Training in progress, step 2500, checkpoint
Browse files- last-checkpoint/config.json +47 -0
- last-checkpoint/model.safetensors +3 -0
- last-checkpoint/optimizer.pt +3 -0
- last-checkpoint/rng_state_0.pth +3 -0
- last-checkpoint/rng_state_1.pth +3 -0
- last-checkpoint/rng_state_2.pth +3 -0
- last-checkpoint/rng_state_3.pth +3 -0
- last-checkpoint/rng_state_4.pth +3 -0
- last-checkpoint/rng_state_5.pth +3 -0
- last-checkpoint/rng_state_6.pth +3 -0
- last-checkpoint/rng_state_7.pth +3 -0
- last-checkpoint/scheduler.pt +3 -0
- last-checkpoint/special_tokens_map.json +37 -0
- last-checkpoint/tokenizer.json +0 -0
- last-checkpoint/tokenizer_config.json +945 -0
- last-checkpoint/trainer_state.json +1791 -0
- last-checkpoint/training_args.bin +3 -0
last-checkpoint/config.json
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "CocoRoF/KoModernBERT-base-mlm-v04-retry-model-chp19",
|
3 |
+
"architectures": [
|
4 |
+
"ModernBertForMaskedLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 50281,
|
9 |
+
"classifier_activation": "gelu",
|
10 |
+
"classifier_bias": false,
|
11 |
+
"classifier_dropout": 0.0,
|
12 |
+
"classifier_pooling": "mean",
|
13 |
+
"cls_token_id": 50281,
|
14 |
+
"decoder_bias": true,
|
15 |
+
"deterministic_flash_attn": false,
|
16 |
+
"embedding_dropout": 0.0,
|
17 |
+
"eos_token_id": 50282,
|
18 |
+
"global_attn_every_n_layers": 3,
|
19 |
+
"global_rope_theta": 160000.0,
|
20 |
+
"gradient_checkpointing": false,
|
21 |
+
"hidden_activation": "gelu",
|
22 |
+
"hidden_size": 768,
|
23 |
+
"initializer_cutoff_factor": 2.0,
|
24 |
+
"initializer_range": 0.02,
|
25 |
+
"intermediate_size": 1152,
|
26 |
+
"layer_norm_eps": 1e-05,
|
27 |
+
"local_attention": 128,
|
28 |
+
"local_rope_theta": 10000.0,
|
29 |
+
"max_position_embeddings": 8192,
|
30 |
+
"mlp_bias": false,
|
31 |
+
"mlp_dropout": 0.0,
|
32 |
+
"model_type": "modernbert",
|
33 |
+
"norm_bias": false,
|
34 |
+
"norm_eps": 1e-05,
|
35 |
+
"num_attention_heads": 12,
|
36 |
+
"num_hidden_layers": 22,
|
37 |
+
"pad_token_id": 50283,
|
38 |
+
"position_embedding_type": "absolute",
|
39 |
+
"reference_compile": false,
|
40 |
+
"repad_logits_with_grad": false,
|
41 |
+
"sep_token_id": 50282,
|
42 |
+
"sparse_pred_ignore_index": -100,
|
43 |
+
"sparse_prediction": false,
|
44 |
+
"torch_dtype": "float16",
|
45 |
+
"transformers_version": "4.48.3",
|
46 |
+
"vocab_size": 95663
|
47 |
+
}
|
last-checkpoint/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:03632c864a1897793ac5db77b6c638ec0fa66a013205214a57dbe9026124507c
|
3 |
+
size 368988278
|
last-checkpoint/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:970c8b3143142e8f7e4f2cd973f6e741a57f447633aec2d39ea0a2f74b8bfb3f
|
3 |
+
size 1107079290
|
last-checkpoint/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:78d3f197f6c6558fa8056324f1563ab9e957255f5a1a959362aa4eed7a9545db
|
3 |
+
size 15984
|
last-checkpoint/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c1a9c65c2869356282cad6b4a0f7dff7f4dd68ab3d9d216c72b7d6cb524f860
|
3 |
+
size 15984
|
last-checkpoint/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:896febe768e17bae5022a95960c041f6425783774ec8859d99d3b149063b1bf9
|
3 |
+
size 15984
|
last-checkpoint/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eac482d57e966585467c8ef44dae2869bf7e5d92886f69c11ed7bccc34c07efe
|
3 |
+
size 15984
|
last-checkpoint/rng_state_4.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e1f27d227a20dc320ac283e0938fb2f6e5b475829a583f8c44d1a16a8c828307
|
3 |
+
size 15984
|
last-checkpoint/rng_state_5.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d05a7106aaeaec4b81704e3f4a998b5123cf9342a6733bd9fd2d578e99108c3b
|
3 |
+
size 15984
|
last-checkpoint/rng_state_6.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b94120d8d88502ec8d8b623ec7550315caca003b44fcffbb5767ab0de91baefe
|
3 |
+
size 15984
|
last-checkpoint/rng_state_7.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:332e4d901be380f740b5d8578f7b80ef1865c7fba83bc288c8a35852205cc668
|
3 |
+
size 15984
|
last-checkpoint/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cbb99a70e49bd5edf38d3f1e84c6f7ef3da838740c7ab8146f580c3f82978779
|
3 |
+
size 1000
|
last-checkpoint/special_tokens_map.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"mask_token": {
|
10 |
+
"content": "[MASK]",
|
11 |
+
"lstrip": true,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"sep_token": {
|
24 |
+
"content": "[SEP]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"unk_token": {
|
31 |
+
"content": "[UNK]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
}
|
37 |
+
}
|
last-checkpoint/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
last-checkpoint/tokenizer_config.json
ADDED
@@ -0,0 +1,945 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "|||IP_ADDRESS|||",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": true,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": false
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<|padding|>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"50254": {
|
20 |
+
"content": " ",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": true,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": false
|
26 |
+
},
|
27 |
+
"50255": {
|
28 |
+
"content": " ",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": true,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": false
|
34 |
+
},
|
35 |
+
"50256": {
|
36 |
+
"content": " ",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": true,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": false
|
42 |
+
},
|
43 |
+
"50257": {
|
44 |
+
"content": " ",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": true,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": false
|
50 |
+
},
|
51 |
+
"50258": {
|
52 |
+
"content": " ",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": true,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": false
|
58 |
+
},
|
59 |
+
"50259": {
|
60 |
+
"content": " ",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": true,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": false
|
66 |
+
},
|
67 |
+
"50260": {
|
68 |
+
"content": " ",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": true,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false,
|
73 |
+
"special": false
|
74 |
+
},
|
75 |
+
"50261": {
|
76 |
+
"content": " ",
|
77 |
+
"lstrip": false,
|
78 |
+
"normalized": true,
|
79 |
+
"rstrip": false,
|
80 |
+
"single_word": false,
|
81 |
+
"special": false
|
82 |
+
},
|
83 |
+
"50262": {
|
84 |
+
"content": " ",
|
85 |
+
"lstrip": false,
|
86 |
+
"normalized": true,
|
87 |
+
"rstrip": false,
|
88 |
+
"single_word": false,
|
89 |
+
"special": false
|
90 |
+
},
|
91 |
+
"50263": {
|
92 |
+
"content": " ",
|
93 |
+
"lstrip": false,
|
94 |
+
"normalized": true,
|
95 |
+
"rstrip": false,
|
96 |
+
"single_word": false,
|
97 |
+
"special": false
|
98 |
+
},
|
99 |
+
"50264": {
|
100 |
+
"content": " ",
|
101 |
+
"lstrip": false,
|
102 |
+
"normalized": true,
|
103 |
+
"rstrip": false,
|
104 |
+
"single_word": false,
|
105 |
+
"special": false
|
106 |
+
},
|
107 |
+
"50265": {
|
108 |
+
"content": " ",
|
109 |
+
"lstrip": false,
|
110 |
+
"normalized": true,
|
111 |
+
"rstrip": false,
|
112 |
+
"single_word": false,
|
113 |
+
"special": false
|
114 |
+
},
|
115 |
+
"50266": {
|
116 |
+
"content": " ",
|
117 |
+
"lstrip": false,
|
118 |
+
"normalized": true,
|
119 |
+
"rstrip": false,
|
120 |
+
"single_word": false,
|
121 |
+
"special": false
|
122 |
+
},
|
123 |
+
"50267": {
|
124 |
+
"content": " ",
|
125 |
+
"lstrip": false,
|
126 |
+
"normalized": true,
|
127 |
+
"rstrip": false,
|
128 |
+
"single_word": false,
|
129 |
+
"special": false
|
130 |
+
},
|
131 |
+
"50268": {
|
132 |
+
"content": " ",
|
133 |
+
"lstrip": false,
|
134 |
+
"normalized": true,
|
135 |
+
"rstrip": false,
|
136 |
+
"single_word": false,
|
137 |
+
"special": false
|
138 |
+
},
|
139 |
+
"50269": {
|
140 |
+
"content": " ",
|
141 |
+
"lstrip": false,
|
142 |
+
"normalized": true,
|
143 |
+
"rstrip": false,
|
144 |
+
"single_word": false,
|
145 |
+
"special": false
|
146 |
+
},
|
147 |
+
"50270": {
|
148 |
+
"content": " ",
|
149 |
+
"lstrip": false,
|
150 |
+
"normalized": true,
|
151 |
+
"rstrip": false,
|
152 |
+
"single_word": false,
|
153 |
+
"special": false
|
154 |
+
},
|
155 |
+
"50271": {
|
156 |
+
"content": " ",
|
157 |
+
"lstrip": false,
|
158 |
+
"normalized": true,
|
159 |
+
"rstrip": false,
|
160 |
+
"single_word": false,
|
161 |
+
"special": false
|
162 |
+
},
|
163 |
+
"50272": {
|
164 |
+
"content": " ",
|
165 |
+
"lstrip": false,
|
166 |
+
"normalized": true,
|
167 |
+
"rstrip": false,
|
168 |
+
"single_word": false,
|
169 |
+
"special": false
|
170 |
+
},
|
171 |
+
"50273": {
|
172 |
+
"content": " ",
|
173 |
+
"lstrip": false,
|
174 |
+
"normalized": true,
|
175 |
+
"rstrip": false,
|
176 |
+
"single_word": false,
|
177 |
+
"special": false
|
178 |
+
},
|
179 |
+
"50274": {
|
180 |
+
"content": " ",
|
181 |
+
"lstrip": false,
|
182 |
+
"normalized": true,
|
183 |
+
"rstrip": false,
|
184 |
+
"single_word": false,
|
185 |
+
"special": false
|
186 |
+
},
|
187 |
+
"50275": {
|
188 |
+
"content": " ",
|
189 |
+
"lstrip": false,
|
190 |
+
"normalized": true,
|
191 |
+
"rstrip": false,
|
192 |
+
"single_word": false,
|
193 |
+
"special": false
|
194 |
+
},
|
195 |
+
"50276": {
|
196 |
+
"content": " ",
|
197 |
+
"lstrip": false,
|
198 |
+
"normalized": true,
|
199 |
+
"rstrip": false,
|
200 |
+
"single_word": false,
|
201 |
+
"special": false
|
202 |
+
},
|
203 |
+
"50277": {
|
204 |
+
"content": "|||EMAIL_ADDRESS|||",
|
205 |
+
"lstrip": false,
|
206 |
+
"normalized": true,
|
207 |
+
"rstrip": false,
|
208 |
+
"single_word": false,
|
209 |
+
"special": false
|
210 |
+
},
|
211 |
+
"50278": {
|
212 |
+
"content": "|||PHONE_NUMBER|||",
|
213 |
+
"lstrip": false,
|
214 |
+
"normalized": true,
|
215 |
+
"rstrip": false,
|
216 |
+
"single_word": false,
|
217 |
+
"special": false
|
218 |
+
},
|
219 |
+
"50279": {
|
220 |
+
"content": "<|endoftext|>",
|
221 |
+
"lstrip": false,
|
222 |
+
"normalized": false,
|
223 |
+
"rstrip": false,
|
224 |
+
"single_word": false,
|
225 |
+
"special": true
|
226 |
+
},
|
227 |
+
"50280": {
|
228 |
+
"content": "[UNK]",
