Training in progress, step 6, 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 32856
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11cbaa6891adbefcac2a863b6f4fa68dc987590aafb68e6915653cf771b7d768
|
3 |
size 32856
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 71358
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b2cd3668392f24ea19ca236ce34ccfba1961858e67be9dd5bf6b1d4f0b73860
|
3 |
size 71358
|
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 sha256:0e27e5357ca903ece90a54f2e15a2927fa7093b1185443a4ae0fa25d47cf0c74
|
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 sha256:92b4cf85d7ba7a497f88ff799bf4dec5af7dd95be6e00f78bf46ba5deb56bbf8
|
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": 3,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -44,6 +44,35 @@
|
|
44 |
"eval_samples_per_second": 667.67,
|
45 |
"eval_steps_per_second": 334.285,
|
46 |
"step": 3
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
47 |
}
|
48 |
],
|
49 |
"logging_steps": 1,
|
@@ -63,7 +92,7 @@
|
|
63 |
"attributes": {}
|
64 |
}
|
65 |
},
|
66 |
-
"total_flos":
|
67 |
"train_batch_size": 2,
|
68 |
"trial_name": null,
|
69 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.013642177064089812,
|
5 |
"eval_steps": 3,
|
6 |
+
"global_step": 6,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
44 |
"eval_samples_per_second": 667.67,
|
45 |
"eval_steps_per_second": 334.285,
|
46 |
"step": 3
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 0.009094784709393207,
|
50 |
+
"grad_norm": 3.7502498626708984,
|
51 |
+
"learning_rate": 4e-05,
|
52 |
+
"loss": 177.5,
|
53 |
+
"step": 4
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 0.011368480886741509,
|
57 |
+
"grad_norm": 3.175806760787964,
|
58 |
+
"learning_rate": 5e-05,
|
59 |
+
"loss": 177.5,
|
60 |
+
"step": 5
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 0.013642177064089812,
|
64 |
+
"grad_norm": 4.255999565124512,
|
65 |
+
"learning_rate": 6e-05,
|
66 |
+
"loss": 177.4375,
|
67 |
+
"step": 6
|
68 |
+
},
|
69 |
+
{
|
70 |
+
"epoch": 0.013642177064089812,
|
71 |
+
"eval_loss": 11.09615421295166,
|
72 |
+
"eval_runtime": 1.1614,
|
73 |
+
"eval_samples_per_second": 638.03,
|
74 |
+
"eval_steps_per_second": 319.446,
|
75 |
+
"step": 6
|
76 |
}
|
77 |
],
|
78 |
"logging_steps": 1,
|
|
|
92 |
"attributes": {}
|
93 |
}
|
94 |
},
|
95 |
+
"total_flos": 22226534400.0,
|
96 |
"train_batch_size": 2,
|
97 |
"trial_name": null,
|
98 |
"trial_params": null
|