Training in progress, step 2350, 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 sha256:01be93de2ebd840ad64337e32da71e5c2df0baf73b62ee581b83caaad090be7a
|
| 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 sha256:82b669ac36a2669466d3993848b47850af5245db049e6b25b071606af4fbe63d
|
| 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:a6fac7e4cc7b362cdff2c65c6d54080aa1613c47816f7212a6a6cee4d1069bd0
|
| 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": 18.
|
| 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,
|
|
@@ -4220,6 +4220,24 @@
|
|
| 4220 |
"mean_token_accuracy": 0.658332034945488,
|
| 4221 |
"num_tokens": 8533890.0,
|
| 4222 |
"step": 2340
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4223 |
}
|
| 4224 |
],
|
| 4225 |
"logging_steps": 5,
|
|
@@ -4239,7 +4257,7 @@
|
|
| 4239 |
"attributes": {}
|
| 4240 |
}
|
| 4241 |
},
|
| 4242 |
-
"total_flos": 4.
|
| 4243 |
"train_batch_size": 4,
|
| 4244 |
"trial_name": null,
|
| 4245 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 18.076923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2350,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4220 |
"mean_token_accuracy": 0.658332034945488,
|
| 4221 |
"num_tokens": 8533890.0,
|
| 4222 |
"step": 2340
|
| 4223 |
+
},
|
| 4224 |
+
{
|
| 4225 |
+
"epoch": 18.03846153846154,
|
| 4226 |
+
"grad_norm": 0.0,
|
| 4227 |
+
"learning_rate": 3.828e-05,
|
| 4228 |
+
"loss": 1.7182,
|
| 4229 |
+
"mean_token_accuracy": 0.6543307691812515,
|
| 4230 |
+
"num_tokens": 8552119.0,
|
| 4231 |
+
"step": 2345
|
| 4232 |
+
},
|
| 4233 |
+
{
|
| 4234 |
+
"epoch": 18.076923076923077,
|
| 4235 |
+
"grad_norm": 0.0,
|
| 4236 |
+
"learning_rate": 3.8255e-05,
|
| 4237 |
+
"loss": 1.721,
|
| 4238 |
+
"mean_token_accuracy": 0.6576748192310333,
|
| 4239 |
+
"num_tokens": 8570610.0,
|
| 4240 |
+
"step": 2350
|
| 4241 |
}
|
| 4242 |
],
|
| 4243 |
"logging_steps": 5,
|
|
|
|
| 4257 |
"attributes": {}
|
| 4258 |
}
|
| 4259 |
},
|
| 4260 |
+
"total_flos": 4.343030414401536e+17,
|
| 4261 |
"train_batch_size": 4,
|
| 4262 |
"trial_name": null,
|
| 4263 |
"trial_params": null
|