Commit
•
9068094
1
Parent(s):
cbf5494
End of training
Browse files- {checkpoint-25 → checkpoint-225}/added_tokens.json +0 -0
- {checkpoint-25 → checkpoint-225}/config.json +0 -0
- {checkpoint-25 → checkpoint-225}/optimizer.pt +1 -1
- {checkpoint-25 → checkpoint-225}/pytorch_model.bin +1 -1
- {checkpoint-25 → checkpoint-225}/rng_state.pth +1 -1
- {checkpoint-25 → checkpoint-225}/scheduler.pt +1 -1
- {checkpoint-25 → checkpoint-225}/special_tokens_map.json +0 -0
- {checkpoint-25 → checkpoint-225}/spm.model +0 -0
- {checkpoint-25 → checkpoint-225}/tokenizer.json +0 -0
- {checkpoint-25 → checkpoint-225}/tokenizer_config.json +0 -0
- checkpoint-225/trainer_state.json +464 -0
- {checkpoint-25 → checkpoint-225}/training_args.bin +0 -0
- checkpoint-25/trainer_state.json +0 -48
- checkpoint-250/added_tokens.json +3 -0
- checkpoint-250/config.json +59 -0
- checkpoint-250/optimizer.pt +3 -0
- checkpoint-250/pytorch_model.bin +3 -0
- checkpoint-250/rng_state.pth +3 -0
- checkpoint-250/scheduler.pt +3 -0
- checkpoint-250/special_tokens_map.json +9 -0
- checkpoint-250/spm.model +3 -0
- checkpoint-250/tokenizer.json +0 -0
- checkpoint-250/tokenizer_config.json +16 -0
- checkpoint-250/trainer_state.json +516 -0
- checkpoint-250/training_args.bin +3 -0
- pytorch_model.bin +1 -1
- runs/Jul22_09-14-20_549e78cb1c68/events.out.tfevents.1690017269.549e78cb1c68.4107.0 +2 -2
- runs/Jul22_09-14-20_549e78cb1c68/events.out.tfevents.1690017398.549e78cb1c68.4107.1 +3 -0
{checkpoint-25 → checkpoint-225}/added_tokens.json
RENAMED
|
File without changes
|
{checkpoint-25 → checkpoint-225}/config.json
RENAMED
|
File without changes
|
{checkpoint-25 → checkpoint-225}/optimizer.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1475556869
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2fd820f31fcb9f0a3c4e0ed57f35d91cbd53e74bcdcf5e4b3181c44e6b5ad1bc
|
| 3 |
size 1475556869
|
{checkpoint-25 → checkpoint-225}/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:f411cf9b1370df99a3a9e69f3cacf49a9ac9bf01014b97f90375c84fcd52083c
|
| 3 |
size 737788917
|
{checkpoint-25 → checkpoint-225}/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:d8598c778ef5797701b1e81000c49423b989e882496df5d8a374e4ec7409f56f
|
| 3 |
size 14575
|
{checkpoint-25 → checkpoint-225}/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 sha256:25896899392a8971cd10f59fcd8d1344e2226fb10799f427fc1578e103a26aa1
|
| 3 |
size 627
|
{checkpoint-25 → checkpoint-225}/special_tokens_map.json
RENAMED
|
File without changes
|
{checkpoint-25 → checkpoint-225}/spm.model
RENAMED
|
File without changes
|
{checkpoint-25 → checkpoint-225}/tokenizer.json
RENAMED
|
File without changes
|
{checkpoint-25 → checkpoint-225}/tokenizer_config.json
RENAMED
|
File without changes
|
checkpoint-225/trainer_state.json
ADDED
|
@@ -0,0 +1,464 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.0,
|
| 5 |
+
"global_step": 225,
|
| 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": 1.9920000000000002e-05,
|
| 13 |
+
"loss": 2.3122,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.52,
|
| 18 |
+
"learning_rate": 1.896e-05,
|
| 19 |
+
"loss": 2.2992,
|
| 20 |
+
"step": 13
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.52,
|
| 24 |
+
"eval_accuracy": 0.1,
|
| 25 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 26 |
+
"eval_disk_space_used": 24.785266876220703,
|
| 27 |
+
"eval_f1": 0.018181818181818184,
|
| 28 |
+
"eval_gpu_ram_allocated": 2.091515064239502,
|
| 29 |
+
"eval_gpu_ram_cached": 24.6484375,
|
| 30 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 31 |
+
"eval_gpu_utilization": 50,
|
| 32 |
+
"eval_loss": 2.303118944168091,
|
| 33 |
+
"eval_precision": 0.01,
|
| 34 |
+
"eval_recall": 0.1,
|
| 35 |
+
"eval_runtime": 0.3632,
|
| 36 |
+
"eval_samples_per_second": 550.672,
|
| 37 |
+
"eval_steps_per_second": 19.274,
|
| 38 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 39 |
+
"eval_system_ram_used": 3.9340057373046875,
|
| 40 |
+
"step": 13
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 1.04,
|
| 44 |
+
"learning_rate": 1.792e-05,
|
| 45 |
+
"loss": 2.3096,
|
| 46 |
+
"step": 26
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 1.04,
|
| 50 |
+
"eval_accuracy": 0.1,
|
| 51 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 52 |
+
"eval_disk_space_used": 29.620643615722656,
|
| 53 |
+
"eval_f1": 0.018181818181818184,
|
| 54 |
+
"eval_gpu_ram_allocated": 2.0915164947509766,
|
| 55 |
+
"eval_gpu_ram_cached": 24.66015625,
|
| 56 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 57 |
+
"eval_gpu_utilization": 43,
|
| 58 |
+
"eval_loss": 2.2983736991882324,
|
| 59 |
+
"eval_precision": 0.01,
|
| 60 |
+
"eval_recall": 0.1,
|
| 61 |
+
"eval_runtime": 0.3843,
|
| 62 |
+
"eval_samples_per_second": 520.372,
|
| 63 |
+
"eval_steps_per_second": 18.213,
|
| 64 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 65 |
+
"eval_system_ram_used": 4.119495391845703,
|
| 66 |
+
"step": 26
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 1.56,
|
| 70 |
+
"learning_rate": 1.688e-05,
|
| 71 |
+
"loss": 2.2906,
|
| 72 |
+
"step": 39
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 1.56,
|
| 76 |
+
"eval_accuracy": 0.145,
|
| 77 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 78 |
+
"eval_disk_space_used": 29.620647430419922,
|
| 79 |
+
"eval_f1": 0.06484230055658627,
|
| 80 |
+
