Training in progress, step 6, 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 645975704
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:83033c3dc69ddf3ae05b834d6ccd7662f05741cadf9fe06f522ab5f6791e052c
|
3 |
size 645975704
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 328468404
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:236a6deae7f0eae59c12a6dd66130f9fe1f39a080f76722305c89b3a193b3fc8
|
3 |
size 328468404
|
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:c893fc6997d849f1c551536052821911ccb72e85a0b7fc5adab0bfa68cf904af
|
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 sha256:92b4cf85d7ba7a497f88ff799bf4dec5af7dd95be6e00f78bf46ba5deb56bbf8
|
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": 3.
|
5 |
"eval_steps": 1,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -54,6 +54,21 @@
|
|
54 |
"eval_samples_per_second": 13.442,
|
55 |
"eval_steps_per_second": 4.481,
|
56 |
"step": 5
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
57 |
}
|
58 |
],
|
59 |
"logging_steps": 3,
|
@@ -68,12 +83,12 @@
|
|
68 |
"should_evaluate": false,
|
69 |
"should_log": false,
|
70 |
"should_save": true,
|
71 |
-
"should_training_stop":
|
72 |
},
|
73 |
"attributes": {}
|
74 |
}
|
75 |
},
|
76 |
-
"total_flos":
|
77 |
"train_batch_size": 8,
|
78 |
"trial_name": null,
|
79 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.857142857142857,
|
5 |
"eval_steps": 1,
|
6 |
+
"global_step": 6,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
54 |
"eval_samples_per_second": 13.442,
|
55 |
"eval_steps_per_second": 4.481,
|
56 |
"step": 5
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 3.857142857142857,
|
60 |
+
"grad_norm": 0.0,
|
61 |
+
"learning_rate": 6e-05,
|
62 |
+
"loss": 0.0,
|
63 |
+
"step": 6
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 3.857142857142857,
|
67 |
+
"eval_loss": NaN,
|
68 |
+
"eval_runtime": 0.2247,
|
69 |
+
"eval_samples_per_second": 13.351,
|
70 |
+
"eval_steps_per_second": 4.45,
|
71 |
+
"step": 6
|
72 |
}
|
73 |
],
|
74 |
"logging_steps": 3,
|
|
|
83 |
"should_evaluate": false,
|
84 |
"should_log": false,
|
85 |
"should_save": true,
|
86 |
+
"should_training_stop": true
|
87 |
},
|
88 |
"attributes": {}
|
89 |
}
|
90 |
},
|
91 |
+
"total_flos": 8531332112056320.0,
|
92 |
"train_batch_size": 8,
|
93 |
"trial_name": null,
|
94 |
"trial_params": null
|