Training in progress, step 15, 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 159967880
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:252b097295c8cb658a95186584c8c191bbf681e89c901ff7fe67c5936bb25b00
|
3 |
size 159967880
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 81730196
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f6ab08126725be321b919615ac92cfbe2e14395147018761831431bcaf5a7ee0
|
3 |
size 81730196
|
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:ab22ddf51bfbb0e52394ea82ce6def3703300cb6b77357d2a920d3ed8bca3047
|
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 sha256:964730355c317bebf1d8ccbe8c0becdecfcea59207dec1596c5fd980e1b6084d
|
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,
|
@@ -52,6 +52,28 @@
|
|
52 |
"eval_samples_per_second": 11.029,
|
53 |
"eval_steps_per_second": 1.387,
|
54 |
"step": 10
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
55 |
}
|
56 |
],
|
57 |
"logging_steps": 3,
|
@@ -71,7 +93,7 @@
|
|
71 |
"attributes": {}
|
72 |
}
|
73 |
},
|
74 |
-
"total_flos": 1.
|
75 |
"train_batch_size": 8,
|
76 |
"trial_name": null,
|
77 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.02206693637366679,
|
5 |
"eval_steps": 5,
|
6 |
+
"global_step": 15,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
52 |
"eval_samples_per_second": 11.029,
|
53 |
"eval_steps_per_second": 1.387,
|
54 |
"step": 10
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.017653549098933432,
|
58 |
+
"grad_norm": 1.658168077468872,
|
59 |
+
"learning_rate": 4.9692208514878444e-05,
|
60 |
+
"loss": 9.3972,
|
61 |
+
"step": 12
|
62 |
+
},
|
63 |
+
{
|
64 |
+
"epoch": 0.02206693637366679,
|
65 |
+
"grad_norm": 1.7478517293930054,
|
66 |
+
"learning_rate": 4.8096988312782174e-05,
|
67 |
+
"loss": 9.1795,
|
68 |
+
"step": 15
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.02206693637366679,
|
72 |
+
"eval_loss": 2.2163238525390625,
|
73 |
+
"eval_runtime": 103.8055,
|
74 |
+
"eval_samples_per_second": 11.03,
|
75 |
+
"eval_steps_per_second": 1.387,
|
76 |
+
"step": 15
|
77 |
}
|
78 |
],
|
79 |
"logging_steps": 3,
|
|
|
93 |
"attributes": {}
|
94 |
}
|
95 |
},
|
96 |
+
"total_flos": 1.960393933062144e+16,
|
97 |
"train_batch_size": 8,
|
98 |
"trial_name": null,
|
99 |
"trial_params": null
|