Training in progress, step 33, 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 556856304
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ed4f8d155ec543795a9b30145df7bf768affa7229f074ee8572fdbe222ee2b5
|
3 |
size 556856304
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 21599060
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b035336e453dbc0c757f89c1d19900766c10600aac5878df2b9b76a10d0a661
|
3 |
size 21599060
|
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 sha256:6aaf39acda48a820e6f1ab66faae9c9978da6a7846a4bc5bd7db8c439fb1e98b
|
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:e2d6cfc80244acd5f4689717566e3ae24af71bd49a8fb4f095519d60f11dea06
|
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": 11,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -59,6 +59,28 @@
|
|
59 |
"eval_samples_per_second": 21.917,
|
60 |
"eval_steps_per_second": 10.958,
|
61 |
"step": 22
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
62 |
}
|
63 |
],
|
64 |
"logging_steps": 5,
|
@@ -78,7 +100,7 @@
|
|
78 |
"attributes": {}
|
79 |
}
|
80 |
},
|
81 |
-
"total_flos":
|
82 |
"train_batch_size": 2,
|
83 |
"trial_name": null,
|
84 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.7951807228915663,
|
5 |
"eval_steps": 11,
|
6 |
+
"global_step": 33,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
59 |
"eval_samples_per_second": 21.917,
|
60 |
"eval_steps_per_second": 10.958,
|
61 |
"step": 22
|
62 |
+
},
|
63 |
+
{
|
64 |
+
"epoch": 0.6024096385542169,
|
65 |
+
"grad_norm": 3.4582600593566895,
|
66 |
+
"learning_rate": 5.490085701647805e-05,
|
67 |
+
"loss": 7.4872,
|
68 |
+
"step": 25
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.7228915662650602,
|
72 |
+
"grad_norm": 7.964458465576172,
|
73 |
+
"learning_rate": 3.086582838174551e-05,
|
74 |
+
"loss": 8.2409,
|
75 |
+
"step": 30
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.7951807228915663,
|
79 |
+
"eval_loss": 1.8038959503173828,
|
80 |
+
"eval_runtime": 0.8269,
|
81 |
+
"eval_samples_per_second": 21.768,
|
82 |
+
"eval_steps_per_second": 10.884,
|
83 |
+
"step": 33
|
84 |
}
|
85 |
],
|
86 |
"logging_steps": 5,
|
|
|
100 |
"attributes": {}
|
101 |
}
|
102 |
},
|
103 |
+
"total_flos": 4799177529753600.0,
|
104 |
"train_batch_size": 2,
|
105 |
"trial_name": null,
|
106 |
"trial_params": null
|