Commit
•
dad6435
1
Parent(s):
7785de4
End of training
Browse files- checkpoint-25/trainer_state.json +0 -48
- {checkpoint-25 → checkpoint-350}/added_tokens.json +0 -0
- {checkpoint-25 → checkpoint-350}/config.json +0 -0
- {checkpoint-25 → checkpoint-350}/optimizer.pt +2 -2
- {checkpoint-25 → checkpoint-350}/pytorch_model.bin +1 -1
- {checkpoint-25 → checkpoint-350}/rng_state.pth +1 -1
- {checkpoint-25 → checkpoint-350}/scheduler.pt +1 -1
- {checkpoint-25 → checkpoint-350}/special_tokens_map.json +0 -0
- {checkpoint-25 → checkpoint-350}/spm.model +0 -0
- {checkpoint-25 → checkpoint-350}/tokenizer.json +0 -0
- {checkpoint-25 → checkpoint-350}/tokenizer_config.json +0 -0
- checkpoint-350/trainer_state.json +490 -0
- {checkpoint-25 → checkpoint-350}/training_args.bin +0 -0
- checkpoint-375/added_tokens.json +3 -0
- checkpoint-375/config.json +59 -0
- checkpoint-375/optimizer.pt +3 -0
- checkpoint-375/pytorch_model.bin +3 -0
- checkpoint-375/rng_state.pth +3 -0
- checkpoint-375/scheduler.pt +3 -0
- checkpoint-375/special_tokens_map.json +9 -0
- checkpoint-375/spm.model +3 -0
- checkpoint-375/tokenizer.json +0 -0
- checkpoint-375/tokenizer_config.json +16 -0
- checkpoint-375/trainer_state.json +516 -0
- checkpoint-375/training_args.bin +3 -0
- pytorch_model.bin +1 -1
- runs/Jul22_09-22-43_549e78cb1c68/events.out.tfevents.1690017769.549e78cb1c68.4107.2 +2 -2
- runs/Jul22_09-22-43_549e78cb1c68/events.out.tfevents.1690017926.549e78cb1c68.4107.3 +3 -0
checkpoint-25/trainer_state.json
DELETED
|
@@ -1,48 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_metric": null,
|
| 3 |
-
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 1.0,
|
| 5 |
-
"global_step": 25,
|
| 6 |
-
"is_hyper_param_search": false,
|
| 7 |
-
"is_local_process_zero": true,
|
| 8 |
-
"is_world_process_zero": true,
|
| 9 |
-
"log_history": [
|
| 10 |
-
{
|
| 11 |
-
"epoch": 0.04,
|
| 12 |
-
"learning_rate": 1.9946666666666667e-05,
|
| 13 |
-
"loss": 2.3122,
|
| 14 |
-
"step": 1
|
| 15 |
-
},
|
| 16 |
-
{
|
| 17 |
-
"epoch": 0.76,
|
| 18 |
-
"learning_rate": 1.898666666666667e-05,
|
| 19 |
-
"loss": 2.3022,
|
| 20 |
-
"step": 19
|
| 21 |
-
},
|
| 22 |
-
{
|
| 23 |
-
"epoch": 0.76,
|
| 24 |
-
"eval_accuracy": 0.1,
|
| 25 |
-
"eval_disk_space_total": 78.1898422241211,
|
| 26 |
-
"eval_disk_space_used": 33.75697326660156,
|
| 27 |
-
"eval_f1": 0.018181818181818184,
|
| 28 |
-
"eval_gpu_ram_allocated": 4.172749996185303,
|
| 29 |
-
"eval_gpu_ram_cached": 26.759765625,
|
| 30 |
-
"eval_gpu_ram_total": 39.56402587890625,
|
| 31 |
-
"eval_gpu_utilization": 45,
|
| 32 |
-
"eval_loss": 2.3011605739593506,
|
| 33 |
-
"eval_precision": 0.01,
|
| 34 |
-
"eval_recall": 0.1,
|
| 35 |
-
"eval_runtime": 0.3917,
|
| 36 |
-
"eval_samples_per_second": 510.562,
|
| 37 |
-
"eval_steps_per_second": 17.87,
|
| 38 |
-
"eval_system_ram_total": 83.48074722290039,
|
| 39 |
-
"eval_system_ram_used": 4.445606231689453,
|
| 40 |
-
"step": 19
|
| 41 |
-
}
|
| 42 |
-
],
|
| 43 |
-
"max_steps": 375,
|
| 44 |
-
"num_train_epochs": 15,
|
| 45 |
-
"total_flos": 54485323206528.0,
|
| 46 |
-
"trial_name": null,
|
| 47 |
-
"trial_params": null
|
| 48 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
{checkpoint-25 → checkpoint-350}/added_tokens.json
RENAMED
|
File without changes
|
{checkpoint-25 → checkpoint-350}/config.json
RENAMED
|
File without changes
|
{checkpoint-25 → checkpoint-350}/optimizer.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ab43cd5a44b21b5a22eef77417e02f84ff4e98fc1b7eabeba4e3e8e7e45f0ff
|
| 3 |
+
size 1475557125
|
{checkpoint-25 → checkpoint-350}/pytorch_model.bin
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 737788917
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:328c4be909b1eef5cc41b750f680802efe8089d37bd9dcf8733d88094f13ce64
|
| 3 |
size 737788917
|
{checkpoint-25 → checkpoint-350}/rng_state.pth
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14575
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c9aced460dfb01f09e32fb5f5dbf1fad9b487697a848ea1f448da69957c04042
|
| 3 |
size 14575
|
{checkpoint-25 → checkpoint-350}/scheduler.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dbb89204c9563d41cdc3199eb481d6f6f625cb563a54343cca262d582298e755
|
| 3 |
size 627
|
{checkpoint-25 → checkpoint-350}/special_tokens_map.json
RENAMED
|
File without changes
|
{checkpoint-25 → checkpoint-350}/spm.model
RENAMED
|
File without changes
|
{checkpoint-25 → checkpoint-350}/tokenizer.json
RENAMED
|
File without changes
|
{checkpoint-25 → checkpoint-350}/tokenizer_config.json
RENAMED
|
File without changes
|
checkpoint-350/trainer_state.json
ADDED
|
@@ -0,0 +1,490 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 14.0,
|
| 5 |
+
"global_step": 350,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.04,
|
| 12 |
+
"learning_rate": 1.9946666666666667e-05,
|
| 13 |
+
"loss": 2.3122,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.76,
|
| 18 |
+
"learning_rate": 1.898666666666667e-05,
|
| 19 |
+
"loss": 2.3022,
|
| 20 |
+
"step": 19
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.76,
|
| 24 |
+
"eval_accuracy": 0.1,
|
| 25 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 26 |
+
"eval_disk_space_used": 33.75697326660156,
|
| 27 |
+
"eval_f1": 0.018181818181818184,
|
| 28 |
+
"eval_gpu_ram_allocated": 4.172749996185303,
|
| 29 |
+
"eval_gpu_ram_cached": 26.759765625,
|
| 30 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 31 |
+
"eval_gpu_utilization": 45,
|
| 32 |
+
"eval_loss": 2.3011605739593506,
|
| 33 |
+
"eval_precision": 0.01,
|
| 34 |
+
"eval_recall": 0.1,
|
| 35 |
+
"eval_runtime": 0.3917,
|
| 36 |
+
"eval_samples_per_second": 510.562,
|
| 37 |
+
"eval_steps_per_second": 17.87,
|
| 38 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 39 |
+
"eval_system_ram_used": 4.445606231689453,
|
| 40 |
+
"step": 19
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 1.52,
|
| 44 |
+
"learning_rate": 1.7973333333333333e-05,
