Training in progress, step 2880, 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:b89598440fee9b0cbde514db2e59240c629395795af3b30841585f61c5f727a3
|
| 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 sha256:359bc9bb1ff7a8d250dc55775c1a55f484f13c9e3d7c15cc75e56eff82e92e08
|
| 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:b53ef75edda82c1190df7e53071c88a6b3ceb226243b33bdae6118bdf91107a8
|
| 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": 22.
|
| 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,
|
|
@@ -5174,6 +5174,24 @@
|
|
| 5174 |
"mean_token_accuracy": 0.6492699027061463,
|
| 5175 |
"num_tokens": 10466020.0,
|
| 5176 |
"step": 2870
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5177 |
}
|
| 5178 |
],
|
| 5179 |
"logging_steps": 5,
|
|
@@ -5193,7 +5211,7 @@
|
|
| 5193 |
"attributes": {}
|
| 5194 |
}
|
| 5195 |
},
|
| 5196 |
-
"total_flos": 5.
|
| 5197 |
"train_batch_size": 4,
|
| 5198 |
"trial_name": null,
|
| 5199 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 22.153846153846153,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2880,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5174 |
"mean_token_accuracy": 0.6492699027061463,
|
| 5175 |
"num_tokens": 10466020.0,
|
| 5176 |
"step": 2870
|
| 5177 |
+
},
|
| 5178 |
+
{
|
| 5179 |
+
"epoch": 22.115384615384617,
|
| 5180 |
+
"grad_norm": 0.0,
|
| 5181 |
+
"learning_rate": 3.563e-05,
|
| 5182 |
+
"loss": 1.7669,
|
| 5183 |
+
"mean_token_accuracy": 0.6457598328590393,
|
| 5184 |
+
"num_tokens": 10483856.0,
|
| 5185 |
+
"step": 2875
|
| 5186 |
+
},
|
| 5187 |
+
{
|
| 5188 |
+
"epoch": 22.153846153846153,
|
| 5189 |
+
"grad_norm": 0.0,
|
| 5190 |
+
"learning_rate": 3.5605e-05,
|
| 5191 |
+
"loss": 1.6918,
|
| 5192 |
+
"mean_token_accuracy": 0.6608535885810852,
|
| 5193 |
+
"num_tokens": 10502391.0,
|
| 5194 |
+
"step": 2880
|
| 5195 |
}
|
| 5196 |
],
|
| 5197 |
"logging_steps": 5,
|
|
|
|
| 5211 |
"attributes": {}
|
| 5212 |
}
|
| 5213 |
},
|
| 5214 |
+
"total_flos": 5.3214179867836416e+17,
|
| 5215 |
"train_batch_size": 4,
|
| 5216 |
"trial_name": null,
|
| 5217 |
"trial_params": null
|