Training in progress, step 5130, 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:e72f34f5872c7bd080b0189f0466967d840e5c7a70babb8b7bcf55cdaa0d3042
|
| 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 sha256:4c4e878a0d6b00ac169edc7bf3230e260e126bcfbd6a34bcc4699062664f82f9
|
| 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 sha256:0b5565d413803b5d934179a9c297f3c359906347ccc5d500b2d7c9a03f37e62a
|
| 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": 39.
|
| 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,
|
|
@@ -9224,6 +9224,24 @@
|
|
| 9224 |
"mean_token_accuracy": 0.6576891779899597,
|
| 9225 |
"num_tokens": 18672794.0,
|
| 9226 |
"step": 5120
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9227 |
}
|
| 9228 |
],
|
| 9229 |
"logging_steps": 5,
|
|
@@ -9243,7 +9261,7 @@
|
|
| 9243 |
"attributes": {}
|
| 9244 |
}
|
| 9245 |
},
|
| 9246 |
-
"total_flos": 9.
|
| 9247 |
"train_batch_size": 4,
|
| 9248 |
"trial_name": null,
|
| 9249 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 39.46153846153846,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5130,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 9224 |
"mean_token_accuracy": 0.6576891779899597,
|
| 9225 |
"num_tokens": 18672794.0,
|
| 9226 |
"step": 5120
|
| 9227 |
+
},
|
| 9228 |
+
{
|
| 9229 |
+
"epoch": 39.42307692307692,
|
| 9230 |
+
"grad_norm": 0.0,
|
| 9231 |
+
"learning_rate": 2.438e-05,
|
| 9232 |
+
"loss": 1.671,
|
| 9233 |
+
"mean_token_accuracy": 0.6607532262802124,
|
| 9234 |
+
"num_tokens": 18692648.0,
|
| 9235 |
+
"step": 5125
|
| 9236 |
+
},
|
| 9237 |
+
{
|
| 9238 |
+
"epoch": 39.46153846153846,
|
| 9239 |
+
"grad_norm": 0.0,
|
| 9240 |
+
"learning_rate": 2.4355e-05,
|
| 9241 |
+
"loss": 1.7717,
|
| 9242 |
+
"mean_token_accuracy": 0.6461830377578736,
|
| 9243 |
+
"num_tokens": 18710735.0,
|
| 9244 |
+
"step": 5130
|
| 9245 |
}
|
| 9246 |
],
|
| 9247 |
"logging_steps": 5,
|
|
|
|
| 9261 |
"attributes": {}
|
| 9262 |
}
|
| 9263 |
},
|
| 9264 |
+
"total_flos": 9.480790150520832e+17,
|
| 9265 |
"train_batch_size": 4,
|
| 9266 |
"trial_name": null,
|
| 9267 |
"trial_params": null
|