Training in progress, step 3960, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1657
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7e40915c4ee02d394a5954e7c93980383be220f898c521dde30c4e8091a1dae
|
| 3 |
size 1657
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14709
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66227a59276ef116311254607610d278a3b42f23893b1780e808c2d18462d8b9
|
| 3 |
size 14709
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1dc0d36a9a3d384fe430dd99ae831ddd2f72df5c4182cae7318fb33b05c84a90
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 30.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -7118,6 +7118,24 @@
|
|
| 7118 |
"mean_token_accuracy": 0.6552271574735642,
|
| 7119 |
"num_tokens": 14406379.0,
|
| 7120 |
"step": 3950
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7121 |
}
|
| 7122 |
],
|
| 7123 |
"logging_steps": 5,
|
|
@@ -7137,7 +7155,7 @@
|
|
| 7137 |
"attributes": {}
|
| 7138 |
}
|
| 7139 |
},
|
| 7140 |
-
"total_flos": 7.
|
| 7141 |
"train_batch_size": 4,
|
| 7142 |
"trial_name": null,
|
| 7143 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 30.46153846153846,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3960,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7118 |
"mean_token_accuracy": 0.6552271574735642,
|
| 7119 |
"num_tokens": 14406379.0,
|
| 7120 |
"step": 3950
|
| 7121 |
+
},
|
| 7122 |
+
{
|
| 7123 |
+
"epoch": 30.423076923076923,
|
| 7124 |
+
"grad_norm": 0.0,
|
| 7125 |
+
"learning_rate": 3.0230000000000004e-05,
|
| 7126 |
+
"loss": 1.7319,
|
| 7127 |
+
"mean_token_accuracy": 0.6521833807229995,
|
| 7128 |
+
"num_tokens": 14424792.0,
|
| 7129 |
+
"step": 3955
|
| 7130 |
+
},
|
| 7131 |
+
{
|
| 7132 |
+
"epoch": 30.46153846153846,
|
| 7133 |
+
"grad_norm": 0.0,
|
| 7134 |
+
"learning_rate": 3.0205e-05,
|
| 7135 |
+
"loss": 1.68,
|
| 7136 |
+
"mean_token_accuracy": 0.6599725693464279,
|
| 7137 |
+
"num_tokens": 14443837.0,
|
| 7138 |
+
"step": 3960
|
| 7139 |
}
|
| 7140 |
],
|
| 7141 |
"logging_steps": 5,
|
|
|
|
| 7155 |
"attributes": {}
|
| 7156 |
}
|
| 7157 |
},
|
| 7158 |
+
"total_flos": 7.320893607346176e+17,
|
| 7159 |
"train_batch_size": 4,
|
| 7160 |
"trial_name": null,
|
| 7161 |
"trial_params": null
|