|
229 |
+
"lstrip": false,
|
230 |
+
"normalized": false,
|
231 |
+
"rstrip": false,
|
232 |
+
"single_word": false,
|
233 |
+
"special": true
|
234 |
+
},
|
235 |
+
"50281": {
|
236 |
+
"content": "[CLS]",
|
237 |
+
"lstrip": false,
|
238 |
+
"normalized": false,
|
239 |
+
"rstrip": false,
|
240 |
+
"single_word": false,
|
241 |
+
"special": true
|
242 |
+
},
|
243 |
+
"50282": {
|
244 |
+
"content": "[SEP]",
|
245 |
+
"lstrip": false,
|
246 |
+
"normalized": false,
|
247 |
+
"rstrip": false,
|
248 |
+
"single_word": false,
|
249 |
+
"special": true
|
250 |
+
},
|
251 |
+
"50283": {
|
252 |
+
"content": "[PAD]",
|
253 |
+
"lstrip": false,
|
254 |
+
"normalized": false,
|
255 |
+
"rstrip": false,
|
256 |
+
"single_word": false,
|
257 |
+
"special": true
|
258 |
+
},
|
259 |
+
"50284": {
|
260 |
+
"content": "[MASK]",
|
261 |
+
"lstrip": true,
|
262 |
+
"normalized": false,
|
263 |
+
"rstrip": false,
|
264 |
+
"single_word": false,
|
265 |
+
"special": true
|
266 |
+
},
|
267 |
+
"95580": {
|
268 |
+
"content": "[unused0]",
|
269 |
+
"lstrip": false,
|
270 |
+
"normalized": true,
|
271 |
+
"rstrip": false,
|
272 |
+
"single_word": false,
|
273 |
+
"special": false
|
274 |
+
},
|
275 |
+
"95581": {
|
276 |
+
"content": "[unused1]",
|
277 |
+
"lstrip": false,
|
278 |
+
"normalized": true,
|
279 |
+
"rstrip": false,
|
280 |
+
"single_word": false,
|
281 |
+
"special": false
|
282 |
+
},
|
283 |
+
"95582": {
|
284 |
+
"content": "[unused2]",
|
285 |
+
"lstrip": false,
|
286 |
+
"normalized": true,
|
287 |
+
"rstrip": false,
|
288 |
+
"single_word": false,
|
289 |
+
"special": false
|
290 |
+
},
|
291 |
+
"95583": {
|
292 |
+
"content": "[unused3]",
|
293 |
+
"lstrip": false,
|
294 |
+
"normalized": true,
|
295 |
+
"rstrip": false,
|
296 |
+
"single_word": false,
|
297 |
+
"special": false
|
298 |
+
},
|
299 |
+
"95584": {
|
300 |
+
"content": "[unused4]",
|
301 |
+
"lstrip": false,
|
302 |
+
"normalized": true,
|
303 |
+
"rstrip": false,
|
304 |
+
"single_word": false,
|
305 |
+
"special": false
|
306 |
+
},
|
307 |
+
"95585": {
|
308 |
+
"content": "[unused5]",
|
309 |
+
"lstrip": false,
|
310 |
+
"normalized": true,
|
311 |
+
"rstrip": false,
|
312 |
+
"single_word": false,
|
313 |
+
"special": false
|
314 |
+
},
|
315 |
+
"95586": {
|
316 |
+
"content": "[unused6]",
|
317 |
+
"lstrip": false,
|
318 |
+
"normalized": true,
|
319 |
+
"rstrip": false,
|
320 |
+
"single_word": false,
|
321 |
+
"special": false
|
322 |
+
},
|
323 |
+
"95587": {
|
324 |
+
"content": "[unused7]",
|
325 |
+
"lstrip": false,
|
326 |
+
"normalized": true,
|
327 |
+
"rstrip": false,
|
328 |
+
"single_word": false,
|
329 |
+
"special": false
|
330 |
+
},
|
331 |
+
"95588": {
|
332 |
+
"content": "[unused8]",
|
333 |
+
"lstrip": false,
|
334 |
+
"normalized": true,
|
335 |
+
"rstrip": false,
|
336 |
+
"single_word": false,
|
337 |
+
"special": false
|
338 |
+
},
|
339 |
+
"95589": {
|
340 |
+
"content": "[unused9]",
|
341 |
+
"lstrip": false,
|
342 |
+
"normalized": true,
|
343 |
+
"rstrip": false,
|
344 |
+
"single_word": false,
|
345 |
+
"special": false
|
346 |
+
},
|
347 |
+
"95590": {
|
348 |
+
"content": "[unused10]",
|
349 |
+
"lstrip": false,
|
350 |
+
"normalized": true,
|
351 |
+
"rstrip": false,
|
352 |
+
"single_word": false,
|
353 |
+
"special": false
|
354 |
+
},
|
355 |
+
"95591": {
|
356 |
+
"content": "[unused11]",
|
357 |
+
"lstrip": false,
|
358 |
+
"normalized": true,
|
359 |
+
"rstrip": false,
|
360 |
+
"single_word": false,
|
361 |
+
"special": false
|
362 |
+
},
|
363 |
+
"95592": {
|
364 |
+
"content": "[unused12]",
|
365 |
+
"lstrip": false,
|
366 |
+
"normalized": true,
|
367 |
+
"rstrip": false,
|
368 |
+
"single_word": false,
|
369 |
+
"special": false
|
370 |
+
},
|
371 |
+
"95593": {
|
372 |
+
"content": "[unused13]",
|
373 |
+
"lstrip": false,
|
374 |
+
"normalized": true,
|
375 |
+
"rstrip": false,
|
376 |
+
"single_word": false,
|
377 |
+
"special": false
|
378 |
+
},
|
379 |
+
"95594": {
|
380 |
+
"content": "[unused14]",
|
381 |
+
"lstrip": false,
|
382 |
+
"normalized": true,
|
383 |
+
"rstrip": false,
|
384 |
+
"single_word": false,
|
385 |
+
"special": false
|
386 |
+
},
|
387 |
+
"95595": {
|
388 |
+
"content": "[unused15]",
|
389 |
+
"lstrip": false,
|
390 |
+
"normalized": true,
|
391 |
+
"rstrip": false,
|
392 |
+
"single_word": false,
|
393 |
+
"special": false
|
394 |
+
},
|
395 |
+
"95596": {
|
396 |
+
"content": "[unused16]",
|
397 |
+
"lstrip": false,
|
398 |
+
"normalized": true,
|
399 |
+
"rstrip": false,
|
400 |
+
"single_word": false,
|
401 |
+
"special": false
|
402 |
+
},
|
403 |
+
"95597": {
|
404 |
+
"content": "[unused17]",
|
405 |
+
"lstrip": false,
|
406 |
+
"normalized": true,
|
407 |
+
"rstrip": false,
|
408 |
+
"single_word": false,
|
409 |
+
"special": false
|
410 |
+
},
|
411 |
+
"95598": {
|
412 |
+
"content": "[unused18]",
|
413 |
+
"lstrip": false,
|
414 |
+
"normalized": true,
|
415 |
+
"rstrip": false,
|
416 |
+
"single_word": false,
|
417 |
+
"special": false
|
418 |
+
},
|
419 |
+
"95599": {
|
420 |
+
"content": "[unused19]",
|
421 |
+
"lstrip": false,
|
422 |
+
"normalized": true,
|
423 |
+
"rstrip": false,
|
424 |
+
"single_word": false,
|
425 |
+
"special": false
|
426 |
+
},
|
427 |
+
"95600": {
|
428 |
+
"content": "[unused20]",
|
429 |
+
"lstrip": false,
|
430 |
+
"normalized": true,
|
431 |
+
"rstrip": false,
|
432 |
+
"single_word": false,
|
433 |
+
"special": false
|
434 |
+
},
|
435 |
+
"95601": {
|
436 |
+
"content": "[unused21]",
|
437 |
+
"lstrip": false,
|
438 |
+
"normalized": true,
|
439 |
+
"rstrip": false,
|
440 |
+
"single_word": false,
|
441 |
+
"special": false
|
442 |
+
},
|
443 |
+
"95602": {
|
444 |
+
"content": "[unused22]",
|
445 |
+
"lstrip": false,
|
446 |
+
"normalized": true,
|
447 |
+
"rstrip": false,
|
448 |
+
"single_word": false,
|
449 |
+
"special": false
|
450 |
+
},
|
451 |
+
"95603": {
|
452 |
+
"content": "[unused23]",
|
453 |
+
"lstrip": false,
|
454 |
+
"normalized": true,
|
455 |
+
"rstrip": false,
|
456 |
+
"single_word": false,
|
457 |
+
"special": false
|
458 |
+
},
|
459 |
+
"95604": {
|
460 |
+
"content": "[unused24]",
|
461 |
+
"lstrip": false,
|
462 |
+
"normalized": true,
|
463 |
+
"rstrip": false,
|
464 |
+
"single_word": false,
|
465 |
+
"special": false
|
466 |
+
},
|
467 |
+
"95605": {
|
468 |
+
"content": "[unused25]",
|
469 |
+
"lstrip": false,
|
470 |
+
"normalized": true,
|
471 |
+
"rstrip": false,
|
472 |
+
"single_word": false,
|
473 |
+
"special": false
|
474 |
+
},
|
475 |
+
"95606": {
|
476 |
+
"content": "[unused26]",
|
477 |
+
"lstrip": false,
|
478 |
+
"normalized": true,
|
479 |
+
"rstrip": false,
|
480 |
+
"single_word": false,
|
481 |
+
"special": false
|
482 |
+
},
|
483 |
+
"95607": {
|
484 |
+
"content": "[unused27]",
|
485 |
+
"lstrip": false,
|
486 |
+
"normalized": true,
|
487 |
+
"rstrip": false,
|
488 |
+
"single_word": false,
|
489 |
+
"special": false
|
490 |
+
},
|
491 |
+
"95608": {
|
492 |
+
"content": "[unused28]",
|
493 |
+
"lstrip": false,
|
494 |
+
"normalized": true,
|
495 |
+
"rstrip": false,
|
496 |
+
"single_word": false,
|
497 |
+
"special": false
|
498 |
+
},
|
499 |
+
"95609": {
|
500 |
+
"content": "[unused29]",
|
501 |
+
"lstrip": false,
|
502 |
+
"normalized": true,
|
503 |
+
"rstrip": false,
|
504 |
+
"single_word": false,
|
505 |
+
"special": false
|
506 |
+
},
|
507 |
+
"95610": {
|
508 |
+
"content": "[unused30]",
|
509 |
+
"lstrip": false,
|
510 |
+
"normalized": true,
|
511 |
+
"rstrip": false,
|
512 |
+
"single_word": false,
|
513 |
+
"special": false
|
514 |
+
},
|
515 |
+
"95611": {
|
516 |
+
"content": "[unused31]",
|
517 |
+
"lstrip": false,
|
518 |
+
"normalized": true,
|
519 |
+
"rstrip": false,
|
520 |
+
"single_word": false,
|
521 |
+
"special": false
|
522 |
+
},
|
523 |
+
"95612": {
|
524 |
+
"content": "[unused32]",
|
525 |
+
"lstrip": false,
|
526 |
+
"normalized": true,
|
527 |
+
"rstrip": false,
|
528 |
+
"single_word": false,
|
529 |
+
"special": false
|
530 |
+
},
|
531 |
+
"95613": {
|
532 |
+
"content": "[unused33]",
|
533 |
+
"lstrip": false,
|
534 |
+
"normalized": true,
|
535 |
+
"rstrip": false,
|
536 |
+
"single_word": false,
|
537 |
+
"special": false
|
538 |
+
},
|
539 |
+
"95614": {
|
540 |
+
"content": "[unused34]",
|
541 |
+
"lstrip": false,
|
542 |
+
"normalized": true,
|
543 |
+
"rstrip": false,
|
544 |
+
"single_word": false,
|
545 |
+
"special": false
|
546 |
+
},
|
547 |
+
"95615": {
|
548 |
+
"content": "[unused35]",
|
549 |
+
"lstrip": false,
|
550 |
+
"normalized": true,
|
551 |
+
"rstrip": false,
|
552 |
+
"single_word": false,
|
553 |
+
"special": false
|
554 |
+
},
|
555 |
+
"95616": {
|
556 |
+
"content": "[unused36]",
|
557 |
+
"lstrip": false,
|
558 |
+
"normalized": true,
|
559 |
+
"rstrip": false,
|
560 |
+
"single_word": false,
|
561 |
+
"special": false
|
562 |
+
},
|
563 |
+
"95617": {
|
564 |
+
"content": "[unused37]",
|
565 |
+
"lstrip": false,
|
566 |
+
"normalized": true,
|
567 |
+
"rstrip": false,
|
568 |
+
"single_word": false,
|
569 |
+
"special": false
|
570 |
+
},
|
571 |
+
"95618": {
|
572 |
+
"content": "[unused38]",
|
573 |
+
"lstrip": false,
|
574 |
+
"normalized": true,
|
575 |
+
"rstrip": false,
|
576 |
+
"single_word": false,
|
577 |
+
"special": false
|
578 |
+
},
|
579 |
+
"95619": {
|
580 |
+
"content": "[unused39]",
|
581 |
+
"lstrip": false,
|
582 |
+
"normalized": true,
|
583 |
+
"rstrip": false,
|
584 |
+
"single_word": false,
|
585 |
+
"special": false
|
586 |
+
},
|
587 |
+
"95620": {
|
588 |
+
"content": "[unused40]",
|
589 |
+
"lstrip": false,
|
590 |
+
"normalized": true,
|
591 |
+
"rstrip": false,
|
592 |
+
"single_word": false,
|
593 |
+
"special": false
|
594 |
+
},
|
595 |
+
"95621": {
|
596 |
+
"content": "[unused41]",
|
597 |
+
"lstrip": false,
|
598 |
+
"normalized": true,
|
599 |
+
"rstrip": false,
|
600 |
+
"single_word": false,
|
601 |
+
"special": false
|
602 |
+
},
|
603 |
+
"95622": {
|
604 |
+
"content": "[unused42]",
|
605 |
+
"lstrip": false,
|
606 |
+
"normalized": true,
|
607 |
+
"rstrip": false,
|
608 |
+
"single_word": false,
|
609 |
+
"special": false
|
610 |
+
},
|
611 |
+
"95623": {
|
612 |
+
"content": "[unused43]",
|
613 |
+
"lstrip": false,
|
614 |
+
"normalized": true,
