Training in progress, step 19, 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 sha256:96ac749519919a36f567a72798297278e0fb43211bf6023c76d37b036f87941e
|
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:d1f4d041145bf9ebc1f049bad1db14f773ac3cd5df1947a70edc5ec03c6c2ade
|
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 sha256:4d8f9db3ae889afbfe292672c6de2a09aba088d6a7f4c3042f848555a48285ed
|
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 sha256:83e3bd115fb7914e3157d1cddd28d2440908da5dddf3ed8b9232586a56c11e23
|
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": 4,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -60,6 +60,14 @@
|
|
60 |
"learning_rate": 4.131759111665349e-05,
|
61 |
"loss": 2.2529,
|
62 |
"step": 15
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
63 |
}
|
64 |
],
|
65 |
"logging_steps": 5,
|
@@ -74,12 +82,12 @@
|
|
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": 1.0266666666666666,
|
5 |
"eval_steps": 4,
|
6 |
+
"global_step": 19,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
60 |
"learning_rate": 4.131759111665349e-05,
|
61 |
"loss": 2.2529,
|
62 |
"step": 15
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.8533333333333334,
|
66 |
+
"eval_loss": 0.6380996108055115,
|
67 |
+
"eval_runtime": 0.3719,
|
68 |
+
"eval_samples_per_second": 21.508,
|
69 |
+
"eval_steps_per_second": 10.754,
|
70 |
+
"step": 16
|
71 |
}
|
72 |
],
|
73 |
"logging_steps": 5,
|
|
|
82 |
"should_evaluate": false,
|
83 |
"should_log": false,
|
84 |
"should_save": true,
|
85 |
+
"should_training_stop": true
|
86 |
},
|
87 |
"attributes": {}
|
88 |
}
|
89 |
},
|
90 |
+
"total_flos": 616166691176448.0,
|
91 |
"train_batch_size": 2,
|
92 |
"trial_name": null,
|
93 |
"trial_params": null
|