Upload folder using huggingface_hub
Browse files- 25_128_e3_3e-5/adapter_config.json +39 -0
- 25_128_e3_3e-5/adapter_model.safetensors +3 -0
- 25_128_e3_3e-5/added_tokens.json +9 -0
- 25_128_e3_3e-5/all_results.json +9 -0
- 25_128_e3_3e-5/chat_template.jinja +62 -0
- 25_128_e3_3e-5/config.json +32 -0
- 25_128_e3_3e-5/merges.txt +0 -0
- 25_128_e3_3e-5/special_tokens_map.json +33 -0
- 25_128_e3_3e-5/tokenizer.json +0 -0
- 25_128_e3_3e-5/tokenizer_config.json +234 -0
- 25_128_e3_3e-5/train_results.json +9 -0
- 25_128_e3_3e-5/trainer_state.json +1849 -0
- 25_128_e3_3e-5/training_args.bin +3 -0
- 25_128_e3_3e-5/vocab.json +0 -0
25_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 |
+
"v_proj",
|
| 28 |
+
"k_proj",
|
| 29 |
+
"gate_proj",
|
| 30 |
+
"o_proj",
|
| 31 |
+
"q_proj",
|
| 32 |
+
"up_proj",
|
| 33 |
+
"down_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
+
"use_dora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
25_128_e3_3e-5/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d3cf93e027f1ee9e3522a63700eb55cc5ad270dac5cbabda195be29aa4ccfb53
|
| 3 |
+
size 791751704
|
25_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 |
+
}
|
25_128_e3_3e-5/all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 2.0359870555944387e+18,
|
| 4 |
+
"train_loss": 0.5806684772450151,
|
| 5 |
+
"train_runtime": 1005.3243,
|
| 6 |
+
"train_samples": 13773,
|
| 7 |
+
"train_samples_per_second": 41.1,
|
| 8 |
+
"train_steps_per_second": 1.286
|
| 9 |
+
}
|
25_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 %}
|
25_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 |
+
}
|
25_128_e3_3e-5/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
25_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 |
+
}
|
25_128_e3_3e-5/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
25_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 |
+
}
|
25_128_e3_3e-5/train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 2.0359870555944387e+18,
|
| 4 |
+
"train_loss": 0.5806684772450151,
|
| 5 |
+
"train_runtime": 1005.3243,
|
| 6 |
+
"train_samples": 13773,
|
| 7 |
+
"train_samples_per_second": 41.1,
|
| 8 |
+
"train_steps_per_second": 1.286
|
| 9 |
+
}
|
25_128_e3_3e-5/trainer_state.json
ADDED
|
@@ -0,0 +1,1849 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 1293,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.011614401858304297,
|
| 14 |
+
"grad_norm": 3.7239036560058594,
|
| 15 |
+
"learning_rate": 1.8461538461538462e-06,
|
| 16 |
+
"loss": 1.5388,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.023228803716608595,
|
| 21 |
+
"grad_norm": 2.49280047416687,
|
| 22 |
+
"learning_rate": 4.1538461538461545e-06,
|
| 23 |
+
"loss": 1.5279,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.03484320557491289,
|
| 28 |
+
"grad_norm": 1.060119390487671,
|
| 29 |
+
"learning_rate": 6.461538461538462e-06,
|
| 30 |
+
"loss": 1.4208,
|
| 31 |
+
"step": 15
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.04645760743321719,
|
| 35 |
+
"grad_norm": 0.6498854756355286,
|
| 36 |
+
"learning_rate": 8.76923076923077e-06,
|
| 37 |
+
"loss": 1.3651,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.05807200929152149,
|
| 42 |
+
"grad_norm": 0.4009834825992584,
|
| 43 |
+
"learning_rate": 1.1076923076923077e-05,
|
| 44 |
+
"loss": 1.3718,
|
| 45 |
+
"step": 25
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.06968641114982578,
|
| 49 |
+
"grad_norm": 0.6162559390068054,
|
| 50 |
+
"learning_rate": 1.3384615384615386e-05,
|
| 51 |
+
"loss": 1.3552,
|
| 52 |
+
"step": 30
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.08130081300813008,
|
| 56 |
+
"grad_norm": 0.33406174182891846,
|
| 57 |
+
"learning_rate": 1.5692307692307693e-05,
|
| 58 |
+
"loss": 1.2759,
|
| 59 |
+
"step": 35
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.09291521486643438,
|
| 63 |
+
"grad_norm": 0.41755595803260803,
|
| 64 |
+
"learning_rate": 1.8e-05,
|
| 65 |
+
"loss": 1.26,
|
| 66 |
+
"step": 40
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.10452961672473868,
|
| 70 |
+
"grad_norm": 0.331603467464447,
|
| 71 |
+
"learning_rate": 2.0307692307692308e-05,
|
| 72 |
+
"loss": 1.2596,
|
| 73 |
+
"step": 45
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.11614401858304298,
|
| 77 |
+
"grad_norm": 0.3664747476577759,
|
| 78 |
+
"learning_rate": 2.2615384615384615e-05,
|
| 79 |
+
"loss": 1.2887,
|
| 80 |
+
"step": 50
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.12775842044134728,
|
| 84 |
+
"grad_norm": 0.32520970702171326,
|
| 85 |
+
"learning_rate": 2.4923076923076926e-05,
|
| 86 |
+
"loss": 1.269,
|
| 87 |
+
"step": 55
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.13937282229965156,
|
| 91 |
+
"grad_norm": 0.3528161346912384,
|
| 92 |
+
"learning_rate": 2.7230769230769233e-05,
|
| 93 |
+
"loss": 1.2601,
|
| 94 |
+
"step": 60
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.15098722415795587,
|
| 98 |
+
"grad_norm": 0.3476129174232483,
|
| 99 |
+
"learning_rate": 2.953846153846154e-05,
|
| 100 |
+
"loss": 1.1839,
|
| 101 |
+
"step": 65
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.16260162601626016,
|
| 105 |
+
"grad_norm": 0.3519430458545685,
|
| 106 |
+
"learning_rate": 2.9999214618860097e-05,
|
| 107 |
+
"loss": 1.2509,
|
| 108 |
+
"step": 70
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.17421602787456447,
|
| 112 |
+
"grad_norm": 0.38617995381355286,
|
| 113 |
+
"learning_rate": 2.9996024148932534e-05,
|
| 114 |
+
"loss": 1.2605,
|
| 115 |
+
"step": 75
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.18583042973286876,
|
| 119 |
+
"grad_norm": 0.44555604457855225,
|
| 120 |
+
"learning_rate": 2.999038002552003e-05,
|
| 121 |
+
"loss": 1.166,
|
| 122 |
+
"step": 80
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.19744483159117304,
|
| 126 |
+
"grad_norm": 0.35843759775161743,
|
| 127 |
+
"learning_rate": 2.9982283172115566e-05,
|
| 128 |
+
"loss": 1.1625,
|
| 129 |
+
"step": 85
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.20905923344947736,
|
| 133 |
+
"grad_norm": 0.3689218759536743,
|
| 134 |
+
"learning_rate": 2.9971734913528465e-05,
|
| 135 |
+
"loss": 1.1718,
|
| 136 |
+
"step": 90
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.22067363530778164,
|
| 140 |
+
"grad_norm": 0.3973144292831421,
|
| 141 |
+
"learning_rate": 2.9958736975667613e-05,
|
| 142 |
+
"loss": 1.1546,
|
| 143 |
+
"step": 95
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.23228803716608595,
|
| 147 |
+
"grad_norm": 0.42336413264274597,
|
| 148 |
+
"learning_rate": 2.9943291485259094e-05,
|
| 149 |
+
"loss": 1.1256,
|
| 150 |
+
"step": 100
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.24390243902439024,
|
| 154 |
+
"grad_norm": 0.4604174494743347,
|
| 155 |
+
"learning_rate": 2.9925400969498173e-05,
|
| 156 |
+
"loss": 1.1204,
|
| 157 |
+
"step": 105
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.25551684088269455,
|
| 161 |
+
"grad_norm": 0.46538224816322327,
|
| 162 |
+
"learning_rate": 2.990506835563583e-05,
|
| 163 |
+
"loss": 1.0944,
|
| 164 |
+
"step": 110
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.26713124274099886,
|
| 168 |
+
"grad_norm": 0.3979334831237793,
|
| 169 |
+
"learning_rate": 2.988229697049979e-05,
|
| 170 |
+
"loss": 1.1457,
|
| 171 |
+
"step": 115
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.2787456445993031,
|
| 175 |
+
"grad_norm": 0.40539079904556274,
|
| 176 |
+
"learning_rate": 2.9857090539950177e-05,
|
| 177 |
+
"loss": 1.0839,
|
| 178 |
+
"step": 120
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.29036004645760743,
|
| 182 |
+
"grad_norm": 0.4645063579082489,
|
| 183 |
+