"eval_gpu_ram_allocated": 2.0915350914001465,
|
| 81 |
+
"eval_gpu_ram_cached": 24.66015625,
|
| 82 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 83 |
+
"eval_gpu_utilization": 51,
|
| 84 |
+
"eval_loss": 2.2851924896240234,
|
| 85 |
+
"eval_precision": 0.05246212121212121,
|
| 86 |
+
"eval_recall": 0.145,
|
| 87 |
+
"eval_runtime": 0.3683,
|
| 88 |
+
"eval_samples_per_second": 542.987,
|
| 89 |
+
"eval_steps_per_second": 19.005,
|
| 90 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 91 |
+
"eval_system_ram_used": 4.205013275146484,
|
| 92 |
+
"step": 39
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 2.08,
|
| 96 |
+
"learning_rate": 1.584e-05,
|
| 97 |
+
"loss": 2.2723,
|
| 98 |
+
"step": 52
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 2.08,
|
| 102 |
+
"eval_accuracy": 0.225,
|
| 103 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 104 |
+
"eval_disk_space_used": 31.69240951538086,
|
| 105 |
+
"eval_f1": 0.12825672433668248,
|
| 106 |
+
"eval_gpu_ram_allocated": 2.091507911682129,
|
| 107 |
+
"eval_gpu_ram_cached": 24.66015625,
|
| 108 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 109 |
+
"eval_gpu_utilization": 43,
|
| 110 |
+
"eval_loss": 2.2198123931884766,
|
| 111 |
+
"eval_precision": 0.16249866509230126,
|
| 112 |
+
"eval_recall": 0.225,
|
| 113 |
+
"eval_runtime": 0.3837,
|
| 114 |
+
"eval_samples_per_second": 521.197,
|
| 115 |
+
"eval_steps_per_second": 18.242,
|
| 116 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 117 |
+
"eval_system_ram_used": 4.216480255126953,
|
| 118 |
+
"step": 52
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 2.6,
|
| 122 |
+
"learning_rate": 1.48e-05,
|
| 123 |
+
"loss": 2.1387,
|
| 124 |
+
"step": 65
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 2.6,
|
| 128 |
+
"eval_accuracy": 0.335,
|
| 129 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 130 |
+
"eval_disk_space_used": 31.69245147705078,
|
| 131 |
+
"eval_f1": 0.2579535245737298,
|
| 132 |
+
"eval_gpu_ram_allocated": 2.091599464416504,
|
| 133 |
+
"eval_gpu_ram_cached": 24.66015625,
|
| 134 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 135 |
+
"eval_gpu_utilization": 56,
|
| 136 |
+
"eval_loss": 2.0293209552764893,
|
| 137 |
+
"eval_precision": 0.2654710140004258,
|
| 138 |
+
"eval_recall": 0.335,
|
| 139 |
+
"eval_runtime": 0.3658,
|
| 140 |
+
"eval_samples_per_second": 546.742,
|
| 141 |
+
"eval_steps_per_second": 19.136,
|
| 142 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 143 |
+
"eval_system_ram_used": 4.2218017578125,
|
| 144 |
+
"step": 65
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 3.12,
|
| 148 |
+
"learning_rate": 1.376e-05,
|
| 149 |
+
"loss": 1.9534,
|
| 150 |
+
"step": 78
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 3.12,
|
| 154 |
+
"eval_accuracy": 0.4,
|
| 155 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 156 |
+
"eval_disk_space_used": 31.692481994628906,
|
| 157 |
+
"eval_f1": 0.37299130397528574,
|
| 158 |
+
"eval_gpu_ram_allocated": 2.091500759124756,
|
| 159 |
+
"eval_gpu_ram_cached": 24.66015625,
|
| 160 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 161 |
+
"eval_gpu_utilization": 41,
|
| 162 |
+
"eval_loss": 1.8756619691848755,
|
| 163 |
+
"eval_precision": 0.44191021478521475,
|
| 164 |
+
"eval_recall": 0.4,
|
| 165 |
+
"eval_runtime": 0.3822,
|
| 166 |
+
"eval_samples_per_second": 523.32,
|
| 167 |
+
"eval_steps_per_second": 18.316,
|
| 168 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 169 |
+
"eval_system_ram_used": 4.2091827392578125,
|
| 170 |
+
"step": 78
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 3.64,
|
| 174 |
+
"learning_rate": 1.2720000000000002e-05,
|
| 175 |
+
"loss": 1.7689,
|
| 176 |
+
"step": 91
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 3.64,
|
| 180 |
+
"eval_accuracy": 0.48,
|
| 181 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 182 |
+
"eval_disk_space_used": 31.692481994628906,
|
| 183 |
+
"eval_f1": 0.4442698143694956,
|
| 184 |
+
"eval_gpu_ram_allocated": 2.0915350914001465,
|
| 185 |
+
"eval_gpu_ram_cached": 24.66015625,
|
| 186 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 187 |
+
"eval_gpu_utilization": 46,
|
| 188 |
+
"eval_loss": 1.7208746671676636,
|
| 189 |
+
"eval_precision": 0.5197521691286822,
|
| 190 |
+
"eval_recall": 0.48,
|
| 191 |
+
"eval_runtime": 0.3705,
|
| 192 |
+
"eval_samples_per_second": 539.861,
|
| 193 |
+
"eval_steps_per_second": 18.895,
|
| 194 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 195 |
+
"eval_system_ram_used": 4.2303466796875,
|
| 196 |
+
"step": 91
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 4.16,
|
| 200 |
+
"learning_rate": 1.1760000000000001e-05,
|
| 201 |
+
"loss": 1.6052,
|
| 202 |
+
"step": 104
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 4.16,
|
| 206 |
+
"eval_accuracy": 0.525,
|
| 207 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 208 |
+
"eval_disk_space_used": 31.69255828857422,
|
| 209 |
+
"eval_f1": 0.5044390342519582,
|
| 210 |
+
"eval_gpu_ram_allocated": 2.0915451049804688,
|
| 211 |
+
"eval_gpu_ram_cached": 24.66015625,
|
| 212 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 213 |
+
"eval_gpu_utilization": 45,
|
| 214 |
+
"eval_loss": 1.6318445205688477,
|
| 215 |
+
"eval_precision": 0.5139384762914174,
|
| 216 |
+
"eval_recall": 0.525,
|
| 217 |
+
"eval_runtime": 0.3806,
|
| 218 |
+
