Training in progress, step 2280, 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 sha256:231a71fc264a9a745853731bfb8998f31ec9bfa0804144e02689e1c475d600e9
|
| 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 sha256:0e41dc2ce23d7147985bfb08ceae346fe91d553e7071dc41dab2e591d276790b
|
| 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 sha256:16d39565fafddcc394c964815124972a783d0966a733915f090811546186fd04
|
| 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": 17.
|
| 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,
|
|
@@ -4094,6 +4094,24 @@
|
|
| 4094 |
"mean_token_accuracy": 0.6438043415546417,
|
| 4095 |
"num_tokens": 8279321.0,
|
| 4096 |
"step": 2270
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4097 |
}
|
| 4098 |
],
|
| 4099 |
"logging_steps": 5,
|
|
@@ -4113,7 +4131,7 @@
|
|
| 4113 |
"attributes": {}
|
| 4114 |
}
|
| 4115 |
},
|
| 4116 |
-
"total_flos": 4.
|
| 4117 |
"train_batch_size": 4,
|
| 4118 |
"trial_name": null,
|
| 4119 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 17.53846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2280,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4094 |
"mean_token_accuracy": 0.6438043415546417,
|
| 4095 |
"num_tokens": 8279321.0,
|
| 4096 |
"step": 2270
|
| 4097 |
+
},
|
| 4098 |
+
{
|
| 4099 |
+
"epoch": 17.5,
|
| 4100 |
+
"grad_norm": 0.0,
|
| 4101 |
+
"learning_rate": 3.863e-05,
|
| 4102 |
+
"loss": 1.7198,
|
| 4103 |
+
"mean_token_accuracy": 0.6564956575632095,
|
| 4104 |
+
"num_tokens": 8298176.0,
|
| 4105 |
+
"step": 2275
|
| 4106 |
+
},
|
| 4107 |
+
{
|
| 4108 |
+
"epoch": 17.53846153846154,
|
| 4109 |
+
"grad_norm": 0.0,
|
| 4110 |
+
"learning_rate": 3.8605e-05,
|
| 4111 |
+
"loss": 1.7513,
|
| 4112 |
+
"mean_token_accuracy": 0.6444843232631683,
|
| 4113 |
+
"num_tokens": 8316630.0,
|
| 4114 |
+
"step": 2280
|
| 4115 |
}
|
| 4116 |
],
|
| 4117 |
"logging_steps": 5,
|
|
|
|
| 4131 |
"attributes": {}
|
| 4132 |
}
|
| 4133 |
},
|
| 4134 |
+
"total_flos": 4.214717810742067e+17,
|
| 4135 |
"train_batch_size": 4,
|
| 4136 |
"trial_name": null,
|
| 4137 |
"trial_params": null
|