Upload folder using huggingface_hub
Browse files- adapter_model.safetensors +1 -1
- optimizer.pt +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +521 -11
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 93378688
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f16612b3558a994f7f9fdb2eda772f0d7ee92b8ab65d308d952c16e2cf5882d6
|
| 3 |
size 93378688
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 187031330
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:33e4753d8e967daf58be3c4586c14128aaf5cf8b18762c58bbde37b302042703
|
| 3 |
size 187031330
|
rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eb920a55454edc05cad446eb986eb35a20c5c33567a5a093ac93baf95f6aec7c
|
| 3 |
size 14244
|
scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:25ab4523fd7262af4b9e1ebf15a79d63c966e86fc99ff91e2840498756cca05b
|
| 3 |
size 1064
|
trainer_state.json
CHANGED
|
@@ -1,27 +1,537 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "/content/Nasa_Mars_Model_Outputs/checkpoint-
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 10,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.004547004660679777,
|
| 13 |
-
"grad_norm":
|
| 14 |
"learning_rate": 2e-05,
|
| 15 |
-
"loss": 0.
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.004547004660679777,
|
| 20 |
-
"eval_loss": 0.
|
| 21 |
-
"eval_runtime": 20.
|
| 22 |
-
"eval_samples_per_second": 2.
|
| 23 |
-
"eval_steps_per_second": 2.
|
| 24 |
"step": 10
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
}
|
| 26 |
],
|
| 27 |
"logging_steps": 10,
|
|
@@ -41,7 +551,7 @@
|
|
| 41 |
"attributes": {}
|
| 42 |
}
|
| 43 |
},
|
| 44 |
-
"total_flos":
|
| 45 |
"train_batch_size": 1,
|
| 46 |
"trial_name": null,
|
| 47 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.8183558583259583,
|
| 3 |
+
"best_model_checkpoint": "/content/Nasa_Mars_Model_Outputs/checkpoint-170",
|
| 4 |
+
"epoch": 0.1591451631237922,
|
| 5 |
"eval_steps": 10,
|
| 6 |
+
"global_step": 350,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.004547004660679777,
|
| 13 |
+
"grad_norm": 8.844450950622559,
|
| 14 |
"learning_rate": 2e-05,
|
| 15 |
+
"loss": 0.5029,
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.004547004660679777,
|
| 20 |
+
"eval_loss": 0.852020800113678,
|
| 21 |
+
"eval_runtime": 20.6332,
|
| 22 |
+
"eval_samples_per_second": 2.423,
|
| 23 |
+
"eval_steps_per_second": 2.423,
|
| 24 |
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.009094009321359554,
|
| 28 |
+
"grad_norm": 6.392278671264648,
|
| 29 |
+
"learning_rate": 4e-05,
|
| 30 |
+
"loss": 0.4208,
|
| 31 |
+
"step": 20
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.009094009321359554,
|
| 35 |
+
"eval_loss": 0.8326458930969238,
|
| 36 |
+
"eval_runtime": 20.8468,
|
| 37 |
+
"eval_samples_per_second": 2.398,
|
| 38 |
+
"eval_steps_per_second": 2.398,
|
| 39 |
+
"step": 20
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.013641013982039332,
|
| 43 |
+
"grad_norm": 5.979872703552246,
|
| 44 |
+
"learning_rate": 6e-05,
|
| 45 |
+
"loss": 0.3174,
|
| 46 |
+
"step": 30
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.013641013982039332,
|
| 50 |
+
"eval_loss": 0.9364193677902222,
|
| 51 |
+
"eval_runtime": 20.7537,
|
| 52 |
+
"eval_samples_per_second": 2.409,
|
| 53 |
+
"eval_steps_per_second": 2.409,
|
| 54 |
+
"step": 30
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.018188018642719107,
|
| 58 |
+
"grad_norm": 8.079290390014648,
|
| 59 |
+
"learning_rate": 8e-05,
|
| 60 |
+
"loss": 0.2436,
|
| 61 |
+
"step": 40
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.018188018642719107,
|
| 65 |
+
"eval_loss": 0.9858406782150269,
|
| 66 |
+
"eval_runtime": 20.7434,
|
| 67 |
+
"eval_samples_per_second": 2.41,
|
| 68 |
+
"eval_steps_per_second": 2.41,
|
| 69 |
+
"step": 40
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.022735023303398886,
