Training in progress, step 600, 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:edb23a065363b999b7351670939909f19ffa25db1129895479711069d7e6d9eb
|
| 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:b4515f382ae0370bced13f221502c2cb3c7770b20d26d76fb6b91ee3f15808e8
|
| 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 sha256:422a01b2e5729fd7a217894d0fa557aa3503b06d372dc7f09045a3d3db5f81c1
|
| 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": 4.
|
| 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,
|
|
@@ -1070,6 +1070,24 @@
|
|
| 1070 |
"mean_token_accuracy": 0.6549283742904664,
|
| 1071 |
"num_tokens": 2151767.0,
|
| 1072 |
"step": 590
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1073 |
}
|
| 1074 |
],
|
| 1075 |
"logging_steps": 5,
|
|
@@ -1089,7 +1107,7 @@
|
|
| 1089 |
"attributes": {}
|
| 1090 |
}
|
| 1091 |
},
|
| 1092 |
-
"total_flos": 1.
|
| 1093 |
"train_batch_size": 4,
|
| 1094 |
"trial_name": null,
|
| 1095 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 4.615384615384615,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 600,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1070 |
"mean_token_accuracy": 0.6549283742904664,
|
| 1071 |
"num_tokens": 2151767.0,
|
| 1072 |
"step": 590
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 4.576923076923077,
|
| 1076 |
+
"grad_norm": 0.0,
|
| 1077 |
+
"learning_rate": 4.703e-05,
|
| 1078 |
+
"loss": 1.7624,
|
| 1079 |
+
"mean_token_accuracy": 0.6483795702457428,
|
| 1080 |
+
"num_tokens": 2169614.0,
|
| 1081 |
+
"step": 595
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 4.615384615384615,
|
| 1085 |
+
"grad_norm": 0.0,
|
| 1086 |
+
"learning_rate": 4.7005e-05,
|
| 1087 |
+
"loss": 1.7502,
|
| 1088 |
+
"mean_token_accuracy": 0.6509936511516571,
|
| 1089 |
+
"num_tokens": 2187439.0,
|
| 1090 |
+
"step": 600
|
| 1091 |
}
|
| 1092 |
],
|
| 1093 |
"logging_steps": 5,
|
|
|
|
| 1107 |
"attributes": {}
|
| 1108 |
}
|
| 1109 |
},
|
| 1110 |
+
"total_flos": 1.1082054023479296e+17,
|
| 1111 |
"train_batch_size": 4,
|
| 1112 |
"trial_name": null,
|
| 1113 |
"trial_params": null
|