Upload 10 files
Browse files- added_tokens.json +5 -0
- config.json +28 -0
- generation_config.json +12 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +20 -0
- tokenizer_config.json +44 -0
- trainer_state.json +1346 -0
- training_args.bin +3 -0
- vocab.json +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|endoftext|>": 151643,
|
| 3 |
+
"<|im_end|>": 151645,
|
| 4 |
+
"<|im_start|>": 151644
|
| 5 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/cpfs01/shared/public/ADLab/hug_ckpts/Qwen1.5-1.8B-Chat",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Qwen2ForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"eos_token_id": 151645,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 2048,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 5504,
|
| 13 |
+
"max_position_embeddings": 32768,
|
| 14 |
+
"max_window_layers": 21,
|
| 15 |
+
"model_type": "qwen2",
|
| 16 |
+
"num_attention_heads": 16,
|
| 17 |
+
"num_hidden_layers": 24,
|
| 18 |
+
"num_key_value_heads": 16,
|
| 19 |
+
"rms_norm_eps": 1e-06,
|
| 20 |
+
"rope_theta": 1000000.0,
|
| 21 |
+
"sliding_window": 32768,
|
| 22 |
+
"tie_word_embeddings": false,
|
| 23 |
+
"torch_dtype": "bfloat16",
|
| 24 |
+
"transformers_version": "4.38.1",
|
| 25 |
+
"use_cache": false,
|
| 26 |
+
"use_sliding_window": false,
|
| 27 |
+
"vocab_size": 151936
|
| 28 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"repetition_penalty": 1.1,
|
| 10 |
+
"top_p": 0.8,
|
| 11 |
+
"transformers_version": "4.38.1"
|
| 12 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91db2bb1215853a60a6a80e7096d9848bfc09c136c151e53eb495f4a0615c842
|
| 3 |
+
size 3673690696
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>"
|
| 5 |
+
],
|
| 6 |
+
"eos_token": {
|
| 7 |
+
"content": "<|im_end|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false
|
| 12 |
+
},
|
| 13 |
+
"pad_token": {
|
| 14 |
+
"content": "<|endoftext|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false
|
| 19 |
+
}
|
| 20 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"151643": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"151644": {
|
| 13 |
+
"content": "<|im_start|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"151645": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
}
|
| 28 |
+
},
|
| 29 |
+
"additional_special_tokens": [
|
| 30 |
+
"<|im_start|>",
|
| 31 |
+
"<|im_end|>"
|
| 32 |
+
],
|
| 33 |
+
"bos_token": null,
|
| 34 |
+
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content']}}{% if (loop.last and add_generation_prompt) or not loop.last %}{{ '<|im_end|>' + '\n'}}{% endif %}{% endfor %}{% if add_generation_prompt and messages[-1]['role'] != 'assistant' %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 35 |
+
"clean_up_tokenization_spaces": false,
|
| 36 |
+
"eos_token": "<|im_end|>",
|
| 37 |
+
"errors": "replace",
|
| 38 |
+
"model_max_length": 8096,
|
| 39 |
+
"pad_token": "<|endoftext|>",
|
| 40 |
+
"padding_side": "right",
|
| 41 |
+
"split_special_tokens": false,
|
| 42 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 43 |
+
"unk_token": null
|
| 44 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1346 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9966865473823724,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 188,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"grad_norm": 3.1747286526672185,
|
| 14 |
+
"learning_rate": 0.0,
|
| 15 |
+
"loss": 0.6071,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.01,
|
| 20 |
+
"grad_norm": 2.8744278125811684,
|
| 21 |
+
"learning_rate": 1e-05,
|
| 22 |
+
"loss": 0.5879,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.02,
|
| 27 |
+
"grad_norm": 2.96401630751086,
|
| 28 |
+
"learning_rate": 1e-05,
|
| 29 |
+
"loss": 0.5972,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.02,
|
| 34 |
+
"grad_norm": 2.5711555686938237,
|
| 35 |
+
"learning_rate": 1e-05,
|
| 36 |
+
"loss": 0.5716,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.03,
|
| 41 |
+
"grad_norm": 2.3039082327504756,
|
| 42 |
+
"learning_rate": 1e-05,
|
| 43 |
+
"loss": 0.5343,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.03,
|
| 48 |
+
"grad_norm": 1.6528760769327044,
|
| 49 |
+
"learning_rate": 1e-05,
|
| 50 |
+
"loss": 0.4759,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.04,
|
| 55 |
+
"grad_norm": 1.5057635329920682,
|
| 56 |
+
"learning_rate": 1e-05,
|
| 57 |
+
"loss": 0.4635,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.04,
|
| 62 |
+
"grad_norm": 1.4512874366733575,
|
| 63 |
+
"learning_rate": 1e-05,
|
| 64 |
+
"loss": 0.4533,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.05,
|
| 69 |
+
"grad_norm": 1.0385378050217222,
|
| 70 |
+
"learning_rate": 1e-05,
|
| 71 |
+