|
| 73 |
+
"grad_norm": 7.087987422943115,
|
| 74 |
+
"learning_rate": 0.0001,
|
| 75 |
+
"loss": 0.2069,
|
| 76 |
+
"step": 50
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.022735023303398886,
|
| 80 |
+
"eval_loss": 0.9912980794906616,
|
| 81 |
+
"eval_runtime": 20.7587,
|
| 82 |
+
"eval_samples_per_second": 2.409,
|
| 83 |
+
"eval_steps_per_second": 2.409,
|
| 84 |
+
"step": 50
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.027282027964078664,
|
| 88 |
+
"grad_norm": 7.0141496658325195,
|
| 89 |
+
"learning_rate": 9.977000919963202e-05,
|
| 90 |
+
"loss": 0.2171,
|
| 91 |
+
"step": 60
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.027282027964078664,
|
| 95 |
+
"eval_loss": 1.029310941696167,
|
| 96 |
+
"eval_runtime": 20.7996,
|
| 97 |
+
"eval_samples_per_second": 2.404,
|
| 98 |
+
"eval_steps_per_second": 2.404,
|
| 99 |
+
"step": 60
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.03182903262475844,
|
| 103 |
+
"grad_norm": 7.3678998947143555,
|
| 104 |
+
"learning_rate": 9.954001839926403e-05,
|
| 105 |
+
"loss": 0.2756,
|
| 106 |
+
"step": 70
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.03182903262475844,
|
| 110 |
+
"eval_loss": 0.9257596731185913,
|
| 111 |
+
"eval_runtime": 20.8032,
|
| 112 |
+
"eval_samples_per_second": 2.403,
|
| 113 |
+
"eval_steps_per_second": 2.403,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.036376037285438215,
|
| 118 |
+
"grad_norm": 8.662162780761719,
|
| 119 |
+
"learning_rate": 9.931002759889605e-05,
|
| 120 |
+
"loss": 0.3853,
|
| 121 |
+
"step": 80
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.036376037285438215,
|
| 125 |
+
"eval_loss": 0.9099023342132568,
|
| 126 |
+
"eval_runtime": 20.8394,
|
| 127 |
+
"eval_samples_per_second": 2.399,
|
| 128 |
+
"eval_steps_per_second": 2.399,
|
| 129 |
+
"step": 80
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.040923041946118,
|
| 133 |
+
"grad_norm": 8.646831512451172,
|
| 134 |
+
"learning_rate": 9.908003679852806e-05,
|
| 135 |
+
"loss": 0.4754,
|
| 136 |
+
"step": 90
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.040923041946118,
|
| 140 |
+
"eval_loss": 0.8751680254936218,
|
| 141 |
+
"eval_runtime": 20.8501,
|
| 142 |
+
"eval_samples_per_second": 2.398,
|
| 143 |
+
"eval_steps_per_second": 2.398,
|
| 144 |
+
"step": 90
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.04547004660679777,
|
| 148 |
+
"grad_norm": 5.3645501136779785,
|
| 149 |
+
"learning_rate": 9.885004599816008e-05,
|
| 150 |
+
"loss": 0.3919,
|
| 151 |
+
"step": 100
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.04547004660679777,
|
| 155 |
+
"eval_loss": 0.8975805640220642,
|
| 156 |
+
"eval_runtime": 20.7625,
|
| 157 |
+
"eval_samples_per_second": 2.408,
|
| 158 |
+
"eval_steps_per_second": 2.408,
|
| 159 |
+
"step": 100
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.05001705126747755,
|
| 163 |
+
"grad_norm": 7.332831859588623,
|
| 164 |
+
"learning_rate": 9.86200551977921e-05,
|
| 165 |
+
"loss": 0.5172,
|
| 166 |
+
"step": 110
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.05001705126747755,
|
| 170 |
+
"eval_loss": 0.8908578753471375,
|
| 171 |
+
"eval_runtime": 20.8039,
|
| 172 |
+
"eval_samples_per_second": 2.403,
|
| 173 |
+
"eval_steps_per_second": 2.403,
|
| 174 |
+
"step": 110
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.05456405592815733,
|
| 178 |
+
"grad_norm": 5.561324119567871,
|
| 179 |
+
"learning_rate": 9.83900643974241e-05,
|
| 180 |
+
"loss": 0.4599,
|
| 181 |
+
"step": 120
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.05456405592815733,
|
| 185 |
+
"eval_loss": 0.8581109046936035,
|
| 186 |
+
"eval_runtime": 20.8113,
|
| 187 |
+
"eval_samples_per_second": 2.403,
|
| 188 |
+
"eval_steps_per_second": 2.403,
|
| 189 |
+
"step": 120
