Training in progress, step 3860, 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 sha256:451692c37bb53e7a8e7bc350d8d8a8734e108982d3fe8d000d88869c195dc6ee
|
| 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 sha256:7ebadfc6c310690ebfe9fabf940d2c58d5d52379f967b84f2b1f8512f5c9cb7d
|
| 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 sha256:2ac253129496491aaf94040635cfd5f560ba6176e90ad6c16a1e5cc7af60cd56
|
| 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": 29.
|
| 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,
|
|
@@ -6938,6 +6938,24 @@
|
|
| 6938 |
"mean_token_accuracy": 0.6485314697027207,
|
| 6939 |
"num_tokens": 14041204.0,
|
| 6940 |
"step": 3850
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6941 |
}
|
| 6942 |
],
|
| 6943 |
"logging_steps": 5,
|
|
@@ -6957,7 +6975,7 @@
|
|
| 6957 |
"attributes": {}
|
| 6958 |
}
|
| 6959 |
},
|
| 6960 |
-
"total_flos": 7.
|
| 6961 |
"train_batch_size": 4,
|
| 6962 |
"trial_name": null,
|
| 6963 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 29.692307692307693,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3860,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6938 |
"mean_token_accuracy": 0.6485314697027207,
|
| 6939 |
"num_tokens": 14041204.0,
|
| 6940 |
"step": 3850
|
| 6941 |
+
},
|
| 6942 |
+
{
|
| 6943 |
+
"epoch": 29.653846153846153,
|
| 6944 |
+
"grad_norm": 0.0,
|
| 6945 |
+
"learning_rate": 3.0730000000000006e-05,
|
| 6946 |
+
"loss": 1.7689,
|
| 6947 |
+
"mean_token_accuracy": 0.6438219338655472,
|
| 6948 |
+
"num_tokens": 14058902.0,
|
| 6949 |
+
"step": 3855
|
| 6950 |
+
},
|
| 6951 |
+
{
|
| 6952 |
+
"epoch": 29.692307692307693,
|
| 6953 |
+
"grad_norm": 0.0,
|
| 6954 |
+
"learning_rate": 3.0705e-05,
|
| 6955 |
+
"loss": 1.7326,
|
| 6956 |
+
"mean_token_accuracy": 0.6497067272663116,
|
| 6957 |
+
"num_tokens": 14077655.0,
|
| 6958 |
+
"step": 3860
|
| 6959 |
}
|
| 6960 |
],
|
| 6961 |
"logging_steps": 5,
|
|
|
|
| 6975 |
"attributes": {}
|
| 6976 |
}
|
| 6977 |
},
|
| 6978 |
+
"total_flos": 7.133934338231501e+17,
|
| 6979 |
"train_batch_size": 4,
|
| 6980 |
"trial_name": null,
|
| 6981 |
"trial_params": null
|