"eval_samples_per_second": 525.479,
|
| 219 |
+
"eval_steps_per_second": 18.392,
|
| 220 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 221 |
+
"eval_system_ram_used": 4.229682922363281,
|
| 222 |
+
"step": 104
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 4.68,
|
| 226 |
+
"learning_rate": 1.072e-05,
|
| 227 |
+
"loss": 1.4606,
|
| 228 |
+
"step": 117
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 4.68,
|
| 232 |
+
"eval_accuracy": 0.575,
|
| 233 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 234 |
+
"eval_disk_space_used": 31.69255828857422,
|
| 235 |
+
"eval_f1": 0.5539001078732381,
|
| 236 |
+
"eval_gpu_ram_allocated": 2.0915350914001465,
|
| 237 |
+
"eval_gpu_ram_cached": 24.66015625,
|
| 238 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 239 |
+
"eval_gpu_utilization": 47,
|
| 240 |
+
"eval_loss": 1.4969176054000854,
|
| 241 |
+
"eval_precision": 0.5787876338221166,
|
| 242 |
+
"eval_recall": 0.575,
|
| 243 |
+
"eval_runtime": 0.3752,
|
| 244 |
+
"eval_samples_per_second": 533.081,
|
| 245 |
+
"eval_steps_per_second": 18.658,
|
| 246 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 247 |
+
"eval_system_ram_used": 4.231475830078125,
|
| 248 |
+
"step": 117
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 5.2,
|
| 252 |
+
"learning_rate": 9.68e-06,
|
| 253 |
+
"loss": 1.2963,
|
| 254 |
+
"step": 130
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 5.2,
|
| 258 |
+
"eval_accuracy": 0.61,
|
| 259 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 260 |
+
"eval_disk_space_used": 31.69259262084961,
|
| 261 |
+
"eval_f1": 0.6036944568156745,
|
| 262 |
+
"eval_gpu_ram_allocated": 2.091599464416504,
|
| 263 |
+
"eval_gpu_ram_cached": 24.66015625,
|
| 264 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 265 |
+
"eval_gpu_utilization": 43,
|
| 266 |
+
"eval_loss": 1.3920272588729858,
|
| 267 |
+
"eval_precision": 0.6063040077990168,
|
| 268 |
+
"eval_recall": 0.61,
|
| 269 |
+
"eval_runtime": 0.381,
|
| 270 |
+
"eval_samples_per_second": 524.941,
|
| 271 |
+
"eval_steps_per_second": 18.373,
|
| 272 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 273 |
+
"eval_system_ram_used": 4.242012023925781,
|
| 274 |
+
"step": 130
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 5.72,
|
| 278 |
+
"learning_rate": 8.64e-06,
|
| 279 |
+
"loss": 1.1948,
|
| 280 |
+
"step": 143
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 5.72,
|
| 284 |
+
"eval_accuracy": 0.63,
|
| 285 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 286 |
+
"eval_disk_space_used": 31.69259262084961,
|
| 287 |
+
"eval_f1": 0.6251401317519267,
|
| 288 |
+
"eval_gpu_ram_allocated": 2.0915136337280273,
|
| 289 |
+
"eval_gpu_ram_cached": 24.66015625,
|
| 290 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 291 |
+
"eval_gpu_utilization": 48,
|
| 292 |
+
"eval_loss": 1.3030096292495728,
|
| 293 |
+
"eval_precision": 0.6292207792207792,
|
| 294 |
+
"eval_recall": 0.63,
|
| 295 |
+
"eval_runtime": 0.3633,
|
| 296 |
+
"eval_samples_per_second": 550.566,
|
| 297 |
+
"eval_steps_per_second": 19.27,
|
| 298 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 299 |
+
"eval_system_ram_used": 4.2687225341796875,
|
| 300 |
+
"step": 143
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 6.24,
|
| 304 |
+
"learning_rate": 7.600000000000001e-06,
|
| 305 |
+
"loss": 1.0248,
|
| 306 |
+
"step": 156
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 6.24,
|
| 310 |
+
"eval_accuracy": 0.625,
|
| 311 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 312 |
+
"eval_disk_space_used": 31.69269561767578,
|
| 313 |
+
"eval_f1": 0.6184008464653626,
|
| 314 |
+
"eval_gpu_ram_allocated": 2.091526508331299,
|
| 315 |
+
"eval_gpu_ram_cached": 24.66015625,
|
| 316 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 317 |
+
"eval_gpu_utilization": 50,
|
| 318 |
+
"eval_loss": 1.2567895650863647,
|
| 319 |
+
"eval_precision": 0.6353763341921237,
|
| 320 |
+
"eval_recall": 0.625,
|
| 321 |
+
"eval_runtime": 0.3724,
|
| 322 |
+
"eval_samples_per_second": 537.06,
|
| 323 |
+
"eval_steps_per_second": 18.797,
|
| 324 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 325 |
+
"eval_system_ram_used": 4.259613037109375,
|
| 326 |
+
"step": 156
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 6.76,
|
| 330 |
+
"learning_rate": 6.560000000000001e-06,
|
| 331 |
+
"loss": 0.9509,
|
| 332 |
+
"step": 169
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 6.76,
|
| 336 |
+
"eval_accuracy": 0.65,
|
| 337 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 338 |
+
"eval_disk_space_used": 31.69269561767578,
|
| 339 |
+
"eval_f1": 0.6448307390509175,
|
| 340 |
+
"eval_gpu_ram_allocated": 2.091519355773926,
|
| 341 |
+
"eval_gpu_ram_cached": 24.66015625,
|
| 342 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 343 |
+
"eval_gpu_utilization": 44,
|
| 344 |
+
"eval_loss": 1.191145420074463,
|
| 345 |
+
"eval_precision": 0.6551875660571312,
|
| 346 |
+
"eval_recall": 0.65,
|
| 347 |
+
"eval_runtime": 0.3664,
|
| 348 |
+
"eval_samples_per_second": 545.815,
|
| 349 |
+
"eval_steps_per_second": 19.104,
|
| 350 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 351 |
+
"eval_system_ram_used": 4.262535095214844,
|
| 352 |
+
"step": 169
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 7.28,
|
| 356 |
+
"learning_rate": 5.5200000000000005e-06,
