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 31064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb7ab842f6c3477fe1f7b083d858a13680c3e8eeb3ac547160c4c674dc87b116
|
3 |
size 31064
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 71718
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c45405f05041be518d3dfbb74663b4ae1cee3c50316b2302e6727aacf036e31
|
3 |
size 71718
|
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 sha256:4ce9ec22e0051f976ac081d26951edb3de92acba5c29f4c684fe32b805e5bc15
|
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": 223.898,
|
38 |
"eval_steps_per_second": 111.949,
|
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": 0.0056049582322824035,
|
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": 223.898,
|
38 |
"eval_steps_per_second": 111.949,
|
39 |
"step": 10
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.0032336297493936943,
|
43 |
+
"grad_norm": 1.069719672203064,
|
44 |
+
"learning_rate": 9.619397662556435e-05,
|
45 |
+
"loss": 41.5022,
|
46 |
+
"step": 15
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 0.004311506332524926,
|
50 |
+
"grad_norm": 0.9299646019935608,
|
51 |
+
"learning_rate": 8.535533905932738e-05,
|
52 |
+
"loss": 41.482,
|
53 |
+
"step": 20
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 0.004311506332524926,
|
57 |
+
"eval_loss": 10.374091148376465,
|
58 |
+
"eval_runtime": 8.7331,
|
59 |
+
"eval_samples_per_second": 223.746,
|
60 |
+
"eval_steps_per_second": 111.873,
|
61 |
+
"step": 20
|
62 |
+
},
|
63 |
+
{
|
64 |
+
"epoch": 0.0053893829156561575,
|
65 |
+
"grad_norm": 1.0937271118164062,
|
66 |
+
"learning_rate": 6.91341716182545e-05,
|
67 |
+
"loss": 41.4792,
|
68 |
+
"step": 25
|
69 |
}
|
70 |
],
|
71 |
"logging_steps": 5,
|
|
|
85 |
"attributes": {}
|
86 |
}
|
87 |
},
|
88 |
+
"total_flos": 667285192704.0,
|
89 |
"train_batch_size": 2,
|
90 |
"trial_name": null,
|
91 |
"trial_params": null
|