Training in progress, step 5500, 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 891558696
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:683c6b844253214d5535f32fb10d971f05c91a8acc294539eaa07b28c3f16d01
|
3 |
size 891558696
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1783272762
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5e606906707907082dc8c6184eedbdf1ad6410646fdfb29ec0957ff6b4fea464
|
3 |
size 1783272762
|
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:cd16ada593cf0a36458682125206d81fb88aab5b155751c1343bff1314ca90c7
|
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 sha256:33ec81ecd0f74edad60756c692726503a5467d4d5a63f6abe2c6e32cac418cdc
|
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": 2.
|
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,
|
@@ -39,9 +39,9 @@
|
|
39 |
{
|
40 |
"epoch": 1.0,
|
41 |
"eval_loss": 0.33670297265052795,
|
42 |
-
"eval_runtime": 28.
|
43 |
-
"eval_samples_per_second": 16.
|
44 |
-
"eval_steps_per_second": 4.
|
45 |
"step": 2316
|
46 |
},
|
47 |
{
|
@@ -82,9 +82,9 @@
|
|
82 |
{
|
83 |
"epoch": 2.0,
|
84 |
"eval_loss": 0.3095574975013733,
|
85 |
-
"eval_runtime": 28.
|
86 |
-
"eval_samples_per_second": 16.
|
87 |
-
"eval_steps_per_second": 4.
|
88 |
"step": 4632
|
89 |
},
|
90 |
{
|
@@ -93,6 +93,13 @@
|
|
93 |
"learning_rate": 5.613126079447323e-06,
|
94 |
"loss": 0.3467,
|
95 |
"step": 5000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
96 |
}
|
97 |
],
|
98 |
"logging_steps": 500,
|
@@ -112,7 +119,7 @@
|
|
112 |
"attributes": {}
|
113 |
}
|
114 |
},
|
115 |
-
"total_flos": 1.
|
116 |
"train_batch_size": 4,
|
117 |
"trial_name": null,
|
118 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.3747841105354057,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 5500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
39 |
{
|
40 |
"epoch": 1.0,
|
41 |
"eval_loss": 0.33670297265052795,
|
42 |
+
"eval_runtime": 28.2248,
|
43 |
+
"eval_samples_per_second": 16.723,
|
44 |
+
"eval_steps_per_second": 4.181,
|
45 |
"step": 2316
|
46 |
},
|
47 |
{
|
|
|
82 |
{
|
83 |
"epoch": 2.0,
|
84 |
"eval_loss": 0.3095574975013733,
|
85 |
+
"eval_runtime": 28.2419,
|
86 |
+
"eval_samples_per_second": 16.713,
|
87 |
+
"eval_steps_per_second": 4.178,
|
88 |
"step": 4632
|
89 |
},
|
90 |
{
|
|
|
93 |
"learning_rate": 5.613126079447323e-06,
|
94 |
"loss": 0.3467,
|
95 |
"step": 5000
|
96 |
+
},
|
97 |
+
{
|
98 |
+
"epoch": 2.3747841105354057,
|
99 |
+
"grad_norm": 0.6125323176383972,
|
100 |
+
"learning_rate": 4.173862982153138e-06,
|
101 |
+
"loss": 0.3513,
|
102 |
+
"step": 5500
|
103 |
}
|
104 |
],
|
105 |
"logging_steps": 500,
|
|
|
119 |
"attributes": {}
|
120 |
}
|
121 |
},
|
122 |
+
"total_flos": 1.339585567653888e+16,
|
123 |
"train_batch_size": 4,
|
124 |
"trial_name": null,
|
125 |
"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 5432
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d2d71d788b491a41c54d3b024285748be4a2e443d732e96343f48dd9941e304a
|
3 |
size 5432
|