Training in progress, epoch 1, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 557116312
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cd46c74284ba73b1189e2b45420e99399bb6205659df2d2c1b122e35dda7736f
|
3 |
size 557116312
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1113991930
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:79564fb6cc7e990450c02dc917f0c75912df3a4125a5bac3ef68dfb81133c309
|
3 |
size 1113991930
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:59624509e89bbc9b94c591ed4735982e33caa7e6875690c4ff16d1a97717d87c
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55dc22eb808a1fd1052bfc779bf751672ec8d853af74b32b8aa1627bdf5827cf
|
3 |
size 1064
|
last-checkpoint/tokenizer.json
CHANGED
@@ -1,11 +1,6 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
"direction": "Right",
|
5 |
-
"max_length": 128,
|
6 |
-
"strategy": "LongestFirst",
|
7 |
-
"stride": 0
|
8 |
-
},
|
9 |
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": null,
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,84 +1,50 @@
|
|
1 |
{
|
2 |
-
"best_metric":
|
3 |
-
"best_model_checkpoint": "my-model/checkpoint-
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.32722513089005234,
|
13 |
-
"grad_norm": 1.
|
14 |
-
"learning_rate": 4.
|
15 |
-
"loss": 0.
|
16 |
"step": 500
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.6544502617801047,
|
20 |
-
"grad_norm": 1.
|
21 |
-
"learning_rate":
|
22 |
-
"loss": 0.
|
23 |
"step": 1000
|
24 |
},
|
25 |
{
|
26 |
"epoch": 0.981675392670157,
|
27 |
-
"grad_norm": 1.
|
28 |
-
"learning_rate": 3.
|
29 |
-
"loss": 0.
|
30 |
"step": 1500
|
31 |
},
|
32 |
{
|
33 |
"epoch": 1.0,
|
34 |
-
"eval_loss": 5.
|
35 |
-
"eval_rouge1":
|
36 |
-
"eval_rouge2":
|
37 |
-
"eval_rougeL":
|
38 |
-
"
|
39 |
-
"
|
40 |
-
"
|
41 |
-
"eval_steps_per_second": 0.521,
|
42 |
"step": 1528
|
43 |
-
},
|
44 |
-
{
|
45 |
-
"epoch": 1.3089005235602094,
|
46 |
-
"grad_norm": 3.5784597396850586,
|
47 |
-
"learning_rate": 2.8184991273996508e-05,
|
48 |
-
"loss": 0.0605,
|
49 |
-
"step": 2000
|
50 |
-
},
|
51 |
-
{
|
52 |
-
"epoch": 1.6361256544502618,
|
53 |
-
"grad_norm": 3.948634624481201,
|
54 |
-
"learning_rate": 2.273123909249564e-05,
|
55 |
-
"loss": 0.1013,
|
56 |
-
"step": 2500
|
57 |
-
},
|
58 |
-
{
|
59 |
-
"epoch": 1.9633507853403143,
|
60 |
-
"grad_norm": 5.947019577026367,
|
61 |
-
"learning_rate": 1.7277486910994763e-05,
|
62 |
-
"loss": 0.2594,
|
63 |
-
"step": 3000
|
64 |
-
},
|
65 |
-
{
|
66 |
-
"epoch": 2.0,
|
67 |
-
"eval_loss": 4.7294816970825195,
|
68 |
-
"eval_rouge1": 3.0744,
|
69 |
-
"eval_rouge2": 0.2582,
|
70 |
-
"eval_rougeL": 3.0319,
|
71 |
-
"eval_rougeLsum": 3.0448,
|
72 |
-
"eval_runtime": 416.9983,
|
73 |
-
"eval_samples_per_second": 5.264,
|
74 |
-
"eval_steps_per_second": 0.528,
|
75 |
-
"step": 3056
|
76 |
}
|
77 |
],
|
78 |
"logging_steps": 500,
|
79 |
-
"max_steps":
|
80 |
"num_input_tokens_seen": 0,
|
81 |
-
"num_train_epochs":
|
82 |
"save_steps": 500,
|
83 |
"stateful_callbacks": {
|
84 |
"TrainerControl": {
|
@@ -92,7 +58,7 @@
|
|
92 |
"attributes": {}
|
93 |
}
|
94 |
},
|
95 |
-
"total_flos":
|
96 |
"train_batch_size": 10,
|
97 |
"trial_name": null,
|
98 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 24.8013,
|
3 |
+
"best_model_checkpoint": "my-model/checkpoint-1528",
|
4 |
+
"epoch": 1.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 1528,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.32722513089005234,
|
13 |
+
"grad_norm": 1.6467379331588745,
|
14 |
+
"learning_rate": 4.5909685863874345e-05,
|
15 |
+
"loss": 0.0168,
|
16 |
"step": 500
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.6544502617801047,
|
20 |
+
"grad_norm": 1.3730037212371826,
|
21 |
+
"learning_rate": 4.181937172774869e-05,
|
22 |
+
"loss": 0.0246,
|
23 |
"step": 1000
|
24 |
},
|
25 |
{
|
26 |
"epoch": 0.981675392670157,
|
27 |
+
"grad_norm": 1.1599562168121338,
|
28 |
+
"learning_rate": 3.7729057591623044e-05,
|
29 |
+
"loss": 0.0308,
|
30 |
"step": 1500
|
31 |
},
|
32 |
{
|
33 |
"epoch": 1.0,
|
34 |
+
"eval_loss": 5.495022296905518,
|
35 |
+
"eval_rouge1": 24.8013,
|
36 |
+
"eval_rouge2": 9.5895,
|
37 |
+
"eval_rougeL": 21.5936,
|
38 |
+
"eval_runtime": 434.7617,
|
39 |
+
"eval_samples_per_second": 5.049,
|
40 |
+
"eval_steps_per_second": 0.506,
|
|
|
41 |
"step": 1528
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
42 |
}
|
43 |
],
|
44 |
"logging_steps": 500,
|
45 |
+
"max_steps": 6112,
|
46 |
"num_input_tokens_seen": 0,
|
47 |
+
"num_train_epochs": 4,
|
48 |
"save_steps": 500,
|
49 |
"stateful_callbacks": {
|
50 |
"TrainerControl": {
|
|
|
58 |
"attributes": {}
|
59 |
}
|
60 |
},
|
61 |
+
"total_flos": 7327420304523264.0,
|
62 |
"train_batch_size": 10,
|
63 |
"trial_name": null,
|
64 |
"trial_params": null
|
last-checkpoint/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 sha256:408bb8b25e44f1ecf1923d9e22dabb6474162771a082c1a83b55da4bd5267fc0
|
3 |
+
size 6968
|