Training in progress, step 39, 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 144805440
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3948f3634ada5ae7c7de8e6d47d0044d8a54908518f3e3dd9df73fa28f350d02
|
3 |
size 144805440
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 74291604
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7531ac50970f6bbbef732ee602ab57612eb67433db95a9c924e4d8a5ff15e720
|
3 |
size 74291604
|
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:a65c7d81c66fb748eb12780de8de63775eeec185658fb414013d833d011ac1c9
|
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 sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
|
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,
|
@@ -66,6 +66,28 @@
|
|
66 |
"learning_rate": 6.91341716182545e-05,
|
67 |
"loss": 0.1652,
|
68 |
"step": 25
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
69 |
}
|
70 |
],
|
71 |
"logging_steps": 5,
|
@@ -85,7 +107,7 @@
|
|
85 |
"attributes": {}
|
86 |
}
|
87 |
},
|
88 |
-
"total_flos":
|
89 |
"train_batch_size": 2,
|
90 |
"trial_name": null,
|
91 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.017747440273037544,
|
5 |
"eval_steps": 10,
|
6 |
+
"global_step": 39,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
66 |
"learning_rate": 6.91341716182545e-05,
|
67 |
"loss": 0.1652,
|
68 |
"step": 25
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.013651877133105802,
|
72 |
+
"grad_norm": 0.0034711698535829782,
|
73 |
+
"learning_rate": 5e-05,
|
74 |
+
"loss": 0.1079,
|
75 |
+
"step": 30
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.013651877133105802,
|
79 |
+
"eval_loss": 0.16020071506500244,
|
80 |
+
"eval_runtime": 193.3016,
|
81 |
+
"eval_samples_per_second": 4.79,
|
82 |
+
"eval_steps_per_second": 2.395,
|
83 |
+
"step": 30
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 0.015927189988623434,
|
87 |
+
"grad_norm": 20.983272552490234,
|
88 |
+
"learning_rate": 3.086582838174551e-05,
|
89 |
+
"loss": 0.1722,
|
90 |
+
"step": 35
|
91 |
}
|
92 |
],
|
93 |
"logging_steps": 5,
|
|
|
107 |
"attributes": {}
|
108 |
}
|
109 |
},
|
110 |
+
"total_flos": 1.2631125277016064e+16,
|
111 |
"train_batch_size": 2,
|
112 |
"trial_name": null,
|
113 |
"trial_params": null
|