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 59933632
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:430de1ae2da4dd6a3b2d79c63a2ececa37abfd84ff8e20f02cdc486e4c3cb7d5
|
3 |
size 59933632
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 31822948
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:143579abe6990b4550bf6e6cf9ed9c0af463372861d4379fcd9e06223fa5707e
|
3 |
size 31822948
|
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:fe300d7c5ab10b566794c92461448fbc4b1030e2c8290ab8f4cd627fc33f0bc0
|
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,
|
@@ -44,6 +44,35 @@
|
|
44 |
"eval_samples_per_second": 29.217,
|
45 |
"eval_steps_per_second": 14.609,
|
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": 0.001014584654407102,
|
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": 29.217,
|
45 |
"eval_steps_per_second": 14.609,
|
46 |
"step": 3
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 0.0006763897696047348,
|
50 |
+
"grad_norm": 8.289449691772461,
|
51 |
+
"learning_rate": 8e-05,
|
52 |
+
"loss": 6.312,
|
53 |
+
"step": 4
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 0.0008454872120059184,
|
57 |
+
"grad_norm": 8.284539222717285,
|
58 |
+
"learning_rate": 0.0001,
|
59 |
+
"loss": 6.4338,
|
60 |
+
"step": 5
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 0.001014584654407102,
|
64 |
+
"grad_norm": 7.369958877563477,
|
65 |
+
"learning_rate": 0.00012,
|
66 |
+
"loss": 5.6306,
|
67 |
+
"step": 6
|
68 |
+
},
|
69 |
+
{
|
70 |
+
"epoch": 0.001014584654407102,
|
71 |
+
"eval_loss": 5.395904541015625,
|
72 |
+
"eval_runtime": 85.4588,
|
73 |
+
"eval_samples_per_second": 29.137,
|
74 |
+
"eval_steps_per_second": 14.568,
|
75 |
+
"step": 6
|
76 |
}
|
77 |
],
|
78 |
"logging_steps": 1,
|
|
|
92 |
"attributes": {}
|
93 |
}
|
94 |
},
|
95 |
+
"total_flos": 719886967898112.0,
|
96 |
"train_batch_size": 2,
|
97 |
"trial_name": null,
|
98 |
"trial_params": null
|