|
| 357 |
+
"loss": 0.9081,
|
| 358 |
+
"step": 182
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 7.28,
|
| 362 |
+
"eval_accuracy": 0.655,
|
| 363 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 364 |
+
"eval_disk_space_used": 31.692707061767578,
|
| 365 |
+
"eval_f1": 0.6441038418902195,
|
| 366 |
+
"eval_gpu_ram_allocated": 2.0915451049804688,
|
| 367 |
+
"eval_gpu_ram_cached": 24.66015625,
|
| 368 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 369 |
+
"eval_gpu_utilization": 50,
|
| 370 |
+
"eval_loss": 1.1784366369247437,
|
| 371 |
+
"eval_precision": 0.6450486800780918,
|
| 372 |
+
"eval_recall": 0.655,
|
| 373 |
+
"eval_runtime": 0.3834,
|
| 374 |
+
"eval_samples_per_second": 521.619,
|
| 375 |
+
"eval_steps_per_second": 18.257,
|
| 376 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 377 |
+
"eval_system_ram_used": 4.19549560546875,
|
| 378 |
+
"step": 182
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 7.8,
|
| 382 |
+
"learning_rate": 4.48e-06,
|
| 383 |
+
"loss": 0.7629,
|
| 384 |
+
"step": 195
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 7.8,
|
| 388 |
+
"eval_accuracy": 0.655,
|
| 389 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 390 |
+
"eval_disk_space_used": 31.692710876464844,
|
| 391 |
+
"eval_f1": 0.659811831437347,
|
| 392 |
+
"eval_gpu_ram_allocated": 2.091515064239502,
|
| 393 |
+
"eval_gpu_ram_cached": 24.66015625,
|
| 394 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 395 |
+
"eval_gpu_utilization": 44,
|
| 396 |
+
"eval_loss": 1.135439157485962,
|
| 397 |
+
"eval_precision": 0.6736920486920487,
|
| 398 |
+
"eval_recall": 0.655,
|
| 399 |
+
"eval_runtime": 0.37,
|
| 400 |
+
"eval_samples_per_second": 540.554,
|
| 401 |
+
"eval_steps_per_second": 18.919,
|
| 402 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 403 |
+
"eval_system_ram_used": 4.186817169189453,
|
| 404 |
+
"step": 195
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 8.32,
|
| 408 |
+
"learning_rate": 3.44e-06,
|
| 409 |
+
"loss": 0.7348,
|
| 410 |
+
"step": 208
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 8.32,
|
| 414 |
+
"eval_accuracy": 0.65,
|
| 415 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 416 |
+
"eval_disk_space_used": 31.692718505859375,
|
| 417 |
+
"eval_f1": 0.6430377731742748,
|
| 418 |
+
"eval_gpu_ram_allocated": 2.0915064811706543,
|
| 419 |
+
"eval_gpu_ram_cached": 24.66015625,
|
| 420 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 421 |
+
"eval_gpu_utilization": 43,
|
| 422 |
+
"eval_loss": 1.1369377374649048,
|
| 423 |
+
"eval_precision": 0.6483042554206238,
|
| 424 |
+
"eval_recall": 0.65,
|
| 425 |
+
"eval_runtime": 0.3889,
|
| 426 |
+
"eval_samples_per_second": 514.251,
|
| 427 |
+
"eval_steps_per_second": 17.999,
|
| 428 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 429 |
+
"eval_system_ram_used": 4.2168426513671875,
|
| 430 |
+
"step": 208
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 8.84,
|
| 434 |
+
"learning_rate": 2.4000000000000003e-06,
|
| 435 |
+
"loss": 0.7443,
|
| 436 |
+
"step": 221
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 8.84,
|
| 440 |
+
"eval_accuracy": 0.66,
|
| 441 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 442 |
+
"eval_disk_space_used": 31.692718505859375,
|
| 443 |
+
"eval_f1": 0.6531333156719726,
|
| 444 |
+
"eval_gpu_ram_allocated": 2.091543674468994,
|
| 445 |
+
"eval_gpu_ram_cached": 24.66015625,
|
| 446 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 447 |
+
"eval_gpu_utilization": 51,
|
| 448 |
+
"eval_loss": 1.127373456954956,
|
| 449 |
+
"eval_precision": 0.6576212193603499,
|
| 450 |
+
"eval_recall": 0.66,
|
| 451 |
+
"eval_runtime": 0.368,
|
| 452 |
+
"eval_samples_per_second": 543.468,
|
| 453 |
+
"eval_steps_per_second": 19.021,
|
| 454 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 455 |
+
"eval_system_ram_used": 4.2272796630859375,
|
| 456 |
+
"step": 221
|
| 457 |
+
}
|
| 458 |
+
],
|
| 459 |
+
"max_steps": 250,
|
| 460 |
+
"num_train_epochs": 10,
|
| 461 |
+
"total_flos": 489381153835392.0,
|
| 462 |
+
"trial_name": null,
|
| 463 |
+
"trial_params": null
|
| 464 |
+
}
|
{checkpoint-25 → checkpoint-225}/training_args.bin
RENAMED
|
File without changes
|
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": 1.9920000000000002e-05,
|
| 13 |
-
"loss": 2.3122,
|
| 14 |
-
"step": 1
|
| 15 |
-
},
|
| 16 |
-
{
|
| 17 |
-
"epoch": 0.52,
|
| 18 |
-
"learning_rate": 1.896e-05,
|
| 19 |
-
"loss": 2.2992,
|
| 20 |
-
"step": 13
|
| 21 |
-
},
|
| 22 |
-
{
|
| 23 |
-
"epoch": 0.52,
|
| 24 |
-
"eval_accuracy": 0.1,
|
| 25 |
-
"eval_disk_space_total": 78.1898422241211,
|
| 26 |
-
"eval_disk_space_used": 24.785266876220703,
|
| 27 |
-
"eval_f1": 0.018181818181818184,
|
| 28 |
-
"eval_gpu_ram_allocated": 2.091515064239502,
|
| 29 |
-
"eval_gpu_ram_cached": 24.6484375,
|
| 30 |
-
"eval_gpu_ram_total": 39.56402587890625,
|
| 31 |
-
"eval_gpu_utilization": 50,
|
| 32 |
-
"eval_loss": 2.303118944168091,
|
| 33 |
-
"eval_precision": 0.01,
|
| 34 |
-
"eval_recall": 0.1,
|
| 35 |
-
"eval_runtime": 0.3632,
|
| 36 |
-
"eval_samples_per_second": 550.672,
|
| 37 |
-
"eval_steps_per_second": 19.274,
|
| 38 |
-
"eval_system_ram_total": 83.48074722290039,
|
| 39 |
-
"eval_system_ram_used": 3.9340057373046875,
|
| 40 |
-
"step": 13
|
| 41 |
-
}
|
| 42 |
-
],
|
| 43 |
-
"max_steps": 250,
|
| 44 |
-