|
| 45 |
+
"loss": 2.2979,
|
| 46 |
+
"step": 38
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 1.52,
|
| 50 |
+
"eval_accuracy": 0.155,
|
| 51 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 52 |
+
"eval_disk_space_used": 38.592166900634766,
|
| 53 |
+
"eval_f1": 0.06350931677018633,
|
| 54 |
+
"eval_gpu_ram_allocated": 4.172748565673828,
|
| 55 |
+
"eval_gpu_ram_cached": 26.771484375,
|
| 56 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 57 |
+
"eval_gpu_utilization": 43,
|
| 58 |
+
"eval_loss": 2.2853753566741943,
|
| 59 |
+
"eval_precision": 0.04491869918699187,
|
| 60 |
+
"eval_recall": 0.155,
|
| 61 |
+
"eval_runtime": 0.3679,
|
| 62 |
+
"eval_samples_per_second": 543.585,
|
| 63 |
+
"eval_steps_per_second": 19.025,
|
| 64 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 65 |
+
"eval_system_ram_used": 5.034675598144531,
|
| 66 |
+
"step": 38
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 2.28,
|
| 70 |
+
"learning_rate": 1.696e-05,
|
| 71 |
+
"loss": 2.2316,
|
| 72 |
+
"step": 57
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 2.28,
|
| 76 |
+
"eval_accuracy": 0.305,
|
| 77 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 78 |
+
"eval_disk_space_used": 40.66392517089844,
|
| 79 |
+
"eval_f1": 0.2284533029124758,
|
| 80 |
+
"eval_gpu_ram_allocated": 4.172748565673828,
|
| 81 |
+
"eval_gpu_ram_cached": 26.771484375,
|
| 82 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 83 |
+
"eval_gpu_utilization": 44,
|
| 84 |
+
"eval_loss": 2.1098108291625977,
|
| 85 |
+
"eval_precision": 0.2806426799007444,
|
| 86 |
+
"eval_recall": 0.305,
|
| 87 |
+
"eval_runtime": 0.3885,
|
| 88 |
+
"eval_samples_per_second": 514.84,
|
| 89 |
+
"eval_steps_per_second": 18.019,
|
| 90 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 91 |
+
"eval_system_ram_used": 5.178070068359375,
|
| 92 |
+
"step": 57
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 3.04,
|
| 96 |
+
"learning_rate": 1.5946666666666668e-05,
|
| 97 |
+
"loss": 1.9915,
|
| 98 |
+
"step": 76
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 3.04,
|
| 102 |
+
"eval_accuracy": 0.43,
|
| 103 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 104 |
+
"eval_disk_space_used": 40.663944244384766,
|
| 105 |
+
"eval_f1": 0.4147692106558386,
|
| 106 |
+
"eval_gpu_ram_allocated": 4.172744274139404,
|
| 107 |
+
"eval_gpu_ram_cached": 26.771484375,
|
| 108 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 109 |
+
"eval_gpu_utilization": 50,
|
| 110 |
+
"eval_loss": 1.8477184772491455,
|
| 111 |
+
"eval_precision": 0.5039625709645932,
|
| 112 |
+
"eval_recall": 0.43,
|
| 113 |
+
"eval_runtime": 0.3674,
|
| 114 |
+
"eval_samples_per_second": 544.402,
|
| 115 |
+
"eval_steps_per_second": 19.054,
|
| 116 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 117 |
+
"eval_system_ram_used": 5.174091339111328,
|
| 118 |
+
"step": 76
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 3.8,
|
| 122 |
+
"learning_rate": 1.4933333333333335e-05,
|
| 123 |
+
"loss": 1.684,
|
| 124 |
+
"step": 95
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 3.8,
|
| 128 |
+
"eval_accuracy": 0.55,
|
| 129 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 130 |
+
"eval_disk_space_used": 40.663944244384766,
|
| 131 |
+
"eval_f1": 0.5271704828853498,
|
| 132 |
+
"eval_gpu_ram_allocated": 4.172764301300049,
|
| 133 |
+
"eval_gpu_ram_cached": 26.771484375,
|
| 134 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 135 |
+
"eval_gpu_utilization": 47,
|
| 136 |
+
"eval_loss": 1.6027369499206543,
|
| 137 |
+
"eval_precision": 0.5665937491057825,
|
| 138 |
+
"eval_recall": 0.55,
|
| 139 |
+
"eval_runtime": 0.3642,
|
| 140 |
+
"eval_samples_per_second": 549.083,
|
| 141 |
+
"eval_steps_per_second": 19.218,
|
| 142 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 143 |
+
"eval_system_ram_used": 5.1766204833984375,
|
| 144 |
+
"step": 95
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 4.56,
|
| 148 |
+
"learning_rate": 1.392e-05,
|
| 149 |
+
"loss": 1.3911,
|
| 150 |
+
"step": 114
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 4.56,
|
| 154 |
+
"eval_accuracy": 0.615,
|
| 155 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 156 |
+
"eval_disk_space_used": 40.66395950317383,
|
| 157 |
+
"eval_f1": 0.6060242411805659,
|
| 158 |
+
"eval_gpu_ram_allocated": 4.172757148742676,
|
| 159 |
+
"eval_gpu_ram_cached": 26.771484375,
|
| 160 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 161 |
+
"eval_gpu_utilization": 49,
|
| 162 |
+
"eval_loss": 1.4364641904830933,
|
| 163 |
+
"eval_precision": 0.619891761052247,
|
| 164 |
+
"eval_recall": 0.615,
|
| 165 |
+
"eval_runtime": 0.3684,
|
| 166 |
+
"eval_samples_per_second": 542.848,
|
| 167 |
+
"eval_steps_per_second": 19.0,
|
| 168 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 169 |
+
"eval_system_ram_used": 5.174568176269531,
|
| 170 |
+
"step": 114
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 5.32,
|
| 174 |
+
"learning_rate": 1.2906666666666668e-05,
|
| 175 |
+
"loss": 1.1477,
|
| 176 |
+
"step": 133
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 5.32,
|
| 180 |
+
"eval_accuracy": 0.615,
|
| 181 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 182 |
+
"eval_disk_space_used": 40.663963317871094,
|
| 183 |
+
"eval_f1": 0.6215457086252978,
|
| 184 |
+
"eval_gpu_ram_allocated": 4.172830104827881,
|
| 185 |
+
"eval_gpu_ram_cached": 26.771484375,
|
| 186 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 187 |
+
"eval_gpu_utilization": 52,
|
| 188 |
+
"eval_loss": 1.2565349340438843,
|
| 189 |
+
"eval_precision": 0.6418622536733991,
|
| 190 |
+
"eval_recall": 0.615,
|
| 191 |
+
"eval_runtime": 0.3792,
|
| 192 |
+
"eval_samples_per_second": 527.473,
|
| 193 |
+
"eval_steps_per_second": 18.462,
|
| 194 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 195 |
+
"eval_system_ram_used": 5.1585845947265625,
|
| 196 |
+
"step": 133
