Training in progress, step 10, 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 191968
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55030b20caca048637fe1ea811707789c40bc170d01c0a47b083e79446548fc6
|
3 |
size 191968
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 253144
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f6a3a45e24257d9848f134bd87b44baf6549dd9f11306859f571086ac246d2a
|
3 |
size 253144
|
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 sha256:47ba7527fe6396c48f048eec5dbebbe83dd44cb9f375a7b9085d2380d5ce3551
|
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:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
|
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": 5,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -30,6 +30,28 @@
|
|
30 |
"eval_samples_per_second": 462.089,
|
31 |
"eval_steps_per_second": 57.761,
|
32 |
"step": 5
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
33 |
}
|
34 |
],
|
35 |
"logging_steps": 3,
|
@@ -49,7 +71,7 @@
|
|
49 |
"attributes": {}
|
50 |
}
|
51 |
},
|
52 |
-
"total_flos":
|
53 |
"train_batch_size": 8,
|
54 |
"trial_name": null,
|
55 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.00701877522372346,
|
5 |
"eval_steps": 5,
|
6 |
+
"global_step": 10,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
30 |
"eval_samples_per_second": 462.089,
|
31 |
"eval_steps_per_second": 57.761,
|
32 |
"step": 5
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.004211265134234076,
|
36 |
+
"grad_norm": 0.06716205924749374,
|
37 |
+
"learning_rate": 6e-05,
|
38 |
+
"loss": 10.3798,
|
39 |
+
"step": 6
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.0063168977013511145,
|
43 |
+
"grad_norm": 0.07351335883140564,
|
44 |
+
"learning_rate": 9e-05,
|
45 |
+
"loss": 10.3792,
|
46 |
+
"step": 9
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 0.00701877522372346,
|
50 |
+
"eval_loss": 10.376435279846191,
|
51 |
+
"eval_runtime": 5.235,
|
52 |
+
"eval_samples_per_second": 458.451,
|
53 |
+
"eval_steps_per_second": 57.306,
|
54 |
+
"step": 10
|
55 |
}
|
56 |
],
|
57 |
"logging_steps": 3,
|
|
|
71 |
"attributes": {}
|
72 |
}
|
73 |
},
|
74 |
+
"total_flos": 1143394271232.0,
|
75 |
"train_batch_size": 8,
|
76 |
"trial_name": null,
|
77 |
"trial_params": null
|