Training in progress, step 50, 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 161714
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e219d3c950434268a4b0b56c4045ddfafaae6cc1b345df7a6355322d6ef614b
|
3 |
size 161714
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 64750
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b02df2451c0373a413fbc8414c98d845f151fbacb61e879a36ab03e93b281bd9
|
3 |
size 64750
|
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 sha256:3c72530c1181e385391bf43f1fdf08c8275fccd52a2134362ec0beb66af41fd8
|
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:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
|
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": 13,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -60,6 +60,20 @@
|
|
60 |
"eval_samples_per_second": 473.558,
|
61 |
"eval_steps_per_second": 236.779,
|
62 |
"step": 39
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
63 |
}
|
64 |
],
|
65 |
"logging_steps": 10,
|
@@ -74,12 +88,12 @@
|
|
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": 0.003565888708613404,
|
5 |
"eval_steps": 13,
|
6 |
+
"global_step": 50,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
60 |
"eval_samples_per_second": 473.558,
|
61 |
"eval_steps_per_second": 236.779,
|
62 |
"step": 39
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.0028527109668907234,
|
66 |
+
"grad_norm": 0.44697293639183044,
|
67 |
+
"learning_rate": 2.339555568810221e-05,
|
68 |
+
"loss": 6.8026,
|
69 |
+
"step": 40
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.003565888708613404,
|
73 |
+
"grad_norm": 0.324945330619812,
|
74 |
+
"learning_rate": 0.0,
|
75 |
+
"loss": 6.7972,
|
76 |
+
"step": 50
|
77 |
}
|
78 |
],
|
79 |
"logging_steps": 10,
|
|
|
88 |
"should_evaluate": false,
|
89 |
"should_log": false,
|
90 |
"should_save": true,
|
91 |
+
"should_training_stop": true
|
92 |
},
|
93 |
"attributes": {}
|
94 |
}
|
95 |
},
|
96 |
+
"total_flos": 76463161344.0,
|
97 |
"train_batch_size": 2,
|
98 |
"trial_name": null,
|
99 |
"trial_params": null
|