Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- added_tokens.json +28 -0
- config.json +32 -0
- generation_config.json +15 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +240 -0
- trainer_state.json +1434 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
added_tokens.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<think>": 151667,
|
| 6 |
+
"<tool_call>": 151657,
|
| 7 |
+
"<tool_response>": 151665,
|
| 8 |
+
"<|box_end|>": 151649,
|
| 9 |
+
"<|box_start|>": 151648,
|
| 10 |
+
"<|endoftext|>": 151643,
|
| 11 |
+
"<|file_sep|>": 151664,
|
| 12 |
+
"<|fim_middle|>": 151660,
|
| 13 |
+
"<|fim_pad|>": 151662,
|
| 14 |
+
"<|fim_prefix|>": 151659,
|
| 15 |
+
"<|fim_suffix|>": 151661,
|
| 16 |
+
"<|im_end|>": 151645,
|
| 17 |
+
"<|im_start|>": 151644,
|
| 18 |
+
"<|image_pad|>": 151655,
|
| 19 |
+
"<|object_ref_end|>": 151647,
|
| 20 |
+
"<|object_ref_start|>": 151646,
|
| 21 |
+
"<|quad_end|>": 151651,
|
| 22 |
+
"<|quad_start|>": 151650,
|
| 23 |
+
"<|repo_name|>": 151663,
|
| 24 |
+
"<|video_pad|>": 151656,
|
| 25 |
+
"<|vision_end|>": 151653,
|
| 26 |
+
"<|vision_pad|>": 151654,
|
| 27 |
+
"<|vision_start|>": 151652
|
| 28 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"eos_token_id": 151643,
|
| 8 |
+
"head_dim": 128,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 1024,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 3072,
|
| 13 |
+
"max_position_embeddings": 32768,
|
| 14 |
+
"max_window_layers": 28,
|
| 15 |
+
"model_type": "qwen3",
|
| 16 |
+
"num_attention_heads": 16,
|
| 17 |
+
"num_hidden_layers": 28,
|
| 18 |
+
"num_key_value_heads": 8,
|
| 19 |
+
"pad_token_id": 151654,
|
| 20 |
+
"rms_norm_eps": 1e-06,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"rope_theta": 1000000,
|
| 23 |
+
"sliding_window": null,
|
| 24 |
+
"tie_word_embeddings": true,
|
| 25 |
+
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.52.4",
|
| 27 |
+
"unsloth_fixed": true,
|
| 28 |
+
"unsloth_version": "2025.6.1",
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"use_sliding_window": false,
|
| 31 |
+
"vocab_size": 151936
|
| 32 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151643,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"max_length": 32768,
|
| 9 |
+
"max_new_tokens": 2048,
|
| 10 |
+
"pad_token_id": 151654,
|
| 11 |
+
"temperature": 0.7,
|
| 12 |
+
"top_k": 20,
|
| 13 |
+
"top_p": 0.95,
|
| 14 |
+
"transformers_version": "4.52.4"
|
| 15 |
+
}
|
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 sha256:3e76a4821df0c018697398ced1b759617ba54ee13638a93a6a80b44f9bbe08a2
|
| 3 |
+
size 2384234968
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2de0368b47038645fa5a0ac9a99e059820bf3ff882984c8868d1f0ea4a30f773
|
| 3 |
+
size 2140048520
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:608fccb6c056ce88cdfd5355e6be2046f4d107a24a87c6b0d2c3b200ce6bb4ea
|
| 3 |
+
size 14244
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9bd55b3848d82967a207e0805911c79200c6adce71e3b37fd24549a718f75738
|
| 3 |
+
size 988
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50d23b4f208a9403528cc4590d75da0ba9842779b9cd25a1b5978ffbe9bcceb1
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|endoftext|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|vision_pad|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,240 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>"
|
| 228 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"clean_up_tokenization_spaces": false,
|
| 231 |
+
"eos_token": "<|endoftext|>",
|
| 232 |
+
"errors": "replace",
|
| 233 |
+
"extra_special_tokens": {},
|
| 234 |
+
"model_max_length": 32768,
|
| 235 |
+
"pad_token": "<|vision_pad|>",
|
| 236 |
+
"padding_side": "right",
|
| 237 |
+
"split_special_tokens": false,
|
| 238 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 239 |
+
"unk_token": null
|
| 240 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1434 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.03949447077409163,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 200,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.00019747235387045813,
|
| 14 |
+
"grad_norm": 5.788590908050537,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 1.0436,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.00039494470774091627,
|
| 21 |
+
"grad_norm": 6.300467491149902,
|
| 22 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 23 |
+
"loss": 1.3195,
|
| 24 |
+
"step": 2
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.0005924170616113745,
|
| 28 |
+
"grad_norm": 6.489816665649414,
|
| 29 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 30 |
+
"loss": 1.5645,
|
| 31 |
+
"step": 3
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.0007898894154818325,
|
| 35 |
+
"grad_norm": 5.287850379943848,
|
| 36 |
+
"learning_rate": 3e-06,
|
| 37 |
+
"loss": 1.154,
|
| 38 |
+
"step": 4
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.0009873617693522906,
|
| 42 |
+
"grad_norm": 6.123354434967041,
|
| 43 |
+
"learning_rate": 4.000000000000001e-06,
|
| 44 |
+
"loss": 1.4052,
|
| 45 |
+
"step": 5
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.001184834123222749,
|
| 49 |
+
"grad_norm": 5.501026630401611,
|
| 50 |
+
"learning_rate": 5e-06,
|
| 51 |
+
"loss": 1.708,
|
| 52 |
+
"step": 6
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.001382306477093207,
|
| 56 |
+
"grad_norm": 4.960855007171631,
|
| 57 |
+
"learning_rate": 6e-06,
|
| 58 |
+
"loss": 1.6143,
|
| 59 |
+
"step": 7
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.001579778830963665,
|
| 63 |
+
"grad_norm": 5.855900764465332,
|
| 64 |
+
"learning_rate": 7e-06,
|
| 65 |
+
"loss": 1.6376,
|
| 66 |
+
"step": 8
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.0017772511848341231,
|
| 70 |
+
"grad_norm": 5.17061710357666,
|
| 71 |
+
"learning_rate": 8.000000000000001e-06,
|
| 72 |
+
"loss": 1.2182,
|
| 73 |
+
"step": 9
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.0019747235387045812,
|
| 77 |
+
"grad_norm": 4.436169624328613,
|
| 78 |
+
"learning_rate": 9e-06,
|
| 79 |
+
"loss": 1.9812,
|
| 80 |
+
"step": 10
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.0021721958925750395,