|
615 |
+
"rstrip": false,
|
616 |
+
"single_word": false,
|
617 |
+
"special": false
|
618 |
+
},
|
619 |
+
"95624": {
|
620 |
+
"content": "[unused44]",
|
621 |
+
"lstrip": false,
|
622 |
+
"normalized": true,
|
623 |
+
"rstrip": false,
|
624 |
+
"single_word": false,
|
625 |
+
"special": false
|
626 |
+
},
|
627 |
+
"95625": {
|
628 |
+
"content": "[unused45]",
|
629 |
+
"lstrip": false,
|
630 |
+
"normalized": true,
|
631 |
+
"rstrip": false,
|
632 |
+
"single_word": false,
|
633 |
+
"special": false
|
634 |
+
},
|
635 |
+
"95626": {
|
636 |
+
"content": "[unused46]",
|
637 |
+
"lstrip": false,
|
638 |
+
"normalized": true,
|
639 |
+
"rstrip": false,
|
640 |
+
"single_word": false,
|
641 |
+
"special": false
|
642 |
+
},
|
643 |
+
"95627": {
|
644 |
+
"content": "[unused47]",
|
645 |
+
"lstrip": false,
|
646 |
+
"normalized": true,
|
647 |
+
"rstrip": false,
|
648 |
+
"single_word": false,
|
649 |
+
"special": false
|
650 |
+
},
|
651 |
+
"95628": {
|
652 |
+
"content": "[unused48]",
|
653 |
+
"lstrip": false,
|
654 |
+
"normalized": true,
|
655 |
+
"rstrip": false,
|
656 |
+
"single_word": false,
|
657 |
+
"special": false
|
658 |
+
},
|
659 |
+
"95629": {
|
660 |
+
"content": "[unused49]",
|
661 |
+
"lstrip": false,
|
662 |
+
"normalized": true,
|
663 |
+
"rstrip": false,
|
664 |
+
"single_word": false,
|
665 |
+
"special": false
|
666 |
+
},
|
667 |
+
"95630": {
|
668 |
+
"content": "[unused50]",
|
669 |
+
"lstrip": false,
|
670 |
+
"normalized": true,
|
671 |
+
"rstrip": false,
|
672 |
+
"single_word": false,
|
673 |
+
"special": false
|
674 |
+
},
|
675 |
+
"95631": {
|
676 |
+
"content": "[unused51]",
|
677 |
+
"lstrip": false,
|
678 |
+
"normalized": true,
|
679 |
+
"rstrip": false,
|
680 |
+
"single_word": false,
|
681 |
+
"special": false
|
682 |
+
},
|
683 |
+
"95632": {
|
684 |
+
"content": "[unused52]",
|
685 |
+
"lstrip": false,
|
686 |
+
"normalized": true,
|
687 |
+
"rstrip": false,
|
688 |
+
"single_word": false,
|
689 |
+
"special": false
|
690 |
+
},
|
691 |
+
"95633": {
|
692 |
+
"content": "[unused53]",
|
693 |
+
"lstrip": false,
|
694 |
+
"normalized": true,
|
695 |
+
"rstrip": false,
|
696 |
+
"single_word": false,
|
697 |
+
"special": false
|
698 |
+
},
|
699 |
+
"95634": {
|
700 |
+
"content": "[unused54]",
|
701 |
+
"lstrip": false,
|
702 |
+
"normalized": true,
|
703 |
+
"rstrip": false,
|
704 |
+
"single_word": false,
|
705 |
+
"special": false
|
706 |
+
},
|
707 |
+
"95635": {
|
708 |
+
"content": "[unused55]",
|
709 |
+
"lstrip": false,
|
710 |
+
"normalized": true,
|
711 |
+
"rstrip": false,
|
712 |
+
"single_word": false,
|
713 |
+
"special": false
|
714 |
+
},
|
715 |
+
"95636": {
|
716 |
+
"content": "[unused56]",
|
717 |
+
"lstrip": false,
|
718 |
+
"normalized": true,
|
719 |
+
"rstrip": false,
|
720 |
+
"single_word": false,
|
721 |
+
"special": false
|
722 |
+
},
|
723 |
+
"95637": {
|
724 |
+
"content": "[unused57]",
|
725 |
+
"lstrip": false,
|
726 |
+
"normalized": true,
|
727 |
+
"rstrip": false,
|
728 |
+
"single_word": false,
|
729 |
+
"special": false
|
730 |
+
},
|
731 |
+
"95638": {
|
732 |
+
"content": "[unused58]",
|
733 |
+
"lstrip": false,
|
734 |
+
"normalized": true,
|
735 |
+
"rstrip": false,
|
736 |
+
"single_word": false,
|
737 |
+
"special": false
|
738 |
+
},
|
739 |
+
"95639": {
|
740 |
+
"content": "[unused59]",
|
741 |
+
"lstrip": false,
|
742 |
+
"normalized": true,
|
743 |
+
"rstrip": false,
|
744 |
+
"single_word": false,
|
745 |
+
"special": false
|
746 |
+
},
|
747 |
+
"95640": {
|
748 |
+
"content": "[unused60]",
|
749 |
+
"lstrip": false,
|
750 |
+
"normalized": true,
|
751 |
+
"rstrip": false,
|
752 |
+
"single_word": false,
|
753 |
+
"special": false
|
754 |
+
},
|
755 |
+
"95641": {
|
756 |
+
"content": "[unused61]",
|
757 |
+
"lstrip": false,
|
758 |
+
"normalized": true,
|
759 |
+
"rstrip": false,
|
760 |
+
"single_word": false,
|
761 |
+
"special": false
|
762 |
+
},
|
763 |
+
"95642": {
|
764 |
+
"content": "[unused62]",
|
765 |
+
"lstrip": false,
|
766 |
+
"normalized": true,
|
767 |
+
"rstrip": false,
|
768 |
+
"single_word": false,
|
769 |
+
"special": false
|
770 |
+
},
|
771 |
+
"95643": {
|
772 |
+
"content": "[unused63]",
|
773 |
+
"lstrip": false,
|
774 |
+
"normalized": true,
|
775 |
+
"rstrip": false,
|
776 |
+
"single_word": false,
|
777 |
+
"special": false
|
778 |
+
},
|
779 |
+
"95644": {
|
780 |
+
"content": "[unused64]",
|
781 |
+
"lstrip": false,
|
782 |
+
"normalized": true,
|
783 |
+
"rstrip": false,
|
784 |
+
"single_word": false,
|
785 |
+
"special": false
|
786 |
+
},
|
787 |
+
"95645": {
|
788 |
+
"content": "[unused65]",
|
789 |
+
"lstrip": false,
|
790 |
+
"normalized": true,
|
791 |
+
"rstrip": false,
|
792 |
+
"single_word": false,
|
793 |
+
"special": false
|
794 |
+
},
|
795 |
+
"95646": {
|
796 |
+
"content": "[unused66]",
|
797 |
+
"lstrip": false,
|
798 |
+
"normalized": true,
|
799 |
+
"rstrip": false,
|
800 |
+
"single_word": false,
|
801 |
+
"special": false
|
802 |
+
},
|
803 |
+
"95647": {
|
804 |
+
"content": "[unused67]",
|
805 |
+
"lstrip": false,
|
806 |
+
"normalized": true,
|
807 |
+
"rstrip": false,
|
808 |
+
"single_word": false,
|
809 |
+
"special": false
|
810 |
+
},
|
811 |
+
"95648": {
|
812 |
+
"content": "[unused68]",
|
813 |
+
"lstrip": false,
|
814 |
+
"normalized": true,
|
815 |
+
"rstrip": false,
|
816 |
+
"single_word": false,
|
817 |
+
"special": false
|
818 |
+
},
|
819 |
+
"95649": {
|
820 |
+
"content": "[unused69]",
|
821 |
+
"lstrip": false,
|
822 |
+
"normalized": true,
|
823 |
+
"rstrip": false,
|
824 |
+
"single_word": false,
|
825 |
+
"special": false
|
826 |
+
},
|
827 |
+
"95650": {
|
828 |
+
"content": "[unused70]",
|
829 |
+
"lstrip": false,
|
830 |
+
"normalized": true,
|
831 |
+
"rstrip": false,
|
832 |
+
"single_word": false,
|
833 |
+
"special": false
|
834 |
+
},
|
835 |
+
"95651": {
|
836 |
+
"content": "[unused71]",
|
837 |
+
"lstrip": false,
|
838 |
+
"normalized": true,
|
839 |
+
"rstrip": false,
|
840 |
+
"single_word": false,
|
841 |
+
"special": false
|
842 |
+
},
|
843 |
+
"95652": {
|
844 |
+
"content": "[unused72]",
|
845 |
+
"lstrip": false,
|
846 |
+
"normalized": true,
|
847 |
+
"rstrip": false,
|
848 |
+
"single_word": false,
|
849 |
+
"special": false
|
850 |
+
},
|
851 |
+
"95653": {
|
852 |
+
"content": "[unused73]",
|
853 |
+
"lstrip": false,
|
854 |
+
"normalized": true,
|
855 |
+
"rstrip": false,
|
856 |
+
"single_word": false,
|
857 |
+
"special": false
|
858 |
+
},
|
859 |
+
"95654": {
|
860 |
+
"content": "[unused74]",
|
861 |
+
"lstrip": false,
|
862 |
+
"normalized": true,
|
863 |
+
"rstrip": false,
|
864 |
+
"single_word": false,
|
865 |
+
"special": false
|
866 |
+
},
|
867 |
+
"95655": {
|
868 |
+
"content": "[unused75]",
|
869 |
+
"lstrip": false,
|
870 |
+
"normalized": true,
|
871 |
+
"rstrip": false,
|
872 |
+
"single_word": false,
|
873 |
+
"special": false
|
874 |
+
},
|
875 |
+
"95656": {
|
876 |
+
"content": "[unused76]",
|
877 |
+
"lstrip": false,
|
878 |
+
"normalized": true,
|
879 |
+
"rstrip": false,
|
880 |
+
"single_word": false,
|
881 |
+
"special": false
|
882 |
+
},
|
883 |
+
"95657": {
|
884 |
+
"content": "[unused77]",
|
885 |
+
"lstrip": false,
|
886 |
+
"normalized": true,
|
887 |
+
"rstrip": false,
|
888 |
+
"single_word": false,
|
889 |
+
"special": false
|
890 |
+
},
|
891 |
+
"95658": {
|
892 |
+
"content": "[unused78]",
|
893 |
+
"lstrip": false,
|
894 |
+
"normalized": true,
|
895 |
+
"rstrip": false,
|
896 |
+
"single_word": false,
|
897 |
+
"special": false
|
898 |
+
},
|
899 |
+
"95659": {
|
900 |
+
"content": "[unused79]",
|
901 |
+
"lstrip": false,
|
902 |
+
"normalized": true,
|
903 |
+
"rstrip": false,
|
904 |
+
"single_word": false,
|
905 |
+
"special": false
|
906 |
+
},
|
907 |
+
"95660": {
|
908 |
+
"content": "[unused80]",
|
909 |
+
"lstrip": false,
|
910 |
+
"normalized": true,
|
911 |
+
"rstrip": false,
|
912 |
+
"single_word": false,
|
913 |
+
"special": false
|
914 |
+
},
|
915 |
+
"95661": {
|
916 |
+
"content": "[unused81]",
|
917 |
+
"lstrip": false,
|
918 |
+
"normalized": true,
|
919 |
+
"rstrip": false,
|
920 |
+
"single_word": false,
|
921 |
+
"special": false
|
922 |
+
},
|
923 |
+
"95662": {
|
924 |
+
"content": "[unused82]",
|
925 |
+
"lstrip": false,
|
926 |
+
"normalized": true,
|
927 |
+
"rstrip": false,
|
928 |
+
"single_word": false,
|
929 |
+
"special": false
|
930 |
+
}
|
931 |
+
},
|
932 |
+
"clean_up_tokenization_spaces": true,
|
933 |
+
"cls_token": "[CLS]",
|
934 |
+
"extra_special_tokens": {},
|
935 |
+
"mask_token": "[MASK]",
|
936 |
+
"model_input_names": [
|
937 |
+
"input_ids",
|
938 |
+
"attention_mask"
|
939 |
+
],
|
940 |
+
"model_max_length": 1000000000000000019884624838656,
|
941 |
+
"pad_token": "[PAD]",
|
942 |
+
"sep_token": "[SEP]",
|
943 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
944 |
+
"unk_token": "[UNK]"
|
945 |
+
}
|
last-checkpoint/trainer_state.json
ADDED
@@ -0,0 +1,1791 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.20007727984934182,
|
5 |
+
"eval_steps": 2500,
|
6 |
+
"global_step": 2500,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0008003091193973672,
|
13 |
+
"grad_norm": 75.25,
|
14 |
+
"learning_rate": 9.999984368969842e-07,
|
15 |
+
"loss": 135.0496,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.0016006182387947345,
|
20 |
+
"grad_norm": 77.9375,
|
21 |
+
"learning_rate": 9.999968737939682e-07,
|
22 |
+
"loss": 134.7034,
|
23 |
+
"step": 20
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.0024009273581921016,
|
27 |
+
"grad_norm": 78.8125,
|
28 |
+
"learning_rate": 9.999953106909524e-07,
|
29 |
+
"loss": 134.1727,
|
30 |
+
"step": 30
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.003201236477589469,
|
34 |
+
"grad_norm": 74.125,
|
35 |
+
"learning_rate": 9.999937475879366e-07,
|
36 |
+
"loss": 134.3995,
|
37 |
+
"step": 40
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.004001545596986836,
|
41 |
+
"grad_norm": 77.8125,
|
42 |
+
"learning_rate": 9.999921844849208e-07,
|
43 |
+
"loss": 133.854,
|
44 |
+
"step": 50
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.004801854716384203,
|
48 |
+
"grad_norm": 73.1875,
|
49 |
+
"learning_rate": 9.999906213819048e-07,
|
50 |
+
"loss": 134.2893,