"num_train_epochs": 10,
|
| 45 |
-
"total_flos": 54485323206528.0,
|
| 46 |
-
"trial_name": null,
|
| 47 |
-
"trial_params": null
|
| 48 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-250/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[MASK]": 128000
|
| 3 |
+
}
|
checkpoint-250/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-250/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:73608c0c2a2a5b189c239e69cc49ce1d0e2ff37ca7d421f44e34215ac138d825
|
| 3 |
+
size 1475556869
|
checkpoint-250/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:330f6a1a51fff83c9f99b4851d64c1cc7f23079fb10a83e95884bcdb02f22b3d
|
| 3 |
+
size 737788917
|
checkpoint-250/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:25d787a8a0189188d02e12b0638102f47bd5d616eb5a8a4e1e93a1eeaff95782
|
| 3 |
+
size 14575
|
checkpoint-250/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:67da39284c30a9554609438e9dea7c9af80a80fd1451e4549ed2005a13185139
|
| 3 |
+
size 627
|
checkpoint-250/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-250/spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
| 3 |
+
size 2464616
|
checkpoint-250/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-250/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-250/trainer_state.json
ADDED
|
@@ -0,0 +1,516 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"global_step": 250,
|
| 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": 1.9920000000000002e-05,
|
| 13 |
+
"loss": 2.3122,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.52,
|
| 18 |
+
"learning_rate": 1.896e-05,
|
| 19 |
+
"loss": 2.2992,
|
| 20 |
+
"step": 13
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.52,
|
| 24 |
+
"eval_accuracy": 0.1,
|
| 25 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 26 |
+
"eval_disk_space_used": 24.785266876220703,
|
| 27 |
+
"eval_f1": 0.018181818181818184,
|
| 28 |
+
"eval_gpu_ram_allocated": 2.091515064239502,
|
| 29 |
+
"eval_gpu_ram_cached": 24.6484375,
|
| 30 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 31 |
+
"eval_gpu_utilization": 50,
|
| 32 |
+
"eval_loss": 2.303118944168091,
|
| 33 |
+
"eval_precision": 0.01,
|
| 34 |
+
"eval_recall": 0.1,
|
| 35 |
+
"eval_runtime": 0.3632,
|
| 36 |
+
"eval_samples_per_second": 550.672,
|
| 37 |
+
"eval_steps_per_second": 19.274,
|
| 38 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 39 |
+
"eval_system_ram_used": 3.9340057373046875,
|
| 40 |
+
"step": 13
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 1.04,
|
| 44 |
+
"learning_rate": 1.792e-05,
|
| 45 |
+
"loss": 2.3096,
|
| 46 |
+
"step": 26
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 1.04,
|
| 50 |
+
"eval_accuracy": 0.1,
|
| 51 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 52 |
+
"eval_disk_space_used": 29.620643615722656,
|
| 53 |
+
"eval_f1": 0.018181818181818184,
|
| 54 |
+
"eval_gpu_ram_allocated": 2.0915164947509766,
|
| 55 |
+
"eval_gpu_ram_cached": 24.66015625,
|
| 56 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 57 |
+
"eval_gpu_utilization": 43,
|
| 58 |
+
"eval_loss": 2.2983736991882324,
|
| 59 |
+
"eval_precision": 0.01,
|
| 60 |
+
"eval_recall": 0.1,
|
| 61 |
+
"eval_runtime": 0.3843,
|
| 62 |
+
"eval_samples_per_second": 520.372,
|
| 63 |
+
"eval_steps_per_second": 18.213,
|
| 64 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 65 |
+
"eval_system_ram_used": 4.119495391845703,
|
| 66 |
+
"step": 26
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 1.56,
|
| 70 |
+
"learning_rate": 1.688e-05,
|
| 71 |
+
"loss": 2.2906,
|
| 72 |
+
"step": 39
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 1.56,
|
| 76 |
+
"eval_accuracy": 0.145,
|
| 77 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 78 |
+
"eval_disk_space_used": 29.620647430419922,
|
| 79 |
+
"eval_f1": 0.06484230055658627,
|
| 80 |
+
"eval_gpu_ram_allocated": 2.0915350914001465,
|
| 81 |
+
"eval_gpu_ram_cached": 24.66015625,
|
| 82 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 83 |
+
"eval_gpu_utilization": 51,
|
| 84 |
+
"eval_loss": 2.2851924896240234,
|
| 85 |
+
"eval_precision": 0.05246212121212121,
|
| 86 |
+
"eval_recall": 0.145,
|
| 87 |
+
"eval_runtime": 0.3683,
|
| 88 |
+
"eval_samples_per_second": 542.987,
|
| 89 |
+
"eval_steps_per_second": 19.005,
|
| 90 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 91 |
+
"eval_system_ram_used": 4.205013275146484,
|
| 92 |
+
"step": 39
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 2.08,
|
| 96 |
+
"learning_rate": 1.584e-05,
|
| 97 |
+
"loss": 2.2723,
|
| 98 |
+
"step": 52
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 2.08,
|
| 102 |
+
"eval_accuracy": 0.225,
|
| 103 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 104 |
+
"eval_disk_space_used": 31.69240951538086,
|
| 105 |
+
"eval_f1": 0.12825672433668248,
|
| 106 |
+
"eval_gpu_ram_allocated": 2.091507911682129,
|
| 107 |
+
"eval_gpu_ram_cached": 24.66015625,
|
| 108 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 109 |
+
"eval_gpu_utilization": 43,
|
| 110 |
+
"eval_loss": 2.2198123931884766,
|
| 111 |
+
"eval_precision": 0.16249866509230126,
|
| 112 |
+
"eval_recall": 0.225,
|
| 113 |
+
"eval_runtime": 0.3837,
|
| 114 |
+
"eval_samples_per_second": 521.197,
|
| 115 |
+
"eval_steps_per_second": 18.242,
|
| 116 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 117 |
+
"eval_system_ram_used": 4.216480255126953,