|
| 84 |
+
"grad_norm": 4.55659818649292,
|
| 85 |
+
"learning_rate": 1e-05,
|
| 86 |
+
"loss": 1.1695,
|
| 87 |
+
"step": 11
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.002369668246445498,
|
| 91 |
+
"grad_norm": 5.105171203613281,
|
| 92 |
+
"learning_rate": 9.947368421052632e-06,
|
| 93 |
+
"loss": 1.1243,
|
| 94 |
+
"step": 12
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.0025671406003159557,
|
| 98 |
+
"grad_norm": 5.100945472717285,
|
| 99 |
+
"learning_rate": 9.894736842105264e-06,
|
| 100 |
+
"loss": 1.8183,
|
| 101 |
+
"step": 13
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.002764612954186414,
|
| 105 |
+
"grad_norm": 4.643738746643066,
|
| 106 |
+
"learning_rate": 9.842105263157896e-06,
|
| 107 |
+
"loss": 1.2569,
|
| 108 |
+
"step": 14
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.002962085308056872,
|
| 112 |
+
"grad_norm": 4.557013034820557,
|
| 113 |
+
"learning_rate": 9.789473684210527e-06,
|
| 114 |
+
"loss": 1.7372,
|
| 115 |
+
"step": 15
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.00315955766192733,
|
| 119 |
+
"grad_norm": 6.458473205566406,
|
| 120 |
+
"learning_rate": 9.736842105263159e-06,
|
| 121 |
+
"loss": 2.1888,
|
| 122 |
+
"step": 16
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.0033570300157977884,
|
| 126 |
+
"grad_norm": 5.135770320892334,
|
| 127 |
+
"learning_rate": 9.68421052631579e-06,
|
| 128 |
+
"loss": 1.2197,
|
| 129 |
+
"step": 17
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.0035545023696682463,
|
| 133 |
+
"grad_norm": 5.171187400817871,
|
| 134 |
+
"learning_rate": 9.631578947368422e-06,
|
| 135 |
+
"loss": 1.6326,
|
| 136 |
+
"step": 18
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.0037519747235387046,
|
| 140 |
+
"grad_norm": 4.825802326202393,
|
| 141 |
+
"learning_rate": 9.578947368421054e-06,
|
| 142 |
+
"loss": 1.4698,
|
| 143 |
+
"step": 19
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.0039494470774091624,
|
| 147 |
+
"grad_norm": 4.34477424621582,
|
| 148 |
+
"learning_rate": 9.526315789473684e-06,
|
| 149 |
+
"loss": 1.6102,
|
| 150 |
+
"step": 20
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.004146919431279621,
|
| 154 |
+
"grad_norm": 4.5733866691589355,
|
| 155 |
+
"learning_rate": 9.473684210526315e-06,
|
| 156 |
+
"loss": 1.8448,
|
| 157 |
+
"step": 21
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.004344391785150079,
|
| 161 |
+
"grad_norm": 4.53968620300293,
|
| 162 |
+
"learning_rate": 9.421052631578949e-06,
|
| 163 |
+
"loss": 1.2972,
|
| 164 |
+
"step": 22
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.004541864139020537,
|
| 168 |
+
"grad_norm": 5.408173084259033,
|
| 169 |
+
"learning_rate": 9.36842105263158e-06,
|
| 170 |
+
"loss": 1.7215,
|
| 171 |
+
"step": 23
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.004739336492890996,
|
| 175 |
+
"grad_norm": 4.2717461585998535,
|
| 176 |
+
"learning_rate": 9.315789473684212e-06,
|
| 177 |
+
"loss": 1.137,
|
| 178 |
+
"step": 24
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.0049368088467614535,
|
| 182 |
+
"grad_norm": 4.3075785636901855,
|
| 183 |
+
"learning_rate": 9.263157894736842e-06,
|
| 184 |
+
"loss": 1.3048,
|
| 185 |
+
"step": 25
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.005134281200631911,
|
| 189 |
+
"grad_norm": 4.659534454345703,
|
| 190 |
+
"learning_rate": 9.210526315789474e-06,
|
| 191 |
+
"loss": 0.9883,
|
| 192 |
+
"step": 26
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.00533175355450237,
|
| 196 |
+
"grad_norm": 4.719169616699219,
|
| 197 |
+
"learning_rate": 9.157894736842105e-06,
|
| 198 |
+
"loss": 1.4926,
|
| 199 |
+
"step": 27
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.005529225908372828,
|
| 203 |
+
"grad_norm": 4.502306938171387,
|
| 204 |
+
"learning_rate": 9.105263157894739e-06,
|
| 205 |
+
"loss": 1.8264,
|
| 206 |
+
"step": 28
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.005726698262243286,
|
| 210 |
+
"grad_norm": 4.353489875793457,
|
| 211 |
+
"learning_rate": 9.05263157894737e-06,
|
| 212 |
+
"loss": 1.6681,
|
| 213 |
+
"step": 29
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.005924170616113744,
|
| 217 |
+
"grad_norm": 5.161799907684326,
|
| 218 |
+
"learning_rate": 9e-06,
|
| 219 |
+
"loss": 1.6566,
|
| 220 |
+
"step": 30
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.006121642969984202,
|
| 224 |
+
"grad_norm": 4.235696315765381,
|
| 225 |
+
"learning_rate": 8.947368421052632e-06,
|
| 226 |
+
"loss": 1.7276,
|
| 227 |
+
"step": 31
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.00631911532385466,
|
| 231 |
+
"grad_norm": 6.545216083526611,
|
| 232 |
+
"learning_rate": 8.894736842105264e-06,
|
| 233 |
+
"loss": 1.0481,
|
| 234 |
+
"step": 32
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.006516587677725118,
|
| 238 |
+
"grad_norm": 4.9834113121032715,
|
| 239 |
+
"learning_rate": 8.842105263157895e-06,
|
| 240 |
+
"loss": 1.4457,
|
| 241 |
+
"step": 33
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.006714060031595577,
|
| 245 |
+
"grad_norm": 4.448666572570801,
|
| 246 |
+
"learning_rate": 8.789473684210527e-06,
|
| 247 |
+
"loss": 1.7361,
|
| 248 |
+
"step": 34
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.006911532385466035,
|
| 252 |
+
"grad_norm": 4.735658168792725,
|
| 253 |
+
"learning_rate": 8.736842105263158e-06,
|
| 254 |
+
"loss": 1.3361,
|
| 255 |
+
"step": 35
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.0071090047393364926,
|
| 259 |
+
"grad_norm": 5.857210636138916,
|
| 260 |
+
"learning_rate": 8.68421052631579e-06,
|
| 261 |
+
"loss": 1.4395,
|
| 262 |
+
"step": 36
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.007306477093206951,
|
| 266 |
+
"grad_norm": 4.746231555938721,
|
| 267 |
+
"learning_rate": 8.631578947368422e-06,
|
| 268 |
+
"loss": 1.4588,
|
| 269 |
+
"step": 37
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.007503949447077409,
|
| 273 |
+
"grad_norm": 5.420529365539551,
|
| 274 |
+
"learning_rate": 8.578947368421053e-06,
|
| 275 |
+
"loss": 1.4352,
|
| 276 |
+
"step": 38
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.007701421800947867,