|
51 |
+
"step": 60
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.005602163835781571,
|
55 |
+
"grad_norm": 74.0625,
|
56 |
+
"learning_rate": 9.99989058278889e-07,
|
57 |
+
"loss": 134.4156,
|
58 |
+
"step": 70
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.006402472955178938,
|
62 |
+
"grad_norm": 72.5625,
|
63 |
+
"learning_rate": 9.999874951758733e-07,
|
64 |
+
"loss": 132.5738,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.007202782074576305,
|
69 |
+
"grad_norm": 80.8125,
|
70 |
+
"learning_rate": 9.999859320728575e-07,
|
71 |
+
"loss": 134.4381,
|
72 |
+
"step": 90
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.008003091193973673,
|
76 |
+
"grad_norm": 78.875,
|
77 |
+
"learning_rate": 9.999843689698417e-07,
|
78 |
+
"loss": 133.9594,
|
79 |
+
"step": 100
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.00880340031337104,
|
83 |
+
"grad_norm": 71.125,
|
84 |
+
"learning_rate": 9.999828058668257e-07,
|
85 |
+
"loss": 133.9086,
|
86 |
+
"step": 110
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.009603709432768406,
|
90 |
+
"grad_norm": 72.0625,
|
91 |
+
"learning_rate": 9.9998124276381e-07,
|
92 |
+
"loss": 133.434,
|
93 |
+
"step": 120
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.010404018552165774,
|
97 |
+
"grad_norm": 79.25,
|
98 |
+
"learning_rate": 9.999796796607942e-07,
|
99 |
+
"loss": 133.4989,
|
100 |
+
"step": 130
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.011204327671563142,
|
104 |
+
"grad_norm": 79.1875,
|
105 |
+
"learning_rate": 9.999781165577784e-07,
|
106 |
+
"loss": 134.517,
|
107 |
+
"step": 140
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.012004636790960508,
|
111 |
+
"grad_norm": 71.9375,
|
112 |
+
"learning_rate": 9.999765534547624e-07,
|
113 |
+
"loss": 133.5077,
|
114 |
+
"step": 150
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.012804945910357876,
|
118 |
+
"grad_norm": 74.625,
|
119 |
+
"learning_rate": 9.999749903517466e-07,
|
120 |
+
"loss": 133.3733,
|
121 |
+
"step": 160
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.013605255029755244,
|
125 |
+
"grad_norm": 78.6875,
|
126 |
+
"learning_rate": 9.999734272487308e-07,
|
127 |
+
"loss": 132.901,
|
128 |
+
"step": 170
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.01440556414915261,
|
132 |
+
"grad_norm": 76.625,
|
133 |
+
"learning_rate": 9.999718641457148e-07,
|
134 |
+
"loss": 135.7891,
|
135 |
+
"step": 180
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.015205873268549977,
|
139 |
+
"grad_norm": 72.6875,
|
140 |
+
"learning_rate": 9.99970301042699e-07,
|
141 |
+
"loss": 134.1953,
|
142 |
+
"step": 190
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.016006182387947345,
|
146 |
+
"grad_norm": 72.1875,
|
147 |
+
"learning_rate": 9.999687379396833e-07,
|
148 |
+
"loss": 132.8302,
|
149 |
+
"step": 200
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.01680649150734471,
|
153 |
+
"grad_norm": 76.375,
|
154 |
+
"learning_rate": 9.999671748366673e-07,
|
155 |
+
"loss": 133.097,
|
156 |
+
"step": 210
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.01760680062674208,
|
160 |
+
"grad_norm": 81.25,
|
161 |
+
"learning_rate": 9.999656117336515e-07,
|
162 |
+
"loss": 133.4282,
|
163 |
+
"step": 220
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.018407109746139447,
|
167 |
+
"grad_norm": 85.125,
|
168 |
+
"learning_rate": 9.999640486306357e-07,
|
169 |
+
"loss": 134.319,
|
170 |
+
"step": 230
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.019207418865536813,
|
174 |
+
"grad_norm": 79.125,
|
175 |
+
"learning_rate": 9.9996248552762e-07,
|
176 |
+
"loss": 132.7719,
|
177 |
+
"step": 240
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.020007727984934182,
|
181 |
+
"grad_norm": 78.5,
|
182 |
+
"learning_rate": 9.999609224246041e-07,
|
183 |
+
"loss": 133.3401,
|
184 |
+
"step": 250
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.02080803710433155,
|
188 |
+
"grad_norm": 82.625,
|
189 |
+
"learning_rate": 9.999593593215884e-07,
|
190 |
+
"loss": 134.8742,
|
191 |
+
"step": 260
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.021608346223728914,
|
195 |
+
"grad_norm": 76.875,
|
196 |
+
"learning_rate": 9.999577962185724e-07,
|
197 |
+
"loss": 135.1933,
|
198 |
+
"step": 270
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.022408655343126284,
|
202 |
+
"grad_norm": 76.3125,
|
203 |
+
"learning_rate": 9.999562331155566e-07,
|
204 |
+
"loss": 134.0234,
|
205 |
+
"step": 280
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.02320896446252365,
|
209 |
+
"grad_norm": 74.5,
|
210 |
+
"learning_rate": 9.999546700125408e-07,
|
211 |
+
"loss": 133.5756,
|
212 |
+
"step": 290
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.024009273581921016,
|
216 |
+
"grad_norm": 81.5625,
|
217 |
+
"learning_rate": 9.99953106909525e-07,
|
218 |
+
"loss": 134.8582,
|
219 |
+
"step": 300
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.024809582701318385,
|
223 |
+
"grad_norm": 73.25,
|
224 |
+
"learning_rate": 9.99951543806509e-07,
|
225 |
+
"loss": 132.5909,
|
226 |
+
"step": 310
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.02560989182071575,
|
230 |
+
"grad_norm": 71.3125,
|
231 |
+
"learning_rate": 9.999499807034932e-07,
|
232 |
+
"loss": 133.9742,
|
233 |
+
"step": 320
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.026410200940113118,
|
237 |
+
"grad_norm": 71.3125,
|
238 |
+
"learning_rate": 9.999484176004775e-07,
|
239 |
+
"loss": 134.9034,
|
240 |
+
"step": 330
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.027210510059510487,
|
244 |
+
"grad_norm": 73.5,
|
245 |
+
"learning_rate": 9.999468544974615e-07,
|
246 |
+
"loss": 132.86,
|
247 |
+
"step": 340
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.028010819178907853,
|
251 |
+
"grad_norm": 73.4375,
|
252 |
+
"learning_rate": 9.999452913944457e-07,
|
253 |
+
"loss": 134.602,
|
254 |
+
"step": 350
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.02881112829830522,
|
258 |
+
"grad_norm": 76.6875,
|
259 |
+
"learning_rate": 9.9994372829143e-07,
|
260 |
+
"loss": 132.606,
|
261 |
+
"step": 360
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.02961143741770259,
|
265 |
+
"grad_norm": 75.9375,
|
266 |
+
"learning_rate": 9.99942165188414e-07,
|
267 |
+
"loss": 134.4456,
|
268 |
+
"step": 370
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.030411746537099955,
|
272 |
+
"grad_norm": 73.8125,
|
273 |
+
"learning_rate": 9.999406020853981e-07,
|
274 |
+
"loss": 132.9977,
|
275 |
+
"step": 380
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.03121205565649732,
|
279 |
+
"grad_norm": 79.375,
|
280 |
+
"learning_rate": 9.999390389823824e-07,
|
281 |
+
"loss": 133.731,
|
282 |
+
"step": 390
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.03201236477589469,
|
286 |
+
"grad_norm": 77.4375,
|
287 |
+
"learning_rate": 9.999374758793666e-07,
|
288 |
+
"loss": 133.9014,
|
289 |
+
"step": 400
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.032812673895292056,
|
293 |
+
"grad_norm": 70.8125,
|
294 |
+
"learning_rate": 9.999359127763508e-07,
|
295 |
+
"loss": 135.4049,
|
296 |
+
"step": 410
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.03361298301468942,
|
300 |
+
"grad_norm": 75.125,
|
301 |
+
"learning_rate": 9.999343496733348e-07,
|
302 |
+
"loss": 135.3231,
|
303 |
+
"step": 420
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.03441329213408679,
|
307 |
+
"grad_norm": 79.6875,
|
308 |
+
"learning_rate": 9.99932786570319e-07,
|
309 |
+
"loss": 132.8583,
|
310 |
+
"step": 430
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.03521360125348416,
|
314 |
+
"grad_norm": 84.0625,
|
315 |
+
"learning_rate": 9.999312234673032e-07,
|
316 |
+
"loss": 133.4561,
|
317 |
+
"step": 440
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.03601391037288153,
|
321 |
+
"grad_norm": 75.125,
|
322 |
+
"learning_rate": 9.999296603642874e-07,
|
323 |
+
"loss": 133.2269,
|
324 |
+
"step": 450
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.03681421949227889,
|
328 |
+
"grad_norm": 71.4375,
|
329 |
+
"learning_rate": 9.999280972612715e-07,
|
330 |
+
"loss": 134.1606,
|
331 |
+
"step": 460
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.03761452861167626,
|
335 |
+
"grad_norm": 72.9375,
|
336 |
+
"learning_rate": 9.999265341582557e-07,
|
337 |
+
"loss": 134.7773,
|
338 |
+
"step": 470
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.038414837731073626,
|
342 |
+
"grad_norm": 76.875,
|
343 |
+
"learning_rate": 9.999249710552399e-07,
|
344 |
+
"loss": 134.0885,
|
345 |
+
"step": 480
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.03921514685047099,
|
349 |
+
"grad_norm": 76.8125,
|
350 |
+
"learning_rate": 9.999234079522241e-07,
|
351 |
+
"loss": 134.5257,
|
352 |
+
"step": 490
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.040015455969868365,
|
356 |
+
"grad_norm": 70.25,
|
357 |
+
"learning_rate": 9.999218448492081e-07,
|
358 |
+
"loss": 134.4442,
|
359 |
+
"step": 500
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.04081576508926573,
|
363 |
+
"grad_norm": 79.875,
|
364 |
+
"learning_rate": 9.999202817461923e-07,
|
365 |
+
"loss": 134.2612,
|
366 |
+
"step": 510
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.0416160742086631,
|
370 |
+
"grad_norm": 75.375,
|
371 |
+
"learning_rate": 9.999187186431766e-07,
|
372 |
+
"loss": 135.1053,
|
373 |
+
"step": 520
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.04241638332806046,
|
377 |
+
"grad_norm": 75.4375,
|
378 |
+
"learning_rate": 9.999171555401606e-07,
|
379 |
+
"loss": 133.3491,
|
380 |
+
"step": 530
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.04321669244745783,
|
384 |
+
"grad_norm": 81.4375,
|
385 |
+
"learning_rate": 9.999155924371448e-07,
|
386 |
+
"loss": 133.6457,
|
387 |
+
"step": 540
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.044017001566855195,
|
391 |
+
"grad_norm": 76.5625,
|
392 |
+
"learning_rate": 9.99914029334129e-07,
|
393 |
+
"loss": 135.0537,
|
394 |
+
"step": 550
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.04481731068625257,
|
398 |
+
"grad_norm": 77.375,
|
399 |
+
"learning_rate": 9.999124662311132e-07,
|
400 |
+
"loss": 134.9535,
|
401 |
+
"step": 560
