Training in progress, step 9, 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 390888
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1975f40cad93d92e7fd273c62a8ceec373e11595ced78873b55003523a137545
|
| 3 |
size 390888
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 819770
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e1ecf959910793a88a62b8408a2d66213dd8f66c83da35e2caac7894d875ae90
|
| 3 |
size 819770
|
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 sha256:96a5a857ed41b50df491280680008400b63a0cea9bbaf95bf767f775a18248db
|
| 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 sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
|
| 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,
|
|
@@ -73,6 +73,35 @@
|
|
| 73 |
"eval_samples_per_second": 138.15,
|
| 74 |
"eval_steps_per_second": 69.075,
|
| 75 |
"step": 6
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 76 |
}
|
| 77 |
],
|
| 78 |
"logging_steps": 1,
|
|
@@ -92,7 +121,7 @@
|
|
| 92 |
"attributes": {}
|
| 93 |
}
|
| 94 |
},
|
| 95 |
-
"total_flos":
|
| 96 |
"train_batch_size": 2,
|
| 97 |
"trial_name": null,
|
| 98 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.000373142063475611,
|
| 5 |
"eval_steps": 3,
|
| 6 |
+
"global_step": 9,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 73 |
"eval_samples_per_second": 138.15,
|
| 74 |
"eval_steps_per_second": 69.075,
|
| 75 |
"step": 6
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.00029022160492547523,
|
| 79 |
+
"grad_norm": 6.252049922943115,
|
| 80 |
+
"learning_rate": 0.00014,
|
| 81 |
+
"loss": 11.5725,
|
| 82 |
+
"step": 7
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.0003316818342005431,
|
| 86 |
+
"grad_norm": 2.5031447410583496,
|
| 87 |
+
"learning_rate": 0.00016,
|
| 88 |
+
"loss": 10.1525,
|
| 89 |
+
"step": 8
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.000373142063475611,
|
| 93 |
+
"grad_norm": 7.207173824310303,
|
| 94 |
+
"learning_rate": 0.00018,
|
| 95 |
+
"loss": 12.1452,
|
| 96 |
+
"step": 9
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.000373142063475611,
|
| 100 |
+
"eval_loss": 11.331543922424316,
|
| 101 |
+
"eval_runtime": 73.6781,
|
| 102 |
+
"eval_samples_per_second": 137.843,
|
| 103 |
+
"eval_steps_per_second": 68.921,
|
| 104 |
+
"step": 9
|
| 105 |
}
|
| 106 |
],
|
| 107 |
"logging_steps": 1,
|
|
|
|
| 121 |
"attributes": {}
|
| 122 |
}
|
| 123 |
},
|
| 124 |
+
"total_flos": 983378165760.0,
|
| 125 |
"train_batch_size": 2,
|
| 126 |
"trial_name": null,
|
| 127 |
"trial_params": null
|