Training in progress, step 3000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 267906392
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:70771d2de6f5c7a445bf8247e2d576286a6f0ed3fc576a84efba3f683e952222
|
| 3 |
size 267906392
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 535874874
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7b24e8e2cadbf54da14d8826622671a279a619acacd74fa7a48f721ee8a8264
|
| 3 |
size 535874874
|
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 sha256:9d0e9aaa6fae5c8b3174f7039cfad80162f1cc8c8a847cf1640147ed61808f02
|
| 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 sha256:4b53eef6d921823ac2e7b9efcce2240967ca8ee91e331823d0035c7199224530
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.4119344651699066,
|
| 3 |
"best_model_checkpoint": "/kaggle/working/results/checkpoint-1000",
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 1000,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -51,6 +51,28 @@
|
|
| 51 |
"eval_samples_per_second": 107.142,
|
| 52 |
"eval_steps_per_second": 0.84,
|
| 53 |
"step": 2000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 54 |
}
|
| 55 |
],
|
| 56 |
"logging_steps": 500,
|
|
@@ -70,7 +92,7 @@
|
|
| 70 |
"attributes": {}
|
| 71 |
}
|
| 72 |
},
|
| 73 |
-
"total_flos":
|
| 74 |
"train_batch_size": 32,
|
| 75 |
"trial_name": null,
|
| 76 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.4119344651699066,
|
| 3 |
"best_model_checkpoint": "/kaggle/working/results/checkpoint-1000",
|
| 4 |
+
"epoch": 0.144355692426138,
|
| 5 |
"eval_steps": 1000,
|
| 6 |
+
"global_step": 3000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 51 |
"eval_samples_per_second": 107.142,
|
| 52 |
"eval_steps_per_second": 0.84,
|
| 53 |
"step": 2000
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.120296410355115,
|
| 57 |
+
"grad_norm": 2.133201837539673,
|
| 58 |
+
"learning_rate": 1.92474256568184e-05,
|
| 59 |
+
"loss": 0.3946,
|
| 60 |
+
"step": 2500
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.144355692426138,
|
| 64 |
+
"grad_norm": 3.307325839996338,
|
| 65 |
+
"learning_rate": 2.309691078818208e-05,
|
| 66 |
+
"loss": 0.3855,
|
| 67 |
+
"step": 3000
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 0.144355692426138,
|
| 71 |
+
"eval_loss": 0.4270198941230774,
|
| 72 |
+
"eval_runtime": 244.1676,
|
| 73 |
+
"eval_samples_per_second": 107.103,
|
| 74 |
+
"eval_steps_per_second": 0.84,
|
| 75 |
+
"step": 3000
|
| 76 |
}
|
| 77 |
],
|
| 78 |
"logging_steps": 500,
|
|
|
|
| 92 |
"attributes": {}
|
| 93 |
}
|
| 94 |
},
|
| 95 |
+
"total_flos": 1.2722313166848e+16,
|
| 96 |
"train_batch_size": 32,
|
| 97 |
"trial_name": null,
|
| 98 |
"trial_params": null
|