Training in progress, step 32, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 9568884
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87c91ebf333f15a013a94037594c64c545499eb6575961fd2a5ddbc9e15d812f
|
3 |
size 9568884
|
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:be21f39dc5e149caa3e5bcbaed58bd09ac2653482648ec02a928f5ae6f98f284
|
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:a387b210316633d05904a757c86d6d5b1f723a9084c82125f530fbd1f5f4ae32
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
"eval_steps": 7,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -53,6 +53,21 @@
|
|
53 |
"eval_samples_per_second": 68.546,
|
54 |
"eval_steps_per_second": 8.813,
|
55 |
"step": 21
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
56 |
}
|
57 |
],
|
58 |
"logging_steps": 10,
|
@@ -67,12 +82,12 @@
|
|
67 |
"should_evaluate": false,
|
68 |
"should_log": false,
|
69 |
"should_save": true,
|
70 |
-
"should_training_stop":
|
71 |
},
|
72 |
"attributes": {}
|
73 |
}
|
74 |
},
|
75 |
-
"total_flos":
|
76 |
"train_batch_size": 8,
|
77 |
"trial_name": null,
|
78 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0281124497991967,
|
5 |
"eval_steps": 7,
|
6 |
+
"global_step": 32,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
53 |
"eval_samples_per_second": 68.546,
|
54 |
"eval_steps_per_second": 8.813,
|
55 |
"step": 21
|
56 |
+
},
|
57 |
+
{
|
58 |
+
"epoch": 0.8995983935742972,
|
59 |
+
"eval_loss": NaN,
|
60 |
+
"eval_runtime": 3.0772,
|
61 |
+
"eval_samples_per_second": 68.245,
|
62 |
+
"eval_steps_per_second": 8.774,
|
63 |
+
"step": 28
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.963855421686747,
|
67 |
+
"grad_norm": NaN,
|
68 |
+
"learning_rate": 1.0926199633097157e-06,
|
69 |
+
"loss": 0.0,
|
70 |
+
"step": 30
|
71 |
}
|
72 |
],
|
73 |
"logging_steps": 10,
|
|
|
82 |
"should_evaluate": false,
|
83 |
"should_log": false,
|
84 |
"should_save": true,
|
85 |
+
"should_training_stop": true
|
86 |
},
|
87 |
"attributes": {}
|
88 |
}
|
89 |
},
|
90 |
+
"total_flos": 7105245471571968.0,
|
91 |
"train_batch_size": 8,
|
92 |
"trial_name": null,
|
93 |
"trial_params": null
|