|
| 280 |
+
"grad_norm": 3.966956853866577,
|
| 281 |
+
"learning_rate": 8.526315789473685e-06,
|
| 282 |
+
"loss": 1.7395,
|
| 283 |
+
"step": 39
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.007898894154818325,
|
| 287 |
+
"grad_norm": 4.626506805419922,
|
| 288 |
+
"learning_rate": 8.473684210526317e-06,
|
| 289 |
+
"loss": 1.2152,
|
| 290 |
+
"step": 40
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.008096366508688783,
|
| 294 |
+
"grad_norm": 5.946537971496582,
|
| 295 |
+
"learning_rate": 8.421052631578948e-06,
|
| 296 |
+
"loss": 1.2569,
|
| 297 |
+
"step": 41
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.008293838862559242,
|
| 301 |
+
"grad_norm": 6.078729152679443,
|
| 302 |
+
"learning_rate": 8.36842105263158e-06,
|
| 303 |
+
"loss": 2.0072,
|
| 304 |
+
"step": 42
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.0084913112164297,
|
| 308 |
+
"grad_norm": 5.362630844116211,
|
| 309 |
+
"learning_rate": 8.315789473684212e-06,
|
| 310 |
+
"loss": 1.6189,
|
| 311 |
+
"step": 43
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.008688783570300158,
|
| 315 |
+
"grad_norm": 4.6319098472595215,
|
| 316 |
+
"learning_rate": 8.263157894736843e-06,
|
| 317 |
+
"loss": 1.1937,
|
| 318 |
+
"step": 44
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.008886255924170616,
|
| 322 |
+
"grad_norm": 5.145988464355469,
|
| 323 |
+
"learning_rate": 8.210526315789475e-06,
|
| 324 |
+
"loss": 1.48,
|
| 325 |
+
"step": 45
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.009083728278041074,
|
| 329 |
+
"grad_norm": 5.191286563873291,
|
| 330 |
+
"learning_rate": 8.157894736842106e-06,
|
| 331 |
+
"loss": 1.6115,
|
| 332 |
+
"step": 46
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.009281200631911532,
|
| 336 |
+
"grad_norm": 4.6075544357299805,
|
| 337 |
+
"learning_rate": 8.105263157894736e-06,
|
| 338 |
+
"loss": 1.3963,
|
| 339 |
+
"step": 47
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.009478672985781991,
|
| 343 |
+
"grad_norm": 4.724617958068848,
|
| 344 |
+
"learning_rate": 8.052631578947368e-06,
|
| 345 |
+
"loss": 1.7869,
|
| 346 |
+
"step": 48
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.009676145339652449,
|
| 350 |
+
"grad_norm": 4.976570129394531,
|
| 351 |
+
"learning_rate": 8.000000000000001e-06,
|
| 352 |
+
"loss": 1.5635,
|
| 353 |
+
"step": 49
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.009873617693522907,
|
| 357 |
+
"grad_norm": 5.121829032897949,
|
| 358 |
+
"learning_rate": 7.947368421052633e-06,
|
| 359 |
+
"loss": 1.246,
|
| 360 |
+
"step": 50
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.010071090047393365,
|
| 364 |
+
"grad_norm": 5.260928153991699,
|
| 365 |
+
"learning_rate": 7.894736842105265e-06,
|
| 366 |
+
"loss": 1.98,
|
| 367 |
+
"step": 51
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.010268562401263823,
|
| 371 |
+
"grad_norm": 5.072506904602051,
|
| 372 |
+
"learning_rate": 7.842105263157895e-06,
|
| 373 |
+
"loss": 1.0555,
|
| 374 |
+
"step": 52
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.01046603475513428,
|
| 378 |
+
"grad_norm": 4.6401872634887695,
|
| 379 |
+
"learning_rate": 7.789473684210526e-06,
|
| 380 |
+
"loss": 1.5456,
|
| 381 |
+
"step": 53
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.01066350710900474,
|
| 385 |
+
"grad_norm": 5.566153526306152,
|
| 386 |
+
"learning_rate": 7.736842105263158e-06,
|
| 387 |
+
"loss": 1.7965,
|
| 388 |
+
"step": 54
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.010860979462875198,
|
| 392 |
+
"grad_norm": 5.0998215675354,
|
| 393 |
+
"learning_rate": 7.68421052631579e-06,
|
| 394 |
+
"loss": 1.3262,
|
| 395 |
+
"step": 55
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.011058451816745656,
|
| 399 |
+
"grad_norm": 4.437518119812012,
|
| 400 |
+
"learning_rate": 7.631578947368423e-06,
|
| 401 |
+
"loss": 1.7174,
|
| 402 |
+
"step": 56
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.011255924170616114,
|
| 406 |
+
"grad_norm": 3.8838698863983154,
|
| 407 |
+
"learning_rate": 7.578947368421054e-06,
|
| 408 |
+
"loss": 1.185,
|
| 409 |
+
"step": 57
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.011453396524486572,
|
| 413 |
+
"grad_norm": 4.112951278686523,
|
| 414 |
+
"learning_rate": 7.526315789473685e-06,
|
| 415 |
+
"loss": 1.3785,
|
| 416 |
+
"step": 58
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.01165086887835703,
|
| 420 |
+
"grad_norm": 4.612501621246338,
|
| 421 |
+
"learning_rate": 7.473684210526316e-06,
|
| 422 |
+
"loss": 1.2861,
|
| 423 |
+
"step": 59
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.011848341232227487,
|
| 427 |
+
"grad_norm": 4.541945457458496,
|
| 428 |
+
"learning_rate": 7.421052631578948e-06,
|
| 429 |
+
"loss": 1.0096,
|
| 430 |
+
"step": 60
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.012045813586097947,
|
| 434 |
+
"grad_norm": 6.567755699157715,
|
| 435 |
+
"learning_rate": 7.368421052631579e-06,
|
| 436 |
+
"loss": 1.0163,
|
| 437 |
+
"step": 61
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.012243285939968405,
|
| 441 |
+
"grad_norm": 4.897511959075928,
|
| 442 |
+
"learning_rate": 7.315789473684212e-06,
|
| 443 |
+
"loss": 1.8322,
|
| 444 |
+
"step": 62
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.012440758293838863,
|
| 448 |
+
"grad_norm": 4.3046064376831055,
|
| 449 |
+
"learning_rate": 7.263157894736843e-06,
|
| 450 |
+
"loss": 1.0891,
|
| 451 |
+
"step": 63
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.01263823064770932,
|
| 455 |
+
"grad_norm": 4.533966064453125,
|
| 456 |
+
"learning_rate": 7.210526315789474e-06,
|
| 457 |
+
"loss": 1.3371,
|
| 458 |
+
"step": 64
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.012835703001579778,
|
| 462 |
+
"grad_norm": 4.470656394958496,
|
| 463 |
+
"learning_rate": 7.157894736842106e-06,
|
| 464 |
+
"loss": 2.3414,
|
| 465 |
+
"step": 65
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.013033175355450236,
|
| 469 |
+
"grad_norm": 4.738101959228516,
|
| 470 |
+
"learning_rate": 7.1052631578947375e-06,
|
| 471 |
+
"loss": 1.765,
|
| 472 |
+
"step": 66