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.045617619805649934,
|
405 |
+
"grad_norm": 77.75,
|
406 |
+
"learning_rate": 9.999109031280974e-07,
|
407 |
+
"loss": 134.2294,
|
408 |
+
"step": 570
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.0464179289250473,
|
412 |
+
"grad_norm": 82.5,
|
413 |
+
"learning_rate": 9.999093400250814e-07,
|
414 |
+
"loss": 133.7713,
|
415 |
+
"step": 580
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.047218238044444666,
|
419 |
+
"grad_norm": 79.125,
|
420 |
+
"learning_rate": 9.999077769220657e-07,
|
421 |
+
"loss": 133.3779,
|
422 |
+
"step": 590
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.04801854716384203,
|
426 |
+
"grad_norm": 78.4375,
|
427 |
+
"learning_rate": 9.999062138190499e-07,
|
428 |
+
"loss": 133.576,
|
429 |
+
"step": 600
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.0488188562832394,
|
433 |
+
"grad_norm": 76.1875,
|
434 |
+
"learning_rate": 9.99904650716034e-07,
|
435 |
+
"loss": 136.3208,
|
436 |
+
"step": 610
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 0.04961916540263677,
|
440 |
+
"grad_norm": 76.3125,
|
441 |
+
"learning_rate": 9.99903087613018e-07,
|
442 |
+
"loss": 132.9463,
|
443 |
+
"step": 620
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.05041947452203414,
|
447 |
+
"grad_norm": 74.0,
|
448 |
+
"learning_rate": 9.999015245100023e-07,
|
449 |
+
"loss": 133.6666,
|
450 |
+
"step": 630
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 0.0512197836414315,
|
454 |
+
"grad_norm": 73.75,
|
455 |
+
"learning_rate": 9.998999614069865e-07,
|
456 |
+
"loss": 134.8779,
|
457 |
+
"step": 640
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.05202009276082887,
|
461 |
+
"grad_norm": 77.3125,
|
462 |
+
"learning_rate": 9.998983983039708e-07,
|
463 |
+
"loss": 133.0986,
|
464 |
+
"step": 650
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.052820401880226235,
|
468 |
+
"grad_norm": 78.5625,
|
469 |
+
"learning_rate": 9.998968352009548e-07,
|
470 |
+
"loss": 135.0677,
|
471 |
+
"step": 660
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.0536207109996236,
|
475 |
+
"grad_norm": 78.1875,
|
476 |
+
"learning_rate": 9.99895272097939e-07,
|
477 |
+
"loss": 133.2067,
|
478 |
+
"step": 670
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 0.054421020119020974,
|
482 |
+
"grad_norm": 70.0625,
|
483 |
+
"learning_rate": 9.998937089949232e-07,
|
484 |
+
"loss": 133.9511,
|
485 |
+
"step": 680
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.05522132923841834,
|
489 |
+
"grad_norm": 80.375,
|
490 |
+
"learning_rate": 9.998921458919072e-07,
|
491 |
+
"loss": 133.9503,
|
492 |
+
"step": 690
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 0.056021638357815706,
|
496 |
+
"grad_norm": 74.6875,
|
497 |
+
"learning_rate": 9.998905827888914e-07,
|
498 |
+
"loss": 134.0494,
|
499 |
+
"step": 700
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 0.05682194747721307,
|
503 |
+
"grad_norm": 77.25,
|
504 |
+
"learning_rate": 9.998890196858756e-07,
|
505 |
+
"loss": 134.0122,
|
506 |
+
"step": 710
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.05762225659661044,
|
510 |
+
"grad_norm": 80.875,
|
511 |
+
"learning_rate": 9.998874565828599e-07,
|
512 |
+
"loss": 134.0668,
|
513 |
+
"step": 720
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.05842256571600781,
|
517 |
+
"grad_norm": 84.125,
|
518 |
+
"learning_rate": 9.99885893479844e-07,
|
519 |
+
"loss": 134.0675,
|
520 |
+
"step": 730
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 0.05922287483540518,
|
524 |
+
"grad_norm": 72.375,
|
525 |
+
"learning_rate": 9.99884330376828e-07,
|
526 |
+
"loss": 133.1081,
|
527 |
+
"step": 740
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.06002318395480254,
|
531 |
+
"grad_norm": 72.5625,
|
532 |
+
"learning_rate": 9.998827672738123e-07,
|
533 |
+
"loss": 134.6276,
|
534 |
+
"step": 750
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.06082349307419991,
|
538 |
+
"grad_norm": 78.3125,
|
539 |
+
"learning_rate": 9.998812041707965e-07,
|
540 |
+
"loss": 134.8289,
|
541 |
+
"step": 760
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 0.061623802193597275,
|
545 |
+
"grad_norm": 78.125,
|
546 |
+
"learning_rate": 9.998796410677807e-07,
|
547 |
+
"loss": 134.8663,
|
548 |
+
"step": 770
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.06242411131299464,
|
552 |
+
"grad_norm": 71.75,
|
553 |
+
"learning_rate": 9.998780779647647e-07,
|
554 |
+
"loss": 133.6727,
|
555 |
+
"step": 780
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.06322442043239201,
|
559 |
+
"grad_norm": 74.4375,
|
560 |
+
"learning_rate": 9.99876514861749e-07,
|
561 |
+
"loss": 133.9329,
|
562 |
+
"step": 790
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 0.06402472955178938,
|
566 |
+
"grad_norm": 74.625,
|
567 |
+
"learning_rate": 9.998749517587332e-07,
|
568 |
+
"loss": 133.3252,
|
569 |
+
"step": 800
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.06482503867118675,
|
573 |
+
"grad_norm": 71.625,
|
574 |
+
"learning_rate": 9.998733886557172e-07,
|
575 |
+
"loss": 134.0405,
|
576 |
+
"step": 810
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 0.06562534779058411,
|
580 |
+
"grad_norm": 80.625,
|
581 |
+
"learning_rate": 9.998718255527014e-07,
|
582 |
+
"loss": 133.8837,
|
583 |
+
"step": 820
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 0.06642565690998148,
|
587 |
+
"grad_norm": 76.5625,
|
588 |
+
"learning_rate": 9.998702624496856e-07,
|
589 |
+
"loss": 134.2091,
|
590 |
+
"step": 830
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.06722596602937884,
|
594 |
+
"grad_norm": 71.75,
|
595 |
+
"learning_rate": 9.998686993466698e-07,
|
596 |
+
"loss": 133.8055,
|
597 |
+
"step": 840
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.06802627514877621,
|
601 |
+
"grad_norm": 78.9375,
|
602 |
+
"learning_rate": 9.998671362436539e-07,
|
603 |
+
"loss": 132.6678,
|
604 |
+
"step": 850
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 0.06882658426817358,
|
608 |
+
"grad_norm": 78.8125,
|
609 |
+
"learning_rate": 9.99865573140638e-07,
|
610 |
+
"loss": 134.7295,
|
611 |
+
"step": 860
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.06962689338757094,
|
615 |
+
"grad_norm": 77.375,
|
616 |
+
"learning_rate": 9.998640100376223e-07,
|
617 |
+
"loss": 134.0342,
|
618 |
+
"step": 870
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 0.07042720250696832,
|
622 |
+
"grad_norm": 76.0625,
|
623 |
+
"learning_rate": 9.998624469346065e-07,
|
624 |
+
"loss": 132.651,
|
625 |
+
"step": 880
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 0.07122751162636569,
|
629 |
+
"grad_norm": 75.0625,
|
630 |
+
"learning_rate": 9.998608838315905e-07,
|
631 |
+
"loss": 133.6062,
|
632 |
+
"step": 890
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.07202782074576305,
|
636 |
+
"grad_norm": 73.5,
|
637 |
+
"learning_rate": 9.998593207285747e-07,
|
638 |
+
"loss": 132.7781,
|
639 |
+
"step": 900
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.07282812986516042,
|
643 |
+
"grad_norm": 82.4375,
|
644 |
+
"learning_rate": 9.99857757625559e-07,
|
645 |
+
"loss": 134.2361,
|
646 |
+
"step": 910
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 0.07362843898455779,
|
650 |
+
"grad_norm": 73.0625,
|
651 |
+
"learning_rate": 9.998561945225432e-07,
|
652 |
+
"loss": 133.2907,
|
653 |
+
"step": 920
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 0.07442874810395515,
|
657 |
+
"grad_norm": 80.6875,
|
658 |
+
"learning_rate": 9.998546314195274e-07,
|
659 |
+
"loss": 134.2265,
|
660 |
+
"step": 930
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 0.07522905722335252,
|
664 |
+
"grad_norm": 80.25,
|
665 |
+
"learning_rate": 9.998530683165114e-07,
|
666 |
+
"loss": 133.9985,
|
667 |
+
"step": 940
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 0.07602936634274989,
|
671 |
+
"grad_norm": 74.125,
|
672 |
+
"learning_rate": 9.998515052134956e-07,
|
673 |
+
"loss": 134.877,
|
674 |
+
"step": 950
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.07682967546214725,
|
678 |
+
"grad_norm": 75.8125,
|
679 |
+
"learning_rate": 9.998499421104798e-07,
|
680 |
+
"loss": 133.8007,
|
681 |
+
"step": 960
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.07762998458154462,
|
685 |
+
"grad_norm": 80.0625,
|
686 |
+
"learning_rate": 9.998483790074638e-07,
|
687 |
+
"loss": 134.6694,
|
688 |
+
"step": 970
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 0.07843029370094198,
|
692 |
+
"grad_norm": 76.125,
|
693 |
+
"learning_rate": 9.99846815904448e-07,
|
694 |
+
"loss": 133.3736,
|
695 |
+
"step": 980
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 0.07923060282033935,
|
699 |
+
"grad_norm": 81.9375,
|
700 |
+
"learning_rate": 9.998452528014323e-07,
|
701 |
+
"loss": 134.208,
|
702 |
+
"step": 990
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 0.08003091193973673,
|
706 |
+
"grad_norm": 75.4375,
|
707 |
+
"learning_rate": 9.998436896984163e-07,
|
708 |
+
"loss": 133.7086,
|
709 |
+
"step": 1000
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 0.0808312210591341,
|
713 |
+
"grad_norm": 79.4375,
|
714 |
+
"learning_rate": 9.998421265954005e-07,
|
715 |
+
"loss": 133.6408,
|
716 |
+
"step": 1010
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 0.08163153017853146,
|
720 |
+
"grad_norm": 77.8125,
|
721 |
+
"learning_rate": 9.998405634923847e-07,
|
722 |
+
"loss": 132.0228,
|
723 |
+
"step": 1020
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 0.08243183929792883,
|
727 |
+
"grad_norm": 79.75,
|
728 |
+
"learning_rate": 9.99839000389369e-07,
|
729 |
+
"loss": 133.7949,
|
730 |
+
"step": 1030
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 0.0832321484173262,
|
734 |
+
"grad_norm": 77.5,
|
735 |
+
"learning_rate": 9.998374372863532e-07,
|
736 |
+
"loss": 132.4473,
|
737 |
+
"step": 1040
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 0.08403245753672356,
|
741 |
+
"grad_norm": 78.625,
|
742 |
+
"learning_rate": 9.998358741833372e-07,
|
743 |
+
"loss": 133.509,
|
744 |
+
"step": 1050
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.08483276665612093,
|
748 |
+
"grad_norm": 74.625,
|
749 |
+
"learning_rate": 9.998343110803214e-07,
|
750 |
+
"loss": 134.2043,