|
| 118 |
+
"step": 52
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 2.6,
|
| 122 |
+
"learning_rate": 1.48e-05,
|
| 123 |
+
"loss": 2.1387,
|
| 124 |
+
"step": 65
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 2.6,
|
| 128 |
+
"eval_accuracy": 0.335,
|
| 129 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 130 |
+
"eval_disk_space_used": 31.69245147705078,
|
| 131 |
+
"eval_f1": 0.2579535245737298,
|
| 132 |
+
"eval_gpu_ram_allocated": 2.091599464416504,
|
| 133 |
+
"eval_gpu_ram_cached": 24.66015625,
|
| 134 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 135 |
+
"eval_gpu_utilization": 56,
|
| 136 |
+
"eval_loss": 2.0293209552764893,
|
| 137 |
+
"eval_precision": 0.2654710140004258,
|
| 138 |
+
"eval_recall": 0.335,
|
| 139 |
+
"eval_runtime": 0.3658,
|
| 140 |
+
"eval_samples_per_second": 546.742,
|
| 141 |
+
"eval_steps_per_second": 19.136,
|
| 142 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 143 |
+
"eval_system_ram_used": 4.2218017578125,
|
| 144 |
+
"step": 65
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 3.12,
|
| 148 |
+
"learning_rate": 1.376e-05,
|
| 149 |
+
"loss": 1.9534,
|
| 150 |
+
"step": 78
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 3.12,
|
| 154 |
+
"eval_accuracy": 0.4,
|
| 155 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 156 |
+
"eval_disk_space_used": 31.692481994628906,
|
| 157 |
+
"eval_f1": 0.37299130397528574,
|
| 158 |
+
"eval_gpu_ram_allocated": 2.091500759124756,
|
| 159 |
+
"eval_gpu_ram_cached": 24.66015625,
|
| 160 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 161 |
+
"eval_gpu_utilization": 41,
|
| 162 |
+
"eval_loss": 1.8756619691848755,
|
| 163 |
+
"eval_precision": 0.44191021478521475,
|
| 164 |
+
"eval_recall": 0.4,
|
| 165 |
+
"eval_runtime": 0.3822,
|
| 166 |
+
"eval_samples_per_second": 523.32,
|
| 167 |
+
"eval_steps_per_second": 18.316,
|
| 168 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 169 |
+
"eval_system_ram_used": 4.2091827392578125,
|
| 170 |
+
"step": 78
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 3.64,
|
| 174 |
+
"learning_rate": 1.2720000000000002e-05,
|
| 175 |
+
"loss": 1.7689,
|
| 176 |
+
"step": 91
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 3.64,
|
| 180 |
+
"eval_accuracy": 0.48,
|
| 181 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 182 |
+
"eval_disk_space_used": 31.692481994628906,
|
| 183 |
+
"eval_f1": 0.4442698143694956,
|
| 184 |
+
"eval_gpu_ram_allocated": 2.0915350914001465,
|
| 185 |
+
"eval_gpu_ram_cached": 24.66015625,
|
| 186 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 187 |
+
"eval_gpu_utilization": 46,
|
| 188 |
+
"eval_loss": 1.7208746671676636,
|
| 189 |
+
"eval_precision": 0.5197521691286822,
|
| 190 |
+
"eval_recall": 0.48,
|
| 191 |
+
"eval_runtime": 0.3705,
|
| 192 |
+
"eval_samples_per_second": 539.861,
|
| 193 |
+
"eval_steps_per_second": 18.895,
|
| 194 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 195 |
+
"eval_system_ram_used": 4.2303466796875,
|
| 196 |
+
"step": 91
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 4.16,
|
| 200 |
+
"learning_rate": 1.1760000000000001e-05,
|
| 201 |
+
"loss": 1.6052,
|
| 202 |
+
"step": 104
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 4.16,
|
| 206 |
+
"eval_accuracy": 0.525,
|
| 207 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 208 |
+
"eval_disk_space_used": 31.69255828857422,
|
| 209 |
+
"eval_f1": 0.5044390342519582,
|
| 210 |
+
"eval_gpu_ram_allocated": 2.0915451049804688,
|
| 211 |
+
"eval_gpu_ram_cached": 24.66015625,
|
| 212 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 213 |
+
"eval_gpu_utilization": 45,
|
| 214 |
+
"eval_loss": 1.6318445205688477,
|
| 215 |
+
"eval_precision": 0.5139384762914174,
|
| 216 |
+
"eval_recall": 0.525,
|
| 217 |
+
"eval_runtime": 0.3806,
|
| 218 |
+
"eval_samples_per_second": 525.479,
|
| 219 |
+
"eval_steps_per_second": 18.392,
|
| 220 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 221 |
+
"eval_system_ram_used": 4.229682922363281,
|
| 222 |
+
"step": 104
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 4.68,
|
| 226 |
+
"learning_rate": 1.072e-05,
|
| 227 |
+
"loss": 1.4606,
|
| 228 |
+
"step": 117
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 4.68,
|
| 232 |
+
"eval_accuracy": 0.575,
|
| 233 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 234 |
+
"eval_disk_space_used": 31.69255828857422,
|
| 235 |
+
"eval_f1": 0.5539001078732381,
|
| 236 |
+
"eval_gpu_ram_allocated": 2.0915350914001465,
|
| 237 |
+
"eval_gpu_ram_cached": 24.66015625,
|
| 238 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 239 |
+
"eval_gpu_utilization": 47,
|
| 240 |
+
"eval_loss": 1.4969176054000854,
|
| 241 |
+
"eval_precision": 0.5787876338221166,
|
| 242 |
+
"eval_recall": 0.575,
|
| 243 |
+
"eval_runtime": 0.3752,
|
| 244 |
+
"eval_samples_per_second": 533.081,
|
| 245 |
+
"eval_steps_per_second": 18.658,
|
| 246 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 247 |
+
"eval_system_ram_used": 4.231475830078125,
|
| 248 |
+
"step": 117
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 5.2,
|
| 252 |
+
"learning_rate": 9.68e-06,
|
| 253 |
+
"loss": 1.2963,
|
| 254 |
+
"step": 130
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 5.2,
|
| 258 |
+
"eval_accuracy": 0.61,
|
| 259 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 260 |