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.013230647709320696,
|
| 476 |
+
"grad_norm": 3.870649814605713,
|
| 477 |
+
"learning_rate": 7.052631578947369e-06,
|
| 478 |
+
"loss": 1.6424,
|
| 479 |
+
"step": 67
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.013428120063191154,
|
| 483 |
+
"grad_norm": 7.043670177459717,
|
| 484 |
+
"learning_rate": 7e-06,
|
| 485 |
+
"loss": 1.5049,
|
| 486 |
+
"step": 68
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.013625592417061612,
|
| 490 |
+
"grad_norm": 4.199113368988037,
|
| 491 |
+
"learning_rate": 6.947368421052632e-06,
|
| 492 |
+
"loss": 1.5253,
|
| 493 |
+
"step": 69
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.01382306477093207,
|
| 497 |
+
"grad_norm": 4.738468170166016,
|
| 498 |
+
"learning_rate": 6.894736842105264e-06,
|
| 499 |
+
"loss": 1.4544,
|
| 500 |
+
"step": 70
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.014020537124802527,
|
| 504 |
+
"grad_norm": 5.083221912384033,
|
| 505 |
+
"learning_rate": 6.842105263157896e-06,
|
| 506 |
+
"loss": 1.4874,
|
| 507 |
+
"step": 71
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.014218009478672985,
|
| 511 |
+
"grad_norm": 4.9555253982543945,
|
| 512 |
+
"learning_rate": 6.789473684210527e-06,
|
| 513 |
+
"loss": 1.7049,
|
| 514 |
+
"step": 72
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.014415481832543445,
|
| 518 |
+
"grad_norm": 4.266180992126465,
|
| 519 |
+
"learning_rate": 6.736842105263158e-06,
|
| 520 |
+
"loss": 1.2864,
|
| 521 |
+
"step": 73
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.014612954186413903,
|
| 525 |
+
"grad_norm": 4.510780334472656,
|
| 526 |
+
"learning_rate": 6.68421052631579e-06,
|
| 527 |
+
"loss": 1.4615,
|
| 528 |
+
"step": 74
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.01481042654028436,
|
| 532 |
+
"grad_norm": 4.075244426727295,
|
| 533 |
+
"learning_rate": 6.631578947368421e-06,
|
| 534 |
+
"loss": 1.0669,
|
| 535 |
+
"step": 75
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.015007898894154818,
|
| 539 |
+
"grad_norm": 4.169254302978516,
|
| 540 |
+
"learning_rate": 6.578947368421054e-06,
|
| 541 |
+
"loss": 1.4458,
|
| 542 |
+
"step": 76
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.015205371248025276,
|
| 546 |
+
"grad_norm": 4.540365695953369,
|
| 547 |
+
"learning_rate": 6.526315789473685e-06,
|
| 548 |
+
"loss": 1.4148,
|
| 549 |
+
"step": 77
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.015402843601895734,
|
| 553 |
+
"grad_norm": 4.700695037841797,
|
| 554 |
+
"learning_rate": 6.473684210526316e-06,
|
| 555 |
+
"loss": 2.0347,
|
| 556 |
+
"step": 78
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.015600315955766192,
|
| 560 |
+
"grad_norm": 4.982248306274414,
|
| 561 |
+
"learning_rate": 6.421052631578948e-06,
|
| 562 |
+
"loss": 1.3731,
|
| 563 |
+
"step": 79
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.01579778830963665,
|
| 567 |
+
"grad_norm": 5.1645941734313965,
|
| 568 |
+
"learning_rate": 6.3684210526315795e-06,
|
| 569 |
+
"loss": 1.1041,
|
| 570 |
+
"step": 80
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.015995260663507108,
|
| 574 |
+
"grad_norm": 3.988223075866699,
|
| 575 |
+
"learning_rate": 6.31578947368421e-06,
|
| 576 |
+
"loss": 1.8261,
|
| 577 |
+
"step": 81
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.016192733017377565,
|
| 581 |
+
"grad_norm": 5.132425785064697,
|
| 582 |
+
"learning_rate": 6.263157894736842e-06,
|
| 583 |
+
"loss": 1.3754,
|
| 584 |
+
"step": 82
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.016390205371248027,
|
| 588 |
+
"grad_norm": 4.158195972442627,
|
| 589 |
+
"learning_rate": 6.2105263157894745e-06,
|
| 590 |
+
"loss": 1.233,
|
| 591 |
+
"step": 83
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.016587677725118485,
|
| 595 |
+
"grad_norm": 5.385928630828857,
|
| 596 |
+
"learning_rate": 6.157894736842106e-06,
|
| 597 |
+
"loss": 1.6838,
|
| 598 |
+
"step": 84
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.016785150078988943,
|
| 602 |
+
"grad_norm": 4.63645076751709,
|
| 603 |
+
"learning_rate": 6.105263157894738e-06,
|
| 604 |
+
"loss": 1.9314,
|
| 605 |
+
"step": 85
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.0169826224328594,
|
| 609 |
+
"grad_norm": 5.3244757652282715,
|
| 610 |
+
"learning_rate": 6.0526315789473685e-06,
|
| 611 |
+
"loss": 1.4223,
|
| 612 |
+
"step": 86
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.017180094786729858,
|
| 616 |
+
"grad_norm": 4.603305339813232,
|
| 617 |
+
"learning_rate": 6e-06,
|
| 618 |
+
"loss": 1.7243,
|
| 619 |
+
"step": 87
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.017377567140600316,
|
| 623 |
+
"grad_norm": 5.223212718963623,
|
| 624 |
+
"learning_rate": 5.947368421052632e-06,
|
| 625 |
+
"loss": 1.337,
|
| 626 |
+
"step": 88
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.017575039494470774,
|
| 630 |
+
"grad_norm": 4.344864845275879,
|
| 631 |
+
"learning_rate": 5.8947368421052634e-06,
|
| 632 |
+
"loss": 1.4767,
|
| 633 |
+
"step": 89
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.017772511848341232,
|
| 637 |
+
"grad_norm": 4.268956184387207,
|
| 638 |
+
"learning_rate": 5.842105263157896e-06,
|
| 639 |
+
"loss": 1.0763,
|
| 640 |
+
"step": 90
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.01796998420221169,
|
| 644 |
+
"grad_norm": 4.882099151611328,
|
| 645 |
+
"learning_rate": 5.789473684210527e-06,
|
| 646 |
+
"loss": 1.7006,
|
| 647 |
+
"step": 91
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.018167456556082148,
|
| 651 |
+
"grad_norm": 5.254153728485107,
|
| 652 |
+
"learning_rate": 5.736842105263158e-06,
|
| 653 |
+
"loss": 2.0318,
|
| 654 |
+
"step": 92
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.018364928909952605,
|
| 658 |
+
"grad_norm": 4.496589660644531,
|
| 659 |
+
"learning_rate": 5.68421052631579e-06,
|
| 660 |
+
"loss": 1.0075,
|
| 661 |
+
"step": 93
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.018562401263823063,
|
| 665 |
+
"grad_norm": 4.610377788543701,
|
| 666 |
+
"learning_rate": 5.631578947368422e-06,
|
| 667 |
+
"loss": 0.973,
|
| 668 |
+
"step": 94
