Training in progress, step 20, 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 239452242
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a8cd78b0763b2a5b758b08c2ffa586ad039bd1a5e002dd7ac6fc9c151b8e88fb
|
3 |
size 239452242
|
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 sha256:6cba71b8400e9751a7ec40a5c65b542bac6c7fcb18bf7d203e4972b12b069895
|
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 sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
|
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": 0.
|
5 |
"eval_steps": 8,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -44,6 +44,35 @@
|
|
44 |
"learning_rate": 9e-05,
|
45 |
"loss": 0.0,
|
46 |
"step": 9
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
47 |
}
|
48 |
],
|
49 |
"logging_steps": 3,
|
@@ -63,7 +92,7 @@
|
|
63 |
"attributes": {}
|
64 |
}
|
65 |
},
|
66 |
-
"total_flos":
|
67 |
"train_batch_size": 2,
|
68 |
"trial_name": null,
|
69 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.02302158273381295,
|
5 |
"eval_steps": 8,
|
6 |
+
"global_step": 20,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
44 |
"learning_rate": 9e-05,
|
45 |
"loss": 0.0,
|
46 |
"step": 9
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 0.01381294964028777,
|
50 |
+
"grad_norm": NaN,
|
51 |
+
"learning_rate": 9.755282581475769e-05,
|
52 |
+
"loss": 0.0,
|
53 |
+
"step": 12
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 0.017266187050359712,
|
57 |
+
"grad_norm": NaN,
|
58 |
+
"learning_rate": 8.535533905932738e-05,
|
59 |
+
"loss": 0.0,
|
60 |
+
"step": 15
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 0.01841726618705036,
|
64 |
+
"eval_loss": NaN,
|
65 |
+
"eval_runtime": 27.9243,
|
66 |
+
"eval_samples_per_second": 13.107,
|
67 |
+
"eval_steps_per_second": 6.553,
|
68 |
+
"step": 16
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.020719424460431655,
|
72 |
+
"grad_norm": NaN,
|
73 |
+
"learning_rate": 6.545084971874738e-05,
|
74 |
+
"loss": 0.0,
|
75 |
+
"step": 18
|
76 |
}
|
77 |
],
|
78 |
"logging_steps": 3,
|
|
|
92 |
"attributes": {}
|
93 |
}
|
94 |
},
|
95 |
+
"total_flos": 3688821581414400.0,
|
96 |
"train_batch_size": 2,
|
97 |
"trial_name": null,
|
98 |
"trial_params": null
|