|
751 |
+
"step": 1060
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 0.08563307577551829,
|
755 |
+
"grad_norm": 79.5,
|
756 |
+
"learning_rate": 9.998327479773056e-07,
|
757 |
+
"loss": 134.1369,
|
758 |
+
"step": 1070
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 0.08643338489491566,
|
762 |
+
"grad_norm": 81.3125,
|
763 |
+
"learning_rate": 9.998311848742898e-07,
|
764 |
+
"loss": 135.2469,
|
765 |
+
"step": 1080
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.08723369401431302,
|
769 |
+
"grad_norm": 76.8125,
|
770 |
+
"learning_rate": 9.99829621771274e-07,
|
771 |
+
"loss": 134.3792,
|
772 |
+
"step": 1090
|
773 |
+
},
|
774 |
+
{
|
775 |
+
"epoch": 0.08803400313371039,
|
776 |
+
"grad_norm": 83.0625,
|
777 |
+
"learning_rate": 9.99828058668258e-07,
|
778 |
+
"loss": 134.3031,
|
779 |
+
"step": 1100
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 0.08883431225310777,
|
783 |
+
"grad_norm": 77.5625,
|
784 |
+
"learning_rate": 9.998264955652423e-07,
|
785 |
+
"loss": 133.6508,
|
786 |
+
"step": 1110
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 0.08963462137250514,
|
790 |
+
"grad_norm": 72.5625,
|
791 |
+
"learning_rate": 9.998249324622265e-07,
|
792 |
+
"loss": 133.622,
|
793 |
+
"step": 1120
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 0.0904349304919025,
|
797 |
+
"grad_norm": 72.4375,
|
798 |
+
"learning_rate": 9.998233693592105e-07,
|
799 |
+
"loss": 133.585,
|
800 |
+
"step": 1130
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 0.09123523961129987,
|
804 |
+
"grad_norm": 83.8125,
|
805 |
+
"learning_rate": 9.998218062561947e-07,
|
806 |
+
"loss": 134.5366,
|
807 |
+
"step": 1140
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 0.09203554873069723,
|
811 |
+
"grad_norm": 75.6875,
|
812 |
+
"learning_rate": 9.99820243153179e-07,
|
813 |
+
"loss": 132.9767,
|
814 |
+
"step": 1150
|
815 |
+
},
|
816 |
+
{
|
817 |
+
"epoch": 0.0928358578500946,
|
818 |
+
"grad_norm": 75.6875,
|
819 |
+
"learning_rate": 9.99818680050163e-07,
|
820 |
+
"loss": 135.017,
|
821 |
+
"step": 1160
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"epoch": 0.09363616696949197,
|
825 |
+
"grad_norm": 78.8125,
|
826 |
+
"learning_rate": 9.998171169471471e-07,
|
827 |
+
"loss": 133.7126,
|
828 |
+
"step": 1170
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"epoch": 0.09443647608888933,
|
832 |
+
"grad_norm": 77.125,
|
833 |
+
"learning_rate": 9.998155538441314e-07,
|
834 |
+
"loss": 133.368,
|
835 |
+
"step": 1180
|
836 |
+
},
|
837 |
+
{
|
838 |
+
"epoch": 0.0952367852082867,
|
839 |
+
"grad_norm": 80.5625,
|
840 |
+
"learning_rate": 9.998139907411156e-07,
|
841 |
+
"loss": 134.3654,
|
842 |
+
"step": 1190
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 0.09603709432768406,
|
846 |
+
"grad_norm": 77.25,
|
847 |
+
"learning_rate": 9.998124276380998e-07,
|
848 |
+
"loss": 133.1469,
|
849 |
+
"step": 1200
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.09683740344708143,
|
853 |
+
"grad_norm": 71.0625,
|
854 |
+
"learning_rate": 9.998108645350838e-07,
|
855 |
+
"loss": 134.3933,
|
856 |
+
"step": 1210
|
857 |
+
},
|
858 |
+
{
|
859 |
+
"epoch": 0.0976377125664788,
|
860 |
+
"grad_norm": 71.125,
|
861 |
+
"learning_rate": 9.99809301432068e-07,
|
862 |
+
"loss": 132.187,
|
863 |
+
"step": 1220
|
864 |
+
},
|
865 |
+
{
|
866 |
+
"epoch": 0.09843802168587618,
|
867 |
+
"grad_norm": 73.0625,
|
868 |
+
"learning_rate": 9.998077383290522e-07,
|
869 |
+
"loss": 134.8376,
|
870 |
+
"step": 1230
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"epoch": 0.09923833080527354,
|
874 |
+
"grad_norm": 72.6875,
|
875 |
+
"learning_rate": 9.998061752260365e-07,
|
876 |
+
"loss": 133.2062,
|
877 |
+
"step": 1240
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 0.10003863992467091,
|
881 |
+
"grad_norm": 82.9375,
|
882 |
+
"learning_rate": 9.998046121230207e-07,
|
883 |
+
"loss": 134.4847,
|
884 |
+
"step": 1250
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 0.10083894904406827,
|
888 |
+
"grad_norm": 80.5,
|
889 |
+
"learning_rate": 9.998030490200047e-07,
|
890 |
+
"loss": 133.9005,
|
891 |
+
"step": 1260
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.10163925816346564,
|
895 |
+
"grad_norm": 75.3125,
|
896 |
+
"learning_rate": 9.99801485916989e-07,
|
897 |
+
"loss": 132.473,
|
898 |
+
"step": 1270
|
899 |
+
},
|
900 |
+
{
|
901 |
+
"epoch": 0.102439567282863,
|
902 |
+
"grad_norm": 72.875,
|
903 |
+
"learning_rate": 9.997999228139731e-07,
|
904 |
+
"loss": 133.0457,
|
905 |
+
"step": 1280
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 0.10323987640226037,
|
909 |
+
"grad_norm": 75.875,
|
910 |
+
"learning_rate": 9.997983597109571e-07,
|
911 |
+
"loss": 132.4673,
|
912 |
+
"step": 1290
|
913 |
+
},
|
914 |
+
{
|
915 |
+
"epoch": 0.10404018552165774,
|
916 |
+
"grad_norm": 78.5625,
|
917 |
+
"learning_rate": 9.997967966079413e-07,
|
918 |
+
"loss": 133.7126,
|
919 |
+
"step": 1300
|
920 |
+
},
|
921 |
+
{
|
922 |
+
"epoch": 0.1048404946410551,
|
923 |
+
"grad_norm": 78.25,
|
924 |
+
"learning_rate": 9.997952335049256e-07,
|
925 |
+
"loss": 133.5371,
|
926 |
+
"step": 1310
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 0.10564080376045247,
|
930 |
+
"grad_norm": 76.1875,
|
931 |
+
"learning_rate": 9.997936704019096e-07,
|
932 |
+
"loss": 132.6477,
|
933 |
+
"step": 1320
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 0.10644111287984984,
|
937 |
+
"grad_norm": 73.875,
|
938 |
+
"learning_rate": 9.997921072988938e-07,
|
939 |
+
"loss": 131.6196,
|
940 |
+
"step": 1330
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"epoch": 0.1072414219992472,
|
944 |
+
"grad_norm": 83.875,
|
945 |
+
"learning_rate": 9.99790544195878e-07,
|
946 |
+
"loss": 133.8508,
|
947 |
+
"step": 1340
|
948 |
+
},
|
949 |
+
{
|
950 |
+
"epoch": 0.10804173111864458,
|
951 |
+
"grad_norm": 72.25,
|
952 |
+
"learning_rate": 9.997889810928622e-07,
|
953 |
+
"loss": 133.3958,
|
954 |
+
"step": 1350
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 0.10884204023804195,
|
958 |
+
"grad_norm": 77.875,
|
959 |
+
"learning_rate": 9.997874179898464e-07,
|
960 |
+
"loss": 134.013,
|
961 |
+
"step": 1360
|
962 |
+
},
|
963 |
+
{
|
964 |
+
"epoch": 0.10964234935743931,
|
965 |
+
"grad_norm": 67.6875,
|
966 |
+
"learning_rate": 9.997858548868304e-07,
|
967 |
+
"loss": 133.0476,
|
968 |
+
"step": 1370
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 0.11044265847683668,
|
972 |
+
"grad_norm": 78.0,
|
973 |
+
"learning_rate": 9.997842917838147e-07,
|
974 |
+
"loss": 134.0779,
|
975 |
+
"step": 1380
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 0.11124296759623405,
|
979 |
+
"grad_norm": 75.25,
|
980 |
+
"learning_rate": 9.997827286807989e-07,
|
981 |
+
"loss": 135.0265,
|
982 |
+
"step": 1390
|
983 |
+
},
|
984 |
+
{
|
985 |
+
"epoch": 0.11204327671563141,
|
986 |
+
"grad_norm": 84.4375,
|
987 |
+
"learning_rate": 9.99781165577783e-07,
|
988 |
+
"loss": 132.7369,
|
989 |
+
"step": 1400
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 0.11284358583502878,
|
993 |
+
"grad_norm": 76.875,
|
994 |
+
"learning_rate": 9.997796024747673e-07,
|
995 |
+
"loss": 132.9652,
|
996 |
+
"step": 1410
|
997 |
+
},
|
998 |
+
{
|
999 |
+
"epoch": 0.11364389495442614,
|
1000 |
+
"grad_norm": 75.8125,
|
1001 |
+
"learning_rate": 9.997780393717513e-07,
|
1002 |
+
"loss": 132.9404,
|
1003 |
+
"step": 1420
|
1004 |
+
},
|
1005 |
+
{
|
1006 |
+
"epoch": 0.11444420407382351,
|
1007 |
+
"grad_norm": 81.5625,
|
1008 |
+
"learning_rate": 9.997764762687355e-07,
|
1009 |
+
"loss": 133.6693,
|
1010 |
+
"step": 1430
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"epoch": 0.11524451319322088,
|
1014 |
+
"grad_norm": 79.0625,
|
1015 |
+
"learning_rate": 9.997749131657198e-07,
|
1016 |
+
"loss": 133.2776,
|
1017 |
+
"step": 1440
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 0.11604482231261824,
|
1021 |
+
"grad_norm": 72.6875,
|
1022 |
+
"learning_rate": 9.997733500627038e-07,
|
1023 |
+
"loss": 133.9213,
|
1024 |
+
"step": 1450
|
1025 |
+
},
|
1026 |
+
{
|
1027 |
+
"epoch": 0.11684513143201562,
|
1028 |
+
"grad_norm": 77.0625,
|
1029 |
+
"learning_rate": 9.99771786959688e-07,
|
1030 |
+
"loss": 133.5122,
|
1031 |
+
"step": 1460
|
1032 |
+
},
|
1033 |
+
{
|
1034 |
+
"epoch": 0.11764544055141299,
|
1035 |
+
"grad_norm": 78.125,
|
1036 |
+
"learning_rate": 9.997702238566722e-07,
|
1037 |
+
"loss": 134.5584,
|
1038 |
+
"step": 1470
|
1039 |
+
},
|
1040 |
+
{
|
1041 |
+
"epoch": 0.11844574967081035,
|
1042 |
+
"grad_norm": 78.0,
|
1043 |
+
"learning_rate": 9.997686607536562e-07,
|
1044 |
+
"loss": 132.1062,
|
1045 |
+
"step": 1480
|
1046 |
+
},
|
1047 |
+
{
|
1048 |
+
"epoch": 0.11924605879020772,
|
1049 |
+
"grad_norm": 81.4375,
|
1050 |
+
"learning_rate": 9.997670976506404e-07,
|
1051 |
+
"loss": 134.1707,
|
1052 |
+
"step": 1490
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 0.12004636790960509,
|
1056 |
+
"grad_norm": 80.375,
|
1057 |
+
"learning_rate": 9.997655345476247e-07,
|
1058 |
+
"loss": 134.8848,
|
1059 |
+
"step": 1500
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.12084667702900245,
|
1063 |
+
"grad_norm": 76.0625,
|
1064 |
+
"learning_rate": 9.997639714446089e-07,
|
1065 |
+
"loss": 131.9225,
|
1066 |
+
"step": 1510
|
1067 |
+
},
|
1068 |
+
{
|
1069 |
+
"epoch": 0.12164698614839982,
|
1070 |
+
"grad_norm": 73.0,
|
1071 |
+
"learning_rate": 9.997624083415929e-07,
|
1072 |
+
"loss": 133.7994,
|
1073 |
+
"step": 1520
|
1074 |
+
},
|
1075 |
+
{
|
1076 |
+
"epoch": 0.12244729526779718,
|
1077 |
+
"grad_norm": 78.3125,
|
1078 |
+
"learning_rate": 9.99760845238577e-07,
|
1079 |
+
"loss": 133.7843,
|
1080 |
+
"step": 1530
|
1081 |
+
},
|
1082 |
+
{
|
1083 |
+
"epoch": 0.12324760438719455,
|
1084 |
+
"grad_norm": 69.4375,
|
1085 |
+
"learning_rate": 9.997592821355613e-07,
|
1086 |
+
"loss": 131.5354,
|
1087 |
+
"step": 1540
|
1088 |
+
},
|
1089 |
+
{
|
1090 |
+
"epoch": 0.12404791350659192,
|
1091 |
+
"grad_norm": 75.0,
|
1092 |
+
"learning_rate": 9.997577190325455e-07,
|
1093 |
+
"loss": 133.611,
|
1094 |
+
"step": 1550
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 0.12484822262598928,
|
1098 |
+
"grad_norm": 75.625,
|
1099 |
+
"learning_rate": 9.997561559295297e-07,
