update model to ckpoint 3500
Browse files- config.json +1 -1
- pytorch_model-00001-of-00002.bin +1 -1
- pytorch_model-00002-of-00002.bin +1 -1
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +58 -0
- training_args.bin +2 -2
config.json
CHANGED
@@ -75,7 +75,7 @@
|
|
75 |
},
|
76 |
"tokenizer_class": "GPT2Tokenizer",
|
77 |
"torch_dtype": "float32",
|
78 |
-
"transformers_version": "4.
|
79 |
"use_cache": true,
|
80 |
"vocab_size": 50257,
|
81 |
"window_size": 256
|
|
|
75 |
},
|
76 |
"tokenizer_class": "GPT2Tokenizer",
|
77 |
"torch_dtype": "float32",
|
78 |
+
"transformers_version": "4.23.1",
|
79 |
"use_cache": true,
|
80 |
"vocab_size": 50257,
|
81 |
"window_size": 256
|
pytorch_model-00001-of-00002.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 9996970517
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b3977a25a38d65c8381c63b8d549e59b819ec5bec1ed892867ce834555f874b
|
3 |
size 9996970517
|
pytorch_model-00002-of-00002.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 742637631
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:547fc177de3ba4ba268864c8128f9b4e05b1196e8a8bdaa44b45d6450e33611f
|
3 |
size 742637631
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9fe4f7564f56a1ffa25a5c606d62664ceee4525fae7d67da25c48a37122eeeaf
|
3 |
+
size 14503
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a8c8325f2941fb440a70e076145fff814af3bb9cb14c7d849f105ea262a5d6cf
|
3 |
+
size 623
|
trainer_state.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.7115339655820856,
|
5 |
+
"global_step": 3500,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.1,
|
12 |
+
"learning_rate": 4.872915819438796e-06,
|
13 |
+
"loss": 3.1058,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.2,
|
18 |
+
"learning_rate": 4.745831638877592e-06,
|
19 |
+
"loss": 3.0496,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.3,
|
24 |
+
"learning_rate": 4.618747458316389e-06,
|
25 |
+
"loss": 3.0295,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.41,
|
30 |
+
"learning_rate": 4.491663277755185e-06,
|
31 |
+
"loss": 3.0068,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.51,
|
36 |
+
"learning_rate": 4.364579097193982e-06,
|
37 |
+
"loss": 2.9939,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.61,
|
42 |
+
"learning_rate": 4.237494916632778e-06,
|
43 |
+
"loss": 2.9796,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.71,
|
48 |
+
"learning_rate": 4.110410736071574e-06,
|
49 |
+
"loss": 2.977,
|
50 |
+
"step": 3500
|
51 |
+
}
|
52 |
+
],
|
53 |
+
"max_steps": 19672,
|
54 |
+
"num_train_epochs": 4,
|
55 |
+
"total_flos": 2.1653725642752e+18,
|
56 |
+
"trial_name": null,
|
57 |
+
"trial_params": null
|
58 |
+
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc7808aebc878ce0f5e2093106139820e524f70e98790daf3c56abdbf1b0d8b6
|
3 |
+
size 3375
|