Training in progress, step 3310, 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:b01f66f2117c7c31144a05259b8661747e9accfc1547dd7cc4a8fcd5d328825e
|
| 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 sha256:74d744832072a942dbf325a3d7b49c210ba623fa41792f49324614eef106050c
|
| 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:e49a2a0c8cd9e9eceae71f9f1a4bb064498f536f464469bd46b76bd0bf164cec
|
| 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": 25.
|
| 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,
|
|
@@ -5948,6 +5948,24 @@
|
|
| 5948 |
"mean_token_accuracy": 0.6442890495061875,
|
| 5949 |
"num_tokens": 12034074.0,
|
| 5950 |
"step": 3300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5951 |
}
|
| 5952 |
],
|
| 5953 |
"logging_steps": 5,
|
|
@@ -5967,7 +5985,7 @@
|
|
| 5967 |
"attributes": {}
|
| 5968 |
}
|
| 5969 |
},
|
| 5970 |
-
"total_flos": 6.
|
| 5971 |
"train_batch_size": 4,
|
| 5972 |
"trial_name": null,
|
| 5973 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 25.46153846153846,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3310,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5948 |
"mean_token_accuracy": 0.6442890495061875,
|
| 5949 |
"num_tokens": 12034074.0,
|
| 5950 |
"step": 3300
|
| 5951 |
+
},
|
| 5952 |
+
{
|
| 5953 |
+
"epoch": 25.423076923076923,
|
| 5954 |
+
"grad_norm": 0.0,
|
| 5955 |
+
"learning_rate": 3.348e-05,
|
| 5956 |
+
"loss": 1.7701,
|
| 5957 |
+
"mean_token_accuracy": 0.6484797149896622,
|
| 5958 |
+
"num_tokens": 12051813.0,
|
| 5959 |
+
"step": 3305
|
| 5960 |
+
},
|
| 5961 |
+
{
|
| 5962 |
+
"epoch": 25.46153846153846,
|
| 5963 |
+
"grad_norm": 0.0,
|
| 5964 |
+
"learning_rate": 3.3455000000000004e-05,
|
| 5965 |
+
"loss": 1.8468,
|
| 5966 |
+
"mean_token_accuracy": 0.632660773396492,
|
| 5967 |
+
"num_tokens": 12068538.0,
|
| 5968 |
+
"step": 3310
|
| 5969 |
}
|
| 5970 |
],
|
| 5971 |
"logging_steps": 5,
|
|
|
|
| 5985 |
"attributes": {}
|
| 5986 |
}
|
| 5987 |
},
|
| 5988 |
+
"total_flos": 6.114427730347622e+17,
|
| 5989 |
"train_batch_size": 4,
|
| 5990 |
"trial_name": null,
|
| 5991 |
"trial_params": null
|