Training in progress, step 4490, 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:be27e24cf7a194824eb98ecdd8982abb9c5dc39c4568111617df28134370c056
|
| 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 sha256:5c333787eec39d38aae97e51731e36c7b179c768c4586b8596773b4d0d6e5e8d
|
| 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:cf92ce3a15cae182ec2db608eb5f8c895956a6519cad69fc1dac74d275d01825
|
| 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": 34.
|
| 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,
|
|
@@ -8072,6 +8072,24 @@
|
|
| 8072 |
"mean_token_accuracy": 0.6563991248607636,
|
| 8073 |
"num_tokens": 16338805.0,
|
| 8074 |
"step": 4480
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8075 |
}
|
| 8076 |
],
|
| 8077 |
"logging_steps": 5,
|
|
@@ -8091,7 +8109,7 @@
|
|
| 8091 |
"attributes": {}
|
| 8092 |
}
|
| 8093 |
},
|
| 8094 |
-
"total_flos": 8.
|
| 8095 |
"train_batch_size": 4,
|
| 8096 |
"trial_name": null,
|
| 8097 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 34.53846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4490,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8072 |
"mean_token_accuracy": 0.6563991248607636,
|
| 8073 |
"num_tokens": 16338805.0,
|
| 8074 |
"step": 4480
|
| 8075 |
+
},
|
| 8076 |
+
{
|
| 8077 |
+
"epoch": 34.5,
|
| 8078 |
+
"grad_norm": 0.0,
|
| 8079 |
+
"learning_rate": 2.758e-05,
|
| 8080 |
+
"loss": 1.718,
|
| 8081 |
+
"mean_token_accuracy": 0.6518977075815201,
|
| 8082 |
+
"num_tokens": 16357675.0,
|
| 8083 |
+
"step": 4485
|
| 8084 |
+
},
|
| 8085 |
+
{
|
| 8086 |
+
"epoch": 34.53846153846154,
|
| 8087 |
+
"grad_norm": 0.0,
|
| 8088 |
+
"learning_rate": 2.7555000000000003e-05,
|
| 8089 |
+
"loss": 1.7261,
|
| 8090 |
+
"mean_token_accuracy": 0.6472561746835709,
|
| 8091 |
+
"num_tokens": 16376357.0,
|
| 8092 |
+
"step": 4490
|
| 8093 |
}
|
| 8094 |
],
|
| 8095 |
"logging_steps": 5,
|
|
|
|
| 8109 |
"attributes": {}
|
| 8110 |
}
|
| 8111 |
},
|
| 8112 |
+
"total_flos": 8.299970281222963e+17,
|
| 8113 |
"train_batch_size": 4,
|
| 8114 |
"trial_name": null,
|
| 8115 |
"trial_params": null
|