"learning_rate": 2.982945318826991e-05,
|
| 184 |
+
"loss": 1.0477,
|
| 185 |
+
"step": 125
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.30197444831591175,
|
| 189 |
+
"grad_norm": 0.4794134795665741,
|
| 190 |
+
"learning_rate": 2.979938943748987e-05,
|
| 191 |
+
"loss": 1.085,
|
| 192 |
+
"step": 130
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.313588850174216,
|
| 196 |
+
"grad_norm": 0.43697139620780945,
|
| 197 |
+
"learning_rate": 2.9766904206648997e-05,
|
| 198 |
+
"loss": 1.035,
|
| 199 |
+
"step": 135
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.3252032520325203,
|
| 203 |
+
"grad_norm": 0.47847357392311096,
|
| 204 |
+
"learning_rate": 2.9732002810989464e-05,
|
| 205 |
+
"loss": 1.0612,
|
| 206 |
+
"step": 140
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.33681765389082463,
|
| 210 |
+
"grad_norm": 0.5038856267929077,
|
| 211 |
+
"learning_rate": 2.969469096108697e-05,
|
| 212 |
+
"loss": 1.0862,
|
| 213 |
+
"step": 145
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.34843205574912894,
|
| 217 |
+
"grad_norm": 0.4716856777667999,
|
| 218 |
+
"learning_rate": 2.9654974761916377e-05,
|
| 219 |
+
"loss": 1.1585,
|
| 220 |
+
"step": 150
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.3600464576074332,
|
| 224 |
+
"grad_norm": 0.5352954864501953,
|
| 225 |
+
"learning_rate": 2.9612860711852828e-05,
|
| 226 |
+
"loss": 0.9909,
|
| 227 |
+
"step": 155
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.3716608594657375,
|
| 231 |
+
"grad_norm": 0.5641031861305237,
|
| 232 |
+
"learning_rate": 2.9568355701608463e-05,
|
| 233 |
+
"loss": 1.0579,
|
| 234 |
+
"step": 160
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.3832752613240418,
|
| 238 |
+
"grad_norm": 0.5172345042228699,
|
| 239 |
+
"learning_rate": 2.9521467013104973e-05,
|
| 240 |
+
"loss": 1.0648,
|
| 241 |
+
"step": 165
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.3948896631823461,
|
| 245 |
+
"grad_norm": 0.5852975249290466,
|
| 246 |
+
"learning_rate": 2.947220231828212e-05,
|
| 247 |
+
"loss": 1.0146,
|
| 248 |
+
"step": 170
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.4065040650406504,
|
| 252 |
+
"grad_norm": 0.6303030848503113,
|
| 253 |
+
"learning_rate": 2.9420569677842456e-05,
|
| 254 |
+
"loss": 0.9513,
|
| 255 |
+
"step": 175
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.4181184668989547,
|
| 259 |
+
"grad_norm": 0.6142143607139587,
|
| 260 |
+
"learning_rate": 2.9366577539932433e-05,
|
| 261 |
+
"loss": 0.9699,
|
| 262 |
+
"step": 180
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.429732868757259,
|
| 266 |
+
"grad_norm": 0.5549263954162598,
|
| 267 |
+
"learning_rate": 2.93102347387601e-05,
|
| 268 |
+
"loss": 0.9979,
|
| 269 |
+
"step": 185
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.4413472706155633,
|
| 273 |
+
"grad_norm": 0.6228923201560974,
|
| 274 |
+
"learning_rate": 2.925155049314967e-05,
|
| 275 |
+
"loss": 1.0035,
|
| 276 |
+
"step": 190
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.4529616724738676,
|
| 280 |
+
"grad_norm": 0.6589254140853882,
|
| 281 |
+
"learning_rate": 2.9190534405033108e-05,
|
| 282 |
+
"loss": 0.9252,
|
| 283 |
+
"step": 195
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.4645760743321719,
|
| 287 |
+
"grad_norm": 0.5856587290763855,
|
| 288 |
+
"learning_rate": 2.9127196457879096e-05,
|
| 289 |
+
"loss": 0.9695,
|
| 290 |
+
"step": 200
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.47619047619047616,
|
| 294 |
+
"grad_norm": 0.6193470358848572,
|
| 295 |
+
"learning_rate": 2.906154701505949e-05,
|
| 296 |
+
"loss": 0.9641,
|
| 297 |
+
"step": 205
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.4878048780487805,
|
| 301 |
+
"grad_norm": 0.6732288002967834,
|
| 302 |
+
"learning_rate": 2.8993596818153703e-05,
|
| 303 |
+
"loss": 0.9541,
|
| 304 |
+
"step": 210
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.4994192799070848,
|
| 308 |
+
"grad_norm": 0.6615795493125916,
|
| 309 |
+
"learning_rate": 2.8923356985191134e-05,
|
| 310 |
+
"loss": 0.9326,
|
| 311 |
+
"step": 215
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.5110336817653891,
|
| 315 |
+
"grad_norm": 0.6849666237831116,
|
| 316 |
+
"learning_rate": 2.885083900883205e-05,
|
| 317 |
+
"loss": 0.9057,
|
| 318 |
+
"step": 220
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.5226480836236934,
|
| 322 |
+
"grad_norm": 0.7001377940177917,
|
| 323 |
+
"learning_rate": 2.877605475448716e-05,
|
| 324 |
+
"loss": 0.9211,
|
| 325 |
+
"step": 225
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.5342624854819977,
|
| 329 |
+
"grad_norm": 0.6646133661270142,
|
| 330 |
+
"learning_rate": 2.8699016458376173e-05,
|
| 331 |
+
"loss": 0.9311,
|
| 332 |
+
"step": 230
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.5458768873403019,
|
| 336 |
+
"grad_norm": 0.6363524794578552,
|
| 337 |
+
"learning_rate": 2.861973672552571e-05,
|
| 338 |
+
"loss": 0.8821,
|
| 339 |
+
"step": 235
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.5574912891986062,
|
| 343 |
+
"grad_norm": 0.6724256277084351,
|
| 344 |
+
"learning_rate": 2.853822852770689e-05,
|
| 345 |
+
"loss": 0.9109,
|
| 346 |
+
"step": 240
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.5691056910569106,
|
| 350 |
+
"grad_norm": 0.6587971448898315,
|
| 351 |
+
"learning_rate": 2.845450520131285e-05,
|
| 352 |
+
"loss": 0.9068,
|
| 353 |
+
"step": 245
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.5807200929152149,
|
| 357 |
+
"grad_norm": 0.7322813868522644,
|
| 358 |
+
"learning_rate": 2.8368580445176668e-05,
|
| 359 |
+
"loss": 0.8869,
|
| 360 |
+
"step": 250
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.5923344947735192,
|
| 364 |
+
"grad_norm": 0.7255988717079163,
|
| 365 |
+
"learning_rate": 2.8280468318329934e-05,
|
| 366 |
+
"loss": 0.8568,
|
| 367 |
+
"step": 255
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.6039488966318235,
|
| 371 |
+
"grad_norm": 0.7958986759185791,
|
| 372 |
+
"learning_rate": 2.8190183237702433e-05,
|
| 373 |
+
"loss": 0.8255,
|
| 374 |
+
"step": 260
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.6155632984901278,
|
| 378 |
+
"grad_norm": 0.7678819298744202,
|
| 379 |
+
"learning_rate": 2.809773997576322e-05,
|
| 380 |
+
"loss": 0.8558,
|
| 381 |
+
"step": 265
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.627177700348432,
|
| 385 |
+
"grad_norm": 0.7441889047622681,
|
| 386 |
+
"learning_rate": 2.8003153658103547e-05,
|
| 387 |
+
"loss": 0.9033,
|
| 388 |
+
"step": 270
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.6387921022067363,
|
| 392 |
+
"grad_norm": 0.7110655307769775,
|
| 393 |
+
"learning_rate": 2.790643976096204e-05,
|
| 394 |
+
"loss": 0.8529,
|
| 395 |
+
"step": 275
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.6504065040650406,
|
| 399 |
+
"grad_norm": 0.7925458550453186,
|
| 400 |
+
"learning_rate": 2.7807614108692426e-05,
|
| 401 |
+
"loss": 0.8516,
|
| 402 |
+
"step": 280
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.662020905923345,
|
| 406 |
+
"grad_norm": 0.7953664064407349,
|
| 407 |
+
"learning_rate": 2.770669287117438e-05,
|
| 408 |
+
"loss": 0.8712,
|
| 409 |
+
"step": 285
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.6736353077816493,
|
| 413 |
+
"grad_norm": 0.8666931986808777,
|
| 414 |
+
"learning_rate": 2.7603692561167807e-05,
|
| 415 |
+
"loss": 0.769,
|
| 416 |
+
"step": 290
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.6852497096399536,
|
| 420 |
+
"grad_norm": 0.79376620054245,
|
| 421 |
+
"learning_rate": 2.7498630031610985e-05,
|
| 422 |
+
"loss": 0.863,
|
| 423 |
+
"step": 295
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.6968641114982579,