"loss": 0.3828,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.05,
|
| 76 |
+
"grad_norm": 1.0514739720980217,
|
| 77 |
+
"learning_rate": 1e-05,
|
| 78 |
+
"loss": 0.3911,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.06,
|
| 83 |
+
"grad_norm": 0.9837237195742387,
|
| 84 |
+
"learning_rate": 1e-05,
|
| 85 |
+
"loss": 0.3603,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.06,
|
| 90 |
+
"grad_norm": 0.9688775834776646,
|
| 91 |
+
"learning_rate": 1e-05,
|
| 92 |
+
"loss": 0.3533,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.07,
|
| 97 |
+
"grad_norm": 0.8654392700384863,
|
| 98 |
+
"learning_rate": 1e-05,
|
| 99 |
+
"loss": 0.3409,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.07,
|
| 104 |
+
"grad_norm": 0.8546547238317309,
|
| 105 |
+
"learning_rate": 1e-05,
|
| 106 |
+
"loss": 0.3371,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.08,
|
| 111 |
+
"grad_norm": 0.7680641258209508,
|
| 112 |
+
"learning_rate": 1e-05,
|
| 113 |
+
"loss": 0.3376,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.08,
|
| 118 |
+
"grad_norm": 0.7158077090915566,
|
| 119 |
+
"learning_rate": 1e-05,
|
| 120 |
+
"loss": 0.3124,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.09,
|
| 125 |
+
"grad_norm": 0.6437657576240935,
|
| 126 |
+
"learning_rate": 1e-05,
|
| 127 |
+
"loss": 0.3026,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.1,
|
| 132 |
+
"grad_norm": 0.6181079816147165,
|
| 133 |
+
"learning_rate": 1e-05,
|
| 134 |
+
"loss": 0.309,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.1,
|
| 139 |
+
"grad_norm": 0.5631504450561933,
|
| 140 |
+
"learning_rate": 1e-05,
|
| 141 |
+
"loss": 0.2937,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.11,
|
| 146 |
+
"grad_norm": 0.5074636865803471,
|
| 147 |
+
"learning_rate": 1e-05,
|
| 148 |
+
"loss": 0.2766,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.11,
|
| 153 |
+
"grad_norm": 0.5348837661889406,
|
| 154 |
+
"learning_rate": 1e-05,
|
| 155 |
+
"loss": 0.2945,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.12,
|
| 160 |
+
"grad_norm": 0.464888526177443,
|
| 161 |
+
"learning_rate": 1e-05,
|
| 162 |
+
"loss": 0.273,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.12,
|
| 167 |
+
"grad_norm": 0.4631046843104534,
|
| 168 |
+
"learning_rate": 1e-05,
|
| 169 |
+
"loss": 0.2661,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.13,
|
| 174 |
+
"grad_norm": 0.45005029898365917,
|
| 175 |
+
"learning_rate": 1e-05,
|
| 176 |
+
"loss": 0.2689,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.13,
|
| 181 |
+
"grad_norm": 0.43003033091413906,
|
| 182 |
+
"learning_rate": 1e-05,
|
| 183 |
+
"loss": 0.2642,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.14,
|
| 188 |
+
"grad_norm": 0.4486774042462993,
|
| 189 |
+
"learning_rate": 1e-05,
|
| 190 |
+
"loss": 0.2547,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.14,
|
| 195 |
+
"grad_norm": 0.4321202903931241,
|
| 196 |
+
"learning_rate": 1e-05,
|
| 197 |
+
"loss": 0.2497,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.15,
|
| 202 |
+
"grad_norm": 0.43198162548067304,
|
| 203 |
+
"learning_rate": 1e-05,
|
| 204 |
+
"loss": 0.2451,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.15,
|
| 209 |
+
"grad_norm": 0.42529053274210193,
|
| 210 |
+
"learning_rate": 1e-05,
|
| 211 |
+
"loss": 0.2416,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.16,
|
| 216 |
+
"grad_norm": 0.42704990652407715,
|
| 217 |
+
"learning_rate": 1e-05,
|
| 218 |
+
"loss": 0.2446,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.16,
|
| 223 |
+
"grad_norm": 0.3958306845876151,
|
| 224 |
+
"learning_rate": 1e-05,
|
| 225 |
+
"loss": 0.2327,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.17,
|
| 230 |
+
"grad_norm": 0.38775187941433076,
|
| 231 |
+
"learning_rate": 1e-05,
|
| 232 |
+
"loss": 0.2361,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.17,
|
| 237 |
+
"grad_norm": 0.39129679015161345,
|
| 238 |
+
"learning_rate": 1e-05,
|
| 239 |
+
"loss": 0.2455,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.18,
|
| 244 |
+
"grad_norm": 0.3746266538880689,
|
| 245 |
+
"learning_rate": 1e-05,
|
| 246 |
+
"loss": 0.225,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.19,
|
| 251 |
+
"grad_norm": 0.37254990504997704,
|
| 252 |
+
"learning_rate": 1e-05,
|
| 253 |
+
"loss": 0.2325,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.19,
|
| 258 |
+
"grad_norm": 0.3516460688448446,
|
| 259 |
+
"learning_rate": 1e-05,
|
| 260 |
+
"loss": 0.2216,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.2,
|
| 265 |
+
"grad_norm": 0.3354724757085697,
|
| 266 |
+
"learning_rate": 1e-05,
|
| 267 |
+
"loss": 0.2208,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.2,
|
| 272 |
+
