Training in progress, step 28, 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 80013120
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6176fcd9ff5767ba145007fefdcbf7fab75e7150d5ab5328d586d3a1d1ca08c4
|
3 |
size 80013120
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 41119636
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:563f5a53921b6394c99152b4858a22a6cfc8d034348c5e37bb0c890a48b9c70f
|
3 |
size 41119636
|
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 sha256:65f15464d6b0aa5ccf50fef2eb140dcf3fae680aa29c7705ea6dfce2709e29b1
|
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 sha256:7cf140526b08395dbd0793ca343f0f70c5fb866a714c27208d9b9b1ce1a60172
|
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": 14,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -30,6 +30,21 @@
|
|
30 |
"eval_samples_per_second": 30.493,
|
31 |
"eval_steps_per_second": 15.268,
|
32 |
"step": 14
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
33 |
}
|
34 |
],
|
35 |
"logging_steps": 10,
|
@@ -49,7 +64,7 @@
|
|
49 |
"attributes": {}
|
50 |
}
|
51 |
},
|
52 |
-
"total_flos":
|
53 |
"train_batch_size": 2,
|
54 |
"trial_name": null,
|
55 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.016816816816816817,
|
5 |
"eval_steps": 14,
|
6 |
+
"global_step": 28,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
30 |
"eval_samples_per_second": 30.493,
|
31 |
"eval_steps_per_second": 15.268,
|
32 |
"step": 14
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.012012012012012012,
|
36 |
+
"grad_norm": 2.6258339881896973,
|
37 |
+
"learning_rate": 0.00015877852522924732,
|
38 |
+
"loss": 1.3072,
|
39 |
+
"step": 20
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.016816816816816817,
|
43 |
+
"eval_loss": 0.19282115995883942,
|
44 |
+
"eval_runtime": 23.0157,
|
45 |
+
"eval_samples_per_second": 30.457,
|
46 |
+
"eval_steps_per_second": 15.25,
|
47 |
+
"step": 28
|
48 |
}
|
49 |
],
|
50 |
"logging_steps": 10,
|
|
|
64 |
"attributes": {}
|
65 |
}
|
66 |
},
|
67 |
+
"total_flos": 4560497877712896.0,
|
68 |
"train_batch_size": 2,
|
69 |
"trial_name": null,
|
70 |
"trial_params": null
|