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.018759873617693525,
|
| 672 |
+
"grad_norm": 4.102587699890137,
|
| 673 |
+
"learning_rate": 5.578947368421052e-06,
|
| 674 |
+
"loss": 1.4508,
|
| 675 |
+
"step": 95
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.018957345971563982,
|
| 679 |
+
"grad_norm": 4.820801258087158,
|
| 680 |
+
"learning_rate": 5.526315789473685e-06,
|
| 681 |
+
"loss": 2.234,
|
| 682 |
+
"step": 96
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.01915481832543444,
|
| 686 |
+
"grad_norm": 4.17614221572876,
|
| 687 |
+
"learning_rate": 5.4736842105263165e-06,
|
| 688 |
+
"loss": 0.9472,
|
| 689 |
+
"step": 97
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.019352290679304898,
|
| 693 |
+
"grad_norm": 4.681643962860107,
|
| 694 |
+
"learning_rate": 5.421052631578948e-06,
|
| 695 |
+
"loss": 0.952,
|
| 696 |
+
"step": 98
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.019549763033175356,
|
| 700 |
+
"grad_norm": 4.793570041656494,
|
| 701 |
+
"learning_rate": 5.36842105263158e-06,
|
| 702 |
+
"loss": 2.1524,
|
| 703 |
+
"step": 99
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.019747235387045814,
|
| 707 |
+
"grad_norm": 5.580649375915527,
|
| 708 |
+
"learning_rate": 5.315789473684211e-06,
|
| 709 |
+
"loss": 1.168,
|
| 710 |
+
"step": 100
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.019944707740916272,
|
| 714 |
+
"grad_norm": 4.42297887802124,
|
| 715 |
+
"learning_rate": 5.263157894736842e-06,
|
| 716 |
+
"loss": 1.0549,
|
| 717 |
+
"step": 101
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.02014218009478673,
|
| 721 |
+
"grad_norm": 4.290710926055908,
|
| 722 |
+
"learning_rate": 5.210526315789474e-06,
|
| 723 |
+
"loss": 1.4328,
|
| 724 |
+
"step": 102
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.020339652448657188,
|
| 728 |
+
"grad_norm": 4.0357255935668945,
|
| 729 |
+
"learning_rate": 5.157894736842106e-06,
|
| 730 |
+
"loss": 0.9894,
|
| 731 |
+
"step": 103
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.020537124802527645,
|
| 735 |
+
"grad_norm": 4.805973529815674,
|
| 736 |
+
"learning_rate": 5.105263157894738e-06,
|
| 737 |
+
"loss": 1.3093,
|
| 738 |
+
"step": 104
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.020734597156398103,
|
| 742 |
+
"grad_norm": 4.185112953186035,
|
| 743 |
+
"learning_rate": 5.052631578947369e-06,
|
| 744 |
+
"loss": 1.4606,
|
| 745 |
+
"step": 105
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.02093206951026856,
|
| 749 |
+
"grad_norm": 4.384559631347656,
|
| 750 |
+
"learning_rate": 5e-06,
|
| 751 |
+
"loss": 1.0051,
|
| 752 |
+
"step": 106
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.02112954186413902,
|
| 756 |
+
"grad_norm": 4.920189380645752,
|
| 757 |
+
"learning_rate": 4.947368421052632e-06,
|
| 758 |
+
"loss": 1.1721,
|
| 759 |
+
"step": 107
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.02132701421800948,
|
| 763 |
+
"grad_norm": 4.506773471832275,
|
| 764 |
+
"learning_rate": 4.894736842105264e-06,
|
| 765 |
+
"loss": 1.4764,
|
| 766 |
+
"step": 108
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.021524486571879938,
|
| 770 |
+
"grad_norm": 4.980959415435791,
|
| 771 |
+
"learning_rate": 4.842105263157895e-06,
|
| 772 |
+
"loss": 1.1304,
|
| 773 |
+
"step": 109
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.021721958925750396,
|
| 777 |
+
"grad_norm": 4.118868827819824,
|
| 778 |
+
"learning_rate": 4.789473684210527e-06,
|
| 779 |
+
"loss": 1.1892,
|
| 780 |
+
"step": 110
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.021919431279620854,
|
| 784 |
+
"grad_norm": 6.19287109375,
|
| 785 |
+
"learning_rate": 4.736842105263158e-06,
|
| 786 |
+
"loss": 1.6254,
|
| 787 |
+
"step": 111
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.022116903633491312,
|
| 791 |
+
"grad_norm": 5.811559200286865,
|
| 792 |
+
"learning_rate": 4.68421052631579e-06,
|
| 793 |
+
"loss": 1.8662,
|
| 794 |
+
"step": 112
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.02231437598736177,
|
| 798 |
+
"grad_norm": 4.6513352394104,
|
| 799 |
+
"learning_rate": 4.631578947368421e-06,
|
| 800 |
+
"loss": 1.3816,
|
| 801 |
+
"step": 113
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.022511848341232227,
|
| 805 |
+
"grad_norm": 5.178617477416992,
|
| 806 |
+
"learning_rate": 4.578947368421053e-06,
|
| 807 |
+
"loss": 1.2535,
|
| 808 |
+
"step": 114
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.022709320695102685,
|
| 812 |
+
"grad_norm": 3.830137014389038,
|
| 813 |
+
"learning_rate": 4.526315789473685e-06,
|
| 814 |
+
"loss": 1.5312,
|
| 815 |
+
"step": 115
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.022906793048973143,
|
| 819 |
+
"grad_norm": 4.620641231536865,
|
| 820 |
+
"learning_rate": 4.473684210526316e-06,
|
| 821 |
+
"loss": 1.5528,
|
| 822 |
+
"step": 116
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.0231042654028436,
|
| 826 |
+
"grad_norm": 5.0326738357543945,
|
| 827 |
+
"learning_rate": 4.4210526315789476e-06,
|
| 828 |
+
"loss": 1.3443,
|
| 829 |
+
"step": 117
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.02330173775671406,
|
| 833 |
+
"grad_norm": 4.62188720703125,
|
| 834 |
+
"learning_rate": 4.368421052631579e-06,
|
| 835 |
+
"loss": 1.0445,
|
| 836 |
+
"step": 118
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.023499210110584517,
|
| 840 |
+
"grad_norm": 3.9635679721832275,
|
| 841 |
+
"learning_rate": 4.315789473684211e-06,
|
| 842 |
+
"loss": 1.5812,
|
| 843 |
+
"step": 119
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.023696682464454975,
|
| 847 |
+
"grad_norm": 5.0226664543151855,
|
| 848 |
+
"learning_rate": 4.2631578947368425e-06,
|
| 849 |
+
"loss": 1.2235,
|
| 850 |
+
"step": 120
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.023894154818325436,
|
| 854 |
+
"grad_norm": 5.353757858276367,
|
| 855 |
+
"learning_rate": 4.210526315789474e-06,
|
| 856 |
+
"loss": 1.5831,
|
| 857 |
+
"step": 121
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.024091627172195894,
|
| 861 |
+
"grad_norm": 4.838202476501465,
|
| 862 |
+
"learning_rate": 4.157894736842106e-06,
|
| 863 |
+
"loss": 1.7689,
|
| 864 |