"grad_norm": 0.32752255887432763,
|
| 273 |
+
"learning_rate": 1e-05,
|
| 274 |
+
"loss": 0.2033,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.21,
|
| 279 |
+
"grad_norm": 0.3651242741496675,
|
| 280 |
+
"learning_rate": 1e-05,
|
| 281 |
+
"loss": 0.2247,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.21,
|
| 286 |
+
"grad_norm": 0.3357989435107463,
|
| 287 |
+
"learning_rate": 1e-05,
|
| 288 |
+
"loss": 0.2112,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.22,
|
| 293 |
+
"grad_norm": 0.3265444947267983,
|
| 294 |
+
"learning_rate": 1e-05,
|
| 295 |
+
"loss": 0.2135,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.22,
|
| 300 |
+
"grad_norm": 0.3312232834623035,
|
| 301 |
+
"learning_rate": 1e-05,
|
| 302 |
+
"loss": 0.2099,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.23,
|
| 307 |
+
"grad_norm": 0.325208128018063,
|
| 308 |
+
"learning_rate": 1e-05,
|
| 309 |
+
"loss": 0.2148,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.23,
|
| 314 |
+
"grad_norm": 0.3103050831142777,
|
| 315 |
+
"learning_rate": 1e-05,
|
| 316 |
+
"loss": 0.201,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.24,
|
| 321 |
+
"grad_norm": 0.3152019901705659,
|
| 322 |
+
"learning_rate": 1e-05,
|
| 323 |
+
"loss": 0.2014,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.24,
|
| 328 |
+
"grad_norm": 0.3111577610569211,
|
| 329 |
+
"learning_rate": 1e-05,
|
| 330 |
+
"loss": 0.199,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.25,
|
| 335 |
+
"grad_norm": 0.3064414033100908,
|
| 336 |
+
"learning_rate": 1e-05,
|
| 337 |
+
"loss": 0.2045,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.25,
|
| 342 |
+
"grad_norm": 0.31614609895667245,
|
| 343 |
+
"learning_rate": 1e-05,
|
| 344 |
+
"loss": 0.2047,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.26,
|
| 349 |
+
"grad_norm": 0.31816702750266984,
|
| 350 |
+
"learning_rate": 1e-05,
|
| 351 |
+
"loss": 0.1903,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.27,
|
| 356 |
+
"grad_norm": 0.29796199012405883,
|
| 357 |
+
"learning_rate": 1e-05,
|
| 358 |
+
"loss": 0.1967,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.27,
|
| 363 |
+
"grad_norm": 0.287633927234579,
|
| 364 |
+
"learning_rate": 1e-05,
|
| 365 |
+
"loss": 0.181,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.28,
|
| 370 |
+
"grad_norm": 0.29390033060707677,
|
| 371 |
+
"learning_rate": 1e-05,
|
| 372 |
+
"loss": 0.1905,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.28,
|
| 377 |
+
"grad_norm": 0.29214020884298275,
|
| 378 |
+
"learning_rate": 1e-05,
|
| 379 |
+
"loss": 0.1842,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.29,
|
| 384 |
+
"grad_norm": 0.2916935333966593,
|
| 385 |
+
"learning_rate": 1e-05,
|
| 386 |
+
"loss": 0.194,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.29,
|
| 391 |
+
"grad_norm": 0.29833227194604023,
|
| 392 |
+
"learning_rate": 1e-05,
|
| 393 |
+
"loss": 0.1856,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.3,
|
| 398 |
+
"grad_norm": 0.29514305891318965,
|
| 399 |
+
"learning_rate": 1e-05,
|
| 400 |
+
"loss": 0.1793,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.3,
|
| 405 |
+
"grad_norm": 0.29330994882347694,
|
| 406 |
+
"learning_rate": 1e-05,
|
| 407 |
+
"loss": 0.18,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.31,
|
| 412 |
+
"grad_norm": 0.31625939409312065,
|
| 413 |
+
"learning_rate": 1e-05,
|
| 414 |
+
"loss": 0.1771,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.31,
|
| 419 |
+
"grad_norm": 0.2851852538890017,
|
| 420 |
+
"learning_rate": 1e-05,
|
| 421 |
+
"loss": 0.179,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.32,
|
| 426 |
+
"grad_norm": 0.29626675222390664,
|
| 427 |
+
"learning_rate": 1e-05,
|
| 428 |
+
"loss": 0.1737,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.32,
|
| 433 |
+
"grad_norm": 0.2935071337888655,
|
| 434 |
+
"learning_rate": 1e-05,
|
| 435 |
+
"loss": 0.183,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.33,
|
| 440 |
+
"grad_norm": 0.28642020017440367,
|
| 441 |
+
"learning_rate": 1e-05,
|
| 442 |
+
"loss": 0.1725,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.33,
|
| 447 |
+
"grad_norm": 0.29701780279529105,
|
| 448 |
+
"learning_rate": 1e-05,
|
| 449 |
+
"loss": 0.1738,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.34,
|
| 454 |
+
"grad_norm": 0.2853975587037228,
|
| 455 |
+
"learning_rate": 1e-05,
|
| 456 |
+
"loss": 0.1658,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.34,
|
| 461 |
+
"grad_norm": 0.280743334098327,
|
| 462 |
+
"learning_rate": 1e-05,
|
| 463 |
+
"loss": 0.1612,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.35,
|
| 468 |
+
"grad_norm": 0.2848068517064538,
|
| 469 |
+
"learning_rate": 1e-05,
|
| 470 |
+
