Training in progress, step 2800, 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:b5bc02c93e02a9ec469787c7330f97cb41231b4e4034abd3a4a1abcacfb4d91f
|
| 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 sha256:596484df5cbb21d1f7bf1f4589268ffd54fc59880b7fa17b7e3bf2d54bc6e1f6
|
| 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 sha256:9cd4e8ade335df7436eddcb12bf5775bf7fc9ae20e235d3193bcd94d16ced960
|
| 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": 21.
|
| 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,
|
|
@@ -5030,6 +5030,24 @@
|
|
| 5030 |
"mean_token_accuracy": 0.6373539805412293,
|
| 5031 |
"num_tokens": 10173181.0,
|
| 5032 |
"step": 2790
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5033 |
}
|
| 5034 |
],
|
| 5035 |
"logging_steps": 5,
|
|
@@ -5049,7 +5067,7 @@
|
|
| 5049 |
"attributes": {}
|
| 5050 |
}
|
| 5051 |
},
|
| 5052 |
-
"total_flos": 5.
|
| 5053 |
"train_batch_size": 4,
|
| 5054 |
"trial_name": null,
|
| 5055 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 21.53846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2800,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5030 |
"mean_token_accuracy": 0.6373539805412293,
|
| 5031 |
"num_tokens": 10173181.0,
|
| 5032 |
"step": 2790
|
| 5033 |
+
},
|
| 5034 |
+
{
|
| 5035 |
+
"epoch": 21.5,
|
| 5036 |
+
"grad_norm": 0.0,
|
| 5037 |
+
"learning_rate": 3.6030000000000006e-05,
|
| 5038 |
+
"loss": 1.7508,
|
| 5039 |
+
"mean_token_accuracy": 0.6406475752592087,
|
| 5040 |
+
"num_tokens": 10191767.0,
|
| 5041 |
+
"step": 2795
|
| 5042 |
+
},
|
| 5043 |
+
{
|
| 5044 |
+
"epoch": 21.53846153846154,
|
| 5045 |
+
"grad_norm": 0.0,
|
| 5046 |
+
"learning_rate": 3.6005e-05,
|
| 5047 |
+
"loss": 1.7051,
|
| 5048 |
+
"mean_token_accuracy": 0.6602169930934906,
|
| 5049 |
+
"num_tokens": 10210631.0,
|
| 5050 |
+
"step": 2800
|
| 5051 |
}
|
| 5052 |
],
|
| 5053 |
"logging_steps": 5,
|
|
|
|
| 5067 |
"attributes": {}
|
| 5068 |
}
|
| 5069 |
},
|
| 5070 |
+
"total_flos": 5.173202417142989e+17,
|
| 5071 |
"train_batch_size": 4,
|
| 5072 |
"trial_name": null,
|
| 5073 |
"trial_params": null
|