+
"step": 122
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.02428909952606635,
|
| 868 |
+
"grad_norm": 4.49991512298584,
|
| 869 |
+
"learning_rate": 4.105263157894737e-06,
|
| 870 |
+
"loss": 0.828,
|
| 871 |
+
"step": 123
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.02448657187993681,
|
| 875 |
+
"grad_norm": 4.480604648590088,
|
| 876 |
+
"learning_rate": 4.052631578947368e-06,
|
| 877 |
+
"loss": 1.6869,
|
| 878 |
+
"step": 124
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.024684044233807267,
|
| 882 |
+
"grad_norm": 4.725250244140625,
|
| 883 |
+
"learning_rate": 4.000000000000001e-06,
|
| 884 |
+
"loss": 0.7038,
|
| 885 |
+
"step": 125
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.024881516587677725,
|
| 889 |
+
"grad_norm": 4.806907653808594,
|
| 890 |
+
"learning_rate": 3.947368421052632e-06,
|
| 891 |
+
"loss": 1.6985,
|
| 892 |
+
"step": 126
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.025078988941548183,
|
| 896 |
+
"grad_norm": 4.734091758728027,
|
| 897 |
+
"learning_rate": 3.894736842105263e-06,
|
| 898 |
+
"loss": 1.5138,
|
| 899 |
+
"step": 127
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.02527646129541864,
|
| 903 |
+
"grad_norm": 5.3406243324279785,
|
| 904 |
+
"learning_rate": 3.842105263157895e-06,
|
| 905 |
+
"loss": 1.7152,
|
| 906 |
+
"step": 128
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.0254739336492891,
|
| 910 |
+
"grad_norm": 4.890450477600098,
|
| 911 |
+
"learning_rate": 3.789473684210527e-06,
|
| 912 |
+
"loss": 1.734,
|
| 913 |
+
"step": 129
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.025671406003159557,
|
| 917 |
+
"grad_norm": 5.458994388580322,
|
| 918 |
+
"learning_rate": 3.736842105263158e-06,
|
| 919 |
+
"loss": 1.5888,
|
| 920 |
+
"step": 130
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.025868878357030015,
|
| 924 |
+
"grad_norm": 4.655605316162109,
|
| 925 |
+
"learning_rate": 3.6842105263157896e-06,
|
| 926 |
+
"loss": 1.7478,
|
| 927 |
+
"step": 131
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.026066350710900472,
|
| 931 |
+
"grad_norm": 7.664575576782227,
|
| 932 |
+
"learning_rate": 3.6315789473684217e-06,
|
| 933 |
+
"loss": 1.5616,
|
| 934 |
+
"step": 132
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.026263823064770934,
|
| 938 |
+
"grad_norm": 5.207353115081787,
|
| 939 |
+
"learning_rate": 3.578947368421053e-06,
|
| 940 |
+
"loss": 1.8918,
|
| 941 |
+
"step": 133
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.02646129541864139,
|
| 945 |
+
"grad_norm": 3.969021797180176,
|
| 946 |
+
"learning_rate": 3.5263157894736846e-06,
|
| 947 |
+
"loss": 1.0807,
|
| 948 |
+
"step": 134
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.02665876777251185,
|
| 952 |
+
"grad_norm": 5.148044586181641,
|
| 953 |
+
"learning_rate": 3.473684210526316e-06,
|
| 954 |
+
"loss": 1.5419,
|
| 955 |
+
"step": 135
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.026856240126382307,
|
| 959 |
+
"grad_norm": 5.609622955322266,
|
| 960 |
+
"learning_rate": 3.421052631578948e-06,
|
| 961 |
+
"loss": 1.2194,
|
| 962 |
+
"step": 136
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.027053712480252765,
|
| 966 |
+
"grad_norm": 4.281411170959473,
|
| 967 |
+
"learning_rate": 3.368421052631579e-06,
|
| 968 |
+
"loss": 0.9111,
|
| 969 |
+
"step": 137
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.027251184834123223,
|
| 973 |
+
"grad_norm": 4.415678977966309,
|
| 974 |
+
"learning_rate": 3.3157894736842107e-06,
|
| 975 |
+
"loss": 1.999,
|
| 976 |
+
"step": 138
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.02744865718799368,
|
| 980 |
+
"grad_norm": 4.46459436416626,
|
| 981 |
+
"learning_rate": 3.2631578947368423e-06,
|
| 982 |
+
"loss": 1.749,
|
| 983 |
+
"step": 139
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.02764612954186414,
|
| 987 |
+
"grad_norm": 4.180970191955566,
|
| 988 |
+
"learning_rate": 3.210526315789474e-06,
|
| 989 |
+
"loss": 1.4696,
|
| 990 |
+
"step": 140
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.027843601895734597,
|
| 994 |
+
"grad_norm": 4.308414459228516,
|
| 995 |
+
"learning_rate": 3.157894736842105e-06,
|
| 996 |
+
"loss": 1.6192,
|
| 997 |
+
"step": 141
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.028041074249605055,
|
| 1001 |
+
"grad_norm": 6.27396821975708,
|
| 1002 |
+
"learning_rate": 3.1052631578947372e-06,
|
| 1003 |
+
"loss": 0.9774,
|
| 1004 |
+
"step": 142
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.028238546603475512,
|
| 1008 |
+
"grad_norm": 5.713791847229004,
|
| 1009 |
+
"learning_rate": 3.052631578947369e-06,
|
| 1010 |
+
"loss": 1.2108,
|
| 1011 |
+
"step": 143
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.02843601895734597,
|
| 1015 |
+
"grad_norm": 3.94455885887146,
|
| 1016 |
+
"learning_rate": 3e-06,
|
| 1017 |
+
"loss": 0.928,
|
| 1018 |
+
"step": 144
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.028633491311216428,
|
| 1022 |
+
"grad_norm": 3.577357769012451,
|
| 1023 |
+
"learning_rate": 2.9473684210526317e-06,
|
| 1024 |
+
"loss": 1.2109,
|
| 1025 |
+
"step": 145
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.02883096366508689,
|
| 1029 |
+
"grad_norm": 4.142393112182617,
|
| 1030 |
+
"learning_rate": 2.8947368421052634e-06,
|
| 1031 |
+
"loss": 0.8309,
|
| 1032 |
+
"step": 146
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.029028436018957347,
|
| 1036 |
+
"grad_norm": 5.459789276123047,
|
| 1037 |
+
"learning_rate": 2.842105263157895e-06,
|
| 1038 |
+
"loss": 1.6238,
|
| 1039 |
+
"step": 147
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.029225908372827805,
|
| 1043 |
+
"grad_norm": 4.358528137207031,
|
| 1044 |
+
"learning_rate": 2.789473684210526e-06,
|
| 1045 |
+
"loss": 1.2229,
|
| 1046 |
+
"step": 148
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.029423380726698263,
|
| 1050 |
+
"grad_norm": 4.201858043670654,
|
| 1051 |
+
"learning_rate": 2.7368421052631583e-06,
|
| 1052 |
+
"loss": 0.8191,
|
| 1053 |
+
"step": 149
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.02962085308056872,
|
| 1057 |
+
"grad_norm": 5.12843656539917,
|
| 1058 |
+