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 6.08,
|
| 200 |
+
"learning_rate": 1.1893333333333335e-05,
|
| 201 |
+
"loss": 0.9198,
|
| 202 |
+
"step": 152
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 6.08,
|
| 206 |
+
"eval_accuracy": 0.64,
|
| 207 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 208 |
+
"eval_disk_space_used": 40.66396713256836,
|
| 209 |
+
"eval_f1": 0.6399837944918036,
|
| 210 |
+
"eval_gpu_ram_allocated": 4.172749996185303,
|
| 211 |
+
"eval_gpu_ram_cached": 26.771484375,
|
| 212 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 213 |
+
"eval_gpu_utilization": 55,
|
| 214 |
+
"eval_loss": 1.175949215888977,
|
| 215 |
+
"eval_precision": 0.6532184905737537,
|
| 216 |
+
"eval_recall": 0.64,
|
| 217 |
+
"eval_runtime": 0.3814,
|
| 218 |
+
"eval_samples_per_second": 524.426,
|
| 219 |
+
"eval_steps_per_second": 18.355,
|
| 220 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 221 |
+
"eval_system_ram_used": 5.180980682373047,
|
| 222 |
+
"step": 152
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 6.84,
|
| 226 |
+
"learning_rate": 1.0880000000000001e-05,
|
| 227 |
+
"loss": 0.7605,
|
| 228 |
+
"step": 171
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 6.84,
|
| 232 |
+
"eval_accuracy": 0.645,
|
| 233 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 234 |
+
"eval_disk_space_used": 40.66401672363281,
|
| 235 |
+
"eval_f1": 0.6418225015596317,
|
| 236 |
+
"eval_gpu_ram_allocated": 4.1727471351623535,
|
| 237 |
+
"eval_gpu_ram_cached": 26.771484375,
|
| 238 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 239 |
+
"eval_gpu_utilization": 45,
|
| 240 |
+
"eval_loss": 1.112830638885498,
|
| 241 |
+
"eval_precision": 0.6564146498179483,
|
| 242 |
+
"eval_recall": 0.645,
|
| 243 |
+
"eval_runtime": 0.3808,
|
| 244 |
+
"eval_samples_per_second": 525.141,
|
| 245 |
+
"eval_steps_per_second": 18.38,
|
| 246 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 247 |
+
"eval_system_ram_used": 5.141529083251953,
|
| 248 |
+
"step": 171
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 7.6,
|
| 252 |
+
"learning_rate": 9.866666666666668e-06,
|
| 253 |
+
"loss": 0.6093,
|
| 254 |
+
"step": 190
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 7.6,
|
| 258 |
+
"eval_accuracy": 0.67,
|
| 259 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 260 |
+
"eval_disk_space_used": 40.66403579711914,
|
| 261 |
+
"eval_f1": 0.6677676797410276,
|
| 262 |
+
"eval_gpu_ram_allocated": 4.172770023345947,
|
| 263 |
+
"eval_gpu_ram_cached": 26.771484375,
|
| 264 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 265 |
+
"eval_gpu_utilization": 43,
|
| 266 |
+
"eval_loss": 1.0766719579696655,
|
| 267 |
+
"eval_precision": 0.6757531007004691,
|
| 268 |
+
"eval_recall": 0.67,
|
| 269 |
+
"eval_runtime": 0.383,
|
| 270 |
+
"eval_samples_per_second": 522.188,
|
| 271 |
+
"eval_steps_per_second": 18.277,
|
| 272 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 273 |
+
"eval_system_ram_used": 5.134746551513672,
|
| 274 |
+
"step": 190
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 8.36,
|
| 278 |
+
"learning_rate": 8.853333333333334e-06,
|
| 279 |
+
"loss": 0.5111,
|
| 280 |
+
"step": 209
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 8.36,
|
| 284 |
+
"eval_accuracy": 0.655,
|
| 285 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 286 |
+
"eval_disk_space_used": 40.6640510559082,
|
| 287 |
+
"eval_f1": 0.655230999157746,
|
| 288 |
+
"eval_gpu_ram_allocated": 4.1727728843688965,
|
| 289 |
+
"eval_gpu_ram_cached": 26.771484375,
|
| 290 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 291 |
+
"eval_gpu_utilization": 52,
|
| 292 |
+
"eval_loss": 1.1033188104629517,
|
| 293 |
+
"eval_precision": 0.6741666516629499,
|
| 294 |
+
"eval_recall": 0.655,
|
| 295 |
+
"eval_runtime": 0.369,
|
| 296 |
+
"eval_samples_per_second": 541.937,
|
| 297 |
+
"eval_steps_per_second": 18.968,
|
| 298 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 299 |
+
"eval_system_ram_used": 5.120639801025391,
|
| 300 |
+
"step": 209
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 9.12,
|
| 304 |
+
"learning_rate": 7.840000000000001e-06,
|
| 305 |
+
"loss": 0.3828,
|
| 306 |
+
"step": 228
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 9.12,
|
| 310 |
+
"eval_accuracy": 0.69,
|
| 311 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 312 |
+
"eval_disk_space_used": 40.664058685302734,
|
| 313 |
+
"eval_f1": 0.6874757485635422,
|
| 314 |
+
"eval_gpu_ram_allocated": 4.17274284362793,
|
| 315 |
+
"eval_gpu_ram_cached": 26.771484375,
|
| 316 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 317 |
+
"eval_gpu_utilization": 44,
|
| 318 |
+
"eval_loss": 1.1062885522842407,
|
| 319 |
+
"eval_precision": 0.692681623931624,
|
| 320 |
+
"eval_recall": 0.69,
|
| 321 |
+
"eval_runtime": 0.373,
|
| 322 |
+
"eval_samples_per_second": 536.14,
|
| 323 |
+
"eval_steps_per_second": 18.765,
|
| 324 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 325 |
+
"eval_system_ram_used": 5.148380279541016,
|
| 326 |
+
"step": 228
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 9.88,
|
| 330 |
+
"learning_rate": 6.826666666666667e-06,
|
| 331 |
+
"loss": 0.3082,
|
| 332 |
+
"step": 247
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 9.88,
|
| 336 |
+
"eval_accuracy": 0.665,
|
| 337 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 338 |
+
"eval_disk_space_used": 40.664058685302734,
|
| 339 |
+
"eval_f1": 0.657310556170902,
|
| 340 |
+
"eval_gpu_ram_allocated": 4.172765731811523,
|
| 341 |
+
"eval_gpu_ram_cached": 26.771484375,
|
| 342 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 343 |
+
"eval_gpu_utilization": 45,
|
| 344 |
+
"eval_loss": 1.1239553689956665,
|
| 345 |
+
"eval_precision": 0.6595053580899589,
|
| 346 |
+
"eval_recall": 0.665,
|
| 347 |
+
"eval_runtime": 0.3747,
|
| 348 |
+
"eval_samples_per_second": 533.805,
|
| 349 |
+
"eval_steps_per_second": 18.683,