"loss": 0.1626,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.36,
|
| 475 |
+
"grad_norm": 0.2826081499641741,
|
| 476 |
+
"learning_rate": 1e-05,
|
| 477 |
+
"loss": 0.1661,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.36,
|
| 482 |
+
"grad_norm": 0.2822062364230369,
|
| 483 |
+
"learning_rate": 1e-05,
|
| 484 |
+
"loss": 0.1622,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.37,
|
| 489 |
+
"grad_norm": 0.28663543900665617,
|
| 490 |
+
"learning_rate": 1e-05,
|
| 491 |
+
"loss": 0.1658,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.37,
|
| 496 |
+
"grad_norm": 0.28336682974385563,
|
| 497 |
+
"learning_rate": 1e-05,
|
| 498 |
+
"loss": 0.1589,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.38,
|
| 503 |
+
"grad_norm": 0.2774115679314652,
|
| 504 |
+
"learning_rate": 1e-05,
|
| 505 |
+
"loss": 0.1655,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.38,
|
| 510 |
+
"grad_norm": 0.27709306628158714,
|
| 511 |
+
"learning_rate": 1e-05,
|
| 512 |
+
"loss": 0.1489,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.39,
|
| 517 |
+
"grad_norm": 0.2862365037916789,
|
| 518 |
+
"learning_rate": 1e-05,
|
| 519 |
+
"loss": 0.1646,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.39,
|
| 524 |
+
"grad_norm": 0.28675576977214917,
|
| 525 |
+
"learning_rate": 1e-05,
|
| 526 |
+
"loss": 0.1614,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.4,
|
| 531 |
+
"grad_norm": 0.276969452071043,
|
| 532 |
+
"learning_rate": 1e-05,
|
| 533 |
+
"loss": 0.1454,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.4,
|
| 538 |
+
"grad_norm": 0.2847613570553893,
|
| 539 |
+
"learning_rate": 1e-05,
|
| 540 |
+
"loss": 0.1647,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.41,
|
| 545 |
+
"grad_norm": 0.2743833852883841,
|
| 546 |
+
"learning_rate": 1e-05,
|
| 547 |
+
"loss": 0.1571,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.41,
|
| 552 |
+
"grad_norm": 0.2842819197108497,
|
| 553 |
+
"learning_rate": 1e-05,
|
| 554 |
+
"loss": 0.1558,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.42,
|
| 559 |
+
"grad_norm": 0.2725891106726455,
|
| 560 |
+
"learning_rate": 1e-05,
|
| 561 |
+
"loss": 0.151,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.42,
|
| 566 |
+
"grad_norm": 0.2731655750714622,
|
| 567 |
+
"learning_rate": 1e-05,
|
| 568 |
+
"loss": 0.1548,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.43,
|
| 573 |
+
"grad_norm": 0.27553369461320953,
|
| 574 |
+
"learning_rate": 1e-05,
|
| 575 |
+
"loss": 0.1495,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.43,
|
| 580 |
+
"grad_norm": 0.26391895632526624,
|
| 581 |
+
"learning_rate": 1e-05,
|
| 582 |
+
"loss": 0.1403,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.44,
|
| 587 |
+
"grad_norm": 0.2711005612262172,
|
| 588 |
+
"learning_rate": 1e-05,
|
| 589 |
+
"loss": 0.1476,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.45,
|
| 594 |
+
"grad_norm": 0.2643848929997021,
|
| 595 |
+
"learning_rate": 1e-05,
|
| 596 |
+
"loss": 0.146,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.45,
|
| 601 |
+
"grad_norm": 0.2728123832588989,
|
| 602 |
+
"learning_rate": 1e-05,
|
| 603 |
+
"loss": 0.1463,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.46,
|
| 608 |
+
"grad_norm": 0.2712303902737227,
|
| 609 |
+
"learning_rate": 1e-05,
|
| 610 |
+
"loss": 0.1483,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.46,
|
| 615 |
+
"grad_norm": 0.27169791564319207,
|
| 616 |
+
"learning_rate": 1e-05,
|
| 617 |
+
"loss": 0.1472,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.47,
|
| 622 |
+
"grad_norm": 0.25810060690144226,
|
| 623 |
+
"learning_rate": 1e-05,
|
| 624 |
+
"loss": 0.1368,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.47,
|
| 629 |
+
"grad_norm": 0.27817282484024414,
|
| 630 |
+
"learning_rate": 1e-05,
|
| 631 |
+
"loss": 0.1543,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.48,
|
| 636 |
+
"grad_norm": 0.2521088146493535,
|
| 637 |
+
"learning_rate": 1e-05,
|
| 638 |
+
"loss": 0.1375,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.48,
|
| 643 |
+
"grad_norm": 0.28364342434736595,
|
| 644 |
+
"learning_rate": 1e-05,
|
| 645 |
+
"loss": 0.1454,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.49,
|
| 650 |
+
"grad_norm": 0.2662616212401991,
|
| 651 |
+
"learning_rate": 1e-05,
|
| 652 |
+
"loss": 0.1416,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.49,
|
| 657 |
+
"grad_norm": 0.2779342897679881,
|
| 658 |
+
"learning_rate": 1e-05,
|
| 659 |
+
"loss": 0.1451,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.5,
|
| 664 |
+
"grad_norm": 0.2646335301665372,
|
| 665 |
+
"learning_rate": 1e-05,
|
| 666 |
+
"loss": 0.1443,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.5,
