Training in progress, step 2360, 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 sha256:67aa2be3a99a9c3773762bb08df38652159f49960e64da4a56d9b8f2362f88b7
|
| 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:dd39b61bdc0316bf75a31b54d8d5e4cde303b6d36e95ae29f8808bcd7d3a64cd
|
| 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 sha256:5793dc8a714a8c6670d825aca5525989cecedfaf04d3cc22ff40c02731ab5618
|
| 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,
|
|
@@ -4238,6 +4238,24 @@
|
|
| 4238 |
"mean_token_accuracy": 0.6576748192310333,
|
| 4239 |
"num_tokens": 8570610.0,
|
| 4240 |
"step": 2350
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4241 |
}
|
| 4242 |
],
|
| 4243 |
"logging_steps": 5,
|
|
@@ -4257,7 +4275,7 @@
|
|
| 4257 |
"attributes": {}
|
| 4258 |
}
|
| 4259 |
},
|
| 4260 |
-
"total_flos": 4.
|
| 4261 |
"train_batch_size": 4,
|
| 4262 |
"trial_name": null,
|
| 4263 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 18.153846153846153,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2360,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4238 |
"mean_token_accuracy": 0.6576748192310333,
|
| 4239 |
"num_tokens": 8570610.0,
|
| 4240 |
"step": 2350
|
| 4241 |
+
},
|
| 4242 |
+
{
|
| 4243 |
+
"epoch": 18.115384615384617,
|
| 4244 |
+
"grad_norm": 0.0,
|
| 4245 |
+
"learning_rate": 3.823e-05,
|
| 4246 |
+
"loss": 1.7423,
|
| 4247 |
+
"mean_token_accuracy": 0.6538129627704621,
|
| 4248 |
+
"num_tokens": 8588510.0,
|
| 4249 |
+
"step": 2355
|
| 4250 |
+
},
|
| 4251 |
+
{
|
| 4252 |
+
"epoch": 18.153846153846153,
|
| 4253 |
+
"grad_norm": 0.0,
|
| 4254 |
+
"learning_rate": 3.8205000000000004e-05,
|
| 4255 |
+
"loss": 1.7196,
|
| 4256 |
+
"mean_token_accuracy": 0.6549855172634125,
|
| 4257 |
+
"num_tokens": 8606513.0,
|
| 4258 |
+
"step": 2360
|
| 4259 |
}
|
| 4260 |
],
|
| 4261 |
"logging_steps": 5,
|
|
|
|
| 4275 |
"attributes": {}
|
| 4276 |
}
|
| 4277 |
},
|
| 4278 |
+
"total_flos": 4.3607041211695104e+17,
|
| 4279 |
"train_batch_size": 4,
|
| 4280 |
"trial_name": null,
|
| 4281 |
"trial_params": null
|