|
1100 |
+
"loss": 132.3119,
|
1101 |
+
"step": 1560
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 0.12564853174538665,
|
1105 |
+
"grad_norm": 81.25,
|
1106 |
+
"learning_rate": 9.997545928265138e-07,
|
1107 |
+
"loss": 132.667,
|
1108 |
+
"step": 1570
|
1109 |
+
},
|
1110 |
+
{
|
1111 |
+
"epoch": 0.12644884086478403,
|
1112 |
+
"grad_norm": 80.8125,
|
1113 |
+
"learning_rate": 9.99753029723498e-07,
|
1114 |
+
"loss": 133.3723,
|
1115 |
+
"step": 1580
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"epoch": 0.12724914998418138,
|
1119 |
+
"grad_norm": 75.9375,
|
1120 |
+
"learning_rate": 9.997514666204822e-07,
|
1121 |
+
"loss": 131.5222,
|
1122 |
+
"step": 1590
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"epoch": 0.12804945910357876,
|
1126 |
+
"grad_norm": 74.6875,
|
1127 |
+
"learning_rate": 9.997499035174664e-07,
|
1128 |
+
"loss": 133.6289,
|
1129 |
+
"step": 1600
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 0.1288497682229761,
|
1133 |
+
"grad_norm": 79.9375,
|
1134 |
+
"learning_rate": 9.997483404144504e-07,
|
1135 |
+
"loss": 133.2038,
|
1136 |
+
"step": 1610
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 0.1296500773423735,
|
1140 |
+
"grad_norm": 76.8125,
|
1141 |
+
"learning_rate": 9.997467773114346e-07,
|
1142 |
+
"loss": 133.7517,
|
1143 |
+
"step": 1620
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 0.13045038646177085,
|
1147 |
+
"grad_norm": 78.125,
|
1148 |
+
"learning_rate": 9.997452142084189e-07,
|
1149 |
+
"loss": 133.22,
|
1150 |
+
"step": 1630
|
1151 |
+
},
|
1152 |
+
{
|
1153 |
+
"epoch": 0.13125069558116823,
|
1154 |
+
"grad_norm": 78.75,
|
1155 |
+
"learning_rate": 9.997436511054029e-07,
|
1156 |
+
"loss": 133.4411,
|
1157 |
+
"step": 1640
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 0.1320510047005656,
|
1161 |
+
"grad_norm": 75.125,
|
1162 |
+
"learning_rate": 9.99742088002387e-07,
|
1163 |
+
"loss": 132.7751,
|
1164 |
+
"step": 1650
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 0.13285131381996296,
|
1168 |
+
"grad_norm": 79.4375,
|
1169 |
+
"learning_rate": 9.997405248993713e-07,
|
1170 |
+
"loss": 133.3775,
|
1171 |
+
"step": 1660
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 0.13365162293936034,
|
1175 |
+
"grad_norm": 82.0,
|
1176 |
+
"learning_rate": 9.997389617963555e-07,
|
1177 |
+
"loss": 133.9474,
|
1178 |
+
"step": 1670
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 0.1344519320587577,
|
1182 |
+
"grad_norm": 76.4375,
|
1183 |
+
"learning_rate": 9.997373986933395e-07,
|
1184 |
+
"loss": 134.6912,
|
1185 |
+
"step": 1680
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 0.13525224117815507,
|
1189 |
+
"grad_norm": 75.875,
|
1190 |
+
"learning_rate": 9.997358355903237e-07,
|
1191 |
+
"loss": 135.1857,
|
1192 |
+
"step": 1690
|
1193 |
+
},
|
1194 |
+
{
|
1195 |
+
"epoch": 0.13605255029755242,
|
1196 |
+
"grad_norm": 82.5625,
|
1197 |
+
"learning_rate": 9.99734272487308e-07,
|
1198 |
+
"loss": 135.5683,
|
1199 |
+
"step": 1700
|
1200 |
+
},
|
1201 |
+
{
|
1202 |
+
"epoch": 0.1368528594169498,
|
1203 |
+
"grad_norm": 74.25,
|
1204 |
+
"learning_rate": 9.997327093842922e-07,
|
1205 |
+
"loss": 133.0515,
|
1206 |
+
"step": 1710
|
1207 |
+
},
|
1208 |
+
{
|
1209 |
+
"epoch": 0.13765316853634715,
|
1210 |
+
"grad_norm": 75.6875,
|
1211 |
+
"learning_rate": 9.997311462812764e-07,
|
1212 |
+
"loss": 134.285,
|
1213 |
+
"step": 1720
|
1214 |
+
},
|
1215 |
+
{
|
1216 |
+
"epoch": 0.13845347765574453,
|
1217 |
+
"grad_norm": 78.0,
|
1218 |
+
"learning_rate": 9.997295831782604e-07,
|
1219 |
+
"loss": 132.9074,
|
1220 |
+
"step": 1730
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 0.13925378677514189,
|
1224 |
+
"grad_norm": 77.0,
|
1225 |
+
"learning_rate": 9.997280200752446e-07,
|
1226 |
+
"loss": 133.4366,
|
1227 |
+
"step": 1740
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 0.14005409589453927,
|
1231 |
+
"grad_norm": 75.5625,
|
1232 |
+
"learning_rate": 9.997264569722288e-07,
|
1233 |
+
"loss": 133.7744,
|
1234 |
+
"step": 1750
|
1235 |
+
},
|
1236 |
+
{
|
1237 |
+
"epoch": 0.14085440501393665,
|
1238 |
+
"grad_norm": 77.1875,
|
1239 |
+
"learning_rate": 9.997248938692128e-07,
|
1240 |
+
"loss": 133.4301,
|
1241 |
+
"step": 1760
|
1242 |
+
},
|
1243 |
+
{
|
1244 |
+
"epoch": 0.141654714133334,
|
1245 |
+
"grad_norm": 76.5625,
|
1246 |
+
"learning_rate": 9.99723330766197e-07,
|
1247 |
+
"loss": 133.3505,
|
1248 |
+
"step": 1770
|
1249 |
+
},
|
1250 |
+
{
|
1251 |
+
"epoch": 0.14245502325273138,
|
1252 |
+
"grad_norm": 81.25,
|
1253 |
+
"learning_rate": 9.997217676631813e-07,
|
1254 |
+
"loss": 133.3679,
|
1255 |
+
"step": 1780
|
1256 |
+
},
|
1257 |
+
{
|
1258 |
+
"epoch": 0.14325533237212873,
|
1259 |
+
"grad_norm": 80.75,
|
1260 |
+
"learning_rate": 9.997202045601655e-07,
|
1261 |
+
"loss": 131.0644,
|
1262 |
+
"step": 1790
|
1263 |
+
},
|
1264 |
+
{
|
1265 |
+
"epoch": 0.1440556414915261,
|
1266 |
+
"grad_norm": 78.6875,
|
1267 |
+
"learning_rate": 9.997186414571495e-07,
|
1268 |
+
"loss": 133.6262,
|
1269 |
+
"step": 1800
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 0.14485595061092346,
|
1273 |
+
"grad_norm": 71.6875,
|
1274 |
+
"learning_rate": 9.997170783541337e-07,
|
1275 |
+
"loss": 133.8133,
|
1276 |
+
"step": 1810
|
1277 |
+
},
|
1278 |
+
{
|
1279 |
+
"epoch": 0.14565625973032084,
|
1280 |
+
"grad_norm": 73.875,
|
1281 |
+
"learning_rate": 9.99715515251118e-07,
|
1282 |
+
"loss": 133.2261,
|
1283 |
+
"step": 1820
|
1284 |
+
},
|
1285 |
+
{
|
1286 |
+
"epoch": 0.1464565688497182,
|
1287 |
+
"grad_norm": 76.375,
|
1288 |
+
"learning_rate": 9.997139521481022e-07,
|
1289 |
+
"loss": 134.2764,
|
1290 |
+
"step": 1830
|
1291 |
+
},
|
1292 |
+
{
|
1293 |
+
"epoch": 0.14725687796911557,
|
1294 |
+
"grad_norm": 80.0,
|
1295 |
+
"learning_rate": 9.997123890450862e-07,
|
1296 |
+
"loss": 133.0369,
|
1297 |
+
"step": 1840
|
1298 |
+
},
|
1299 |
+
{
|
1300 |
+
"epoch": 0.14805718708851293,
|
1301 |
+
"grad_norm": 79.25,
|
1302 |
+
"learning_rate": 9.997108259420704e-07,
|
1303 |
+
"loss": 132.5432,
|
1304 |
+
"step": 1850
|
1305 |
+
},
|
1306 |
+
{
|
1307 |
+
"epoch": 0.1488574962079103,
|
1308 |
+
"grad_norm": 76.4375,
|
1309 |
+
"learning_rate": 9.997092628390546e-07,
|
1310 |
+
"loss": 132.448,
|
1311 |
+
"step": 1860
|
1312 |
+
},
|
1313 |
+
{
|
1314 |
+
"epoch": 0.14965780532730769,
|
1315 |
+
"grad_norm": 74.3125,
|
1316 |
+
"learning_rate": 9.997076997360388e-07,
|
1317 |
+
"loss": 134.039,
|
1318 |
+
"step": 1870
|
1319 |
+
},
|
1320 |
+
{
|
1321 |
+
"epoch": 0.15045811444670504,
|
1322 |
+
"grad_norm": 76.625,
|
1323 |
+
"learning_rate": 9.99706136633023e-07,
|
1324 |
+
"loss": 133.9122,
|
1325 |
+
"step": 1880
|
1326 |
+
},
|
1327 |
+
{
|
1328 |
+
"epoch": 0.15125842356610242,
|
1329 |
+
"grad_norm": 73.9375,
|
1330 |
+
"learning_rate": 9.99704573530007e-07,
|
1331 |
+
"loss": 133.0405,
|
1332 |
+
"step": 1890
|
1333 |
+
},
|
1334 |
+
{
|
1335 |
+
"epoch": 0.15205873268549977,
|
1336 |
+
"grad_norm": 76.25,
|
1337 |
+
"learning_rate": 9.997030104269913e-07,
|
1338 |
+
"loss": 133.0878,
|
1339 |
+
"step": 1900
|
1340 |
+
},
|
1341 |
+
{
|
1342 |
+
"epoch": 0.15285904180489715,
|
1343 |
+
"grad_norm": 74.0625,
|
1344 |
+
"learning_rate": 9.997014473239755e-07,
|
1345 |
+
"loss": 132.5003,
|
1346 |
+
"step": 1910
|
1347 |
+
},
|
1348 |
+
{
|
1349 |
+
"epoch": 0.1536593509242945,
|
1350 |
+
"grad_norm": 76.8125,
|
1351 |
+
"learning_rate": 9.996998842209595e-07,
|
1352 |
+
"loss": 134.9118,
|
1353 |
+
"step": 1920
|
1354 |
+
},
|
1355 |
+
{
|
1356 |
+
"epoch": 0.15445966004369188,
|
1357 |
+
"grad_norm": 86.4375,
|
1358 |
+
"learning_rate": 9.996983211179437e-07,
|
1359 |
+
"loss": 134.4519,
|
1360 |
+
"step": 1930
|
1361 |
+
},
|
1362 |
+
{
|
1363 |
+
"epoch": 0.15525996916308923,
|
1364 |
+
"grad_norm": 76.8125,
|
1365 |
+
"learning_rate": 9.99696758014928e-07,
|
1366 |
+
"loss": 133.9741,
|
1367 |
+
"step": 1940
|
1368 |
+
},
|
1369 |
+
{
|
1370 |
+
"epoch": 0.15606027828248661,
|
1371 |
+
"grad_norm": 76.1875,
|
1372 |
+
"learning_rate": 9.996951949119121e-07,
|
1373 |
+
"loss": 133.7216,
|
1374 |
+
"step": 1950
|
1375 |
+
},
|
1376 |
+
{
|
1377 |
+
"epoch": 0.15686058740188397,
|
1378 |
+
"grad_norm": 72.125,
|
1379 |
+
"learning_rate": 9.996936318088962e-07,
|
1380 |
+
"loss": 132.1554,
|
1381 |
+
"step": 1960
|
1382 |
+
},
|
1383 |
+
{
|
1384 |
+
"epoch": 0.15766089652128135,
|
1385 |
+
"grad_norm": 79.375,
|
1386 |
+
"learning_rate": 9.996920687058804e-07,
|
1387 |
+
"loss": 133.7076,
|
1388 |
+
"step": 1970
|
1389 |
+
},
|
1390 |
+
{
|
1391 |
+
"epoch": 0.1584612056406787,
|
1392 |
+
"grad_norm": 79.375,
|
1393 |
+
"learning_rate": 9.996905056028646e-07,
|
1394 |
+
"loss": 133.1065,
|
1395 |
+
"step": 1980
|
1396 |
+
},
|
1397 |
+
{
|
1398 |
+
"epoch": 0.15926151476007608,
|
1399 |
+
"grad_norm": 78.625,
|
1400 |
+
"learning_rate": 9.996889424998486e-07,
|
1401 |
+
"loss": 133.6056,
|
1402 |
+
"step": 1990
|
1403 |
+
},
|
1404 |
+
{
|
1405 |
+
"epoch": 0.16006182387947346,
|
1406 |
+
"grad_norm": 79.9375,
|
1407 |
+
"learning_rate": 9.996873793968328e-07,
|
1408 |
+
"loss": 133.6693,
|
1409 |
+
"step": 2000
|
1410 |
+
},
|
1411 |
+
{
|
1412 |
+
"epoch": 0.1608621329988708,
|
1413 |
+
"grad_norm": 73.5625,
|
1414 |
+
"learning_rate": 9.99685816293817e-07,
|
1415 |
+
"loss": 133.3085,
|
1416 |
+
"step": 2010
|
1417 |
+
},
|
1418 |
+
{
|
1419 |
+
"epoch": 0.1616624421182682,
|
1420 |
+
"grad_norm": 72.625,
|
1421 |
+
"learning_rate": 9.996842531908013e-07,
|
1422 |
+
"loss": 132.2977,
|
1423 |
+
"step": 2020
|
1424 |
+
},
|
1425 |
+
{
|
1426 |
+
"epoch": 0.16246275123766554,
|
1427 |
+
"grad_norm": 73.6875,
|
1428 |
+
"learning_rate": 9.996826900877855e-07,
|
1429 |
+
"loss": 133.0748,
|
1430 |
+
"step": 2030
|
1431 |
+
},
|
1432 |
+
{
|
1433 |
+
"epoch": 0.16326306035706292,
|
1434 |
+
"grad_norm": 78.5625,
|
1435 |
+
"learning_rate": 9.996811269847697e-07,
|
1436 |
+
"loss": 134.3872,
|
1437 |
+
"step": 2040
|
1438 |
+
},
|
1439 |
+
{
|
1440 |
+
"epoch": 0.16406336947646027,
|
1441 |
+
"grad_norm": 75.5625,
|
1442 |
+
"learning_rate": 9.996795638817537e-07,
|
1443 |
+
"loss": 130.7821,
|
1444 |
+
"step": 2050
|
1445 |
+
},
|
1446 |
+
{
|
1447 |
+