|
| 350 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 351 |
+
"eval_system_ram_used": 5.143707275390625,
|
| 352 |
+
"step": 247
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 10.64,
|
| 356 |
+
"learning_rate": 5.813333333333334e-06,
|
| 357 |
+
"loss": 0.2716,
|
| 358 |
+
"step": 266
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 10.64,
|
| 362 |
+
"eval_accuracy": 0.665,
|
| 363 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 364 |
+
"eval_disk_space_used": 40.66410827636719,
|
| 365 |
+
"eval_f1": 0.6603758535972988,
|
| 366 |
+
"eval_gpu_ram_allocated": 4.172775745391846,
|
| 367 |
+
"eval_gpu_ram_cached": 26.771484375,
|
| 368 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 369 |
+
"eval_gpu_utilization": 45,
|
| 370 |
+
"eval_loss": 1.157199501991272,
|
| 371 |
+
"eval_precision": 0.666485053212742,
|
| 372 |
+
"eval_recall": 0.665,
|
| 373 |
+
"eval_runtime": 0.3689,
|
| 374 |
+
"eval_samples_per_second": 542.088,
|
| 375 |
+
"eval_steps_per_second": 18.973,
|
| 376 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 377 |
+
"eval_system_ram_used": 5.068927764892578,
|
| 378 |
+
"step": 266
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 11.4,
|
| 382 |
+
"learning_rate": 4.800000000000001e-06,
|
| 383 |
+
"loss": 0.2442,
|
| 384 |
+
"step": 285
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 11.4,
|
| 388 |
+
"eval_accuracy": 0.675,
|
| 389 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 390 |
+
"eval_disk_space_used": 40.66411209106445,
|
| 391 |
+
"eval_f1": 0.6764825046795931,
|
| 392 |
+
"eval_gpu_ram_allocated": 4.17277717590332,
|
| 393 |
+
"eval_gpu_ram_cached": 26.771484375,
|
| 394 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 395 |
+
"eval_gpu_utilization": 42,
|
| 396 |
+
"eval_loss": 1.1057575941085815,
|
| 397 |
+
"eval_precision": 0.6826701222753855,
|
| 398 |
+
"eval_recall": 0.675,
|
| 399 |
+
"eval_runtime": 0.3756,
|
| 400 |
+
"eval_samples_per_second": 532.455,
|
| 401 |
+
"eval_steps_per_second": 18.636,
|
| 402 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 403 |
+
"eval_system_ram_used": 5.031635284423828,
|
| 404 |
+
"step": 285
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 12.16,
|
| 408 |
+
"learning_rate": 3.7866666666666667e-06,
|
| 409 |
+
"loss": 0.1791,
|
| 410 |
+
"step": 304
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 12.16,
|
| 414 |
+
"eval_accuracy": 0.645,
|
| 415 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 416 |
+
"eval_disk_space_used": 40.664119720458984,
|
| 417 |
+
"eval_f1": 0.6445427433817439,
|
| 418 |
+
"eval_gpu_ram_allocated": 4.172751426696777,
|
| 419 |
+
"eval_gpu_ram_cached": 26.771484375,
|
| 420 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 421 |
+
"eval_gpu_utilization": 46,
|
| 422 |
+
"eval_loss": 1.1455398797988892,
|
| 423 |
+
"eval_precision": 0.6514674297225784,
|
| 424 |
+
"eval_recall": 0.645,
|
| 425 |
+
"eval_runtime": 0.37,
|
| 426 |
+
"eval_samples_per_second": 540.499,
|
| 427 |
+
"eval_steps_per_second": 18.917,
|
| 428 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 429 |
+
"eval_system_ram_used": 5.071483612060547,
|
| 430 |
+
"step": 304
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 12.92,
|
| 434 |
+
"learning_rate": 2.7733333333333336e-06,
|
| 435 |
+
"loss": 0.1604,
|
| 436 |
+
"step": 323
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 12.92,
|
| 440 |
+
"eval_accuracy": 0.66,
|
| 441 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 442 |
+
"eval_disk_space_used": 40.66413116455078,
|
| 443 |
+
"eval_f1": 0.6578390320866488,
|
| 444 |
+
"eval_gpu_ram_allocated": 4.172774314880371,
|
| 445 |
+
"eval_gpu_ram_cached": 26.771484375,
|
| 446 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 447 |
+
"eval_gpu_utilization": 57,
|
| 448 |
+
"eval_loss": 1.1514325141906738,
|
| 449 |
+
"eval_precision": 0.6686316887895163,
|
| 450 |
+
"eval_recall": 0.66,
|
| 451 |
+
"eval_runtime": 0.368,
|
| 452 |
+
"eval_samples_per_second": 543.448,
|
| 453 |
+
"eval_steps_per_second": 19.021,
|
| 454 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 455 |
+
"eval_system_ram_used": 5.0727691650390625,
|
| 456 |
+
"step": 323
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 13.68,
|
| 460 |
+
"learning_rate": 1.76e-06,
|
| 461 |
+
"loss": 0.1389,
|
| 462 |
+
"step": 342
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 13.68,
|
| 466 |
+
"eval_accuracy": 0.675,
|
| 467 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 468 |
+
"eval_disk_space_used": 40.66417694091797,
|
| 469 |
+
"eval_f1": 0.6714518778998741,
|
| 470 |
+
"eval_gpu_ram_allocated": 4.172738552093506,
|
| 471 |
+
"eval_gpu_ram_cached": 26.771484375,
|
| 472 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 473 |
+
"eval_gpu_utilization": 48,
|
| 474 |
+
"eval_loss": 1.160007357597351,
|
| 475 |
+
"eval_precision": 0.6807936997642879,
|
| 476 |
+
"eval_recall": 0.675,
|
| 477 |
+
"eval_runtime": 0.3735,
|
| 478 |
+
"eval_samples_per_second": 535.495,
|
| 479 |
+
"eval_steps_per_second": 18.742,
|
| 480 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 481 |
+
"eval_system_ram_used": 5.065456390380859,
|
| 482 |
+
"step": 342
|
| 483 |
+
}
|
| 484 |
+
],
|
| 485 |
+
"max_steps": 375,
|
| 486 |
+
"num_train_epochs": 15,
|
| 487 |
+
"total_flos": 771116158921728.0,
|
| 488 |
+
"trial_name": null,
|
| 489 |
+
"trial_params": null
|
| 490 |
+
}
|
{checkpoint-25 → checkpoint-350}/training_args.bin
RENAMED
|
File without changes
|
checkpoint-375/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 128000
|
| 3 |
+
}
|
checkpoint-375/config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/deberta-v3-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DebertaV2ForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.1,
|
| 9 |
+
"hidden_size": 768,
|
| 10 |
+
"id2label": {
|
| 11 |
+
"0": "Society & Culture",
|
| 12 |
+
