Training in progress, epoch 2, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2682482800
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8aa16a28bc536e630d504ee7ef7d8eb4957ee245ed7326e8127cbb18529dfead
|
| 3 |
size 2682482800
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5365108834
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:635ae1e9bedffca1d254b32da5d69cee31ec196fb65247c6b4baca9342ce9f50
|
| 3 |
size 5365108834
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15006
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:655729fdbb2449b8afc2d1e4cb11a0fab0990005292396cdecfbe97903ecb770
|
| 3 |
size 15006
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1788b20b604031eae3a2120fb28a2609fbbb263157aa49683a8b4c9ebd48c5d
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 50,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -82,6 +82,81 @@
|
|
| 82 |
"eval_samples_per_second": 41.533,
|
| 83 |
"eval_steps_per_second": 20.766,
|
| 84 |
"step": 250
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 85 |
}
|
| 86 |
],
|
| 87 |
"logging_steps": 50,
|
|
@@ -101,7 +176,7 @@
|
|
| 101 |
"attributes": {}
|
| 102 |
}
|
| 103 |
},
|
| 104 |
-
"total_flos":
|
| 105 |
"train_batch_size": 2,
|
| 106 |
"trial_name": null,
|
| 107 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
"eval_steps": 50,
|
| 6 |
+
"global_step": 546,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 82 |
"eval_samples_per_second": 41.533,
|
| 83 |
"eval_steps_per_second": 20.766,
|
| 84 |
"step": 250
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 1.0992533026995979,
|
| 88 |
+
"grad_norm": 54.570987701416016,
|
| 89 |
+
"learning_rate": 8.897058823529412e-05,
|
| 90 |
+
"loss": 1.1632,
|
| 91 |
+
"step": 300
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 1.0992533026995979,
|
| 95 |
+
"eval_loss": 1.2854100465774536,
|
| 96 |
+
"eval_runtime": 116.058,
|
| 97 |
+
"eval_samples_per_second": 41.583,
|
| 98 |
+
"eval_steps_per_second": 20.791,
|
| 99 |
+
"step": 300
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 1.2830557151062607,
|
| 103 |
+
"grad_norm": 62.69035720825195,
|
| 104 |
+
"learning_rate": 8.713235294117648e-05,
|
| 105 |
+
"loss": 1.1598,
|
| 106 |
+
"step": 350
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 1.2830557151062607,
|
| 110 |
+
"eval_loss": 1.2804261445999146,
|
| 111 |
+
"eval_runtime": 116.1289,
|
| 112 |
+
"eval_samples_per_second": 41.557,
|
| 113 |
+
"eval_steps_per_second": 20.779,
|
| 114 |
+
"step": 350
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.4668581275129235,
|
| 118 |
+
"grad_norm": 66.37086486816406,
|
| 119 |
+
"learning_rate": 8.529411764705883e-05,
|
| 120 |
+
"loss": 1.1419,
|
| 121 |
+
"step": 400
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.4668581275129235,
|
| 125 |
+
"eval_loss": 1.272080898284912,
|
| 126 |
+
"eval_runtime": 116.1097,
|
| 127 |
+
"eval_samples_per_second": 41.564,
|
| 128 |
+
"eval_steps_per_second": 20.782,
|
| 129 |
+
"step": 400
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 1.6506605399195864,
|
| 133 |
+
"grad_norm": 55.69127655029297,
|
| 134 |
+
"learning_rate": 8.345588235294118e-05,
|
| 135 |
+
"loss": 1.1256,
|
| 136 |
+
"step": 450
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 1.6506605399195864,
|
| 140 |
+
"eval_loss": 1.2628560066223145,
|
| 141 |
+
"eval_runtime": 116.0668,
|
| 142 |
+
"eval_samples_per_second": 41.58,
|
| 143 |
+
"eval_steps_per_second": 20.79,
|
| 144 |
+
"step": 450
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.8344629523262492,
|
| 148 |
+
"grad_norm": 84.45687103271484,
|
| 149 |
+
"learning_rate": 8.161764705882353e-05,
|
| 150 |
+
"loss": 1.1115,
|
| 151 |
+
"step": 500
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.8344629523262492,
|
| 155 |
+
"eval_loss": 1.2613238096237183,
|
| 156 |
+
"eval_runtime": 116.2349,
|
| 157 |
+
"eval_samples_per_second": 41.519,
|
| 158 |
+
"eval_steps_per_second": 20.76,
|
| 159 |
+
"step": 500
|
| 160 |
}
|
| 161 |
],
|
| 162 |
"logging_steps": 50,
|
|
|
|
| 176 |
"attributes": {}
|
| 177 |
}
|
| 178 |
},
|
| 179 |
+
"total_flos": 1.4029905594626867e+17,
|
| 180 |
"train_batch_size": 2,
|
| 181 |
"trial_name": null,
|
| 182 |
"trial_params": null
|