"epoch": 0.16486367859585765,
|
1448 |
+
"grad_norm": 72.4375,
|
1449 |
+
"learning_rate": 9.99678000778738e-07,
|
1450 |
+
"loss": 132.3199,
|
1451 |
+
"step": 2060
|
1452 |
+
},
|
1453 |
+
{
|
1454 |
+
"epoch": 0.165663987715255,
|
1455 |
+
"grad_norm": 77.1875,
|
1456 |
+
"learning_rate": 9.996764376757221e-07,
|
1457 |
+
"loss": 132.7069,
|
1458 |
+
"step": 2070
|
1459 |
+
},
|
1460 |
+
{
|
1461 |
+
"epoch": 0.1664642968346524,
|
1462 |
+
"grad_norm": 78.75,
|
1463 |
+
"learning_rate": 9.996748745727061e-07,
|
1464 |
+
"loss": 134.6731,
|
1465 |
+
"step": 2080
|
1466 |
+
},
|
1467 |
+
{
|
1468 |
+
"epoch": 0.16726460595404974,
|
1469 |
+
"grad_norm": 77.8125,
|
1470 |
+
"learning_rate": 9.996733114696904e-07,
|
1471 |
+
"loss": 132.4518,
|
1472 |
+
"step": 2090
|
1473 |
+
},
|
1474 |
+
{
|
1475 |
+
"epoch": 0.16806491507344712,
|
1476 |
+
"grad_norm": 80.0625,
|
1477 |
+
"learning_rate": 9.996717483666746e-07,
|
1478 |
+
"loss": 131.4908,
|
1479 |
+
"step": 2100
|
1480 |
+
},
|
1481 |
+
{
|
1482 |
+
"epoch": 0.1688652241928445,
|
1483 |
+
"grad_norm": 79.4375,
|
1484 |
+
"learning_rate": 9.996701852636586e-07,
|
1485 |
+
"loss": 132.5609,
|
1486 |
+
"step": 2110
|
1487 |
+
},
|
1488 |
+
{
|
1489 |
+
"epoch": 0.16966553331224185,
|
1490 |
+
"grad_norm": 75.75,
|
1491 |
+
"learning_rate": 9.996686221606428e-07,
|
1492 |
+
"loss": 133.5363,
|
1493 |
+
"step": 2120
|
1494 |
+
},
|
1495 |
+
{
|
1496 |
+
"epoch": 0.17046584243163923,
|
1497 |
+
"grad_norm": 74.8125,
|
1498 |
+
"learning_rate": 9.99667059057627e-07,
|
1499 |
+
"loss": 133.372,
|
1500 |
+
"step": 2130
|
1501 |
+
},
|
1502 |
+
{
|
1503 |
+
"epoch": 0.17126615155103658,
|
1504 |
+
"grad_norm": 78.125,
|
1505 |
+
"learning_rate": 9.996654959546112e-07,
|
1506 |
+
"loss": 134.09,
|
1507 |
+
"step": 2140
|
1508 |
+
},
|
1509 |
+
{
|
1510 |
+
"epoch": 0.17206646067043396,
|
1511 |
+
"grad_norm": 73.6875,
|
1512 |
+
"learning_rate": 9.996639328515952e-07,
|
1513 |
+
"loss": 134.2827,
|
1514 |
+
"step": 2150
|
1515 |
+
},
|
1516 |
+
{
|
1517 |
+
"epoch": 0.17286676978983131,
|
1518 |
+
"grad_norm": 75.6875,
|
1519 |
+
"learning_rate": 9.996623697485795e-07,
|
1520 |
+
"loss": 133.4792,
|
1521 |
+
"step": 2160
|
1522 |
+
},
|
1523 |
+
{
|
1524 |
+
"epoch": 0.1736670789092287,
|
1525 |
+
"grad_norm": 80.8125,
|
1526 |
+
"learning_rate": 9.996608066455637e-07,
|
1527 |
+
"loss": 133.7547,
|
1528 |
+
"step": 2170
|
1529 |
+
},
|
1530 |
+
{
|
1531 |
+
"epoch": 0.17446738802862605,
|
1532 |
+
"grad_norm": 75.5625,
|
1533 |
+
"learning_rate": 9.99659243542548e-07,
|
1534 |
+
"loss": 132.9351,
|
1535 |
+
"step": 2180
|
1536 |
+
},
|
1537 |
+
{
|
1538 |
+
"epoch": 0.17526769714802343,
|
1539 |
+
"grad_norm": 72.125,
|
1540 |
+
"learning_rate": 9.996576804395321e-07,
|
1541 |
+
"loss": 131.2331,
|
1542 |
+
"step": 2190
|
1543 |
+
},
|
1544 |
+
{
|
1545 |
+
"epoch": 0.17606800626742078,
|
1546 |
+
"grad_norm": 79.4375,
|
1547 |
+
"learning_rate": 9.996561173365161e-07,
|
1548 |
+
"loss": 134.6388,
|
1549 |
+
"step": 2200
|
1550 |
+
},
|
1551 |
+
{
|
1552 |
+
"epoch": 0.17686831538681816,
|
1553 |
+
"grad_norm": 77.125,
|
1554 |
+
"learning_rate": 9.996545542335003e-07,
|
1555 |
+
"loss": 133.2961,
|
1556 |
+
"step": 2210
|
1557 |
+
},
|
1558 |
+
{
|
1559 |
+
"epoch": 0.17766862450621554,
|
1560 |
+
"grad_norm": 75.875,
|
1561 |
+
"learning_rate": 9.996529911304846e-07,
|
1562 |
+
"loss": 133.8811,
|
1563 |
+
"step": 2220
|
1564 |
+
},
|
1565 |
+
{
|
1566 |
+
"epoch": 0.1784689336256129,
|
1567 |
+
"grad_norm": 73.5625,
|
1568 |
+
"learning_rate": 9.996514280274688e-07,
|
1569 |
+
"loss": 133.1757,
|
1570 |
+
"step": 2230
|
1571 |
+
},
|
1572 |
+
{
|
1573 |
+
"epoch": 0.17926924274501027,
|
1574 |
+
"grad_norm": 78.875,
|
1575 |
+
"learning_rate": 9.996498649244528e-07,
|
1576 |
+
"loss": 132.6364,
|
1577 |
+
"step": 2240
|
1578 |
+
},
|
1579 |
+
{
|
1580 |
+
"epoch": 0.18006955186440762,
|
1581 |
+
"grad_norm": 75.0,
|
1582 |
+
"learning_rate": 9.99648301821437e-07,
|
1583 |
+
"loss": 133.5787,
|
1584 |
+
"step": 2250
|
1585 |
+
},
|
1586 |
+
{
|
1587 |
+
"epoch": 0.180869860983805,
|
1588 |
+
"grad_norm": 73.75,
|
1589 |
+
"learning_rate": 9.996467387184212e-07,
|
1590 |
+
"loss": 133.0472,
|
1591 |
+
"step": 2260
|
1592 |
+
},
|
1593 |
+
{
|
1594 |
+
"epoch": 0.18167017010320236,
|
1595 |
+
"grad_norm": 73.5,
|
1596 |
+
"learning_rate": 9.996451756154052e-07,
|
1597 |
+
"loss": 132.8575,
|
1598 |
+
"step": 2270
|
1599 |
+
},
|
1600 |
+
{
|
1601 |
+
"epoch": 0.18247047922259974,
|
1602 |
+
"grad_norm": 81.75,
|
1603 |
+
"learning_rate": 9.996436125123894e-07,
|
1604 |
+
"loss": 132.7385,
|
1605 |
+
"step": 2280
|
1606 |
+
},
|
1607 |
+
{
|
1608 |
+
"epoch": 0.1832707883419971,
|
1609 |
+
"grad_norm": 71.5,
|
1610 |
+
"learning_rate": 9.996420494093737e-07,
|
1611 |
+
"loss": 132.8017,
|
1612 |
+
"step": 2290
|
1613 |
+
},
|
1614 |
+
{
|
1615 |
+
"epoch": 0.18407109746139447,
|
1616 |
+
"grad_norm": 73.75,
|
1617 |
+
"learning_rate": 9.996404863063579e-07,
|
1618 |
+
"loss": 134.2902,
|
1619 |
+
"step": 2300
|
1620 |
+
},
|
1621 |
+
{
|
1622 |
+
"epoch": 0.18487140658079182,
|
1623 |
+
"grad_norm": 72.375,
|
1624 |
+
"learning_rate": 9.996389232033419e-07,
|
1625 |
+
"loss": 133.3126,
|
1626 |
+
"step": 2310
|
1627 |
+
},
|
1628 |
+
{
|
1629 |
+
"epoch": 0.1856717157001892,
|
1630 |
+
"grad_norm": 72.875,
|
1631 |
+
"learning_rate": 9.99637360100326e-07,
|
1632 |
+
"loss": 133.4326,
|
1633 |
+
"step": 2320
|
1634 |
+
},
|
1635 |
+
{
|
1636 |
+
"epoch": 0.18647202481958655,
|
1637 |
+
"grad_norm": 79.875,
|
1638 |
+
"learning_rate": 9.996357969973103e-07,
|
1639 |
+
"loss": 135.3909,
|
1640 |
+
"step": 2330
|
1641 |
+
},
|
1642 |
+
{
|
1643 |
+
"epoch": 0.18727233393898393,
|
1644 |
+
"grad_norm": 77.0625,
|
1645 |
+
"learning_rate": 9.996342338942945e-07,
|
1646 |
+
"loss": 133.5528,
|
1647 |
+
"step": 2340
|
1648 |
+
},
|
1649 |
+
{
|
1650 |
+
"epoch": 0.1880726430583813,
|
1651 |
+
"grad_norm": 77.5,
|
1652 |
+
"learning_rate": 9.996326707912788e-07,
|
1653 |
+
"loss": 133.1468,
|
1654 |
+
"step": 2350
|
1655 |
+
},
|
1656 |
+
{
|
1657 |
+
"epoch": 0.18887295217777866,
|
1658 |
+
"grad_norm": 79.0,
|
1659 |
+
"learning_rate": 9.996311076882628e-07,
|
1660 |
+
"loss": 132.3221,
|
1661 |
+
"step": 2360
|
1662 |
+
},
|
1663 |
+
{
|
1664 |
+
"epoch": 0.18967326129717604,
|
1665 |
+
"grad_norm": 78.625,
|
1666 |
+
"learning_rate": 9.99629544585247e-07,
|
1667 |
+
"loss": 134.5704,
|
1668 |
+
"step": 2370
|
1669 |
+
},
|
1670 |
+
{
|
1671 |
+
"epoch": 0.1904735704165734,
|
1672 |
+
"grad_norm": 75.0,
|
1673 |
+
"learning_rate": 9.996279814822312e-07,
|
1674 |
+
"loss": 133.3002,
|
1675 |
+
"step": 2380
|
1676 |
+
},
|
1677 |
+
{
|
1678 |
+
"epoch": 0.19127387953597078,
|
1679 |
+
"grad_norm": 81.8125,
|
1680 |
+
"learning_rate": 9.996264183792154e-07,
|
1681 |
+
"loss": 133.6831,
|
1682 |
+
"step": 2390
|
1683 |
+
},
|
1684 |
+
{
|
1685 |
+
"epoch": 0.19207418865536813,
|
1686 |
+
"grad_norm": 74.375,
|
1687 |
+
"learning_rate": 9.996248552761994e-07,
|
1688 |
+
"loss": 132.5035,
|
1689 |
+
"step": 2400
|
1690 |
+
},
|
1691 |
+
{
|
1692 |
+
"epoch": 0.1928744977747655,
|
1693 |
+
"grad_norm": 83.8125,
|
1694 |
+
"learning_rate": 9.996232921731836e-07,
|
1695 |
+
"loss": 132.3072,
|
1696 |
+
"step": 2410
|
1697 |
+
},
|
1698 |
+
{
|
1699 |
+
"epoch": 0.19367480689416286,
|
1700 |
+
"grad_norm": 76.6875,
|
1701 |
+
"learning_rate": 9.996217290701679e-07,
|
1702 |
+
"loss": 133.4728,
|
1703 |
+
"step": 2420
|
1704 |
+
},
|
1705 |
+
{
|
1706 |
+
"epoch": 0.19447511601356024,
|
1707 |
+
"grad_norm": 80.25,
|
1708 |
+
"learning_rate": 9.996201659671519e-07,
|
1709 |
+
"loss": 132.2028,
|
1710 |
+
"step": 2430
|
1711 |
+
},
|
1712 |
+
{
|
1713 |
+
"epoch": 0.1952754251329576,
|
1714 |
+
"grad_norm": 72.5625,
|
1715 |
+
"learning_rate": 9.99618602864136e-07,
|
1716 |
+
"loss": 133.2437,
|
1717 |
+
"step": 2440
|
1718 |
+
},
|
1719 |
+
{
|
1720 |
+
"epoch": 0.19607573425235497,
|
1721 |
+
"grad_norm": 77.125,
|
1722 |
+
"learning_rate": 9.996170397611203e-07,
|
1723 |
+
"loss": 134.2502,
|
1724 |
+
"step": 2450
|
1725 |
+
},
|
1726 |
+
{
|
1727 |
+
"epoch": 0.19687604337175235,
|
1728 |
+
"grad_norm": 78.0,
|
1729 |
+
"learning_rate": 9.996154766581043e-07,
|
1730 |
+
"loss": 134.4984,
|
1731 |
+
"step": 2460
|
1732 |
+
},
|
1733 |
+
{
|
1734 |
+
"epoch": 0.1976763524911497,
|
1735 |
+
"grad_norm": 80.3125,
|
1736 |
+
"learning_rate": 9.996139135550885e-07,
|
1737 |
+
"loss": 132.5038,
|
1738 |
+
"step": 2470
|
1739 |
+
},
|
1740 |
+
{
|
1741 |
+
"epoch": 0.19847666161054708,
|
1742 |
+
"grad_norm": 72.5,
|
1743 |
+
"learning_rate": 9.996123504520728e-07,
|
1744 |
+
"loss": 130.4979,
|
1745 |
+
"step": 2480
|
1746 |
+
},
|
1747 |
+
{
|
1748 |
+
"epoch": 0.19927697072994444,
|
1749 |
+
"grad_norm": 76.3125,
|
1750 |
+
"learning_rate": 9.99610787349057e-07,
|
1751 |
+
"loss": 132.6546,
|
1752 |
+
"step": 2490
|
1753 |
+
},
|
1754 |
+
{
|
1755 |
+
"epoch": 0.20007727984934182,
|
1756 |
+
"grad_norm": 74.5,
|
1757 |
+
"learning_rate": 9.996092242460412e-07,
|
1758 |
+
"loss": 132.9037,
|
1759 |
+
"step": 2500
|
1760 |
+
},
|
1761 |
+
{
|
1762 |
+
"epoch": 0.20007727984934182,
|
1763 |
+
"eval_loss": 2.079555034637451,
|
1764 |
+
"eval_runtime": 423.7834,
|
1765 |
+
"eval_samples_per_second": 1548.333,
|
1766 |
+
"eval_steps_per_second": 48.386,
|
1767 |
+
"step": 2500
|
1768 |
+
}
|
1769 |
+
],
|
1770 |
+
"logging_steps": 10,
|
1771 |
+
"max_steps": 12495,
|
1772 |
+
"num_input_tokens_seen": 0,
|
1773 |
+
"num_train_epochs": 1,
|
1774 |
+
"save_steps": 2500,
|
1775 |
+
"stateful_callbacks": {
|
1776 |
+
"TrainerControl": {
|
1777 |
+
"args": {
|
1778 |
+
"should_epoch_stop": false,
|
1779 |
+
"should_evaluate": false,
|
1780 |
+
"should_log": false,
|
1781 |
+
"should_save": true,
|
1782 |
+
"should_training_stop": false
|
1783 |
+
},
|
1784 |
+
"attributes": {}
|
1785 |
+
}
|
1786 |
+
},
|
1787 |
+
"total_flos": 6.902791444365312e+18,
|
1788 |
+
"train_batch_size": 4,
|
1789 |
+
"trial_name": null,
|
1790 |
+
"trial_params": null
|
1791 |
+
}
|
last-checkpoint/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:88d965b15b996d01a6d551562afe1ab8d0b8a2130af1cbd8fedae1d7e57bdaef
|
3 |
+
size 5368
|