"1": "Science & Mathematics",
|
| 13 |
+
"2": "Health",
|
| 14 |
+
"3": "Education & Reference",
|
| 15 |
+
"4": "Computers & Internet",
|
| 16 |
+
"5": "Sports",
|
| 17 |
+
"6": "Business & Finance",
|
| 18 |
+
"7": "Entertainment & Music",
|
| 19 |
+
"8": "Family & Relationships",
|
| 20 |
+
"9": "Politics & Government"
|
| 21 |
+
},
|
| 22 |
+
"initializer_range": 0.02,
|
| 23 |
+
"intermediate_size": 3072,
|
| 24 |
+
"label2id": {
|
| 25 |
+
"Business & Finance": 6,
|
| 26 |
+
"Computers & Internet": 4,
|
| 27 |
+
"Education & Reference": 3,
|
| 28 |
+
"Entertainment & Music": 7,
|
| 29 |
+
"Family & Relationships": 8,
|
| 30 |
+
"Health": 2,
|
| 31 |
+
"Politics & Government": 9,
|
| 32 |
+
"Science & Mathematics": 1,
|
| 33 |
+
"Society & Culture": 0,
|
| 34 |
+
"Sports": 5
|
| 35 |
+
},
|
| 36 |
+
"layer_norm_eps": 1e-07,
|
| 37 |
+
"max_position_embeddings": 512,
|
| 38 |
+
"max_relative_positions": -1,
|
| 39 |
+
"model_type": "deberta-v2",
|
| 40 |
+
"norm_rel_ebd": "layer_norm",
|
| 41 |
+
"num_attention_heads": 12,
|
| 42 |
+
"num_hidden_layers": 12,
|
| 43 |
+
"pad_token_id": 0,
|
| 44 |
+
"pooler_dropout": 0,
|
| 45 |
+
"pooler_hidden_act": "gelu",
|
| 46 |
+
"pooler_hidden_size": 768,
|
| 47 |
+
"pos_att_type": [
|
| 48 |
+
"p2c",
|
| 49 |
+
"c2p"
|
| 50 |
+
],
|
| 51 |
+
"position_biased_input": false,
|
| 52 |
+
"position_buckets": 256,
|
| 53 |
+
"relative_attention": true,
|
| 54 |
+
"share_att_key": true,
|
| 55 |
+
"torch_dtype": "float32",
|
| 56 |
+
"transformers_version": "4.31.0",
|
| 57 |
+
"type_vocab_size": 0,
|
| 58 |
+
"vocab_size": 128100
|
| 59 |
+
}
|
checkpoint-375/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5594f7693a00c08caf3e70e1ecaa87394cd62bfcfdd82b4b0c82ce4b244d92f1
|
| 3 |
+
size 1475557125
|
checkpoint-375/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ffc4b810698b3fcb8652ef309273ad4a6eee6a8b551f0cf6d1cbcc23c8eb1803
|
| 3 |
+
size 737788917
|
checkpoint-375/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cdeeb11d8cde2c5546ab64b9bc25bfce6f182490f39f172e19cfcfb132e4bd2a
|
| 3 |
+
size 14575
|
checkpoint-375/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f23724ff4d7c845b1dc0676ea3af8abdc294d9247ce526b3a4b06fbdb54c60d
|
| 3 |
+
size 627
|
checkpoint-375/special_tokens_map.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"eos_token": "[SEP]",
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"pad_token": "[PAD]",
|
| 7 |
+
"sep_token": "[SEP]",
|
| 8 |
+
"unk_token": "[UNK]"
|
| 9 |
+
}
|
checkpoint-375/spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
| 3 |
+
size 2464616
|
checkpoint-375/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-375/tokenizer_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"clean_up_tokenization_spaces": true,
|
| 4 |
+
"cls_token": "[CLS]",
|
| 5 |
+
"do_lower_case": false,
|
| 6 |
+
"eos_token": "[SEP]",
|
| 7 |
+
"mask_token": "[MASK]",
|
| 8 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 9 |
+
"pad_token": "[PAD]",
|
| 10 |
+
"sep_token": "[SEP]",
|
| 11 |
+
"sp_model_kwargs": {},
|
| 12 |
+
"split_by_punct": false,
|
| 13 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 14 |
+
"unk_token": "[UNK]",
|
| 15 |
+
"vocab_type": "spm"
|
| 16 |
+
}
|
checkpoint-375/trainer_state.json
ADDED
|
@@ -0,0 +1,516 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 15.0,
|
| 5 |
+
"global_step": 375,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.04,
|
| 12 |
+
"learning_rate": 1.9946666666666667e-05,
|
| 13 |
+
"loss": 2.3122,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.76,
|
| 18 |
+
"learning_rate": 1.898666666666667e-05,
|
| 19 |
+
"loss": 2.3022,
|
| 20 |
+
"step": 19
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.76,
|
| 24 |
+
"eval_accuracy": 0.1,
|
| 25 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 26 |
+
"eval_disk_space_used": 33.75697326660156,
|
| 27 |
+
"eval_f1": 0.018181818181818184,
|
| 28 |
+
"eval_gpu_ram_allocated": 4.172749996185303,
|
| 29 |
+
"eval_gpu_ram_cached": 26.759765625,
|
| 30 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 31 |
+
"eval_gpu_utilization": 45,
|
| 32 |
+
"eval_loss": 2.3011605739593506,
|
| 33 |
+
"eval_precision": 0.01,
|
| 34 |
+
"eval_recall": 0.1,
|
| 35 |
+
"eval_runtime": 0.3917,
|
| 36 |
+
"eval_samples_per_second": 510.562,
|
| 37 |
+
"eval_steps_per_second": 17.87,
|
| 38 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 39 |
+
"eval_system_ram_used": 4.445606231689453,
|
| 40 |
+
"step": 19
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 1.52,
|
| 44 |
+
"learning_rate": 1.7973333333333333e-05,
|
| 45 |
+
"loss": 2.2979,
|
| 46 |
+
"step": 38
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 1.52,
|
| 50 |
+
"eval_accuracy": 0.155,
|
| 51 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 52 |
+
"eval_disk_space_used": 38.592166900634766,
|
| 53 |
+
"eval_f1": 0.06350931677018633,
|
| 54 |
+
"eval_gpu_ram_allocated": 4.172748565673828,
|
| 55 |
+
"eval_gpu_ram_cached": 26.771484375,
|
| 56 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 57 |
+
"eval_gpu_utilization": 43,
|
| 58 |
+
"eval_loss": 2.2853753566741943,
|
| 59 |
+
"eval_precision": 0.04491869918699187,
|
| 60 |
+
"eval_recall": 0.155,
|
| 61 |
+
"eval_runtime": 0.3679,
|
| 62 |
+
"eval_samples_per_second": 543.585,
|
| 63 |
+
"eval_steps_per_second": 19.025,
|
| 64 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 65 |
+
"eval_system_ram_used": 5.034675598144531,
|
| 66 |
+
"step": 38
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 2.28,
|
| 70 |
+
"learning_rate": 1.696e-05,
|
| 71 |
+
"loss": 2.2316,
|
| 72 |
+
"step": 57
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 2.28,
|
| 76 |
+
"eval_accuracy": 0.305,
|
| 77 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 78 |
+
"eval_disk_space_used": 40.66392517089844,
|
| 79 |
+
"eval_f1": 0.2284533029124758,
|
| 80 |
+
"eval_gpu_ram_allocated": 4.172748565673828,