|
| 427 |
+
"grad_norm": 0.7933903336524963,
|
| 428 |
+
"learning_rate": 2.7391522472863123e-05,
|
| 429 |
+
"loss": 0.8059,
|
| 430 |
+
"step": 300
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.7084785133565621,
|
| 434 |
+
"grad_norm": 0.7302671074867249,
|
| 435 |
+
"learning_rate": 2.7282387409891653e-05,
|
| 436 |
+
"loss": 0.818,
|
| 437 |
+
"step": 305
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.7200929152148664,
|
| 441 |
+
"grad_norm": 0.8621637225151062,
|
| 442 |
+
"learning_rate": 2.7171242699404788e-05,
|
| 443 |
+
"loss": 0.7648,
|
| 444 |
+
"step": 310
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.7317073170731707,
|
| 448 |
+
"grad_norm": 0.7623394131660461,
|
| 449 |
+
"learning_rate": 2.705810652692981e-05,
|
| 450 |
+
"loss": 0.8269,
|
| 451 |
+
"step": 315
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.743321718931475,
|
| 455 |
+
"grad_norm": 0.784396767616272,
|
| 456 |
+
"learning_rate": 2.694299740383753e-05,
|
| 457 |
+
"loss": 0.8105,
|
| 458 |
+
"step": 320
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.7549361207897793,
|
| 462 |
+
"grad_norm": 0.8236751556396484,
|
| 463 |
+
"learning_rate": 2.6825934164313492e-05,
|
| 464 |
+
"loss": 0.824,
|
| 465 |
+
"step": 325
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.7665505226480837,
|
| 469 |
+
"grad_norm": 0.8309207558631897,
|
| 470 |
+
"learning_rate": 2.6706935962276268e-05,
|
| 471 |
+
"loss": 0.8326,
|
| 472 |
+
"step": 330
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.778164924506388,
|
| 476 |
+
"grad_norm": 0.8117490410804749,
|
| 477 |
+
"learning_rate": 2.6586022268243526e-05,
|
| 478 |
+
"loss": 0.7619,
|
| 479 |
+
"step": 335
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.7897793263646922,
|
| 483 |
+
"grad_norm": 0.8275243639945984,
|
| 484 |
+
"learning_rate": 2.6463212866146246e-05,
|
| 485 |
+
"loss": 0.7847,
|
| 486 |
+
"step": 340
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.8013937282229965,
|
| 490 |
+
"grad_norm": 0.7706731557846069,
|
| 491 |
+
"learning_rate": 2.633852785009168e-05,
|
| 492 |
+
"loss": 0.7217,
|
| 493 |
+
"step": 345
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.8130081300813008,
|
| 497 |
+
"grad_norm": 0.8583183288574219,
|
| 498 |
+
"learning_rate": 2.621198762107551e-05,
|
| 499 |
+
"loss": 0.7879,
|
| 500 |
+
"step": 350
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.8246225319396051,
|
| 504 |
+
"grad_norm": 0.8016027808189392,
|
| 505 |
+
"learning_rate": 2.6083612883643888e-05,
|
| 506 |
+
"loss": 0.7647,
|
| 507 |
+
"step": 355
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.8362369337979094,
|
| 511 |
+
"grad_norm": 0.8635758757591248,
|
| 512 |
+
"learning_rate": 2.595342464250571e-05,
|
| 513 |
+
"loss": 0.7656,
|
| 514 |
+
"step": 360
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.8478513356562137,
|
| 518 |
+
"grad_norm": 0.8534408211708069,
|
| 519 |
+
"learning_rate": 2.5821444199095833e-05,
|
| 520 |
+
"loss": 0.765,
|
| 521 |
+
"step": 365
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.859465737514518,
|
| 525 |
+
"grad_norm": 0.8564404249191284,
|
| 526 |
+
"learning_rate": 2.568769314808973e-05,
|
| 527 |
+
"loss": 0.743,
|
| 528 |
+
"step": 370
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.8710801393728222,
|
| 532 |
+
"grad_norm": 0.828381359577179,
|
| 533 |
+
"learning_rate": 2.5552193373870175e-05,
|
| 534 |
+
"loss": 0.6896,
|
| 535 |
+
"step": 375
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.8826945412311266,
|
| 539 |
+
"grad_norm": 0.8003427386283875,
|
| 540 |
+
"learning_rate": 2.5414967046946482e-05,
|
| 541 |
+
"loss": 0.7801,
|
| 542 |
+
"step": 380
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.8943089430894309,
|
| 546 |
+
"grad_norm": 0.9103115797042847,
|
| 547 |
+
"learning_rate": 2.5276036620327e-05,
|
| 548 |
+
"loss": 0.687,
|
| 549 |
+
"step": 385
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.9059233449477352,
|
| 553 |
+
"grad_norm": 0.899299681186676,
|
| 554 |
+
"learning_rate": 2.513542482584531e-05,
|
| 555 |
+
"loss": 0.7451,
|
| 556 |
+
"step": 390
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.9175377468060395,
|
| 560 |
+
"grad_norm": 0.9081295728683472,
|
| 561 |
+
"learning_rate": 2.4993154670440866e-05,
|
| 562 |
+
"loss": 0.718,
|
| 563 |
+
"step": 395
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.9291521486643438,
|
| 567 |
+
"grad_norm": 0.9310486912727356,
|
| 568 |
+
"learning_rate": 2.4849249432394568e-05,
|
| 569 |
+
"loss": 0.6786,
|
| 570 |
+
"step": 400
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.9407665505226481,
|
| 574 |
+
"grad_norm": 1.0035141706466675,
|
| 575 |
+
"learning_rate": 2.4703732657519984e-05,
|
| 576 |
+
"loss": 0.6999,
|
| 577 |
+
"step": 405
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.9523809523809523,
|
| 581 |
+
"grad_norm": 0.884985625743866,
|
| 582 |
+
"learning_rate": 2.4556628155310766e-05,
|
| 583 |
+
"loss": 0.7024,
|
| 584 |
+
"step": 410
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.9639953542392566,
|
| 588 |
+
"grad_norm": 0.8092682361602783,
|
| 589 |
+
"learning_rate": 2.4407959995044943e-05,
|
| 590 |
+
"loss": 0.667,
|
| 591 |
+
"step": 415
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.975609756097561,
|
| 595 |
+
"grad_norm": 0.9335992932319641,
|
| 596 |
+
"learning_rate": 2.425775250184668e-05,
|
| 597 |
+
"loss": 0.7228,
|
| 598 |
+
"step": 420
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.9872241579558653,
|
| 602 |
+
"grad_norm": 0.8802455067634583,
|
| 603 |
+
"learning_rate": 2.4106030252706223e-05,
|
| 604 |
+
"loss": 0.6878,
|
| 605 |
+
"step": 425
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.9988385598141696,
|
| 609 |
+
"grad_norm": 0.9185948967933655,
|
| 610 |
+
"learning_rate": 2.3952818072458588e-05,
|
| 611 |
+
"loss": 0.6512,
|
| 612 |
+
"step": 430
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.0092915214866434,
|
| 616 |
+
"grad_norm": 0.885767936706543,
|
| 617 |
+
"learning_rate": 2.3798141029721706e-05,
|
| 618 |
+
"loss": 0.5856,
|
| 619 |
+
"step": 435
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.0209059233449478,
|
| 623 |
+
"grad_norm": 0.91026771068573,
|
| 624 |
+
"learning_rate": 2.3642024432794714e-05,
|
| 625 |
+
"loss": 0.5936,
|
| 626 |
+
"step": 440
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.032520325203252,
|
| 630 |
+
"grad_norm": 0.9716700911521912,
|
| 631 |
+
"learning_rate": 2.3484493825516985e-05,
|
| 632 |
+
"loss": 0.5798,
|
| 633 |
+
"step": 445
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.0441347270615564,
|
| 637 |
+
"grad_norm": 0.9666943550109863,
|
| 638 |
+
"learning_rate": 2.3325574983088652e-05,
|
| 639 |
+
"loss": 0.5409,
|
| 640 |
+
"step": 450
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.0557491289198606,
|
| 644 |
+
"grad_norm": 0.991735577583313,
|
| 645 |
+
"learning_rate": 2.3165293907853227e-05,
|
| 646 |
+
"loss": 0.5806,
|
| 647 |
+
"step": 455
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.0673635307781648,
|
| 651 |
+
"grad_norm": 0.9840120673179626,
|
| 652 |
+
"learning_rate": 2.3003676825043165e-05,
|
| 653 |
+
"loss": 0.5449,
|
| 654 |
+
"step": 460
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.0789779326364692,
|
| 658 |
+
"grad_norm": 0.908309817314148,
|
| 659 |
+
"learning_rate": 2.28407501784888e-05,
|
| 660 |
+
"loss": 0.5399,
|
| 661 |
+
"step": 465
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.0905923344947734,
|
| 665 |
+
"grad_norm": 0.895395815372467,
|
| 666 |
+
"learning_rate": 2.2676540626291643e-05,
|
| 667 |
+
"loss": 0.5555,
