Commit
•
1d6a4b3
1
Parent(s):
4e70eea
Training in progress, step 500
Browse files- model.safetensors +1 -1
- trainer_state.json +62 -0
- training_args.bin +1 -1
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 267844872
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f69bb94f5679e22f8e88404f97a740e2ce37469d1d53c77b5f363f747f022b6a
|
| 3 |
size 267844872
|
trainer_state.json
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"learning_rate": 1e-05,
|
| 14 |
+
"loss": 0.8202,
|
| 15 |
+
"step": 250
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 1.0,
|
| 19 |
+
"eval_accuracy": 0.901,
|
| 20 |
+
"eval_f1": 0.9000590964742174,
|
| 21 |
+
"eval_loss": 0.3247230350971222,
|
| 22 |
+
"eval_runtime": 4.5139,
|
| 23 |
+
"eval_samples_per_second": 443.079,
|
| 24 |
+
"eval_steps_per_second": 7.089,
|
| 25 |
+
"step": 250
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 2.0,
|
| 29 |
+
"learning_rate": 0.0,
|
| 30 |
+
"loss": 0.2547,
|
| 31 |
+
"step": 500
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 2.0,
|
| 35 |
+
"eval_accuracy": 0.9205,
|
| 36 |
+
"eval_f1": 0.9204480932224948,
|
| 37 |
+
"eval_loss": 0.21922191977500916,
|
| 38 |
+
"eval_runtime": 4.5051,
|
| 39 |
+
"eval_samples_per_second": 443.938,
|
| 40 |
+
"eval_steps_per_second": 7.103,
|
| 41 |
+
"step": 500
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 2.0,
|
| 45 |
+
"step": 500,
|
| 46 |
+
"total_flos": 720342861696000.0,
|
| 47 |
+
"train_loss": 0.5374606018066406,
|
| 48 |
+
"train_runtime": 260.6287,
|
| 49 |
+
"train_samples_per_second": 122.78,
|
| 50 |
+
"train_steps_per_second": 1.918
|
| 51 |
+
}
|
| 52 |
+
],
|
| 53 |
+
"logging_steps": 250,
|
| 54 |
+
"max_steps": 500,
|
| 55 |
+
"num_input_tokens_seen": 0,
|
| 56 |
+
"num_train_epochs": 2,
|
| 57 |
+
"save_steps": 500,
|
| 58 |
+
"total_flos": 720342861696000.0,
|
| 59 |
+
"train_batch_size": 64,
|
| 60 |
+
"trial_name": null,
|
| 61 |
+
"trial_params": null
|
| 62 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4728
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:98ab995a6f6b3efbd34a24c2da3e03ebd6d386366b4c58a3f9f5eac9ece73f5a
|
| 3 |
size 4728
|