": 0.27,
|
| 1494 |
+
"step": 1060
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 2.656679151061174,
|
| 1498 |
+
"grad_norm": 1.2252774238586426,
|
| 1499 |
+
"learning_rate": 1.0833285228992284e-06,
|
| 1500 |
+
"loss": 0.2411,
|
| 1501 |
+
"step": 1065
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 2.66916354556804,
|
| 1505 |
+
"grad_norm": 0.9871050715446472,
|
| 1506 |
+
"learning_rate": 1.0076620690654554e-06,
|
| 1507 |
+
"loss": 0.2362,
|
| 1508 |
+
"step": 1070
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 2.6816479400749063,
|
| 1512 |
+
"grad_norm": 1.2114794254302979,
|
| 1513 |
+
"learning_rate": 9.346428410167085e-07,
|
| 1514 |
+
"loss": 0.2234,
|
| 1515 |
+
"step": 1075
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 2.6941323345817727,
|
| 1519 |
+
"grad_norm": 1.018224835395813,
|
| 1520 |
+
"learning_rate": 8.642846533409615e-07,
|
| 1521 |
+
"loss": 0.2502,
|
| 1522 |
+
"step": 1080
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 2.706616729088639,
|
| 1526 |
+
"grad_norm": 1.0699653625488281,
|
| 1527 |
+
"learning_rate": 7.966008171810357e-07,
|
| 1528 |
+
"loss": 0.2801,
|
| 1529 |
+
"step": 1085
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 2.7191011235955056,
|
| 1533 |
+
"grad_norm": 1.0360287427902222,
|
| 1534 |
+
"learning_rate": 7.316041377162514e-07,
|
| 1535 |
+
"loss": 0.2525,
|
| 1536 |
+
"step": 1090
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 2.731585518102372,
|
| 1540 |
+
"grad_norm": 1.0694209337234497,
|
| 1541 |
+
"learning_rate": 6.693069117398004e-07,
|
| 1542 |
+
"loss": 0.2356,
|
| 1543 |
+
"step": 1095
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 2.7440699126092385,
|
| 1547 |
+
"grad_norm": 1.0921366214752197,
|
| 1548 |
+
"learning_rate": 6.09720925332306e-07,
|
| 1549 |
+
"loss": 0.2494,
|
| 1550 |
+
"step": 1100
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 2.756554307116105,
|
| 1554 |
+
"grad_norm": 1.1573783159255981,
|
| 1555 |
+
"learning_rate": 5.528574516319945e-07,
|
| 1556 |
+
"loss": 0.2809,
|
| 1557 |
+
"step": 1105
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 2.7690387016229714,
|
| 1561 |
+
"grad_norm": 1.1061475276947021,
|
| 1562 |
+
"learning_rate": 4.987272487019279e-07,
|
| 1563 |
+
"loss": 0.2372,
|
| 1564 |
+
"step": 1110
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 2.781523096129838,
|
| 1568 |
+
"grad_norm": 0.9549543261528015,
|
| 1569 |
+
"learning_rate": 4.473405574946654e-07,
|
| 1570 |
+
"loss": 0.2287,
|
| 1571 |
+
"step": 1115
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 2.7940074906367043,
|
| 1575 |
+
"grad_norm": 1.068056583404541,
|
| 1576 |
+
"learning_rate": 3.9870709991476685e-07,
|
| 1577 |
+
"loss": 0.2321,
|
| 1578 |
+
"step": 1120
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 2.8064918851435703,
|
| 1582 |
+
"grad_norm": 1.077315330505371,
|
| 1583 |
+
"learning_rate": 3.5283607697950195e-07,
|
| 1584 |
+
"loss": 0.2339,
|
| 1585 |
+
"step": 1125
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 2.818976279650437,
|
| 1589 |
+
"grad_norm": 1.1574848890304565,
|
| 1590 |
+
"learning_rate": 3.097361670780946e-07,
|
| 1591 |
+
"loss": 0.2114,
|
| 1592 |
+
"step": 1130
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 2.831460674157303,
|
| 1596 |
+
"grad_norm": 1.14369797706604,
|
| 1597 |
+
"learning_rate": 2.694155243298463e-07,
|
| 1598 |
+
"loss": 0.2347,
|
| 1599 |
+
"step": 1135
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 2.8439450686641696,
|
| 1603 |
+
"grad_norm": 1.1754659414291382,
|
| 1604 |
+
"learning_rate": 2.3188177704145498e-07,
|
| 1605 |
+
"loss": 0.2478,
|
| 1606 |
+
"step": 1140
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 2.856429463171036,
|
| 1610 |
+
"grad_norm": 1.0041310787200928,
|
| 1611 |
+
"learning_rate": 1.9714202626380462e-07,
