Training in progress, step 26, 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 sha256:2f0e1f3958db37933089f994826bc701c9a74bd6075f6af8944725c5956514e3
|
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:abe9f0fd7aedba5364a97ca0fc7ff23b691a4bc1b21b5caf1478ad37e1deb75a
|
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 sha256:72d2123828a202521fed49695ce20694823d9999d33262dd05d88a1ab8cbe183
|
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 sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
|
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": 10,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -37,6 +37,35 @@
|
|
37 |
"eval_samples_per_second": 8.312,
|
38 |
"eval_steps_per_second": 4.156,
|
39 |
"step": 10
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
40 |
}
|
41 |
],
|
42 |
"logging_steps": 5,
|
@@ -56,7 +85,7 @@
|
|
56 |
"attributes": {}
|
57 |
}
|
58 |
},
|
59 |
-
"total_flos":
|
60 |
"train_batch_size": 2,
|
61 |
"trial_name": null,
|
62 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.007347227128223242,
|
5 |
"eval_steps": 10,
|
6 |
+
"global_step": 26,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
37 |
"eval_samples_per_second": 8.312,
|
38 |
"eval_steps_per_second": 4.156,
|
39 |
"step": 10
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.0042387848816672555,
|
43 |
+
"grad_norm": 4.463286399841309,
|
44 |
+
"learning_rate": 9.619397662556435e-05,
|
45 |
+
"loss": 2.0209,
|
46 |
+
"step": 15
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 0.00565171317555634,
|
50 |
+
"grad_norm": 2.5350608825683594,
|
51 |
+
"learning_rate": 8.535533905932738e-05,
|
52 |
+
"loss": 1.6406,
|
53 |
+
"step": 20
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 0.00565171317555634,
|
57 |
+
"eval_loss": 0.3515169620513916,
|
58 |
+
"eval_runtime": 179.1491,
|
59 |
+
"eval_samples_per_second": 8.317,
|
60 |
+
"eval_steps_per_second": 4.159,
|
61 |
+
"step": 20
|
62 |
+
},
|
63 |
+
{
|
64 |
+
"epoch": 0.007064641469445425,
|
65 |
+
"grad_norm": 2.713797092437744,
|
66 |
+
"learning_rate": 6.91341716182545e-05,
|
67 |
+
"loss": 1.3488,
|
68 |
+
"step": 25
|
69 |
}
|
70 |
],
|
71 |
"logging_steps": 5,
|
|
|
85 |
"attributes": {}
|
86 |
}
|
87 |
},
|
88 |
+
"total_flos": 9113893355913216.0,
|
89 |
"train_batch_size": 2,
|
90 |
"trial_name": null,
|
91 |
"trial_params": null
|