|
| 81 |
+
"eval_gpu_ram_cached": 26.771484375,
|
| 82 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 83 |
+
"eval_gpu_utilization": 44,
|
| 84 |
+
"eval_loss": 2.1098108291625977,
|
| 85 |
+
"eval_precision": 0.2806426799007444,
|
| 86 |
+
"eval_recall": 0.305,
|
| 87 |
+
"eval_runtime": 0.3885,
|
| 88 |
+
"eval_samples_per_second": 514.84,
|
| 89 |
+
"eval_steps_per_second": 18.019,
|
| 90 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 91 |
+
"eval_system_ram_used": 5.178070068359375,
|
| 92 |
+
"step": 57
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 3.04,
|
| 96 |
+
"learning_rate": 1.5946666666666668e-05,
|
| 97 |
+
"loss": 1.9915,
|
| 98 |
+
"step": 76
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 3.04,
|
| 102 |
+
"eval_accuracy": 0.43,
|
| 103 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 104 |
+
"eval_disk_space_used": 40.663944244384766,
|
| 105 |
+
"eval_f1": 0.4147692106558386,
|
| 106 |
+
"eval_gpu_ram_allocated": 4.172744274139404,
|
| 107 |
+
"eval_gpu_ram_cached": 26.771484375,
|
| 108 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 109 |
+
"eval_gpu_utilization": 50,
|
| 110 |
+
"eval_loss": 1.8477184772491455,
|
| 111 |
+
"eval_precision": 0.5039625709645932,
|
| 112 |
+
"eval_recall": 0.43,
|
| 113 |
+
"eval_runtime": 0.3674,
|
| 114 |
+
"eval_samples_per_second": 544.402,
|
| 115 |
+
"eval_steps_per_second": 19.054,
|
| 116 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 117 |
+
"eval_system_ram_used": 5.174091339111328,
|
| 118 |
+
"step": 76
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 3.8,
|
| 122 |
+
"learning_rate": 1.4933333333333335e-05,
|
| 123 |
+
"loss": 1.684,
|
| 124 |
+
"step": 95
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 3.8,
|
| 128 |
+
"eval_accuracy": 0.55,
|
| 129 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 130 |
+
"eval_disk_space_used": 40.663944244384766,
|
| 131 |
+
"eval_f1": 0.5271704828853498,
|
| 132 |
+
"eval_gpu_ram_allocated": 4.172764301300049,
|
| 133 |
+
"eval_gpu_ram_cached": 26.771484375,
|
| 134 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 135 |
+
"eval_gpu_utilization": 47,
|
| 136 |
+
"eval_loss": 1.6027369499206543,
|
| 137 |
+
"eval_precision": 0.5665937491057825,
|
| 138 |
+
"eval_recall": 0.55,
|
| 139 |
+
"eval_runtime": 0.3642,
|
| 140 |
+
"eval_samples_per_second": 549.083,
|
| 141 |
+
"eval_steps_per_second": 19.218,
|
| 142 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 143 |
+
"eval_system_ram_used": 5.1766204833984375,
|
| 144 |
+
"step": 95
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 4.56,
|
| 148 |
+
"learning_rate": 1.392e-05,
|
| 149 |
+
"loss": 1.3911,
|
| 150 |
+
"step": 114
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 4.56,
|
| 154 |
+
"eval_accuracy": 0.615,
|
| 155 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 156 |
+
"eval_disk_space_used": 40.66395950317383,
|
| 157 |
+
"eval_f1": 0.6060242411805659,
|
| 158 |
+
"eval_gpu_ram_allocated": 4.172757148742676,
|
| 159 |
+
"eval_gpu_ram_cached": 26.771484375,
|
| 160 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 161 |
+
"eval_gpu_utilization": 49,
|
| 162 |
+
"eval_loss": 1.4364641904830933,
|
| 163 |
+
"eval_precision": 0.619891761052247,
|
| 164 |
+
"eval_recall": 0.615,
|
| 165 |
+
"eval_runtime": 0.3684,
|
| 166 |
+
"eval_samples_per_second": 542.848,
|
| 167 |
+
"eval_steps_per_second": 19.0,
|
| 168 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 169 |
+
"eval_system_ram_used": 5.174568176269531,
|
| 170 |
+
"step": 114
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 5.32,
|
| 174 |
+
"learning_rate": 1.2906666666666668e-05,
|
| 175 |
+
"loss": 1.1477,
|
| 176 |
+
"step": 133
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 5.32,
|
| 180 |
+
"eval_accuracy": 0.615,
|
| 181 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 182 |
+
"eval_disk_space_used": 40.663963317871094,
|
| 183 |
+
"eval_f1": 0.6215457086252978,
|
| 184 |
+
"eval_gpu_ram_allocated": 4.172830104827881,
|
| 185 |
+
"eval_gpu_ram_cached": 26.771484375,
|
| 186 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 187 |
+
"eval_gpu_utilization": 52,
|
| 188 |
+
"eval_loss": 1.2565349340438843,
|
| 189 |
+
"eval_precision": 0.6418622536733991,
|
| 190 |
+
"eval_recall": 0.615,
|
| 191 |
+
"eval_runtime": 0.3792,
|
| 192 |
+
"eval_samples_per_second": 527.473,
|
| 193 |
+
"eval_steps_per_second": 18.462,
|
| 194 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 195 |
+
"eval_system_ram_used": 5.1585845947265625,
|
| 196 |
+
"step": 133
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 6.08,
|
| 200 |
+
"learning_rate": 1.1893333333333335e-05,
|
| 201 |
+
"loss": 0.9198,
|
| 202 |
+
"step": 152
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 6.08,
|
| 206 |
+
"eval_accuracy": 0.64,
|
| 207 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 208 |
+
"eval_disk_space_used": 40.66396713256836,
|
| 209 |
+
"eval_f1": 0.6399837944918036,
|
| 210 |
+
"eval_gpu_ram_allocated": 4.172749996185303,
|
| 211 |
+
"eval_gpu_ram_cached": 26.771484375,
|
| 212 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 213 |
+
"eval_gpu_utilization": 55,
|
| 214 |
+
"eval_loss": 1.175949215888977,
|
| 215 |
+
"eval_precision": 0.6532184905737537,
|
| 216 |
+
"eval_recall": 0.64,
|
| 217 |
+
"eval_runtime": 0.3814,
|
| 218 |
+
"eval_samples_per_second": 524.426,
|
| 219 |
+
"eval_steps_per_second": 18.355,
|
| 220 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 221 |
+
"eval_system_ram_used": 5.180980682373047,
|
| 222 |
+
"step": 152
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 6.84,
|
| 226 |
+
"learning_rate": 1.0880000000000001e-05,
|
| 227 |
+
"loss": 0.7605,
|
| 228 |
+
"step": 171
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 6.84,
|
| 232 |
+
"eval_accuracy": 0.645,
|
| 233 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 234 |
+