|
| 668 |
+
"step": 470
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.1022067363530779,
|
| 672 |
+
"grad_norm": 0.9629302620887756,
|
| 673 |
+
"learning_rate": 2.2511075036462583e-05,
|
| 674 |
+
"loss": 0.5488,
|
| 675 |
+
"step": 475
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.113821138211382,
|
| 679 |
+
"grad_norm": 0.9868640303611755,
|
| 680 |
+
"learning_rate": 2.2344380482525716e-05,
|
| 681 |
+
"loss": 0.6052,
|
| 682 |
+
"step": 480
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.1254355400696865,
|
| 686 |
+
"grad_norm": 0.9448416233062744,
|
| 687 |
+
"learning_rate": 2.217648423908857e-05,
|
| 688 |
+
"loss": 0.6069,
|
| 689 |
+
"step": 485
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.1370499419279907,
|
| 693 |
+
"grad_norm": 1.0542551279067993,
|
| 694 |
+
"learning_rate": 2.200741377737943e-05,
|
| 695 |
+
"loss": 0.5707,
|
| 696 |
+
"step": 490
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.1486643437862951,
|
| 700 |
+
"grad_norm": 0.9438780546188354,
|
| 701 |
+
"learning_rate": 2.18371967607525e-05,
|
| 702 |
+
"loss": 0.5595,
|
| 703 |
+
"step": 495
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.1602787456445993,
|
| 707 |
+
"grad_norm": 0.959209680557251,
|
| 708 |
+
"learning_rate": 2.1665861040161598e-05,
|
| 709 |
+
"loss": 0.582,
|
| 710 |
+
"step": 500
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.1718931475029035,
|
| 714 |
+
"grad_norm": 1.056666374206543,
|
| 715 |
+
"learning_rate": 2.149343464960318e-05,
|
| 716 |
+
"loss": 0.5928,
|
| 717 |
+
"step": 505
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.183507549361208,
|
| 721 |
+
"grad_norm": 0.9853843450546265,
|
| 722 |
+
"learning_rate": 2.1319945801529425e-05,
|
| 723 |
+
"loss": 0.5713,
|
| 724 |
+
"step": 510
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.1951219512195121,
|
| 728 |
+
"grad_norm": 1.1093785762786865,
|
| 729 |
+
"learning_rate": 2.1145422882232085e-05,
|
| 730 |
+
"loss": 0.5636,
|
| 731 |
+
"step": 515
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.2067363530778166,
|
| 735 |
+
"grad_norm": 1.055412769317627,
|
| 736 |
+
"learning_rate": 2.0969894447197927e-05,
|
| 737 |
+
"loss": 0.5334,
|
| 738 |
+
"step": 520
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.2183507549361208,
|
| 742 |
+
"grad_norm": 0.921072781085968,
|
| 743 |
+
"learning_rate": 2.0793389216436477e-05,
|
| 744 |
+
"loss": 0.5418,
|
| 745 |
+
"step": 525
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.229965156794425,
|
| 749 |
+
"grad_norm": 0.9304271340370178,
|
| 750 |
+
"learning_rate": 2.0615936069780826e-05,
|
| 751 |
+
"loss": 0.496,
|
| 752 |
+
"step": 530
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.2415795586527294,
|
| 756 |
+
"grad_norm": 0.9475392699241638,
|
| 757 |
+
"learning_rate": 2.043756404216233e-05,
|
| 758 |
+
"loss": 0.5214,
|
| 759 |
+
"step": 535
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.2531939605110336,
|
| 763 |
+
"grad_norm": 0.9725027084350586,
|
| 764 |
+
"learning_rate": 2.0258302318859882e-05,
|
| 765 |
+
"loss": 0.5317,
|
| 766 |
+
"step": 540
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.264808362369338,
|
| 770 |
+
"grad_norm": 1.0067145824432373,
|
| 771 |
+
"learning_rate": 2.0078180230724645e-05,
|
| 772 |
+
"loss": 0.4972,
|
| 773 |
+
"step": 545
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.2764227642276422,
|
| 777 |
+
"grad_norm": 1.0448566675186157,
|
| 778 |
+
"learning_rate": 1.9897227249380873e-05,
|
| 779 |
+
"loss": 0.5188,
|
| 780 |
+
"step": 550
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.2880371660859466,
|
| 784 |
+
"grad_norm": 0.9800556302070618,
|
| 785 |
+
"learning_rate": 1.971547298240381e-05,
|
| 786 |
+
"loss": 0.5429,
|
| 787 |
+
"step": 555
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.2996515679442509,
|
| 791 |
+
"grad_norm": 1.0093374252319336,
|
| 792 |
+
"learning_rate": 1.953294716847527e-05,
|
| 793 |
+
"loss": 0.518,
|
| 794 |
+
"step": 560
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.3112659698025553,
|
| 798 |
+
"grad_norm": 0.8734726309776306,
|
| 799 |
+
"learning_rate": 1.9349679672517778e-05,
|
| 800 |
+
"loss": 0.4876,
|
| 801 |
+
"step": 565
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.3228803716608595,
|
| 805 |
+
"grad_norm": 1.1090798377990723,
|
| 806 |
+
"learning_rate": 1.9165700480808073e-05,
|
| 807 |
+
"loss": 0.5526,
|
| 808 |
+
"step": 570
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.3344947735191637,
|
| 812 |
+
"grad_norm": 1.0246576070785522,
|
| 813 |
+
"learning_rate": 1.8981039696070744e-05,
|
| 814 |
+
"loss": 0.5061,
|
| 815 |
+
"step": 575
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.346109175377468,
|
| 819 |
+
"grad_norm": 1.0585824251174927,
|
| 820 |
+
"learning_rate": 1.879572753255282e-05,
|
| 821 |
+
"loss": 0.48,
|
| 822 |
+
"step": 580
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.3577235772357723,
|
| 826 |
+
"grad_norm": 0.9529991745948792,
|
| 827 |
+
"learning_rate": 1.8609794311080093e-05,
|
| 828 |
+
"loss": 0.5082,
|
| 829 |
+
"step": 585
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.3693379790940767,
|
| 833 |
+
"grad_norm": 0.991818368434906,
|
| 834 |
+
"learning_rate": 1.842327045409602e-05,
|
| 835 |
+
"loss": 0.4937,
|
| 836 |
+
"step": 590
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.380952380952381,
|
| 840 |
+
"grad_norm": 0.9719640016555786,
|
| 841 |
+
"learning_rate": 1.8236186480684006e-05,
|
| 842 |
+
"loss": 0.4753,
|
| 843 |
+
"step": 595
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.3925667828106851,
|
| 847 |
+
"grad_norm": 1.0128206014633179,
|
| 848 |
+
"learning_rate": 1.8048573001573856e-05,
|
| 849 |
+
"loss": 0.5529,
|
| 850 |
+
"step": 600
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.4041811846689896,
|
| 854 |
+
"grad_norm": 0.9569838047027588,
|
| 855 |
+
"learning_rate": 1.786046071413324e-05,
|
| 856 |
+
"loss": 0.4864,
|
| 857 |
+
"step": 605
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.415795586527294,
|
| 861 |
+
"grad_norm": 0.9988173842430115,
|
| 862 |
+
"learning_rate": 1.7671880397344973e-05,
|
| 863 |
+
"loss": 0.451,
|
| 864 |
+
"step": 610
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.4274099883855982,
|
| 868 |
+
"grad_norm": 1.0235010385513306,
|
| 869 |
+
"learning_rate": 1.7482862906770957e-05,
|
| 870 |
+
"loss": 0.5122,
|
| 871 |
+
"step": 615
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.4390243902439024,
|
| 875 |
+
"grad_norm": 1.152029275894165,
|
| 876 |
+
"learning_rate": 1.72934391695036e-05,
|
| 877 |
+
"loss": 0.4664,
|
| 878 |
+
"step": 620
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.4506387921022068,
|
| 882 |
+
"grad_norm": 1.1890580654144287,
|
| 883 |
+
"learning_rate": 1.710364017910549e-05,
|
| 884 |
+
"loss": 0.4704,
|
| 885 |
+
"step": 625
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.462253193960511,
|
| 889 |
+
"grad_norm": 1.0152846574783325,
|
| 890 |
+
"learning_rate": 1.6913496990538227e-05,
|
| 891 |
+
"loss": 0.5124,
|
| 892 |
+
"step": 630
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 1.4738675958188154,
|
| 896 |
+
"grad_norm": 1.0904698371887207,
|
| 897 |
+
"learning_rate": 1.6723040715081228e-05,
|
| 898 |
+
"loss": 0.4861,
|
| 899 |
+
"step": 635
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 1.4854819976771196,
|
| 903 |
+
"grad_norm": 1.0022042989730835,
|
| 904 |
+
"learning_rate": 1.6532302515241254e-05,
|
| 905 |
+
"loss": 0.4891,
|
| 906 |
+
"step": 640
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.4970963995354238,
|
| 910 |
+
"grad_norm": 0.9874012470245361,
