tuanna08go
commited on
Training in progress, step 22, 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 36981072
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b4b3fd3314a532fa4eb57102e874e966deb8f9101a60567d0d5662c70169df7
|
3 |
size 36981072
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 19859140
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0dee10a4022d0d0b3427da7f99b17f1a83f16150a68c0f26d26ec82235c5806a
|
3 |
size 19859140
|
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 sha256:456c7446b83d2243e9b274c114bba5d6818f12660ff7b84af528a8b8a8bbc927
|
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 sha256:1565387b96ec5f770ad7b2f4817988cb2fc09f94ceb911096ae3c468010baf3d
|
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": 5,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -46,6 +46,21 @@
|
|
46 |
"eval_samples_per_second": 50.316,
|
47 |
"eval_steps_per_second": 6.548,
|
48 |
"step": 15
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
49 |
}
|
50 |
],
|
51 |
"logging_steps": 10,
|
@@ -60,12 +75,12 @@
|
|
60 |
"should_evaluate": false,
|
61 |
"should_log": false,
|
62 |
"should_save": true,
|
63 |
-
"should_training_stop":
|
64 |
},
|
65 |
"attributes": {}
|
66 |
}
|
67 |
},
|
68 |
-
"total_flos":
|
69 |
"train_batch_size": 8,
|
70 |
"trial_name": null,
|
71 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0173410404624277,
|
5 |
"eval_steps": 5,
|
6 |
+
"global_step": 22,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
46 |
"eval_samples_per_second": 50.316,
|
47 |
"eval_steps_per_second": 6.548,
|
48 |
"step": 15
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 0.9248554913294798,
|
52 |
+
"grad_norm": 13.683239936828613,
|
53 |
+
"learning_rate": 2.4471741852423237e-06,
|
54 |
+
"loss": 7.7794,
|
55 |
+
"step": 20
|
56 |
+
},
|
57 |
+
{
|
58 |
+
"epoch": 0.9248554913294798,
|
59 |
+
"eval_loss": 6.403977394104004,
|
60 |
+
"eval_runtime": 2.8555,
|
61 |
+
"eval_samples_per_second": 51.129,
|
62 |
+
"eval_steps_per_second": 6.654,
|
63 |
+
"step": 20
|
64 |
}
|
65 |
],
|
66 |
"logging_steps": 10,
|
|
|
75 |
"should_evaluate": false,
|
76 |
"should_log": false,
|
77 |
"should_save": true,
|
78 |
+
"should_training_stop": true
|
79 |
},
|
80 |
"attributes": {}
|
81 |
}
|
82 |
},
|
83 |
+
"total_flos": 1.1407191243227136e+16,
|
84 |
"train_batch_size": 8,
|
85 |
"trial_name": null,
|
86 |
"trial_params": null
|