|
| 671 |
+
"grad_norm": 0.255789758256267,
|
| 672 |
+
"learning_rate": 1e-05,
|
| 673 |
+
"loss": 0.1361,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.51,
|
| 678 |
+
"grad_norm": 0.2549905453416931,
|
| 679 |
+
"learning_rate": 1e-05,
|
| 680 |
+
"loss": 0.1358,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.51,
|
| 685 |
+
"grad_norm": 0.26632260810259295,
|
| 686 |
+
"learning_rate": 1e-05,
|
| 687 |
+
"loss": 0.1314,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.52,
|
| 692 |
+
"grad_norm": 0.26809336997796596,
|
| 693 |
+
"learning_rate": 1e-05,
|
| 694 |
+
"loss": 0.1341,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.52,
|
| 699 |
+
"grad_norm": 0.27461397618850975,
|
| 700 |
+
"learning_rate": 1e-05,
|
| 701 |
+
"loss": 0.1428,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.53,
|
| 706 |
+
"grad_norm": 0.2651115096422905,
|
| 707 |
+
"learning_rate": 1e-05,
|
| 708 |
+
"loss": 0.1334,
|
| 709 |
+
"step": 100
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.54,
|
| 713 |
+
"grad_norm": 0.2613007356057435,
|
| 714 |
+
"learning_rate": 1e-05,
|
| 715 |
+
"loss": 0.1325,
|
| 716 |
+
"step": 101
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.54,
|
| 720 |
+
"grad_norm": 0.2633742260809078,
|
| 721 |
+
"learning_rate": 1e-05,
|
| 722 |
+
"loss": 0.1303,
|
| 723 |
+
"step": 102
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.55,
|
| 727 |
+
"grad_norm": 0.2597852394304056,
|
| 728 |
+
"learning_rate": 1e-05,
|
| 729 |
+
"loss": 0.1284,
|
| 730 |
+
"step": 103
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.55,
|
| 734 |
+
"grad_norm": 0.25826526698011837,
|
| 735 |
+
"learning_rate": 1e-05,
|
| 736 |
+
"loss": 0.1304,
|
| 737 |
+
"step": 104
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.56,
|
| 741 |
+
"grad_norm": 0.2655794821040693,
|
| 742 |
+
"learning_rate": 1e-05,
|
| 743 |
+
"loss": 0.1321,
|
| 744 |
+
"step": 105
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.56,
|
| 748 |
+
"grad_norm": 0.27098219099500953,
|
| 749 |
+
"learning_rate": 1e-05,
|
| 750 |
+
"loss": 0.1294,
|
| 751 |
+
"step": 106
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.57,
|
| 755 |
+
"grad_norm": 0.26226028196977447,
|
| 756 |
+
"learning_rate": 1e-05,
|
| 757 |
+
"loss": 0.129,
|
| 758 |
+
"step": 107
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.57,
|
| 762 |
+
"grad_norm": 0.263399252714501,
|
| 763 |
+
"learning_rate": 1e-05,
|
| 764 |
+
"loss": 0.1353,
|
| 765 |
+
"step": 108
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.58,
|
| 769 |
+
"grad_norm": 0.2714025066703335,
|
| 770 |
+
"learning_rate": 1e-05,
|
| 771 |
+
"loss": 0.1314,
|
| 772 |
+
"step": 109
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.58,
|
| 776 |
+
"grad_norm": 0.2515224984062514,
|
| 777 |
+
"learning_rate": 1e-05,
|
| 778 |
+
"loss": 0.1194,
|
| 779 |
+
"step": 110
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.59,
|
| 783 |
+
"grad_norm": 0.26605486225954983,
|
| 784 |
+
"learning_rate": 1e-05,
|
| 785 |
+
"loss": 0.1229,
|
| 786 |
+
"step": 111
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.59,
|
| 790 |
+
"grad_norm": 0.2549018171846725,
|
| 791 |
+
"learning_rate": 1e-05,
|
| 792 |
+
"loss": 0.1197,
|
| 793 |
+
"step": 112
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.6,
|
| 797 |
+
"grad_norm": 0.2560680072201203,
|
| 798 |
+
"learning_rate": 1e-05,
|
| 799 |
+
"loss": 0.1217,
|
| 800 |
+
"step": 113
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.6,
|
| 804 |
+
"grad_norm": 0.2534651230289815,
|
| 805 |
+
"learning_rate": 1e-05,
|
| 806 |
+
"loss": 0.1264,
|
| 807 |
+
"step": 114
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.61,
|
| 811 |
+
"grad_norm": 0.2648967427767519,
|
| 812 |
+
"learning_rate": 1e-05,
|
| 813 |
+
"loss": 0.1218,
|
| 814 |
+
"step": 115
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.61,
|
| 818 |
+
"grad_norm": 0.26771279234407747,
|
| 819 |
+
"learning_rate": 1e-05,
|
| 820 |
+
"loss": 0.1296,
|
| 821 |
+
"step": 116
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.62,
|
| 825 |
+
"grad_norm": 0.25894648053010244,
|
| 826 |
+
"learning_rate": 1e-05,
|
| 827 |
+
"loss": 0.1169,
|
| 828 |
+
"step": 117
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.63,
|
| 832 |
+
"grad_norm": 0.2585875460715992,
|
| 833 |
+
"learning_rate": 1e-05,
|
| 834 |
+
"loss": 0.1199,
|
| 835 |
+
"step": 118
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.63,
|
| 839 |
+
"grad_norm": 0.2548488101104416,
|
| 840 |
+
"learning_rate": 1e-05,
|
| 841 |
+
"loss": 0.1213,
|
| 842 |
+
"step": 119
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.64,
|
| 846 |
+
"grad_norm": 0.24487209204733212,
|
| 847 |
+