|
| 911 |
+
"learning_rate": 1.634131359965362e-05,
|
| 912 |
+
"loss": 0.5167,
|
| 913 |
+
"step": 645
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.5087108013937283,
|
| 917 |
+
"grad_norm": 0.9787576794624329,
|
| 918 |
+
"learning_rate": 1.6150105217975794e-05,
|
| 919 |
+
"loss": 0.5184,
|
| 920 |
+
"step": 650
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.5203252032520327,
|
| 924 |
+
"grad_norm": 0.9576313495635986,
|
| 925 |
+
"learning_rate": 1.5958708655774387e-05,
|
| 926 |
+
"loss": 0.4847,
|
| 927 |
+
"step": 655
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.5319396051103369,
|
| 931 |
+
"grad_norm": 1.0970077514648438,
|
| 932 |
+
"learning_rate": 1.576715522940612e-05,
|
| 933 |
+
"loss": 0.4991,
|
| 934 |
+
"step": 660
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.543554006968641,
|
| 938 |
+
"grad_norm": 1.065991997718811,
|
| 939 |
+
"learning_rate": 1.557547628089389e-05,
|
| 940 |
+
"loss": 0.4761,
|
| 941 |
+
"step": 665
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.5551684088269453,
|
| 945 |
+
"grad_norm": 1.136781930923462,
|
| 946 |
+
"learning_rate": 1.538370317279855e-05,
|
| 947 |
+
"loss": 0.4695,
|
| 948 |
+
"step": 670
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 1.5667828106852497,
|
| 952 |
+
"grad_norm": 1.0636974573135376,
|
| 953 |
+
"learning_rate": 1.5191867283087384e-05,
|
| 954 |
+
"loss": 0.4477,
|
| 955 |
+
"step": 675
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.5783972125435541,
|
| 959 |
+
"grad_norm": 1.1356184482574463,
|
| 960 |
+
"learning_rate": 1.5e-05,
|
| 961 |
+
"loss": 0.4324,
|
| 962 |
+
"step": 680
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.5900116144018583,
|
| 966 |
+
"grad_norm": 1.1115050315856934,
|
| 967 |
+
"learning_rate": 1.480813271691262e-05,
|
| 968 |
+
"loss": 0.3999,
|
| 969 |
+
"step": 685
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.6016260162601625,
|
| 973 |
+
"grad_norm": 1.0832542181015015,
|
| 974 |
+
"learning_rate": 1.4616296827201453e-05,
|
| 975 |
+
"loss": 0.4461,
|
| 976 |
+
"step": 690
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.6132404181184667,
|
| 980 |
+
"grad_norm": 1.0706605911254883,
|
| 981 |
+
"learning_rate": 1.4424523719106112e-05,
|
| 982 |
+
"loss": 0.4653,
|
| 983 |
+
"step": 695
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.6248548199767712,
|
| 987 |
+
"grad_norm": 1.0427998304367065,
|
| 988 |
+
"learning_rate": 1.4232844770593881e-05,
|
| 989 |
+
"loss": 0.4318,
|
| 990 |
+
"step": 700
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.6364692218350756,
|
| 994 |
+
"grad_norm": 1.127982258796692,
|
| 995 |
+
"learning_rate": 1.4041291344225615e-05,
|
| 996 |
+
"loss": 0.4475,
|
| 997 |
+
"step": 705
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 1.6480836236933798,
|
| 1001 |
+
"grad_norm": 1.1579025983810425,
|
| 1002 |
+
"learning_rate": 1.3849894782024207e-05,
|
| 1003 |
+
"loss": 0.4715,
|
| 1004 |
+
"step": 710
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.659698025551684,
|
| 1008 |
+
"grad_norm": 1.0416160821914673,
|
| 1009 |
+
"learning_rate": 1.3658686400346386e-05,
|
| 1010 |
+
"loss": 0.46,
|
| 1011 |
+
"step": 715
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 1.6713124274099884,
|
| 1015 |
+
"grad_norm": 0.9889193177223206,
|
| 1016 |
+
"learning_rate": 1.3467697484758746e-05,
|
| 1017 |
+
"loss": 0.4903,
|
| 1018 |
+
"step": 720
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.6829268292682928,
|
| 1022 |
+
"grad_norm": 0.9814087152481079,
|
| 1023 |
+
"learning_rate": 1.3276959284918774e-05,
|
| 1024 |
+
"loss": 0.4239,
|
| 1025 |
+
"step": 725
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 1.694541231126597,
|
| 1029 |
+
"grad_norm": 1.0258443355560303,
|
| 1030 |
+
"learning_rate": 1.3086503009461775e-05,
|
| 1031 |
+
"loss": 0.4665,
|
| 1032 |
+
"step": 730
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 1.7061556329849012,
|
| 1036 |
+
"grad_norm": 1.0588767528533936,
|
| 1037 |
+
"learning_rate": 1.2896359820894514e-05,
|
| 1038 |
+
"loss": 0.4374,
|
| 1039 |
+
"step": 735
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 1.7177700348432055,
|
| 1043 |
+
"grad_norm": 1.1612567901611328,
|
| 1044 |
+
"learning_rate": 1.2706560830496401e-05,
|
| 1045 |
+
"loss": 0.4354,
|
| 1046 |
+
"step": 740
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.7293844367015099,
|
| 1050 |
+
"grad_norm": 1.0602537393569946,
|
| 1051 |
+
"learning_rate": 1.2517137093229043e-05,
|
| 1052 |
+
"loss": 0.3714,
|
| 1053 |
+
"step": 745
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 1.7409988385598143,
|
| 1057 |
+
"grad_norm": 1.03526771068573,
|
| 1058 |
+
"learning_rate": 1.2328119602655031e-05,
|
| 1059 |
+
"loss": 0.4183,
|
| 1060 |
+
"step": 750
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 1.7526132404181185,
|
| 1064 |
+
"grad_norm": 1.3858877420425415,
|
| 1065 |
+
"learning_rate": 1.2139539285866758e-05,
|
| 1066 |
+
"loss": 0.4428,
|
| 1067 |
+
"step": 755
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 1.7642276422764227,
|
| 1071 |
+
"grad_norm": 1.0921659469604492,
|
| 1072 |
+
"learning_rate": 1.1951426998426143e-05,
|
| 1073 |
+
"loss": 0.4248,
|
| 1074 |
+
"step": 760
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.775842044134727,
|
| 1078 |
+
"grad_norm": 1.0866457223892212,
|
| 1079 |
+
"learning_rate": 1.1763813519315994e-05,
|
| 1080 |
+
"loss": 0.4604,
|
| 1081 |
+
"step": 765
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 1.7874564459930313,
|
| 1085 |
+
"grad_norm": 1.1888844966888428,
|
| 1086 |
+
"learning_rate": 1.1576729545903983e-05,
|
| 1087 |
+
"loss": 0.4036,
|
| 1088 |
+
"step": 770
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 1.7990708478513358,
|
| 1092 |
+
"grad_norm": 1.0188145637512207,
|
| 1093 |
+
"learning_rate": 1.1390205688919908e-05,
|
| 1094 |
+
"loss": 0.3986,
|
| 1095 |
+
"step": 775
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 1.81068524970964,
|
| 1099 |
+
"grad_norm": 1.1359866857528687,
|
| 1100 |
+
"learning_rate": 1.1204272467447177e-05,
|
| 1101 |
+
"loss": 0.428,
|
| 1102 |
+
"step": 780
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 1.8222996515679442,
|
| 1106 |
+
"grad_norm": 1.0662692785263062,
|
| 1107 |
+
"learning_rate": 1.1018960303929253e-05,
|
| 1108 |
+
"loss": 0.4188,
|
| 1109 |
+
"step": 785
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 1.8339140534262486,
|
| 1113 |
+
"grad_norm": 1.0792381763458252,
|
| 1114 |
+
"learning_rate": 1.0834299519191928e-05,
|
| 1115 |
+
"loss": 0.3942,
|
| 1116 |
+
"step": 790
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 1.845528455284553,
|
| 1120 |
+
"grad_norm": 1.0623815059661865,
|
| 1121 |
+
"learning_rate": 1.0650320327482223e-05,
|
| 1122 |
+
"loss": 0.3978,
|
| 1123 |
+
"step": 795
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 1.8571428571428572,
|
| 1127 |
+
"grad_norm": 1.1844643354415894,
|
| 1128 |
+
"learning_rate": 1.046705283152473e-05,
|
| 1129 |
+
"loss": 0.4163,
|
| 1130 |
+
"step": 800
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 1.8687572590011614,
|
| 1134 |
+
"grad_norm": 1.0871316194534302,
|
| 1135 |
+
"learning_rate": 1.028452701759619e-05,
|
| 1136 |
+
"loss": 0.436,
|
| 1137 |
+
"step": 805
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 1.8803716608594656,
|
| 1141 |
+
"grad_norm": 1.1240311861038208,
|
| 1142 |
+
"learning_rate": 1.010277275061913e-05,
|
| 1143 |
+
"loss": 0.4137,
|
| 1144 |
+
"step": 810
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 1.89198606271777,
|
| 1148 |
+
"grad_norm": 1.019579291343689,
|
| 1149 |
