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 80792096
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0215574c323dd4c46e90221bdae7f4a5af6d5f5f1206c0e387873fa8815e6e0b
|
3 |
size 80792096
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 41459700
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2553a700e270441c866c7000da2d1fe173c39c0f33d946dd4e01c96629a6404e
|
3 |
size 41459700
|
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 sha256:99a3cc9eb641440785b6ac309d15d1e46933f13498b469d3d8b963ccec1fb91a
|
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": 11.575,
|
37 |
"eval_steps_per_second": 5.788,
|
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": 0.013296398891966758,
|
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": 11.575,
|
37 |
"eval_steps_per_second": 5.788,
|
38 |
"step": 3
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.00886426592797784,
|
42 |
+
"grad_norm": 0.21325641870498657,
|
43 |
+
"learning_rate": 8e-05,
|
44 |
+
"loss": 0.3279,
|
45 |
+
"step": 4
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.0110803324099723,
|
49 |
+
"grad_norm": 0.19823859632015228,
|
50 |
+
"learning_rate": 0.0001,
|
51 |
+
"loss": 0.3385,
|
52 |
+
"step": 5
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 0.013296398891966758,
|
56 |
+
"grad_norm": 0.22237731516361237,
|
57 |
+
"learning_rate": 0.00012,
|
58 |
+
"loss": 0.3052,
|
59 |
+
"step": 6
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 0.013296398891966758,
|
63 |
+
"eval_loss": 0.3171418011188507,
|
64 |
+
"eval_runtime": 16.4816,
|
65 |
+
"eval_samples_per_second": 11.528,
|
66 |
+
"eval_steps_per_second": 5.764,
|
67 |
+
"step": 6
|
68 |
}
|
69 |
],
|
70 |
"logging_steps": 1,
|
|
|
84 |
"attributes": {}
|
85 |
}
|
86 |
},
|
87 |
+
"total_flos": 1263411133415424.0,
|
88 |
"train_batch_size": 2,
|
89 |
"trial_name": null,
|
90 |
"trial_params": null
|