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.059111060588837104,
|
| 193 |
+
"grad_norm": 7.407668113708496,
|
| 194 |
+
"learning_rate": 9.816007359705612e-05,
|
| 195 |
+
"loss": 0.5029,
|
| 196 |
+
"step": 130
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.059111060588837104,
|
| 200 |
+
"eval_loss": 0.8726012706756592,
|
| 201 |
+
"eval_runtime": 20.8342,
|
| 202 |
+
"eval_samples_per_second": 2.4,
|
| 203 |
+
"eval_steps_per_second": 2.4,
|
| 204 |
+
"step": 130
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.06365806524951688,
|
| 208 |
+
"grad_norm": 5.486892223358154,
|
| 209 |
+
"learning_rate": 9.793008279668814e-05,
|
| 210 |
+
"loss": 0.4758,
|
| 211 |
+
"step": 140
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.06365806524951688,
|
| 215 |
+
"eval_loss": 0.8502522110939026,
|
| 216 |
+
"eval_runtime": 20.7835,
|
| 217 |
+
"eval_samples_per_second": 2.406,
|
| 218 |
+
"eval_steps_per_second": 2.406,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.06820506991019666,
|
| 223 |
+
"grad_norm": 7.221977710723877,
|
| 224 |
+
"learning_rate": 9.770009199632015e-05,
|
| 225 |
+
"loss": 0.6792,
|
| 226 |
+
"step": 150
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.06820506991019666,
|
| 230 |
+
"eval_loss": 0.827602207660675,
|
| 231 |
+
"eval_runtime": 20.7446,
|
| 232 |
+
"eval_samples_per_second": 2.41,
|
| 233 |
+
"eval_steps_per_second": 2.41,
|
| 234 |
+
"step": 150
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.07275207457087643,
|
| 238 |
+
"grad_norm": 5.567179203033447,
|
| 239 |
+
"learning_rate": 9.747010119595217e-05,
|
| 240 |
+
"loss": 0.6319,
|
| 241 |
+
"step": 160
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.07275207457087643,
|
| 245 |
+
"eval_loss": 0.8225394487380981,
|
| 246 |
+
"eval_runtime": 20.7953,
|
| 247 |
+
"eval_samples_per_second": 2.404,
|
| 248 |
+
"eval_steps_per_second": 2.404,
|
| 249 |
+
"step": 160
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.07729907923155621,
|
| 253 |
+
"grad_norm": 6.063055992126465,
|
| 254 |
+
"learning_rate": 9.724011039558418e-05,
|
| 255 |
+
"loss": 0.7255,
|
| 256 |
+
"step": 170
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 0.07729907923155621,
|
| 260 |
+
"eval_loss": 0.8183558583259583,
|
| 261 |
+
"eval_runtime": 20.804,
|
| 262 |
+
"eval_samples_per_second": 2.403,
|
| 263 |
+
"eval_steps_per_second": 2.403,
|
| 264 |
+
"step": 170
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.081846083892236,
|
| 268 |
+
"grad_norm": 8.263747215270996,
|
| 269 |
+
"learning_rate": 9.70101195952162e-05,
|
| 270 |
+
"loss": 0.6679,
|
| 271 |
+
"step": 180
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.081846083892236,
|
| 275 |
+
"eval_loss": 0.8275816440582275,
|
| 276 |
+
"eval_runtime": 20.8116,
|
| 277 |
+
"eval_samples_per_second": 2.403,
|
| 278 |
+
"eval_steps_per_second": 2.403,
|
| 279 |
+
"step": 180
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.08639308855291576,
|
| 283 |
+
"grad_norm": 8.163738250732422,
|
| 284 |
+
"learning_rate": 9.678012879484822e-05,
|
| 285 |
+
"loss": 0.6618,
|
| 286 |
+
"step": 190
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.08639308855291576,
|
| 290 |
+
"eval_loss": 0.8254545331001282,
|
| 291 |
+
"eval_runtime": 20.8251,
|
| 292 |
+
"eval_samples_per_second": 2.401,
|
| 293 |
+
"eval_steps_per_second": 2.401,
|
| 294 |
+
"step": 190
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.09094009321359554,
|
| 298 |
+
"grad_norm": 10.39909839630127,
|
| 299 |
+
"learning_rate": 9.655013799448022e-05,
|
| 300 |
+
"loss": 0.7477,
|
| 301 |
+
"step": 200
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 0.09094009321359554,
|
| 305 |
+
"eval_loss": 0.8232752084732056,
|
| 306 |
+
"eval_runtime": 20.7836,
|
| 307 |
+
"eval_samples_per_second": 2.406,
|
| 308 |
+
"eval_steps_per_second": 2.406,