|
| 1612 |
+
"loss": 0.2492,
|
| 1613 |
+
"step": 1145
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 2.8689138576779025,
|
| 1617 |
+
"grad_norm": 0.9712026119232178,
|
| 1618 |
+
"learning_rate": 1.6520284444850987e-07,
|
| 1619 |
+
"loss": 0.2685,
|
| 1620 |
+
"step": 1150
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 2.881398252184769,
|
| 1624 |
+
"grad_norm": 1.073612928390503,
|
| 1625 |
+
"learning_rate": 1.3607027420446728e-07,
|
| 1626 |
+
"loss": 0.2132,
|
| 1627 |
+
"step": 1155
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 2.8938826466916354,
|
| 1631 |
+
"grad_norm": 1.0427110195159912,
|
| 1632 |
+
"learning_rate": 1.0974982715464321e-07,
|
| 1633 |
+
"loss": 0.2313,
|
| 1634 |
+
"step": 1160
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 2.906367041198502,
|
| 1638 |
+
"grad_norm": 1.0295484066009521,
|
| 1639 |
+
"learning_rate": 8.624648289333459e-08,
|
| 1640 |
+
"loss": 0.2446,
|
| 1641 |
+
"step": 1165
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 2.9188514357053683,
|
| 1645 |
+
"grad_norm": 0.9902641773223877,
|
| 1646 |
+
"learning_rate": 6.556468804405913e-08,
|
| 1647 |
+
"loss": 0.2353,
|
| 1648 |
+
"step": 1170
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 2.9313358302122348,
|
| 1652 |
+
"grad_norm": 1.169481635093689,
|
| 1653 |
+
"learning_rate": 4.770835541830665e-08,
|
| 1654 |
+
"loss": 0.2392,
|
| 1655 |
+
"step": 1175
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 2.943820224719101,
|
| 1659 |
+
"grad_norm": 1.0117815732955933,
|
| 1660 |
+
"learning_rate": 3.268086327526454e-08,
|
| 1661 |
+
"loss": 0.2139,
|
| 1662 |
+
"step": 1180
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 2.9563046192259677,
|
| 1666 |
+
"grad_norm": 1.1123095750808716,
|
| 1667 |
+
"learning_rate": 2.0485054682677363e-08,
|
| 1668 |
+
"loss": 0.2809,
|
| 1669 |
+
"step": 1185
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 2.968789013732834,
|
| 1673 |
+
"grad_norm": 0.9268423914909363,
|
| 1674 |
+
"learning_rate": 1.1123236978975437e-08,
|
| 1675 |
+
"loss": 0.229,
|
| 1676 |
+
"step": 1190
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 2.9812734082397006,
|
| 1680 |
+
"grad_norm": 1.0891536474227905,
|
| 1681 |
+
"learning_rate": 4.597181336730705e-09,
|
| 1682 |
+
"loss": 0.2521,
|
| 1683 |
+
"step": 1195
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 2.9937578027465666,
|
| 1687 |
+
"grad_norm": 1.1411787271499634,
|
| 1688 |
+
"learning_rate": 9.081224275830913e-10,
|
| 1689 |
+
"loss": 0.2705,
|
| 1690 |
+
"step": 1200
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 3.0,
|
| 1694 |
+
"step": 1203,
|
| 1695 |
+
"total_flos": 1.7520698214297108e+18,
|
| 1696 |
+
"train_loss": 0.538740111408091,
|
| 1697 |
+
"train_runtime": 824.1982,
|
| 1698 |
+
"train_samples_per_second": 46.638,
|
| 1699 |
+
"train_steps_per_second": 1.46
|
| 1700 |
+
}
|
| 1701 |
+
],
|
| 1702 |
+
"logging_steps": 5,
|
| 1703 |
+
"max_steps": 1203,
|
| 1704 |
+
"num_input_tokens_seen": 0,
|
| 1705 |
+
"num_train_epochs": 3,
|
| 1706 |
+
"save_steps": 20000,
|
| 1707 |
+
"stateful_callbacks": {
|
| 1708 |
+
"TrainerControl": {
|
| 1709 |
+
"args": {
|
| 1710 |
+
"should_epoch_stop": false,
|
| 1711 |
+
"should_evaluate": false,
|
| 1712 |
+
"should_log": false,
|
| 1713 |
+
"should_save": false,
|
| 1714 |
+
"should_training_stop": false
|
| 1715 |
+
},
|
| 1716 |
+
"attributes": {}
|
| 1717 |
+
}
|
| 1718 |
+
},
|
| 1719 |
+
"total_flos": 1.7520698214297108e+18,
|
| 1720 |
+
"train_batch_size": 2,
|
| 1721 |
+
"trial_name": null,
|
| 1722 |
+
"trial_params": null
|
| 1723 |
+
}
|
107_128_e3_3e-5/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eddab39136edb49e51686922bccce09c2b70f48cb62474e5896f230fb317be6b
|
| 3 |
+
size 8273
|
107_128_e3_3e-5/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|