"eval_disk_space_used": 40.66401672363281,
|
| 235 |
+
"eval_f1": 0.6418225015596317,
|
| 236 |
+
"eval_gpu_ram_allocated": 4.1727471351623535,
|
| 237 |
+
"eval_gpu_ram_cached": 26.771484375,
|
| 238 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 239 |
+
"eval_gpu_utilization": 45,
|
| 240 |
+
"eval_loss": 1.112830638885498,
|
| 241 |
+
"eval_precision": 0.6564146498179483,
|
| 242 |
+
"eval_recall": 0.645,
|
| 243 |
+
"eval_runtime": 0.3808,
|
| 244 |
+
"eval_samples_per_second": 525.141,
|
| 245 |
+
"eval_steps_per_second": 18.38,
|
| 246 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 247 |
+
"eval_system_ram_used": 5.141529083251953,
|
| 248 |
+
"step": 171
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 7.6,
|
| 252 |
+
"learning_rate": 9.866666666666668e-06,
|
| 253 |
+
"loss": 0.6093,
|
| 254 |
+
"step": 190
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 7.6,
|
| 258 |
+
"eval_accuracy": 0.67,
|
| 259 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 260 |
+
"eval_disk_space_used": 40.66403579711914,
|
| 261 |
+
"eval_f1": 0.6677676797410276,
|
| 262 |
+
"eval_gpu_ram_allocated": 4.172770023345947,
|
| 263 |
+
"eval_gpu_ram_cached": 26.771484375,
|
| 264 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 265 |
+
"eval_gpu_utilization": 43,
|
| 266 |
+
"eval_loss": 1.0766719579696655,
|
| 267 |
+
"eval_precision": 0.6757531007004691,
|
| 268 |
+
"eval_recall": 0.67,
|
| 269 |
+
"eval_runtime": 0.383,
|
| 270 |
+
"eval_samples_per_second": 522.188,
|
| 271 |
+
"eval_steps_per_second": 18.277,
|
| 272 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 273 |
+
"eval_system_ram_used": 5.134746551513672,
|
| 274 |
+
"step": 190
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 8.36,
|
| 278 |
+
"learning_rate": 8.853333333333334e-06,
|
| 279 |
+
"loss": 0.5111,
|
| 280 |
+
"step": 209
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 8.36,
|
| 284 |
+
"eval_accuracy": 0.655,
|
| 285 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 286 |
+
"eval_disk_space_used": 40.6640510559082,
|
| 287 |
+
"eval_f1": 0.655230999157746,
|
| 288 |
+
"eval_gpu_ram_allocated": 4.1727728843688965,
|
| 289 |
+
"eval_gpu_ram_cached": 26.771484375,
|
| 290 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 291 |
+
"eval_gpu_utilization": 52,
|
| 292 |
+
"eval_loss": 1.1033188104629517,
|
| 293 |
+
"eval_precision": 0.6741666516629499,
|
| 294 |
+
"eval_recall": 0.655,
|
| 295 |
+
"eval_runtime": 0.369,
|
| 296 |
+
"eval_samples_per_second": 541.937,
|
| 297 |
+
"eval_steps_per_second": 18.968,
|
| 298 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 299 |
+
"eval_system_ram_used": 5.120639801025391,
|
| 300 |
+
"step": 209
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 9.12,
|
| 304 |
+
"learning_rate": 7.840000000000001e-06,
|
| 305 |
+
"loss": 0.3828,
|
| 306 |
+
"step": 228
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 9.12,
|
| 310 |
+
"eval_accuracy": 0.69,
|
| 311 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 312 |
+
"eval_disk_space_used": 40.664058685302734,
|
| 313 |
+
"eval_f1": 0.6874757485635422,
|
| 314 |
+
"eval_gpu_ram_allocated": 4.17274284362793,
|
| 315 |
+
"eval_gpu_ram_cached": 26.771484375,
|
| 316 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 317 |
+
"eval_gpu_utilization": 44,
|
| 318 |
+
"eval_loss": 1.1062885522842407,
|
| 319 |
+
"eval_precision": 0.692681623931624,
|
| 320 |
+
"eval_recall": 0.69,
|
| 321 |
+
"eval_runtime": 0.373,
|
| 322 |
+
"eval_samples_per_second": 536.14,
|
| 323 |
+
"eval_steps_per_second": 18.765,
|
| 324 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 325 |
+
"eval_system_ram_used": 5.148380279541016,
|
| 326 |
+
"step": 228
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 9.88,
|
| 330 |
+
"learning_rate": 6.826666666666667e-06,
|
| 331 |
+
"loss": 0.3082,
|
| 332 |
+
"step": 247
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 9.88,
|
| 336 |
+
"eval_accuracy": 0.665,
|
| 337 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 338 |
+
"eval_disk_space_used": 40.664058685302734,
|
| 339 |
+
"eval_f1": 0.657310556170902,
|
| 340 |
+
"eval_gpu_ram_allocated": 4.172765731811523,
|
| 341 |
+
"eval_gpu_ram_cached": 26.771484375,
|
| 342 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 343 |
+
"eval_gpu_utilization": 45,
|
| 344 |
+
"eval_loss": 1.1239553689956665,
|
| 345 |
+
"eval_precision": 0.6595053580899589,
|
| 346 |
+
"eval_recall": 0.665,
|
| 347 |
+
"eval_runtime": 0.3747,
|
| 348 |
+
"eval_samples_per_second": 533.805,
|
| 349 |
+
"eval_steps_per_second": 18.683,
|
| 350 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 351 |
+
"eval_system_ram_used": 5.143707275390625,
|
| 352 |
+
"step": 247
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 10.64,
|
| 356 |
+
"learning_rate": 5.813333333333334e-06,
|
| 357 |
+
"loss": 0.2716,
|
| 358 |
+
"step": 266
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 10.64,
|
| 362 |
+
"eval_accuracy": 0.665,
|
| 363 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 364 |
+
"eval_disk_space_used": 40.66410827636719,
|
| 365 |
+
"eval_f1": 0.6603758535972988,
|
| 366 |
+
"eval_gpu_ram_allocated": 4.172775745391846,
|
| 367 |
+
"eval_gpu_ram_cached": 26.771484375,
|
| 368 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 369 |
+
"eval_gpu_utilization": 45,
|
| 370 |
+
"eval_loss": 1.157199501991272,
|
| 371 |
+
"eval_precision": 0.666485053212742,
|
| 372 |
+
"eval_recall": 0.665,
|
| 373 |
+
"eval_runtime": 0.3689,
|
| 374 |
+
"eval_samples_per_second": 542.088,
|
| 375 |
+
"eval_steps_per_second": 18.973,
|
| 376 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 377 |
+
"eval_system_ram_used": 5.068927764892578,
|
| 378 |
+
"step": 266
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 11.4,
|
| 382 |
+
"learning_rate": 4.800000000000001e-06,
|
| 383 |
+
"loss": 0.2442,
|
| 384 |
+
"step": 285
