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 14696
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b43e582f9f23c2737fd9798b5f858afc782ffd7f7ac5f759e874caf0b8e714d6
|
3 |
size 14696
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 39398
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7800a3e988f37263567222d747e4f8f07b1e0d0dd8f8b0c291a16a368da8d682
|
3 |
size 39398
|
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 sha256:1ea8f278f29641100a56e280ef65934b0fccc8f8d9851be121c701ebed8ce795
|
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 sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
|
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,
|
@@ -36,6 +36,35 @@
|
|
36 |
"eval_samples_per_second": 18.967,
|
37 |
"eval_steps_per_second": 9.483,
|
38 |
"step": 3
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
39 |
}
|
40 |
],
|
41 |
"logging_steps": 1,
|
@@ -55,7 +84,7 @@
|
|
55 |
"attributes": {}
|
56 |
}
|
57 |
},
|
58 |
-
"total_flos":
|
59 |
"train_batch_size": 2,
|
60 |
"trial_name": null,
|
61 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.002711558016043385,
|
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,
|
|
|
36 |
"eval_samples_per_second": 18.967,
|
37 |
"eval_steps_per_second": 9.483,
|
38 |
"step": 3
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.0018077053440289234,
|
42 |
+
"grad_norm": 0.04630984365940094,
|
43 |
+
"learning_rate": 8e-05,
|
44 |
+
"loss": 11.9486,
|
45 |
+
"step": 4
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.002259631680036154,
|
49 |
+
"grad_norm": 0.04539979621767998,
|
50 |
+
"learning_rate": 0.0001,
|
51 |
+
"loss": 11.9474,
|
52 |
+
"step": 5
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 0.002711558016043385,
|
56 |
+
"grad_norm": 0.04202263057231903,
|
57 |
+
"learning_rate": 0.00012,
|
58 |
+
"loss": 11.9499,
|
59 |
+
"step": 6
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 0.002711558016043385,
|
63 |
+
"eval_loss": 11.947790145874023,
|
64 |
+
"eval_runtime": 49.1438,
|
65 |
+
"eval_samples_per_second": 18.965,
|
66 |
+
"eval_steps_per_second": 9.482,
|
67 |
+
"step": 6
|
68 |
}
|
69 |
],
|
70 |
"logging_steps": 1,
|
|
|
84 |
"attributes": {}
|
85 |
}
|
86 |
},
|
87 |
+
"total_flos": 1211154432.0,
|
88 |
"train_batch_size": 2,
|
89 |
"trial_name": null,
|
90 |
"trial_params": null
|