"learning_rate": 1e-05,
|
| 848 |
+
"loss": 0.1168,
|
| 849 |
+
"step": 120
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.64,
|
| 853 |
+
"grad_norm": 0.2554367919231805,
|
| 854 |
+
"learning_rate": 1e-05,
|
| 855 |
+
"loss": 0.1249,
|
| 856 |
+
"step": 121
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.65,
|
| 860 |
+
"grad_norm": 0.25526673295561314,
|
| 861 |
+
"learning_rate": 1e-05,
|
| 862 |
+
"loss": 0.1174,
|
| 863 |
+
"step": 122
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.65,
|
| 867 |
+
"grad_norm": 0.24318890394737153,
|
| 868 |
+
"learning_rate": 1e-05,
|
| 869 |
+
"loss": 0.1118,
|
| 870 |
+
"step": 123
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.66,
|
| 874 |
+
"grad_norm": 0.24844490489908636,
|
| 875 |
+
"learning_rate": 1e-05,
|
| 876 |
+
"loss": 0.1207,
|
| 877 |
+
"step": 124
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.66,
|
| 881 |
+
"grad_norm": 0.24957568713820535,
|
| 882 |
+
"learning_rate": 1e-05,
|
| 883 |
+
"loss": 0.1123,
|
| 884 |
+
"step": 125
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.67,
|
| 888 |
+
"grad_norm": 0.26167543296489026,
|
| 889 |
+
"learning_rate": 1e-05,
|
| 890 |
+
"loss": 0.119,
|
| 891 |
+
"step": 126
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.67,
|
| 895 |
+
"grad_norm": 0.2528970008222453,
|
| 896 |
+
"learning_rate": 1e-05,
|
| 897 |
+
"loss": 0.1119,
|
| 898 |
+
"step": 127
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.68,
|
| 902 |
+
"grad_norm": 0.25446291827800727,
|
| 903 |
+
"learning_rate": 1e-05,
|
| 904 |
+
"loss": 0.1197,
|
| 905 |
+
"step": 128
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.68,
|
| 909 |
+
"grad_norm": 0.2452294668436806,
|
| 910 |
+
"learning_rate": 1e-05,
|
| 911 |
+
"loss": 0.106,
|
| 912 |
+
"step": 129
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.69,
|
| 916 |
+
"grad_norm": 0.26097488739530145,
|
| 917 |
+
"learning_rate": 1e-05,
|
| 918 |
+
"loss": 0.1172,
|
| 919 |
+
"step": 130
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.69,
|
| 923 |
+
"grad_norm": 0.23710311994460034,
|
| 924 |
+
"learning_rate": 1e-05,
|
| 925 |
+
"loss": 0.1046,
|
| 926 |
+
"step": 131
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.7,
|
| 930 |
+
"grad_norm": 0.25535125260602537,
|
| 931 |
+
"learning_rate": 1e-05,
|
| 932 |
+
"loss": 0.1126,
|
| 933 |
+
"step": 132
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.71,
|
| 937 |
+
"grad_norm": 0.2451995286688119,
|
| 938 |
+
"learning_rate": 1e-05,
|
| 939 |
+
"loss": 0.1083,
|
| 940 |
+
"step": 133
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.71,
|
| 944 |
+
"grad_norm": 0.2507401212273221,
|
| 945 |
+
"learning_rate": 1e-05,
|
| 946 |
+
"loss": 0.1161,
|
| 947 |
+
"step": 134
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.72,
|
| 951 |
+
"grad_norm": 0.2548047383624151,
|
| 952 |
+
"learning_rate": 1e-05,
|
| 953 |
+
"loss": 0.1088,
|
| 954 |
+
"step": 135
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.72,
|
| 958 |
+
"grad_norm": 0.25184336668602836,
|
| 959 |
+
"learning_rate": 1e-05,
|
| 960 |
+
"loss": 0.1092,
|
| 961 |
+
"step": 136
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.73,
|
| 965 |
+
"grad_norm": 0.2389388344872007,
|
| 966 |
+
"learning_rate": 1e-05,
|
| 967 |
+
"loss": 0.1077,
|
| 968 |
+
"step": 137
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.73,
|
| 972 |
+
"grad_norm": 0.2368111690990983,
|
| 973 |
+
"learning_rate": 1e-05,
|
| 974 |
+
"loss": 0.1007,
|
| 975 |
+
"step": 138
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.74,
|
| 979 |
+
"grad_norm": 0.23422758337451635,
|
| 980 |
+
"learning_rate": 1e-05,
|
| 981 |
+
"loss": 0.1044,
|
| 982 |
+
"step": 139
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.74,
|
| 986 |
+
"grad_norm": 0.2502487147266415,
|
| 987 |
+
"learning_rate": 1e-05,
|
| 988 |
+
"loss": 0.1094,
|
| 989 |
+
"step": 140
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.75,
|
| 993 |
+
"grad_norm": 0.25134141633205564,
|
| 994 |
+
"learning_rate": 1e-05,
|
| 995 |
+
"loss": 0.104,
|
| 996 |
+
"step": 141
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.75,
|
| 1000 |
+
"grad_norm": 0.23275616546020486,
|
| 1001 |
+
"learning_rate": 1e-05,
|
| 1002 |
+
"loss": 0.1031,
|
| 1003 |
+
"step": 142
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.76,
|
| 1007 |
+
"grad_norm": 0.23810819147753784,
|
| 1008 |
+
"learning_rate": 1e-05,
|
| 1009 |
+
"loss": 0.1016,
|
| 1010 |
+
"step": 143
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.76,
|
| 1014 |
+
"grad_norm": 0.24027783267609687,
|
| 1015 |
+
"learning_rate": 1e-05,
|
| 1016 |
+
"loss": 0.1073,
|
| 1017 |
+
"step": 144
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.77,
