Training in progress, epoch 2, 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 737722356
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ea30daae0592b02221da8fb0c6105104119bec2ae2f145b638286ab7785221d
|
| 3 |
size 737722356
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1475564538
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e53fcdea3800a6c4a037004d3347e8b161fa4ef9d5f28ed17feb0c597af576a2
|
| 3 |
size 1475564538
|
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:fa6c484363b704d2d27d1973f02acb48e688696ed37a1566e3b2b3bc7a5ca0d8
|
| 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 sha256:70284bfdb1d09271a898e9d38e6b9b443ed793a4577ae065a8449c0b8b45a5c7
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "debertalarge-medical-classifier/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -23,6 +23,29 @@
|
|
| 23 |
"eval_samples_per_second": 7.065,
|
| 24 |
"eval_steps_per_second": 3.533,
|
| 25 |
"step": 183
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
}
|
| 27 |
],
|
| 28 |
"logging_steps": 100,
|
|
@@ -42,7 +65,7 @@
|
|
| 42 |
"attributes": {}
|
| 43 |
}
|
| 44 |
},
|
| 45 |
-
"total_flos":
|
| 46 |
"train_batch_size": 2,
|
| 47 |
"trial_name": null,
|
| 48 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.2747629944426283,
|
| 3 |
+
"best_model_checkpoint": "debertalarge-medical-classifier/checkpoint-366",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 366,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 23 |
"eval_samples_per_second": 7.065,
|
| 24 |
"eval_steps_per_second": 3.533,
|
| 25 |
"step": 183
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 1.092896174863388,
|
| 29 |
+
"grad_norm": 3.7559633255004883,
|
| 30 |
+
"learning_rate": 4.7814207650273224e-05,
|
| 31 |
+
"loss": 1.0895,
|
| 32 |
+
"step": 200
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 1.639344262295082,
|
| 36 |
+
"grad_norm": 10.271145820617676,
|
| 37 |
+
"learning_rate": 4.672131147540984e-05,
|
| 38 |
+
"loss": 1.1036,
|
| 39 |
+
"step": 300
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 2.0,
|
| 43 |
+
"eval_f1": 0.2747629944426283,
|
| 44 |
+
"eval_loss": 1.123813271522522,
|
| 45 |
+
"eval_runtime": 13.0611,
|
| 46 |
+
"eval_samples_per_second": 7.044,
|
| 47 |
+
"eval_steps_per_second": 3.522,
|
| 48 |
+
"step": 366
|
| 49 |
}
|
| 50 |
],
|
| 51 |
"logging_steps": 100,
|
|
|
|
| 65 |
"attributes": {}
|
| 66 |
}
|
| 67 |
},
|
| 68 |
+
"total_flos": 975387153780000.0,
|
| 69 |
"train_batch_size": 2,
|
| 70 |
"trial_name": null,
|
| 71 |
"trial_params": null
|