"learning_rate": 2.68421052631579e-06,
|
| 1059 |
+
"loss": 2.0575,
|
| 1060 |
+
"step": 150
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.02981832543443918,
|
| 1064 |
+
"grad_norm": 3.9480583667755127,
|
| 1065 |
+
"learning_rate": 2.631578947368421e-06,
|
| 1066 |
+
"loss": 1.2752,
|
| 1067 |
+
"step": 151
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.030015797788309637,
|
| 1071 |
+
"grad_norm": 4.900203227996826,
|
| 1072 |
+
"learning_rate": 2.578947368421053e-06,
|
| 1073 |
+
"loss": 0.6156,
|
| 1074 |
+
"step": 152
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.030213270142180094,
|
| 1078 |
+
"grad_norm": 5.017102241516113,
|
| 1079 |
+
"learning_rate": 2.5263157894736844e-06,
|
| 1080 |
+
"loss": 1.4791,
|
| 1081 |
+
"step": 153
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.030410742496050552,
|
| 1085 |
+
"grad_norm": 4.326578140258789,
|
| 1086 |
+
"learning_rate": 2.473684210526316e-06,
|
| 1087 |
+
"loss": 1.1194,
|
| 1088 |
+
"step": 154
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.03060821484992101,
|
| 1092 |
+
"grad_norm": 4.385910511016846,
|
| 1093 |
+
"learning_rate": 2.4210526315789477e-06,
|
| 1094 |
+
"loss": 1.8029,
|
| 1095 |
+
"step": 155
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.030805687203791468,
|
| 1099 |
+
"grad_norm": 3.988187551498413,
|
| 1100 |
+
"learning_rate": 2.368421052631579e-06,
|
| 1101 |
+
"loss": 0.9693,
|
| 1102 |
+
"step": 156
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.031003159557661926,
|
| 1106 |
+
"grad_norm": 4.455026149749756,
|
| 1107 |
+
"learning_rate": 2.3157894736842105e-06,
|
| 1108 |
+
"loss": 1.3069,
|
| 1109 |
+
"step": 157
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.031200631911532384,
|
| 1113 |
+
"grad_norm": 5.547366142272949,
|
| 1114 |
+
"learning_rate": 2.2631578947368426e-06,
|
| 1115 |
+
"loss": 1.5911,
|
| 1116 |
+
"step": 158
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.03139810426540284,
|
| 1120 |
+
"grad_norm": 5.407074928283691,
|
| 1121 |
+
"learning_rate": 2.2105263157894738e-06,
|
| 1122 |
+
"loss": 1.4276,
|
| 1123 |
+
"step": 159
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.0315955766192733,
|
| 1127 |
+
"grad_norm": 4.332579135894775,
|
| 1128 |
+
"learning_rate": 2.1578947368421054e-06,
|
| 1129 |
+
"loss": 1.0162,
|
| 1130 |
+
"step": 160
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.03179304897314376,
|
| 1134 |
+
"grad_norm": 4.770085334777832,
|
| 1135 |
+
"learning_rate": 2.105263157894737e-06,
|
| 1136 |
+
"loss": 1.5811,
|
| 1137 |
+
"step": 161
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.031990521327014215,
|
| 1141 |
+
"grad_norm": 4.930882930755615,
|
| 1142 |
+
"learning_rate": 2.0526315789473687e-06,
|
| 1143 |
+
"loss": 1.1303,
|
| 1144 |
+
"step": 162
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.03218799368088467,
|
| 1148 |
+
"grad_norm": 5.203794479370117,
|
| 1149 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 1150 |
+
"loss": 1.135,
|
| 1151 |
+
"step": 163
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.03238546603475513,
|
| 1155 |
+
"grad_norm": 3.9070425033569336,
|
| 1156 |
+
"learning_rate": 1.9473684210526315e-06,
|
| 1157 |
+
"loss": 0.9977,
|
| 1158 |
+
"step": 164
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.032582938388625596,
|
| 1162 |
+
"grad_norm": 5.830733299255371,
|
| 1163 |
+
"learning_rate": 1.8947368421052634e-06,
|
| 1164 |
+
"loss": 1.8587,
|
| 1165 |
+
"step": 165
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.032780410742496054,
|
| 1169 |
+
"grad_norm": 4.05476713180542,
|
| 1170 |
+
"learning_rate": 1.8421052631578948e-06,
|
| 1171 |
+
"loss": 1.9495,
|
| 1172 |
+
"step": 166
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.03297788309636651,
|
| 1176 |
+
"grad_norm": 3.980226755142212,
|
| 1177 |
+
"learning_rate": 1.7894736842105265e-06,
|
| 1178 |
+
"loss": 1.6,
|
| 1179 |
+
"step": 167
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.03317535545023697,
|
| 1183 |
+
"grad_norm": 6.381178379058838,
|
| 1184 |
+
"learning_rate": 1.736842105263158e-06,
|
| 1185 |
+
"loss": 1.6905,
|
| 1186 |
+
"step": 168
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.03337282780410743,
|
| 1190 |
+
"grad_norm": 4.4184889793396,
|
| 1191 |
+
"learning_rate": 1.6842105263157895e-06,
|
| 1192 |
+
"loss": 1.4703,
|
| 1193 |
+
"step": 169
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.033570300157977885,
|
| 1197 |
+
"grad_norm": 4.5157470703125,
|
| 1198 |
+
"learning_rate": 1.6315789473684212e-06,
|
| 1199 |
+
"loss": 1.273,
|
| 1200 |
+
"step": 170
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.03376777251184834,
|
| 1204 |
+
"grad_norm": 4.454701900482178,
|
| 1205 |
+
"learning_rate": 1.5789473684210526e-06,
|
| 1206 |
+
"loss": 1.9122,
|
| 1207 |
+
"step": 171
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.0339652448657188,
|
| 1211 |
+
"grad_norm": 4.891290664672852,
|
| 1212 |
+
"learning_rate": 1.5263157894736844e-06,
|
| 1213 |
+
"loss": 1.514,
|
| 1214 |
+
"step": 172
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.03416271721958926,
|
| 1218 |
+
"grad_norm": 4.397899627685547,
|
| 1219 |
+
"learning_rate": 1.4736842105263159e-06,
|
| 1220 |
+
"loss": 1.7544,
|
| 1221 |
+
"step": 173
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.034360189573459717,
|
| 1225 |
+
"grad_norm": 5.422823429107666,
|
| 1226 |
+
"learning_rate": 1.4210526315789475e-06,
|
| 1227 |
+
"loss": 1.5294,
|
| 1228 |
+
"step": 174
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.034557661927330174,
|
| 1232 |
+
"grad_norm": 5.267470359802246,
|
| 1233 |
+
"learning_rate": 1.3684210526315791e-06,
|
| 1234 |
+
"loss": 1.2176,
|
| 1235 |
+
"step": 175
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.03475513428120063,
|
| 1239 |
+
"grad_norm": 4.583755016326904,
|
| 1240 |
+
"learning_rate": 1.3157894736842106e-06,
|
| 1241 |
+
"loss": 1.3583,
|
| 1242 |
+
"step": 176
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.03495260663507109,
|
| 1246 |
+
"grad_norm": 4.745589733123779,
|
| 1247 |
+
"learning_rate": 1.2631578947368422e-06,
|
| 1248 |