|
| 1021 |
+
"grad_norm": 0.23865216510806872,
|
| 1022 |
+
"learning_rate": 1e-05,
|
| 1023 |
+
"loss": 0.1006,
|
| 1024 |
+
"step": 145
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.77,
|
| 1028 |
+
"grad_norm": 0.23204373209989085,
|
| 1029 |
+
"learning_rate": 1e-05,
|
| 1030 |
+
"loss": 0.1019,
|
| 1031 |
+
"step": 146
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.78,
|
| 1035 |
+
"grad_norm": 0.2389114299180096,
|
| 1036 |
+
"learning_rate": 1e-05,
|
| 1037 |
+
"loss": 0.1044,
|
| 1038 |
+
"step": 147
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.78,
|
| 1042 |
+
"grad_norm": 0.23039463317481657,
|
| 1043 |
+
"learning_rate": 1e-05,
|
| 1044 |
+
"loss": 0.0987,
|
| 1045 |
+
"step": 148
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.79,
|
| 1049 |
+
"grad_norm": 0.23845334911947455,
|
| 1050 |
+
"learning_rate": 1e-05,
|
| 1051 |
+
"loss": 0.1028,
|
| 1052 |
+
"step": 149
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.8,
|
| 1056 |
+
"grad_norm": 0.23652539759935484,
|
| 1057 |
+
"learning_rate": 1e-05,
|
| 1058 |
+
"loss": 0.1021,
|
| 1059 |
+
"step": 150
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.8,
|
| 1063 |
+
"grad_norm": 0.23252388772767615,
|
| 1064 |
+
"learning_rate": 1e-05,
|
| 1065 |
+
"loss": 0.0999,
|
| 1066 |
+
"step": 151
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.81,
|
| 1070 |
+
"grad_norm": 0.2387303176721335,
|
| 1071 |
+
"learning_rate": 1e-05,
|
| 1072 |
+
"loss": 0.1011,
|
| 1073 |
+
"step": 152
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.81,
|
| 1077 |
+
"grad_norm": 0.23834307535754162,
|
| 1078 |
+
"learning_rate": 1e-05,
|
| 1079 |
+
"loss": 0.0977,
|
| 1080 |
+
"step": 153
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.82,
|
| 1084 |
+
"grad_norm": 0.22614856805557293,
|
| 1085 |
+
"learning_rate": 1e-05,
|
| 1086 |
+
"loss": 0.1004,
|
| 1087 |
+
"step": 154
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.82,
|
| 1091 |
+
"grad_norm": 0.22810172167379886,
|
| 1092 |
+
"learning_rate": 1e-05,
|
| 1093 |
+
"loss": 0.0953,
|
| 1094 |
+
"step": 155
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.83,
|
| 1098 |
+
"grad_norm": 0.23276576120771708,
|
| 1099 |
+
"learning_rate": 1e-05,
|
| 1100 |
+
"loss": 0.0964,
|
| 1101 |
+
"step": 156
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.83,
|
| 1105 |
+
"grad_norm": 0.23860552375581268,
|
| 1106 |
+
"learning_rate": 1e-05,
|
| 1107 |
+
"loss": 0.1019,
|
| 1108 |
+
"step": 157
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.84,
|
| 1112 |
+
"grad_norm": 0.2278245783683838,
|
| 1113 |
+
"learning_rate": 1e-05,
|
| 1114 |
+
"loss": 0.0925,
|
| 1115 |
+
"step": 158
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.84,
|
| 1119 |
+
"grad_norm": 0.24433715719422633,
|
| 1120 |
+
"learning_rate": 1e-05,
|
| 1121 |
+
"loss": 0.0955,
|
| 1122 |
+
"step": 159
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.85,
|
| 1126 |
+
"grad_norm": 0.23944392401086093,
|
| 1127 |
+
"learning_rate": 1e-05,
|
| 1128 |
+
"loss": 0.096,
|
| 1129 |
+
"step": 160
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.85,
|
| 1133 |
+
"grad_norm": 0.2328615631041631,
|
| 1134 |
+
"learning_rate": 1e-05,
|
| 1135 |
+
"loss": 0.0939,
|
| 1136 |
+
"step": 161
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.86,
|
| 1140 |
+
"grad_norm": 0.2290088869757385,
|
| 1141 |
+
"learning_rate": 1e-05,
|
| 1142 |
+
"loss": 0.0959,
|
| 1143 |
+
"step": 162
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.86,
|
| 1147 |
+
"grad_norm": 0.22438340751204006,
|
| 1148 |
+
"learning_rate": 1e-05,
|
| 1149 |
+
"loss": 0.095,
|
| 1150 |
+
"step": 163
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.87,
|
| 1154 |
+
"grad_norm": 0.22880044061044771,
|
| 1155 |
+
"learning_rate": 1e-05,
|
| 1156 |
+
"loss": 0.0916,
|
| 1157 |
+
"step": 164
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.87,
|
| 1161 |
+
"grad_norm": 0.22084052201833856,
|
| 1162 |
+
"learning_rate": 1e-05,
|
| 1163 |
+
"loss": 0.0876,
|
| 1164 |
+
"step": 165
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.88,
|
| 1168 |
+
"grad_norm": 0.22372739836885092,
|
| 1169 |
+
"learning_rate": 1e-05,
|
| 1170 |
+
"loss": 0.0905,
|
| 1171 |
+
"step": 166
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.89,
|
| 1175 |
+
"grad_norm": 0.21868291038919785,
|
| 1176 |
+
"learning_rate": 1e-05,
|
| 1177 |
+
"loss": 0.0926,
|
| 1178 |
+
"step": 167
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.89,
|
| 1182 |
+
"grad_norm": 0.23455367163368512,
|
| 1183 |
+
"learning_rate": 1e-05,
|
| 1184 |
+
"loss": 0.0923,
|
| 1185 |
+
"step": 168
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.9,
|