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 11.4,
|
| 388 |
+
"eval_accuracy": 0.675,
|
| 389 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 390 |
+
"eval_disk_space_used": 40.66411209106445,
|
| 391 |
+
"eval_f1": 0.6764825046795931,
|
| 392 |
+
"eval_gpu_ram_allocated": 4.17277717590332,
|
| 393 |
+
"eval_gpu_ram_cached": 26.771484375,
|
| 394 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 395 |
+
"eval_gpu_utilization": 42,
|
| 396 |
+
"eval_loss": 1.1057575941085815,
|
| 397 |
+
"eval_precision": 0.6826701222753855,
|
| 398 |
+
"eval_recall": 0.675,
|
| 399 |
+
"eval_runtime": 0.3756,
|
| 400 |
+
"eval_samples_per_second": 532.455,
|
| 401 |
+
"eval_steps_per_second": 18.636,
|
| 402 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 403 |
+
"eval_system_ram_used": 5.031635284423828,
|
| 404 |
+
"step": 285
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 12.16,
|
| 408 |
+
"learning_rate": 3.7866666666666667e-06,
|
| 409 |
+
"loss": 0.1791,
|
| 410 |
+
"step": 304
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 12.16,
|
| 414 |
+
"eval_accuracy": 0.645,
|
| 415 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 416 |
+
"eval_disk_space_used": 40.664119720458984,
|
| 417 |
+
"eval_f1": 0.6445427433817439,
|
| 418 |
+
"eval_gpu_ram_allocated": 4.172751426696777,
|
| 419 |
+
"eval_gpu_ram_cached": 26.771484375,
|
| 420 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 421 |
+
"eval_gpu_utilization": 46,
|
| 422 |
+
"eval_loss": 1.1455398797988892,
|
| 423 |
+
"eval_precision": 0.6514674297225784,
|
| 424 |
+
"eval_recall": 0.645,
|
| 425 |
+
"eval_runtime": 0.37,
|
| 426 |
+
"eval_samples_per_second": 540.499,
|
| 427 |
+
"eval_steps_per_second": 18.917,
|
| 428 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 429 |
+
"eval_system_ram_used": 5.071483612060547,
|
| 430 |
+
"step": 304
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 12.92,
|
| 434 |
+
"learning_rate": 2.7733333333333336e-06,
|
| 435 |
+
"loss": 0.1604,
|
| 436 |
+
"step": 323
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 12.92,
|
| 440 |
+
"eval_accuracy": 0.66,
|
| 441 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 442 |
+
"eval_disk_space_used": 40.66413116455078,
|
| 443 |
+
"eval_f1": 0.6578390320866488,
|
| 444 |
+
"eval_gpu_ram_allocated": 4.172774314880371,
|
| 445 |
+
"eval_gpu_ram_cached": 26.771484375,
|
| 446 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 447 |
+
"eval_gpu_utilization": 57,
|
| 448 |
+
"eval_loss": 1.1514325141906738,
|
| 449 |
+
"eval_precision": 0.6686316887895163,
|
| 450 |
+
"eval_recall": 0.66,
|
| 451 |
+
"eval_runtime": 0.368,
|
| 452 |
+
"eval_samples_per_second": 543.448,
|
| 453 |
+
"eval_steps_per_second": 19.021,
|
| 454 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 455 |
+
"eval_system_ram_used": 5.0727691650390625,
|
| 456 |
+
"step": 323
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 13.68,
|
| 460 |
+
"learning_rate": 1.76e-06,
|
| 461 |
+
"loss": 0.1389,
|
| 462 |
+
"step": 342
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 13.68,
|
| 466 |
+
"eval_accuracy": 0.675,
|
| 467 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 468 |
+
"eval_disk_space_used": 40.66417694091797,
|
| 469 |
+
"eval_f1": 0.6714518778998741,
|
| 470 |
+
"eval_gpu_ram_allocated": 4.172738552093506,
|
| 471 |
+
"eval_gpu_ram_cached": 26.771484375,
|
| 472 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 473 |
+
"eval_gpu_utilization": 48,
|
| 474 |
+
"eval_loss": 1.160007357597351,
|
| 475 |
+
"eval_precision": 0.6807936997642879,
|
| 476 |
+
"eval_recall": 0.675,
|
| 477 |
+
"eval_runtime": 0.3735,
|
| 478 |
+
"eval_samples_per_second": 535.495,
|
| 479 |
+
"eval_steps_per_second": 18.742,
|
| 480 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 481 |
+
"eval_system_ram_used": 5.065456390380859,
|
| 482 |
+
"step": 342
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 14.44,
|
| 486 |
+
"learning_rate": 7.466666666666668e-07,
|
| 487 |
+
"loss": 0.151,
|
| 488 |
+
"step": 361
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 14.44,
|
| 492 |
+
"eval_accuracy": 0.665,
|
| 493 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 494 |
+
"eval_disk_space_used": 40.664188385009766,
|
| 495 |
+
"eval_f1": 0.6625899013665082,
|
| 496 |
+
"eval_gpu_ram_allocated": 4.172741413116455,
|
| 497 |
+
"eval_gpu_ram_cached": 26.771484375,
|
| 498 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 499 |
+
"eval_gpu_utilization": 48,
|
| 500 |
+
"eval_loss": 1.1573272943496704,
|
| 501 |
+
"eval_precision": 0.6686724234321488,
|
| 502 |
+
"eval_recall": 0.665,
|
| 503 |
+
"eval_runtime": 0.3721,
|
| 504 |
+
"eval_samples_per_second": 537.558,
|
| 505 |
+
"eval_steps_per_second": 18.815,
|
| 506 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 507 |
+
"eval_system_ram_used": 5.058799743652344,
|
| 508 |
+
"step": 361
|
| 509 |
+
}
|
| 510 |
+
],
|
| 511 |
+
"max_steps": 375,
|
| 512 |
+
"num_train_epochs": 15,
|
| 513 |
+
"total_flos": 825897508635264.0,
|
| 514 |
+
"trial_name": null,
|
| 515 |
+
"trial_params": null
|
| 516 |
+
}
|
checkpoint-375/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5f706732951169848f8127a8491def3af20921df42d30cfab655bcd2fbe3ce7
|
| 3 |
+
size 4091
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 737788917
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ffc4b810698b3fcb8652ef309273ad4a6eee6a8b551f0cf6d1cbcc23c8eb1803
|
| 3 |
size 737788917
|
runs/Jul22_09-22-43_549e78cb1c68/events.out.tfevents.1690017769.549e78cb1c68.4107.2
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9dd61c877e41419fbc01111d461dfaffcb6b789b2b80f7175a1e3b0896ef0406
|
| 3 |
+
size 26284
|
runs/Jul22_09-22-43_549e78cb1c68/events.out.tfevents.1690017926.549e78cb1c68.4107.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0e799275b2b89f5dc2cb436ad443f357c6c29221e10e3c030e9ff5198768ee0
|
| 3 |
+
size 1033
|