+
"loss": 1.6765,
|
| 1249 |
+
"step": 177
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.03515007898894155,
|
| 1253 |
+
"grad_norm": 4.703863620758057,
|
| 1254 |
+
"learning_rate": 1.2105263157894738e-06,
|
| 1255 |
+
"loss": 1.2263,
|
| 1256 |
+
"step": 178
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.035347551342812006,
|
| 1260 |
+
"grad_norm": 4.113995552062988,
|
| 1261 |
+
"learning_rate": 1.1578947368421053e-06,
|
| 1262 |
+
"loss": 1.8098,
|
| 1263 |
+
"step": 179
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.035545023696682464,
|
| 1267 |
+
"grad_norm": 5.088428020477295,
|
| 1268 |
+
"learning_rate": 1.1052631578947369e-06,
|
| 1269 |
+
"loss": 1.7887,
|
| 1270 |
+
"step": 180
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.03574249605055292,
|
| 1274 |
+
"grad_norm": 4.361863613128662,
|
| 1275 |
+
"learning_rate": 1.0526315789473685e-06,
|
| 1276 |
+
"loss": 1.8482,
|
| 1277 |
+
"step": 181
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.03593996840442338,
|
| 1281 |
+
"grad_norm": 3.7712790966033936,
|
| 1282 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1283 |
+
"loss": 1.0318,
|
| 1284 |
+
"step": 182
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.03613744075829384,
|
| 1288 |
+
"grad_norm": 4.38617467880249,
|
| 1289 |
+
"learning_rate": 9.473684210526317e-07,
|
| 1290 |
+
"loss": 1.1747,
|
| 1291 |
+
"step": 183
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.036334913112164295,
|
| 1295 |
+
"grad_norm": 4.757498741149902,
|
| 1296 |
+
"learning_rate": 8.947368421052632e-07,
|
| 1297 |
+
"loss": 1.591,
|
| 1298 |
+
"step": 184
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.03653238546603475,
|
| 1302 |
+
"grad_norm": 4.661401748657227,
|
| 1303 |
+
"learning_rate": 8.421052631578948e-07,
|
| 1304 |
+
"loss": 1.2443,
|
| 1305 |
+
"step": 185
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.03672985781990521,
|
| 1309 |
+
"grad_norm": 4.178214073181152,
|
| 1310 |
+
"learning_rate": 7.894736842105263e-07,
|
| 1311 |
+
"loss": 1.6486,
|
| 1312 |
+
"step": 186
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.03692733017377567,
|
| 1316 |
+
"grad_norm": 4.652418613433838,
|
| 1317 |
+
"learning_rate": 7.368421052631579e-07,
|
| 1318 |
+
"loss": 1.7046,
|
| 1319 |
+
"step": 187
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.03712480252764613,
|
| 1323 |
+
"grad_norm": 5.367217540740967,
|
| 1324 |
+
"learning_rate": 6.842105263157896e-07,
|
| 1325 |
+
"loss": 1.1643,
|
| 1326 |
+
"step": 188
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.037322274881516584,
|
| 1330 |
+
"grad_norm": 5.026525020599365,
|
| 1331 |
+
"learning_rate": 6.315789473684211e-07,
|
| 1332 |
+
"loss": 1.8984,
|
| 1333 |
+
"step": 189
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.03751974723538705,
|
| 1337 |
+
"grad_norm": 5.15156888961792,
|
| 1338 |
+
"learning_rate": 5.789473684210526e-07,
|
| 1339 |
+
"loss": 1.199,
|
| 1340 |
+
"step": 190
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.03771721958925751,
|
| 1344 |
+
"grad_norm": 4.1339111328125,
|
| 1345 |
+
"learning_rate": 5.263157894736843e-07,
|
| 1346 |
+
"loss": 1.2138,
|
| 1347 |
+
"step": 191
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.037914691943127965,
|
| 1351 |
+
"grad_norm": 4.904068946838379,
|
| 1352 |
+
"learning_rate": 4.7368421052631585e-07,
|
| 1353 |
+
"loss": 0.9992,
|
| 1354 |
+
"step": 192
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.03811216429699842,
|
| 1358 |
+
"grad_norm": 4.655853271484375,
|
| 1359 |
+
"learning_rate": 4.210526315789474e-07,
|
| 1360 |
+
"loss": 0.9699,
|
| 1361 |
+
"step": 193
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.03830963665086888,
|
| 1365 |
+
"grad_norm": 4.786022663116455,
|
| 1366 |
+
"learning_rate": 3.6842105263157896e-07,
|
| 1367 |
+
"loss": 1.1047,
|
| 1368 |
+
"step": 194
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.03850710900473934,
|
| 1372 |
+
"grad_norm": 4.2019362449646,
|
| 1373 |
+
"learning_rate": 3.1578947368421055e-07,
|
| 1374 |
+
"loss": 1.3494,
|
| 1375 |
+
"step": 195
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.038704581358609796,
|
| 1379 |
+
"grad_norm": 4.608132839202881,
|
| 1380 |
+
"learning_rate": 2.6315789473684213e-07,
|
| 1381 |
+
"loss": 1.5102,
|
| 1382 |
+
"step": 196
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.038902053712480254,
|
| 1386 |
+
"grad_norm": 3.955866813659668,
|
| 1387 |
+
"learning_rate": 2.105263157894737e-07,
|
| 1388 |
+
"loss": 0.9329,
|
| 1389 |
+
"step": 197
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.03909952606635071,
|
| 1393 |
+
"grad_norm": 3.948068857192993,
|
| 1394 |
+
"learning_rate": 1.5789473684210527e-07,
|
| 1395 |
+
"loss": 0.9115,
|
| 1396 |
+
"step": 198
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.03929699842022117,
|
| 1400 |
+
"grad_norm": 4.394677639007568,
|
| 1401 |
+
"learning_rate": 1.0526315789473685e-07,
|
| 1402 |
+
"loss": 0.842,
|
| 1403 |
+
"step": 199
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.03949447077409163,
|
| 1407 |
+
"grad_norm": 4.138340473175049,
|
| 1408 |
+
"learning_rate": 5.263157894736842e-08,
|
| 1409 |
+
"loss": 1.0818,
|
| 1410 |
+
"step": 200
|
| 1411 |
+
}
|
| 1412 |
+
],
|
| 1413 |
+
"logging_steps": 1,
|
| 1414 |
+
"max_steps": 200,
|
| 1415 |
+
"num_input_tokens_seen": 0,
|
| 1416 |
+
"num_train_epochs": 1,
|
| 1417 |
+
"save_steps": 500,
|
| 1418 |
+
"stateful_callbacks": {
|
| 1419 |
+
"TrainerControl": {
|
| 1420 |
+
"args": {
|
| 1421 |
+
"should_epoch_stop": false,
|
| 1422 |
+
"should_evaluate": false,
|
| 1423 |
+
"should_log": false,
|
| 1424 |
+
"should_save": true,
|
| 1425 |
+
"should_training_stop": true
|
| 1426 |
+
},
|
| 1427 |
+
"attributes": {}
|
| 1428 |
+
}
|
| 1429 |
+
},
|
| 1430 |
+
"total_flos": 6305414963527680.0,
|
| 1431 |
+
"train_batch_size": 4,
|
| 1432 |
+
"trial_name": null,
|
| 1433 |
+
"trial_params": null
|
| 1434 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7cbea050b55f31497b6be2f0869c49066f2f601d76bf1b3f527cb6528ae9ffc
|
| 3 |
+
size 5496
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|