| 1189 |
+
"grad_norm": 0.2204351585120366,
|
| 1190 |
+
"learning_rate": 1e-05,
|
| 1191 |
+
"loss": 0.0896,
|
| 1192 |
+
"step": 169
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.9,
|
| 1196 |
+
"grad_norm": 0.23401978770074194,
|
| 1197 |
+
"learning_rate": 1e-05,
|
| 1198 |
+
"loss": 0.0922,
|
| 1199 |
+
"step": 170
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.91,
|
| 1203 |
+
"grad_norm": 0.23006845604541815,
|
| 1204 |
+
"learning_rate": 1e-05,
|
| 1205 |
+
"loss": 0.0929,
|
| 1206 |
+
"step": 171
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.91,
|
| 1210 |
+
"grad_norm": 0.22367772927110594,
|
| 1211 |
+
"learning_rate": 1e-05,
|
| 1212 |
+
"loss": 0.0925,
|
| 1213 |
+
"step": 172
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.92,
|
| 1217 |
+
"grad_norm": 0.21905617183568088,
|
| 1218 |
+
"learning_rate": 1e-05,
|
| 1219 |
+
"loss": 0.0862,
|
| 1220 |
+
"step": 173
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.92,
|
| 1224 |
+
"grad_norm": 0.21928032048467122,
|
| 1225 |
+
"learning_rate": 1e-05,
|
| 1226 |
+
"loss": 0.0917,
|
| 1227 |
+
"step": 174
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.93,
|
| 1231 |
+
"grad_norm": 0.2155940569925008,
|
| 1232 |
+
"learning_rate": 1e-05,
|
| 1233 |
+
"loss": 0.0861,
|
| 1234 |
+
"step": 175
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.93,
|
| 1238 |
+
"grad_norm": 0.20905996557943637,
|
| 1239 |
+
"learning_rate": 1e-05,
|
| 1240 |
+
"loss": 0.0852,
|
| 1241 |
+
"step": 176
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.94,
|
| 1245 |
+
"grad_norm": 0.21285005995058925,
|
| 1246 |
+
"learning_rate": 1e-05,
|
| 1247 |
+
"loss": 0.0845,
|
| 1248 |
+
"step": 177
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.94,
|
| 1252 |
+
"grad_norm": 0.209712828323914,
|
| 1253 |
+
"learning_rate": 1e-05,
|
| 1254 |
+
"loss": 0.0809,
|
| 1255 |
+
"step": 178
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.95,
|
| 1259 |
+
"grad_norm": 0.2221522197639559,
|
| 1260 |
+
"learning_rate": 1e-05,
|
| 1261 |
+
"loss": 0.0913,
|
| 1262 |
+
"step": 179
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.95,
|
| 1266 |
+
"grad_norm": 0.22600512819104449,
|
| 1267 |
+
"learning_rate": 1e-05,
|
| 1268 |
+
"loss": 0.0889,
|
| 1269 |
+
"step": 180
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.96,
|
| 1273 |
+
"grad_norm": 0.2253717005046901,
|
| 1274 |
+
"learning_rate": 1e-05,
|
| 1275 |
+
"loss": 0.0919,
|
| 1276 |
+
"step": 181
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.96,
|
| 1280 |
+
"grad_norm": 0.22151678395197472,
|
| 1281 |
+
"learning_rate": 1e-05,
|
| 1282 |
+
"loss": 0.0906,
|
| 1283 |
+
"step": 182
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.97,
|
| 1287 |
+
"grad_norm": 0.22227797000994332,
|
| 1288 |
+
"learning_rate": 1e-05,
|
| 1289 |
+
"loss": 0.0877,
|
| 1290 |
+
"step": 183
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.98,
|
| 1294 |
+
"grad_norm": 0.22082709093842154,
|
| 1295 |
+
"learning_rate": 1e-05,
|
| 1296 |
+
"loss": 0.0885,
|
| 1297 |
+
"step": 184
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.98,
|
| 1301 |
+
"grad_norm": 0.2202821891298244,
|
| 1302 |
+
"learning_rate": 1e-05,
|
| 1303 |
+
"loss": 0.0855,
|
| 1304 |
+
"step": 185
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.99,
|
| 1308 |
+
"grad_norm": 0.20938170922248253,
|
| 1309 |
+
"learning_rate": 1e-05,
|
| 1310 |
+
"loss": 0.0831,
|
| 1311 |
+
"step": 186
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.99,
|
| 1315 |
+
"grad_norm": 0.21449178686089804,
|
| 1316 |
+
"learning_rate": 1e-05,
|
| 1317 |
+
"loss": 0.0876,
|
| 1318 |
+
"step": 187
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 1.0,
|
| 1322 |
+
"grad_norm": 0.2030838804724525,
|
| 1323 |
+
"learning_rate": 1e-05,
|
| 1324 |
+
"loss": 0.0824,
|
| 1325 |
+
"step": 188
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 1.0,
|
| 1329 |
+
"step": 188,
|
| 1330 |
+
"total_flos": 217108736114688.0,
|
| 1331 |
+
"train_loss": 0.17206811350076756,
|
| 1332 |
+
"train_runtime": 8910.5782,
|
| 1333 |
+
"train_samples_per_second": 2.031,
|
| 1334 |
+
"train_steps_per_second": 0.021
|
| 1335 |
+
}
|
| 1336 |
+
],
|
| 1337 |
+
"logging_steps": 1.0,
|
| 1338 |
+
"max_steps": 188,
|
| 1339 |
+
"num_input_tokens_seen": 0,
|
| 1340 |
+
"num_train_epochs": 1,
|
| 1341 |
+
"save_steps": 1000,
|
| 1342 |
+
"total_flos": 217108736114688.0,
|
| 1343 |
+
"train_batch_size": 2,
|
| 1344 |
+
"trial_name": null,
|
| 1345 |
+
"trial_params": null
|
| 1346 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:38211656ed81e8b85532b8f83ec58b79c4bbf84c5d4d551705e659ee1262fef0
|
| 3 |
+
size 6971
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|