+
"eval_disk_space_used": 31.69259262084961,
|
| 261 |
+
"eval_f1": 0.6036944568156745,
|
| 262 |
+
"eval_gpu_ram_allocated": 2.091599464416504,
|
| 263 |
+
"eval_gpu_ram_cached": 24.66015625,
|
| 264 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 265 |
+
"eval_gpu_utilization": 43,
|
| 266 |
+
"eval_loss": 1.3920272588729858,
|
| 267 |
+
"eval_precision": 0.6063040077990168,
|
| 268 |
+
"eval_recall": 0.61,
|
| 269 |
+
"eval_runtime": 0.381,
|
| 270 |
+
"eval_samples_per_second": 524.941,
|
| 271 |
+
"eval_steps_per_second": 18.373,
|
| 272 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 273 |
+
"eval_system_ram_used": 4.242012023925781,
|
| 274 |
+
"step": 130
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 5.72,
|
| 278 |
+
"learning_rate": 8.64e-06,
|
| 279 |
+
"loss": 1.1948,
|
| 280 |
+
"step": 143
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 5.72,
|
| 284 |
+
"eval_accuracy": 0.63,
|
| 285 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 286 |
+
"eval_disk_space_used": 31.69259262084961,
|
| 287 |
+
"eval_f1": 0.6251401317519267,
|
| 288 |
+
"eval_gpu_ram_allocated": 2.0915136337280273,
|
| 289 |
+
"eval_gpu_ram_cached": 24.66015625,
|
| 290 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 291 |
+
"eval_gpu_utilization": 48,
|
| 292 |
+
"eval_loss": 1.3030096292495728,
|
| 293 |
+
"eval_precision": 0.6292207792207792,
|
| 294 |
+
"eval_recall": 0.63,
|
| 295 |
+
"eval_runtime": 0.3633,
|
| 296 |
+
"eval_samples_per_second": 550.566,
|
| 297 |
+
"eval_steps_per_second": 19.27,
|
| 298 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 299 |
+
"eval_system_ram_used": 4.2687225341796875,
|
| 300 |
+
"step": 143
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 6.24,
|
| 304 |
+
"learning_rate": 7.600000000000001e-06,
|
| 305 |
+
"loss": 1.0248,
|
| 306 |
+
"step": 156
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 6.24,
|
| 310 |
+
"eval_accuracy": 0.625,
|
| 311 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 312 |
+
"eval_disk_space_used": 31.69269561767578,
|
| 313 |
+
"eval_f1": 0.6184008464653626,
|
| 314 |
+
"eval_gpu_ram_allocated": 2.091526508331299,
|
| 315 |
+
"eval_gpu_ram_cached": 24.66015625,
|
| 316 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 317 |
+
"eval_gpu_utilization": 50,
|
| 318 |
+
"eval_loss": 1.2567895650863647,
|
| 319 |
+
"eval_precision": 0.6353763341921237,
|
| 320 |
+
"eval_recall": 0.625,
|
| 321 |
+
"eval_runtime": 0.3724,
|
| 322 |
+
"eval_samples_per_second": 537.06,
|
| 323 |
+
"eval_steps_per_second": 18.797,
|
| 324 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 325 |
+
"eval_system_ram_used": 4.259613037109375,
|
| 326 |
+
"step": 156
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 6.76,
|
| 330 |
+
"learning_rate": 6.560000000000001e-06,
|
| 331 |
+
"loss": 0.9509,
|
| 332 |
+
"step": 169
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 6.76,
|
| 336 |
+
"eval_accuracy": 0.65,
|
| 337 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 338 |
+
"eval_disk_space_used": 31.69269561767578,
|
| 339 |
+
"eval_f1": 0.6448307390509175,
|
| 340 |
+
"eval_gpu_ram_allocated": 2.091519355773926,
|
| 341 |
+
"eval_gpu_ram_cached": 24.66015625,
|
| 342 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 343 |
+
"eval_gpu_utilization": 44,
|
| 344 |
+
"eval_loss": 1.191145420074463,
|
| 345 |
+
"eval_precision": 0.6551875660571312,
|
| 346 |
+
"eval_recall": 0.65,
|
| 347 |
+
"eval_runtime": 0.3664,
|
| 348 |
+
"eval_samples_per_second": 545.815,
|
| 349 |
+
"eval_steps_per_second": 19.104,
|
| 350 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 351 |
+
"eval_system_ram_used": 4.262535095214844,
|
| 352 |
+
"step": 169
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 7.28,
|
| 356 |
+
"learning_rate": 5.5200000000000005e-06,
|
| 357 |
+
"loss": 0.9081,
|
| 358 |
+
"step": 182
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 7.28,
|
| 362 |
+
"eval_accuracy": 0.655,
|
| 363 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 364 |
+
"eval_disk_space_used": 31.692707061767578,
|
| 365 |
+
"eval_f1": 0.6441038418902195,
|
| 366 |
+
"eval_gpu_ram_allocated": 2.0915451049804688,
|
| 367 |
+
"eval_gpu_ram_cached": 24.66015625,
|
| 368 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 369 |
+
"eval_gpu_utilization": 50,
|
| 370 |
+
"eval_loss": 1.1784366369247437,
|
| 371 |
+
"eval_precision": 0.6450486800780918,
|
| 372 |
+
"eval_recall": 0.655,
|
| 373 |
+
"eval_runtime": 0.3834,
|
| 374 |
+
"eval_samples_per_second": 521.619,
|
| 375 |
+
"eval_steps_per_second": 18.257,
|
| 376 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 377 |
+
"eval_system_ram_used": 4.19549560546875,
|
| 378 |
+
"step": 182
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 7.8,
|
| 382 |
+
"learning_rate": 4.48e-06,
|
| 383 |
+
"loss": 0.7629,
|
| 384 |
+
"step": 195
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 7.8,
|
| 388 |
+
"eval_accuracy": 0.655,
|
| 389 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 390 |
+
"eval_disk_space_used": 31.692710876464844,
|
| 391 |
+
"eval_f1": 0.659811831437347,
|
| 392 |
+
"eval_gpu_ram_allocated": 2.091515064239502,
|
| 393 |
+
"eval_gpu_ram_cached": 24.66015625,
|
| 394 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 395 |
+
"eval_gpu_utilization": 44,
|
| 396 |
