Training in progress, step 39, 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 83945296
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:59b580750888ea7d8abce7a14d4f56dbd00f7db466644347e0d4b6e0599a474d
|
3 |
size 83945296
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 43122580
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a138952f84f9a99f08b97d104ff0a77c31e83057ec5e554c490cbc21ac96237
|
3 |
size 43122580
|
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:a0472ce311e84cd5509f168867d58579c252d4413aee368c17e4cfad44ac2bb7
|
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 sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
|
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,
|
@@ -45,6 +45,21 @@
|
|
45 |
"eval_samples_per_second": 26.624,
|
46 |
"eval_steps_per_second": 13.312,
|
47 |
"step": 26
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
48 |
}
|
49 |
],
|
50 |
"logging_steps": 10,
|
@@ -64,7 +79,7 @@
|
|
64 |
"attributes": {}
|
65 |
}
|
66 |
},
|
67 |
-
"total_flos":
|
68 |
"train_batch_size": 2,
|
69 |
"trial_name": null,
|
70 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.11935730680948738,
|
5 |
"eval_steps": 13,
|
6 |
+
"global_step": 39,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
45 |
"eval_samples_per_second": 26.624,
|
46 |
"eval_steps_per_second": 13.312,
|
47 |
"step": 26
|
48 |
+
},
|
49 |
+
{
|
50 |
+
"epoch": 0.09181331293037491,
|
51 |
+
"grad_norm": 0.5139346122741699,
|
52 |
+
"learning_rate": 5e-05,
|
53 |
+
"loss": 0.4389,
|
54 |
+
"step": 30
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.11935730680948738,
|
58 |
+
"eval_loss": 0.43966734409332275,
|
59 |
+
"eval_runtime": 5.1801,
|
60 |
+
"eval_samples_per_second": 26.64,
|
61 |
+
"eval_steps_per_second": 13.32,
|
62 |
+
"step": 39
|
63 |
}
|
64 |
],
|
65 |
"logging_steps": 10,
|
|
|
79 |
"attributes": {}
|
80 |
}
|
81 |
},
|
82 |
+
"total_flos": 8970386603507712.0,
|
83 |
"train_batch_size": 2,
|
84 |
"trial_name": null,
|
85 |
"trial_params": null
|