Training in progress, step 42, 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 39256456
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ece37aa1a63efb549f4eb62fce17222094e2543029874067c99a52ad4d4dd03b
|
3 |
size 39256456
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 20632826
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:162c232297d6b0e4a7853129f12d07675fb7ad529b46c108bfac430a19323237
|
3 |
size 20632826
|
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:f07d8c860cd7de8ee301f608ccd3584f3827e66ed38993f94733b1c5732af739
|
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 sha256:43352a0ea01b8f309df99bb65027960564fe5f2f452a04b8b6c955b0ecfed4cf
|
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": 11,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -60,6 +60,13 @@
|
|
60 |
"eval_samples_per_second": 50.515,
|
61 |
"eval_steps_per_second": 25.258,
|
62 |
"step": 33
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
63 |
}
|
64 |
],
|
65 |
"logging_steps": 10,
|
@@ -74,12 +81,12 @@
|
|
74 |
"should_evaluate": false,
|
75 |
"should_log": false,
|
76 |
"should_save": true,
|
77 |
-
"should_training_stop":
|
78 |
},
|
79 |
"attributes": {}
|
80 |
}
|
81 |
},
|
82 |
-
"total_flos":
|
83 |
"train_batch_size": 2,
|
84 |
"trial_name": null,
|
85 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0179640718562875,
|
5 |
"eval_steps": 11,
|
6 |
+
"global_step": 42,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
60 |
"eval_samples_per_second": 50.515,
|
61 |
"eval_steps_per_second": 25.258,
|
62 |
"step": 33
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.9580838323353293,
|
66 |
+
"grad_norm": 0.0008888053125701845,
|
67 |
+
"learning_rate": 0.0002,
|
68 |
+
"loss": 0.0,
|
69 |
+
"step": 40
|
70 |
}
|
71 |
],
|
72 |
"logging_steps": 10,
|
|
|
81 |
"should_evaluate": false,
|
82 |
"should_log": false,
|
83 |
"should_save": true,
|
84 |
+
"should_training_stop": true
|
85 |
},
|
86 |
"attributes": {}
|
87 |
}
|
88 |
},
|
89 |
+
"total_flos": 2055806732206080.0,
|
90 |
"train_batch_size": 2,
|
91 |
"trial_name": null,
|
92 |
"trial_params": null
|