Training in progress, step 6170, 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:ef04d3cc15d3f0189b4dc97a18739ceec48aeae64bb94fe0e579a8d90e17bb22
|
| 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:b14b4b1b3c0b7a9b4004ffc48df54d13a6c59971652d07102e7e05ec951d0e7a
|
| 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 sha256:977b2c4c45abe949c305779517fb56e2815af28cef7f6e2e49189d27cf8caf73
|
| 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": 47.
|
| 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,
|
|
@@ -11096,6 +11096,24 @@
|
|
| 11096 |
"mean_token_accuracy": 0.6357954889535904,
|
| 11097 |
"num_tokens": 22467696.0,
|
| 11098 |
"step": 6160
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11099 |
}
|
| 11100 |
],
|
| 11101 |
"logging_steps": 5,
|
|
@@ -11115,7 +11133,7 @@
|
|
| 11115 |
"attributes": {}
|
| 11116 |
}
|
| 11117 |
},
|
| 11118 |
-
"total_flos": 1.
|
| 11119 |
"train_batch_size": 4,
|
| 11120 |
"trial_name": null,
|
| 11121 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 47.46153846153846,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6170,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11096 |
"mean_token_accuracy": 0.6357954889535904,
|
| 11097 |
"num_tokens": 22467696.0,
|
| 11098 |
"step": 6160
|
| 11099 |
+
},
|
| 11100 |
+
{
|
| 11101 |
+
"epoch": 47.42307692307692,
|
| 11102 |
+
"grad_norm": 0.0,
|
| 11103 |
+
"learning_rate": 1.918e-05,
|
| 11104 |
+
"loss": 1.7551,
|
| 11105 |
+
"mean_token_accuracy": 0.6453001827001572,
|
| 11106 |
+
"num_tokens": 22486250.0,
|
| 11107 |
+
"step": 6165
|
| 11108 |
+
},
|
| 11109 |
+
{
|
| 11110 |
+
"epoch": 47.46153846153846,
|
| 11111 |
+
"grad_norm": 0.0,
|
| 11112 |
+
"learning_rate": 1.9155000000000002e-05,
|
| 11113 |
+
"loss": 1.7741,
|
| 11114 |
+
"mean_token_accuracy": 0.6439648687839508,
|
| 11115 |
+
"num_tokens": 22504172.0,
|
| 11116 |
+
"step": 6170
|
| 11117 |
}
|
| 11118 |
],
|
| 11119 |
"logging_steps": 5,
|
|
|
|
| 11133 |
"attributes": {}
|
| 11134 |
}
|
| 11135 |
},
|
| 11136 |
+
"total_flos": 1.1406050810339328e+18,
|
| 11137 |
"train_batch_size": 4,
|
| 11138 |
"trial_name": null,
|
| 11139 |
"trial_params": null
|