+
"learning_rate": 9.921819769275356e-06,
|
| 1150 |
+
"loss": 0.338,
|
| 1151 |
+
"step": 815
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.9036004645760745,
|
| 1155 |
+
"grad_norm": 1.1016135215759277,
|
| 1156 |
+
"learning_rate": 9.741697681140113e-06,
|
| 1157 |
+
"loss": 0.3778,
|
| 1158 |
+
"step": 820
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 1.9152148664343787,
|
| 1162 |
+
"grad_norm": 1.0139800310134888,
|
| 1163 |
+
"learning_rate": 9.562435957837673e-06,
|
| 1164 |
+
"loss": 0.3907,
|
| 1165 |
+
"step": 825
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 1.9268292682926829,
|
| 1169 |
+
"grad_norm": 1.1818102598190308,
|
| 1170 |
+
"learning_rate": 9.384063930219178e-06,
|
| 1171 |
+
"loss": 0.3602,
|
| 1172 |
+
"step": 830
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 1.938443670150987,
|
| 1176 |
+
"grad_norm": 0.9864258170127869,
|
| 1177 |
+
"learning_rate": 9.20661078356353e-06,
|
| 1178 |
+
"loss": 0.343,
|
| 1179 |
+
"step": 835
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 1.9500580720092915,
|
| 1183 |
+
"grad_norm": 1.038926601409912,
|
| 1184 |
+
"learning_rate": 9.030105552802077e-06,
|
| 1185 |
+
"loss": 0.39,
|
| 1186 |
+
"step": 840
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 1.961672473867596,
|
| 1190 |
+
"grad_norm": 0.9714798927307129,
|
| 1191 |
+
"learning_rate": 8.854577117767922e-06,
|
| 1192 |
+
"loss": 0.3602,
|
| 1193 |
+
"step": 845
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 1.9732868757259001,
|
| 1197 |
+
"grad_norm": 1.0614789724349976,
|
| 1198 |
+
"learning_rate": 8.680054198470581e-06,
|
| 1199 |
+
"loss": 0.3859,
|
| 1200 |
+
"step": 850
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 1.9849012775842043,
|
| 1204 |
+
"grad_norm": 1.1027911901474,
|
| 1205 |
+
"learning_rate": 8.506565350396824e-06,
|
| 1206 |
+
"loss": 0.4069,
|
| 1207 |
+
"step": 855
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 1.9965156794425087,
|
| 1211 |
+
"grad_norm": 1.1654589176177979,
|
| 1212 |
+
"learning_rate": 8.334138959838404e-06,
|
| 1213 |
+
"loss": 0.3802,
|
| 1214 |
+
"step": 860
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 2.0069686411149825,
|
| 1218 |
+
"grad_norm": 0.8810543417930603,
|
| 1219 |
+
"learning_rate": 8.162803239247503e-06,
|
| 1220 |
+
"loss": 0.3578,
|
| 1221 |
+
"step": 865
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 2.0185830429732867,
|
| 1225 |
+
"grad_norm": 1.1703990697860718,
|
| 1226 |
+
"learning_rate": 7.99258622262057e-06,
|
| 1227 |
+
"loss": 0.3419,
|
| 1228 |
+
"step": 870
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 2.0301974448315914,
|
| 1232 |
+
"grad_norm": 1.094256043434143,
|
| 1233 |
+
"learning_rate": 7.823515760911436e-06,
|
| 1234 |
+
"loss": 0.3105,
|
| 1235 |
+
"step": 875
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 2.0418118466898956,
|
| 1239 |
+
"grad_norm": 1.0097821950912476,
|
| 1240 |
+
"learning_rate": 7.655619517474288e-06,
|
| 1241 |
+
"loss": 0.3196,
|
| 1242 |
+
"step": 880
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 2.0534262485481998,
|
| 1246 |
+
"grad_norm": 1.013162612915039,
|
| 1247 |
+
"learning_rate": 7.488924963537418e-06,
|
| 1248 |
+
"loss": 0.3148,
|
| 1249 |
+
"step": 885
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 2.065040650406504,
|
| 1253 |
+
"grad_norm": 1.051941156387329,
|
| 1254 |
+
"learning_rate": 7.323459373708364e-06,
|
| 1255 |
+
"loss": 0.3155,
|
| 1256 |
+
"step": 890
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 2.076655052264808,
|
| 1260 |
+
"grad_norm": 1.172757863998413,
|
| 1261 |
+
"learning_rate": 7.1592498215112075e-06,
|
| 1262 |
+
"loss": 0.3207,
|
| 1263 |
+
"step": 895
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 2.088269454123113,
|
| 1267 |
+
"grad_norm": 1.209959626197815,
|
| 1268 |
+
"learning_rate": 6.996323174956836e-06,
|
| 1269 |
+
"loss": 0.3182,
|
| 1270 |
+
"step": 900
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 2.099883855981417,
|
| 1274 |
+
"grad_norm": 0.9459628462791443,
|
| 1275 |
+
"learning_rate": 6.8347060921467735e-06,
|
| 1276 |
+
"loss": 0.314,
|
| 1277 |
+
"step": 905
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 2.1114982578397212,
|
| 1281 |
+
"grad_norm": 0.980540931224823,
|
| 1282 |
+
"learning_rate": 6.674425016911355e-06,
|
| 1283 |
+
"loss": 0.2989,
|
| 1284 |
+
"step": 910
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 2.1231126596980254,
|
| 1288 |
+
"grad_norm": 1.1647413969039917,
|
| 1289 |
+
"learning_rate": 6.515506174483018e-06,
|
| 1290 |
+
"loss": 0.2964,
|
| 1291 |
+
"step": 915
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 2.1347270615563296,
|
| 1295 |
+
"grad_norm": 1.052589774131775,
|
| 1296 |
+
"learning_rate": 6.3579755672052885e-06,
|
| 1297 |
+
"loss": 0.3124,
|
| 1298 |
+
"step": 920
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 2.1463414634146343,
|
| 1302 |
+
"grad_norm": 1.0232487916946411,
|
| 1303 |
+
"learning_rate": 6.201858970278294e-06,
|
| 1304 |
+
"loss": 0.358,
|
| 1305 |
+
"step": 925
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 2.1579558652729385,
|
| 1309 |
+
"grad_norm": 1.2013530731201172,
|
| 1310 |
+
"learning_rate": 6.047181927541417e-06,
|
| 1311 |
+
"loss": 0.3343,
|
| 1312 |
+
"step": 930
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 2.1695702671312427,
|
| 1316 |
+
"grad_norm": 0.9949542880058289,
|
| 1317 |
+
"learning_rate": 5.893969747293777e-06,
|
| 1318 |
+
"loss": 0.3133,
|
| 1319 |
+
"step": 935
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 2.181184668989547,
|
| 1323 |
+
"grad_norm": 1.1188600063323975,
|
| 1324 |
+
"learning_rate": 5.742247498153319e-06,
|
| 1325 |
+
"loss": 0.2977,
|
| 1326 |
+
"step": 940
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 2.1927990708478515,
|
| 1330 |
+
"grad_norm": 1.1514487266540527,
|
| 1331 |
+
"learning_rate": 5.592040004955061e-06,
|
| 1332 |
+
"loss": 0.326,
|
| 1333 |
+
"step": 945
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 2.2044134727061557,
|
| 1337 |
+
"grad_norm": 1.2033545970916748,
|
| 1338 |
+
"learning_rate": 5.4433718446892334e-06,
|
| 1339 |
+
"loss": 0.2963,
|
| 1340 |
+
"step": 950
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 2.21602787456446,
|
| 1344 |
+
"grad_norm": 1.0538955926895142,
|
| 1345 |
+
"learning_rate": 5.29626734248002e-06,
|
| 1346 |
+
"loss": 0.2924,
|
| 1347 |
+
"step": 955
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 2.227642276422764,
|
| 1351 |
+
"grad_norm": 1.198915719985962,
|
| 1352 |
+
"learning_rate": 5.150750567605435e-06,
|
| 1353 |
+
"loss": 0.3074,
|
| 1354 |
+
"step": 960
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 2.2392566782810683,
|
| 1358 |
+
"grad_norm": 1.136529564857483,
|
| 1359 |
+
"learning_rate": 5.0068453295591346e-06,
|
| 1360 |
+
"loss": 0.3147,
|
| 1361 |
+
"step": 965
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 2.250871080139373,
|
| 1365 |
+
"grad_norm": 1.2167537212371826,
|
| 1366 |
+
"learning_rate": 4.864575174154692e-06,
|
| 1367 |
+
"loss": 0.2943,
|
| 1368 |
+
"step": 970
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 2.262485481997677,
|
| 1372 |
+
"grad_norm": 1.0729284286499023,
|
| 1373 |
+
"learning_rate": 4.723963379673002e-06,
|
| 1374 |
+
"loss": 0.291,
|
| 1375 |
+
"step": 975
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 2.2740998838559814,
|
| 1379 |
+
"grad_norm": 1.017930030822754,
|
| 1380 |
+
"learning_rate": 4.585032953053515e-06,
|
| 1381 |
+
"loss": 0.3062,
|
| 1382 |
+
"step": 980
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 2.2857142857142856,
|
| 1386 |
+