+
"eval_loss": 1.135439157485962,
|
| 397 |
+
"eval_precision": 0.6736920486920487,
|
| 398 |
+
"eval_recall": 0.655,
|
| 399 |
+
"eval_runtime": 0.37,
|
| 400 |
+
"eval_samples_per_second": 540.554,
|
| 401 |
+
"eval_steps_per_second": 18.919,
|
| 402 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 403 |
+
"eval_system_ram_used": 4.186817169189453,
|
| 404 |
+
"step": 195
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 8.32,
|
| 408 |
+
"learning_rate": 3.44e-06,
|
| 409 |
+
"loss": 0.7348,
|
| 410 |
+
"step": 208
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 8.32,
|
| 414 |
+
"eval_accuracy": 0.65,
|
| 415 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 416 |
+
"eval_disk_space_used": 31.692718505859375,
|
| 417 |
+
"eval_f1": 0.6430377731742748,
|
| 418 |
+
"eval_gpu_ram_allocated": 2.0915064811706543,
|
| 419 |
+
"eval_gpu_ram_cached": 24.66015625,
|
| 420 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 421 |
+
"eval_gpu_utilization": 43,
|
| 422 |
+
"eval_loss": 1.1369377374649048,
|
| 423 |
+
"eval_precision": 0.6483042554206238,
|
| 424 |
+
"eval_recall": 0.65,
|
| 425 |
+
"eval_runtime": 0.3889,
|
| 426 |
+
"eval_samples_per_second": 514.251,
|
| 427 |
+
"eval_steps_per_second": 17.999,
|
| 428 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 429 |
+
"eval_system_ram_used": 4.2168426513671875,
|
| 430 |
+
"step": 208
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 8.84,
|
| 434 |
+
"learning_rate": 2.4000000000000003e-06,
|
| 435 |
+
"loss": 0.7443,
|
| 436 |
+
"step": 221
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 8.84,
|
| 440 |
+
"eval_accuracy": 0.66,
|
| 441 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 442 |
+
"eval_disk_space_used": 31.692718505859375,
|
| 443 |
+
"eval_f1": 0.6531333156719726,
|
| 444 |
+
"eval_gpu_ram_allocated": 2.091543674468994,
|
| 445 |
+
"eval_gpu_ram_cached": 24.66015625,
|
| 446 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 447 |
+
"eval_gpu_utilization": 51,
|
| 448 |
+
"eval_loss": 1.127373456954956,
|
| 449 |
+
"eval_precision": 0.6576212193603499,
|
| 450 |
+
"eval_recall": 0.66,
|
| 451 |
+
"eval_runtime": 0.368,
|
| 452 |
+
"eval_samples_per_second": 543.468,
|
| 453 |
+
"eval_steps_per_second": 19.021,
|
| 454 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 455 |
+
"eval_system_ram_used": 4.2272796630859375,
|
| 456 |
+
"step": 221
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 9.36,
|
| 460 |
+
"learning_rate": 1.3600000000000001e-06,
|
| 461 |
+
"loss": 0.5945,
|
| 462 |
+
"step": 234
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 9.36,
|
| 466 |
+
"eval_accuracy": 0.67,
|
| 467 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 468 |
+
"eval_disk_space_used": 31.69280242919922,
|
| 469 |
+
"eval_f1": 0.6639595381548392,
|
| 470 |
+
"eval_gpu_ram_allocated": 2.091496467590332,
|
| 471 |
+
"eval_gpu_ram_cached": 24.66015625,
|
| 472 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 473 |
+
"eval_gpu_utilization": 44,
|
| 474 |
+
"eval_loss": 1.1228123903274536,
|
| 475 |
+
"eval_precision": 0.6693841536673345,
|
| 476 |
+
"eval_recall": 0.67,
|
| 477 |
+
"eval_runtime": 0.3763,
|
| 478 |
+
"eval_samples_per_second": 531.481,
|
| 479 |
+
"eval_steps_per_second": 18.602,
|
| 480 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 481 |
+
"eval_system_ram_used": 4.179080963134766,
|
| 482 |
+
"step": 234
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 9.88,
|
| 486 |
+
"learning_rate": 3.2e-07,
|
| 487 |
+
"loss": 0.6885,
|
| 488 |
+
"step": 247
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 9.88,
|
| 492 |
+
"eval_accuracy": 0.65,
|
| 493 |
+
"eval_disk_space_total": 78.1898422241211,
|
| 494 |
+
"eval_disk_space_used": 31.692806243896484,
|
| 495 |
+
"eval_f1": 0.6462726710486212,
|
| 496 |
+
"eval_gpu_ram_allocated": 2.0915064811706543,
|
| 497 |
+
"eval_gpu_ram_cached": 24.66015625,
|
| 498 |
+
"eval_gpu_ram_total": 39.56402587890625,
|
| 499 |
+
"eval_gpu_utilization": 48,
|
| 500 |
+
"eval_loss": 1.1145195960998535,
|
| 501 |
+
"eval_precision": 0.651370558312778,
|
| 502 |
+
"eval_recall": 0.65,
|
| 503 |
+
"eval_runtime": 0.361,
|
| 504 |
+
"eval_samples_per_second": 554.051,
|
| 505 |
+
"eval_steps_per_second": 19.392,
|
| 506 |
+
"eval_system_ram_total": 83.48074722290039,
|
| 507 |
+
"eval_system_ram_used": 4.184871673583984,
|
| 508 |
+
"step": 247
|
| 509 |
+
}
|
| 510 |
+
],
|
| 511 |
+
"max_steps": 250,
|
| 512 |
+
"num_train_epochs": 10,
|
| 513 |
+
"total_flos": 544326962719488.0,
|
| 514 |
+
"trial_name": null,
|
| 515 |
+
"trial_params": null
|
| 516 |
+
}
|
checkpoint-250/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2418b115209f2e4ba6e7e8442936bab7815c05be91f0380b9d3b20748a2ca41f
|
| 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 sha256:330f6a1a51fff83c9f99b4851d64c1cc7f23079fb10a83e95884bcdb02f22b3d
|
| 3 |
size 737788917
|
runs/Jul22_09-14-20_549e78cb1c68/events.out.tfevents.1690017269.549e78cb1c68.4107.0
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:decb4743dd0cedf7af87ec94c5cd872f375fcf2967d007ccad8fec52544fa003
|
| 3 |
+
size 26224
|
runs/Jul22_09-14-20_549e78cb1c68/events.out.tfevents.1690017398.549e78cb1c68.4107.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd94a85f7cb718bd587ccc5632238a48ee20fed58f6866c2b7bd73605bd2b43f
|
| 3 |
+
size 1033
|