|
| 309 |
+
"step": 200
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.09548709787427533,
|
| 313 |
+
"grad_norm": 5.135624885559082,
|
| 314 |
+
"learning_rate": 9.632014719411224e-05,
|
| 315 |
+
"loss": 0.6157,
|
| 316 |
+
"step": 210
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 0.09548709787427533,
|
| 320 |
+
"eval_loss": 0.8450194597244263,
|
| 321 |
+
"eval_runtime": 20.7915,
|
| 322 |
+
"eval_samples_per_second": 2.405,
|
| 323 |
+
"eval_steps_per_second": 2.405,
|
| 324 |
+
"step": 210
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.1000341025349551,
|
| 328 |
+
"grad_norm": 5.748319149017334,
|
| 329 |
+
"learning_rate": 9.609015639374425e-05,
|
| 330 |
+
"loss": 0.6228,
|
| 331 |
+
"step": 220
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.1000341025349551,
|
| 335 |
+
"eval_loss": 0.8414835333824158,
|
| 336 |
+
"eval_runtime": 20.8517,
|
| 337 |
+
"eval_samples_per_second": 2.398,
|
| 338 |
+
"eval_steps_per_second": 2.398,
|
| 339 |
+
"step": 220
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.10458110719563488,
|
| 343 |
+
"grad_norm": 6.394444942474365,
|
| 344 |
+
"learning_rate": 9.586016559337627e-05,
|
| 345 |
+
"loss": 0.846,
|
| 346 |
+
"step": 230
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.10458110719563488,
|
| 350 |
+
"eval_loss": 0.8268595933914185,
|
| 351 |
+
"eval_runtime": 20.7853,
|
| 352 |
+
"eval_samples_per_second": 2.406,
|
| 353 |
+
"eval_steps_per_second": 2.406,
|
| 354 |
+
"step": 230
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.10912811185631466,
|
| 358 |
+
"grad_norm": 5.815967082977295,
|
| 359 |
+
"learning_rate": 9.563017479300829e-05,
|
| 360 |
+
"loss": 0.7647,
|
| 361 |
+
"step": 240
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.10912811185631466,
|
| 365 |
+
"eval_loss": 0.8257486820220947,
|
| 366 |
+
"eval_runtime": 20.7865,
|
| 367 |
+
"eval_samples_per_second": 2.405,
|
| 368 |
+
"eval_steps_per_second": 2.405,
|
| 369 |
+
"step": 240
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.11367511651699443,
|
| 373 |
+
"grad_norm": 7.9722161293029785,
|
| 374 |
+
"learning_rate": 9.54001839926403e-05,
|
| 375 |
+
"loss": 0.6884,
|
| 376 |
+
"step": 250
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.11367511651699443,
|
| 380 |
+
"eval_loss": 0.8330263495445251,
|
| 381 |
+
"eval_runtime": 20.7919,
|
| 382 |
+
"eval_samples_per_second": 2.405,
|
| 383 |
+
"eval_steps_per_second": 2.405,
|
| 384 |
+
"step": 250
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.11822212117767421,
|
| 388 |
+
"grad_norm": 6.1814799308776855,
|
| 389 |
+
"learning_rate": 9.517019319227232e-05,
|
| 390 |
+
"loss": 0.7325,
|
| 391 |
+
"step": 260
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 0.11822212117767421,
|
| 395 |
+
"eval_loss": 0.8296122550964355,
|
| 396 |
+
"eval_runtime": 20.7856,
|
| 397 |
+
"eval_samples_per_second": 2.406,
|
| 398 |
+
"eval_steps_per_second": 2.406,
|
| 399 |
+
"step": 260
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.12276912583835399,
|
| 403 |
+
"grad_norm": 14.889198303222656,
|
| 404 |
+
"learning_rate": 9.494020239190432e-05,
|
| 405 |
+
"loss": 0.6521,
|
| 406 |
+
"step": 270
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 0.12276912583835399,
|
| 410 |
+
"eval_loss": 0.8349407911300659,
|
| 411 |
+
"eval_runtime": 20.7358,
|
| 412 |
+
"eval_samples_per_second": 2.411,
|
| 413 |
+
"eval_steps_per_second": 2.411,
|
| 414 |
+
"step": 270
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.12731613049903376,
|
| 418 |
+
"grad_norm": 9.311092376708984,
|
| 419 |
+
"learning_rate": 9.471021159153634e-05,
|
| 420 |
+
"loss": 0.6413,
|
| 421 |
+
"step": 280
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 0.12731613049903376,
|
| 425 |
+
"eval_loss": 0.8341807723045349,
|
| 426 |
+