"grad_norm": 1.1780880689620972,
|
| 1387 |
+
"learning_rate": 4.447806626129828e-06,
|
| 1388 |
+
"loss": 0.2673,
|
| 1389 |
+
"step": 985
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 2.2973286875725902,
|
| 1393 |
+
"grad_norm": 1.2414166927337646,
|
| 1394 |
+
"learning_rate": 4.31230685191027e-06,
|
| 1395 |
+
"loss": 0.3006,
|
| 1396 |
+
"step": 990
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 2.3089430894308944,
|
| 1400 |
+
"grad_norm": 1.160487174987793,
|
| 1401 |
+
"learning_rate": 4.178555800904174e-06,
|
| 1402 |
+
"loss": 0.3004,
|
| 1403 |
+
"step": 995
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 2.3205574912891986,
|
| 1407 |
+
"grad_norm": 1.17868173122406,
|
| 1408 |
+
"learning_rate": 4.0465753574942935e-06,
|
| 1409 |
+
"loss": 0.2868,
|
| 1410 |
+
"step": 1000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 2.332171893147503,
|
| 1414 |
+
"grad_norm": 1.1315648555755615,
|
| 1415 |
+
"learning_rate": 3.916387116356113e-06,
|
| 1416 |
+
"loss": 0.2965,
|
| 1417 |
+
"step": 1005
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 2.343786295005807,
|
| 1421 |
+
"grad_norm": 1.1295381784439087,
|
| 1422 |
+
"learning_rate": 3.788012378924493e-06,
|
| 1423 |
+
"loss": 0.2668,
|
| 1424 |
+
"step": 1010
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 2.3554006968641117,
|
| 1428 |
+
"grad_norm": 1.0476168394088745,
|
| 1429 |
+
"learning_rate": 3.6614721499083235e-06,
|
| 1430 |
+
"loss": 0.2998,
|
| 1431 |
+
"step": 1015
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 2.367015098722416,
|
| 1435 |
+
"grad_norm": 1.119430661201477,
|
| 1436 |
+
"learning_rate": 3.5367871338537503e-06,
|
| 1437 |
+
"loss": 0.2722,
|
| 1438 |
+
"step": 1020
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 2.37862950058072,
|
| 1442 |
+
"grad_norm": 1.212213397026062,
|
| 1443 |
+
"learning_rate": 3.4139777317564763e-06,
|
| 1444 |
+
"loss": 0.2914,
|
| 1445 |
+
"step": 1025
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 2.3902439024390243,
|
| 1449 |
+
"grad_norm": 1.0197581052780151,
|
| 1450 |
+
"learning_rate": 3.2930640377237343e-06,
|
| 1451 |
+
"loss": 0.2821,
|
| 1452 |
+
"step": 1030
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 2.4018583042973285,
|
| 1456 |
+
"grad_norm": 1.0621126890182495,
|
| 1457 |
+
"learning_rate": 3.174065835686511e-06,
|
| 1458 |
+
"loss": 0.3137,
|
| 1459 |
+
"step": 1035
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 2.413472706155633,
|
| 1463 |
+
"grad_norm": 1.1943347454071045,
|
| 1464 |
+
"learning_rate": 3.0570025961624666e-06,
|
| 1465 |
+
"loss": 0.3059,
|
| 1466 |
+
"step": 1040
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 2.4250871080139373,
|
| 1470 |
+
"grad_norm": 1.1790246963500977,
|
| 1471 |
+
"learning_rate": 2.9418934730701903e-06,
|
| 1472 |
+
"loss": 0.2983,
|
| 1473 |
+
"step": 1045
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 2.4367015098722415,
|
| 1477 |
+
"grad_norm": 1.0878653526306152,
|
| 1478 |
+
"learning_rate": 2.8287573005952118e-06,
|
| 1479 |
+
"loss": 0.2866,
|
| 1480 |
+
"step": 1050
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 2.4483159117305457,
|
| 1484 |
+
"grad_norm": 1.1005710363388062,
|
| 1485 |
+
"learning_rate": 2.717612590108347e-06,
|
| 1486 |
+
"loss": 0.3107,
|
| 1487 |
+
"step": 1055
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 2.45993031358885,
|
| 1491 |
+
"grad_norm": 1.1504753828048706,
|
| 1492 |
+
"learning_rate": 2.6084775271368805e-06,
|
| 1493 |
+
"loss": 0.2875,
|
| 1494 |
+
"step": 1060
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 2.4715447154471546,
|
| 1498 |
+
"grad_norm": 1.1118510961532593,
|
| 1499 |
+
"learning_rate": 2.501369968389019e-06,
|
| 1500 |
+
"loss": 0.2843,
|
| 1501 |
+
"step": 1065
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 2.483159117305459,
|
| 1505 |
+
"grad_norm": 1.0834742784500122,
|
| 1506 |
+
"learning_rate": 2.396307438832195e-06,
|
| 1507 |
+
"loss": 0.2993,
|
| 1508 |
+
"step": 1070
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 2.494773519163763,
|
| 1512 |
+
"grad_norm": 1.2306410074234009,
|
| 1513 |
+
"learning_rate": 2.2933071288256193e-06,
|
| 1514 |
+
"loss": 0.3025,
|
| 1515 |
+
"step": 1075
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 2.506387921022067,
|
| 1519 |
+
"grad_norm": 0.9859291315078735,
|
| 1520 |
+
"learning_rate": 2.1923858913075735e-06,
|
| 1521 |
+
"loss": 0.2913,
|
| 1522 |
+
"step": 1080
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 2.5180023228803714,
|
| 1526 |
+
"grad_norm": 1.0358084440231323,
|
| 1527 |
+
"learning_rate": 2.093560239037959e-06,
|
| 1528 |
+
"loss": 0.2918,
|
| 1529 |
+
"step": 1085
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 2.529616724738676,
|
| 1533 |
+
"grad_norm": 1.0371265411376953,
|
| 1534 |
+
"learning_rate": 1.996846341896452e-06,
|
| 1535 |
+
"loss": 0.2764,
|
| 1536 |
+
"step": 1090
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 2.5412311265969802,
|
| 1540 |
+
"grad_norm": 1.1168688535690308,
|
| 1541 |
+
"learning_rate": 1.9022600242367843e-06,
|
| 1542 |
+
"loss": 0.3061,
|
| 1543 |
+
"step": 1095
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 2.5528455284552845,
|
| 1547 |
+
"grad_norm": 1.000887393951416,
|
| 1548 |
+
"learning_rate": 1.8098167622975693e-06,
|
| 1549 |
+
"loss": 0.3254,
|
| 1550 |
+
"step": 1100
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 2.564459930313589,
|
| 1554 |
+
"grad_norm": 1.1483852863311768,
|
| 1555 |
+
"learning_rate": 1.7195316816700662e-06,
|
| 1556 |
+
"loss": 0.2878,
|
| 1557 |
+
"step": 1105
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 2.5760743321718933,
|
| 1561 |
+
"grad_norm": 1.1495416164398193,
|
| 1562 |
+
"learning_rate": 1.6314195548233319e-06,
|
| 1563 |
+
"loss": 0.284,
|
| 1564 |
+
"step": 1110
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 2.5876887340301975,
|
| 1568 |
+
"grad_norm": 1.0184448957443237,
|
| 1569 |
+
"learning_rate": 1.5454947986871509e-06,
|
| 1570 |
+
"loss": 0.2905,
|
| 1571 |
+
"step": 1115
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 2.5993031358885017,
|
| 1575 |
+
"grad_norm": 1.090733528137207,
|
| 1576 |
+
"learning_rate": 1.4617714722931109e-06,
|
| 1577 |
+
"loss": 0.2635,
|
| 1578 |
+
"step": 1120
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 2.610917537746806,
|
| 1582 |
+
"grad_norm": 0.9690793752670288,
|
| 1583 |
+
"learning_rate": 1.3802632744742878e-06,
|
| 1584 |
+
"loss": 0.3299,
|
| 1585 |
+
"step": 1125
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 2.6225319396051106,
|
| 1589 |
+
"grad_norm": 1.1170541048049927,
|
| 1590 |
+
"learning_rate": 1.3009835416238296e-06,
|
| 1591 |
+
"loss": 0.2845,
|
| 1592 |
+
"step": 1130
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 2.6341463414634148,
|
| 1596 |
+
"grad_norm": 1.1148786544799805,
|
| 1597 |
+
"learning_rate": 1.2239452455128392e-06,
|
| 1598 |
+
"loss": 0.3209,
|
| 1599 |
+
"step": 1135
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 2.645760743321719,
|
| 1603 |
+
"grad_norm": 1.1871299743652344,
|
| 1604 |
+
"learning_rate": 1.1491609911679484e-06,
|
| 1605 |
+
"loss": 0.2956,
|
| 1606 |
+
"step": 1140
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 2.657375145180023,
|
| 1610 |
+
"grad_norm": 1.153961181640625,
|
| 1611 |
+
"learning_rate": 1.0766430148088686e-06,
|
| 1612 |
+
"loss": 0.2666,
|
| 1613 |
+
"step": 1145
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 2.6689895470383274,
|
| 1617 |
+
"grad_norm": 1.2079453468322754,
|
| 1618 |
+
"learning_rate": 1.0064031818462982e-06,
|
| 1619 |
+
"loss": 0.2883,
|
| 1620 |
+
"step": 1150
