Training in progress, step 39, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 12609312
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80b983e23e05d3db956d6d2aaf1c5b5b2b5e1f90e4b727c29785fd4d09820ca1
|
3 |
size 12609312
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6615034
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:79b243ce138a477e7f19121d01e18203442bf69c151138c9b10c07a3b660fa5b
|
3 |
size 6615034
|
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 sha256:27917d88cdf4e1cd610266e1bad5287f7c270415c57a7781c0adaab154ebaaf5
|
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 sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
|
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": 10,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -66,6 +66,28 @@
|
|
66 |
"learning_rate": 6.91341716182545e-05,
|
67 |
"loss": 13.662,
|
68 |
"step": 25
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
69 |
}
|
70 |
],
|
71 |
"logging_steps": 5,
|
@@ -85,7 +107,7 @@
|
|
85 |
"attributes": {}
|
86 |
}
|
87 |
},
|
88 |
-
"total_flos":
|
89 |
"train_batch_size": 2,
|
90 |
"trial_name": null,
|
91 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.003623356714823245,
|
5 |
"eval_steps": 10,
|
6 |
+
"global_step": 39,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
66 |
"learning_rate": 6.91341716182545e-05,
|
67 |
"loss": 13.662,
|
68 |
"step": 25
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.002787197472940958,
|
72 |
+
"grad_norm": 62.32259750366211,
|
73 |
+
"learning_rate": 5e-05,
|
74 |
+
"loss": 13.374,
|
75 |
+
"step": 30
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.002787197472940958,
|
79 |
+
"eval_loss": 3.3690028190612793,
|
80 |
+
"eval_runtime": 82.7158,
|
81 |
+
"eval_samples_per_second": 54.79,
|
82 |
+
"eval_steps_per_second": 27.395,
|
83 |
+
"step": 30
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 0.0032517303850977844,
|
87 |
+
"grad_norm": 45.002403259277344,
|
88 |
+
"learning_rate": 3.086582838174551e-05,
|
89 |
+
"loss": 13.2412,
|
90 |
+
"step": 35
|
91 |
}
|
92 |
],
|
93 |
"logging_steps": 5,
|
|
|
107 |
"attributes": {}
|
108 |
}
|
109 |
},
|
110 |
+
"total_flos": 355300691410944.0,
|
111 |
"train_batch_size": 2,
|
112 |
"trial_name": null,
|
113 |
"trial_params": null
|