"eval_runtime": 20.7945,
|
| 427 |
+
"eval_samples_per_second": 2.404,
|
| 428 |
+
"eval_steps_per_second": 2.404,
|
| 429 |
+
"step": 280
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.13186313515971354,
|
| 433 |
+
"grad_norm": 2.8647501468658447,
|
| 434 |
+
"learning_rate": 9.448022079116836e-05,
|
| 435 |
+
"loss": 0.6104,
|
| 436 |
+
"step": 290
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.13186313515971354,
|
| 440 |
+
"eval_loss": 0.8275405764579773,
|
| 441 |
+
"eval_runtime": 20.7773,
|
| 442 |
+
"eval_samples_per_second": 2.406,
|
| 443 |
+
"eval_steps_per_second": 2.406,
|
| 444 |
+
"step": 290
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.13641013982039332,
|
| 448 |
+
"grad_norm": 6.136713027954102,
|
| 449 |
+
"learning_rate": 9.425022999080037e-05,
|
| 450 |
+
"loss": 0.5325,
|
| 451 |
+
"step": 300
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.13641013982039332,
|
| 455 |
+
"eval_loss": 0.8468616008758545,
|
| 456 |
+
"eval_runtime": 20.7933,
|
| 457 |
+
"eval_samples_per_second": 2.405,
|
| 458 |
+
"eval_steps_per_second": 2.405,
|
| 459 |
+
"step": 300
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.1409571444810731,
|
| 463 |
+
"grad_norm": 9.0726900100708,
|
| 464 |
+
"learning_rate": 9.402023919043239e-05,
|
| 465 |
+
"loss": 0.6315,
|
| 466 |
+
"step": 310
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.1409571444810731,
|
| 470 |
+
"eval_loss": 0.8461413383483887,
|
| 471 |
+
"eval_runtime": 20.7716,
|
| 472 |
+
"eval_samples_per_second": 2.407,
|
| 473 |
+
"eval_steps_per_second": 2.407,
|
| 474 |
+
"step": 310
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.14550414914175286,
|
| 478 |
+
"grad_norm": 7.699874401092529,
|
| 479 |
+
"learning_rate": 9.379024839006441e-05,
|
| 480 |
+
"loss": 0.6473,
|
| 481 |
+
"step": 320
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 0.14550414914175286,
|
| 485 |
+
"eval_loss": 0.8356756567955017,
|
| 486 |
+
"eval_runtime": 20.7971,
|
| 487 |
+
"eval_samples_per_second": 2.404,
|
| 488 |
+
"eval_steps_per_second": 2.404,
|
| 489 |
+
"step": 320
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.15005115380243264,
|
| 493 |
+
"grad_norm": 7.28955602645874,
|
| 494 |
+
"learning_rate": 9.356025758969642e-05,
|
| 495 |
+
"loss": 0.5936,
|
| 496 |
+
"step": 330
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 0.15005115380243264,
|
| 500 |
+
"eval_loss": 0.8357100486755371,
|
| 501 |
+
"eval_runtime": 20.7802,
|
| 502 |
+
"eval_samples_per_second": 2.406,
|
| 503 |
+
"eval_steps_per_second": 2.406,
|
| 504 |
+
"step": 330
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 0.15459815846311242,
|
| 508 |
+
"grad_norm": 4.673826217651367,
|
| 509 |
+
"learning_rate": 9.333026678932844e-05,
|
| 510 |
+
"loss": 0.5555,
|
| 511 |
+
"step": 340
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 0.15459815846311242,
|
| 515 |
+
"eval_loss": 0.8365601897239685,
|
| 516 |
+
"eval_runtime": 20.7353,
|
| 517 |
+
"eval_samples_per_second": 2.411,
|
| 518 |
+
"eval_steps_per_second": 2.411,
|
| 519 |
+
"step": 340
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.1591451631237922,
|
| 523 |
+
"grad_norm": 5.104877948760986,
|
| 524 |
+
"learning_rate": 9.310027598896044e-05,
|
| 525 |
+
"loss": 0.5903,
|
| 526 |
+
"step": 350
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 0.1591451631237922,
|
| 530 |
+
"eval_loss": 0.8396795392036438,
|
| 531 |
+
"eval_runtime": 20.7413,
|
| 532 |
+
"eval_samples_per_second": 2.411,
|
| 533 |
+
"eval_steps_per_second": 2.411,
|
| 534 |
+
"step": 350
|
| 535 |
}
|
| 536 |
],
|
| 537 |
"logging_steps": 10,
|
|
|
|
| 551 |
"attributes": {}
|
| 552 |
}
|
| 553 |
},
|
| 554 |
+
"total_flos": 2.854748142605779e+16,
|
| 555 |
"train_batch_size": 1,
|
| 556 |
"trial_name": null,
|
| 557 |
"trial_params": null
|