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 2.680603948896632,
|
| 1624 |
+
"grad_norm": 1.0874303579330444,
|
| 1625 |
+
"learning_rate": 9.384529849405077e-07,
|
| 1626 |
+
"loss": 0.2431,
|
| 1627 |
+
"step": 1155
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 2.692218350754936,
|
| 1631 |
+
"grad_norm": 1.0171637535095215,
|
| 1632 |
+
"learning_rate": 8.728035421209058e-07,
|
| 1633 |
+
"loss": 0.2774,
|
| 1634 |
+
"step": 1160
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 2.7038327526132404,
|
| 1638 |
+
"grad_norm": 0.9877467155456543,
|
| 1639 |
+
"learning_rate": 8.094655949668917e-07,
|
| 1640 |
+
"loss": 0.2673,
|
| 1641 |
+
"step": 1165
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 2.7154471544715446,
|
| 1645 |
+
"grad_norm": 1.1348854303359985,
|
| 1646 |
+
"learning_rate": 7.484495068503361e-07,
|
| 1647 |
+
"loss": 0.2752,
|
| 1648 |
+
"step": 1170
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 2.727061556329849,
|
| 1652 |
+
"grad_norm": 1.0911859273910522,
|
| 1653 |
+
"learning_rate": 6.897652612399024e-07,
|
| 1654 |
+
"loss": 0.2725,
|
| 1655 |
+
"step": 1175
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 2.7386759581881535,
|
| 1659 |
+
"grad_norm": 1.1613843441009521,
|
| 1660 |
+
"learning_rate": 6.334224600675687e-07,
|
| 1661 |
+
"loss": 0.2817,
|
| 1662 |
+
"step": 1180
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 2.7502903600464577,
|
| 1666 |
+
"grad_norm": 1.0359234809875488,
|
| 1667 |
+
"learning_rate": 5.794303221575437e-07,
|
| 1668 |
+
"loss": 0.2707,
|
| 1669 |
+
"step": 1185
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 2.761904761904762,
|
| 1673 |
+
"grad_norm": 1.0068219900131226,
|
| 1674 |
+
"learning_rate": 5.277976817178793e-07,
|
| 1675 |
+
"loss": 0.2909,
|
| 1676 |
+
"step": 1190
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 2.773519163763066,
|
| 1680 |
+
"grad_norm": 0.9488641023635864,
|
| 1681 |
+
"learning_rate": 4.785329868950278e-07,
|
| 1682 |
+
"loss": 0.284,
|
| 1683 |
+
"step": 1195
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 2.7851335656213703,
|
| 1687 |
+
"grad_norm": 1.1597959995269775,
|
| 1688 |
+
"learning_rate": 4.316442983915364e-07,
|
| 1689 |
+
"loss": 0.2874,
|
| 1690 |
+
"step": 1200
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 2.796747967479675,
|
| 1694 |
+
"grad_norm": 1.0681912899017334,
|
| 1695 |
+
"learning_rate": 3.871392881471736e-07,
|
| 1696 |
+
"loss": 0.2937,
|
| 1697 |
+
"step": 1205
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 2.808362369337979,
|
| 1701 |
+
"grad_norm": 0.9509957432746887,
|
| 1702 |
+
"learning_rate": 3.4502523808362497e-07,
|
| 1703 |
+
"loss": 0.2643,
|
| 1704 |
+
"step": 1210
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 2.8199767711962833,
|
| 1708 |
+
"grad_norm": 1.2249250411987305,
|
| 1709 |
+
"learning_rate": 3.053090389130314e-07,
|
| 1710 |
+
"loss": 0.2851,
|
| 1711 |
+
"step": 1215
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 2.831591173054588,
|
| 1715 |
+
"grad_norm": 1.1051902770996094,
|
| 1716 |
+
"learning_rate": 2.6799718901053596e-07,
|
| 1717 |
+
"loss": 0.2843,
|
| 1718 |
+
"step": 1220
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 2.8432055749128917,
|
| 1722 |
+
"grad_norm": 1.2920292615890503,
|
| 1723 |
+
"learning_rate": 2.3309579335100251e-07,
|
| 1724 |
+
"loss": 0.3155,
|
| 1725 |
+
"step": 1225
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 2.8548199767711964,
|
| 1729 |
+
"grad_norm": 1.1401209831237793,
|
| 1730 |
+
"learning_rate": 2.0061056251013175e-07,
|
| 1731 |
+
"loss": 0.2531,
|
| 1732 |
+
"step": 1230
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 2.8664343786295006,
|
| 1736 |
+
"grad_norm": 1.1830666065216064,
|
| 1737 |
+
"learning_rate": 1.7054681173009012e-07,
|
| 1738 |
+
"loss": 0.2571,
|
| 1739 |
+
"step": 1235
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 2.8780487804878048,
|
| 1743 |
+
"grad_norm": 1.0032836198806763,
|
| 1744 |
+
"learning_rate": 1.4290946004982375e-07,
|
| 1745 |
+
"loss": 0.2523,
|
| 1746 |
+
"step": 1240
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 2.8896631823461094,
|
| 1750 |
+
"grad_norm": 0.9659789204597473,
|
| 1751 |
+
"learning_rate": 1.1770302950021239e-07,
|
| 1752 |
+
"loss": 0.2761,
|
| 1753 |
+
"step": 1245
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 2.9012775842044136,
|
| 1757 |
+
"grad_norm": 1.0413161516189575,
|
| 1758 |
+
"learning_rate": 9.493164436417124e-08,
|
| 1759 |
+
"loss": 0.3343,
|
| 1760 |
+
"step": 1250
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 2.912891986062718,
|
| 1764 |
+
"grad_norm": 0.995083212852478,
|
| 1765 |
+
"learning_rate": 7.459903050182903e-08,
|
| 1766 |
+
"loss": 0.2817,
|
| 1767 |
+
"step": 1255
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 2.924506387921022,
|
| 1771 |
+
"grad_norm": 1.0436125993728638,
|
| 1772 |
+
"learning_rate": 5.6708514740907434e-08,
|
| 1773 |
+
"loss": 0.2674,
|
| 1774 |
+
"step": 1260
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 2.9361207897793262,
|
| 1778 |
+
"grad_norm": 1.1036518812179565,
|
| 1779 |
+
"learning_rate": 4.126302433238638e-08,
|
| 1780 |
+
"loss": 0.3021,
|
| 1781 |
+
"step": 1265
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 2.947735191637631,
|
| 1785 |
+
"grad_norm": 1.0590194463729858,
|
| 1786 |
+
"learning_rate": 2.826508647153725e-08,
|
| 1787 |
+
"loss": 0.2548,
|
| 1788 |
+
"step": 1270
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 2.959349593495935,
|
| 1792 |
+
"grad_norm": 1.1428706645965576,
|
| 1793 |
+
"learning_rate": 1.7716827884435295e-08,
|
| 1794 |
+
"loss": 0.2704,
|
| 1795 |
+
"step": 1275
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 2.9709639953542393,
|
| 1799 |
+
"grad_norm": 1.0792584419250488,
|
| 1800 |
+
"learning_rate": 9.61997447996965e-09,
|
| 1801 |
+
"loss": 0.2867,
|
| 1802 |
+
"step": 1280
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 2.9825783972125435,
|
| 1806 |
+
"grad_norm": 1.0899779796600342,
|
| 1807 |
+
"learning_rate": 3.975851067464231e-09,
|
| 1808 |
+
"loss": 0.2644,
|
| 1809 |
+
"step": 1285
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 2.9941927990708477,
|
| 1813 |
+
"grad_norm": 1.174023151397705,
|
| 1814 |
+
"learning_rate": 7.853811399027854e-10,
|
| 1815 |
+
"loss": 0.2955,
|
| 1816 |
+
"step": 1290
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 3.0,
|
| 1820 |
+
"step": 1293,
|
| 1821 |
+
"total_flos": 2.0359870555944387e+18,
|
| 1822 |
+
"train_loss": 0.5806684772450151,
|
| 1823 |
+
"train_runtime": 1005.3243,
|
| 1824 |
+
"train_samples_per_second": 41.1,
|
| 1825 |
+
"train_steps_per_second": 1.286
|
| 1826 |
+
}
|
| 1827 |
+
],
|
| 1828 |
+
"logging_steps": 5,
|
| 1829 |
+
"max_steps": 1293,
|
| 1830 |
+
"num_input_tokens_seen": 0,
|
| 1831 |
+
"num_train_epochs": 3,
|
| 1832 |
+
"save_steps": 20000,
|
| 1833 |
+
"stateful_callbacks": {
|
| 1834 |
+
"TrainerControl": {
|
| 1835 |
+
"args": {
|
| 1836 |
+
"should_epoch_stop": false,
|
| 1837 |
+
"should_evaluate": false,
|
| 1838 |
+
"should_log": false,
|
| 1839 |
+
"should_save": false,
|
| 1840 |
+
"should_training_stop": false
|
| 1841 |
+
},
|
| 1842 |
+
"attributes": {}
|
| 1843 |
+
}
|
| 1844 |
+
},
|
| 1845 |
+
"total_flos": 2.0359870555944387e+18,
|
| 1846 |
+
"train_batch_size": 2,
|
| 1847 |
+
"trial_name": null,
|
| 1848 |
+
"trial_params": null
|
| 1849 |
+
}
|
25_128_e3_3e-5/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:698efa641c4b78c546e5f7c4fc4ef0bc2e87aae8ac996cd858aca4ba2b4e39d6
|
| 3 |
+
size 8209
|
25_128_e3_3e-5/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|