Training in progress, step 4120, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 70430032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:39809768485ed7213e828aa1117fd3373192ee5e1f52a62dbc39b3e8fa1c7689
|
| 3 |
size 70430032
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 141058579
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0cec767c800e79c2547e666d75f382fe2a0e9abfc0a25112d17400a6e617b7d1
|
| 3 |
size 141058579
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ace53224d1b1577125a09e63208f2a3f1330c86b6aaaeb0e29e16558f332ddf3
|
| 3 |
size 14645
|
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:a6aeb1f52232f9bd405c486e9d1290975d5ffe513e4aeabd2f1d6ee03a1a7d41
|
| 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": 0.
|
| 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,
|
|
@@ -4128,6 +4128,16 @@
|
|
| 4128 |
"mean_token_accuracy": 0.7953767567873001,
|
| 4129 |
"num_tokens": 19155980.0,
|
| 4130 |
"step": 4110
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4131 |
}
|
| 4132 |
],
|
| 4133 |
"logging_steps": 10,
|
|
@@ -4147,7 +4157,7 @@
|
|
| 4147 |
"attributes": {}
|
| 4148 |
}
|
| 4149 |
},
|
| 4150 |
-
"total_flos": 9.
|
| 4151 |
"train_batch_size": 4,
|
| 4152 |
"trial_name": null,
|
| 4153 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.8789333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4120,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4128 |
"mean_token_accuracy": 0.7953767567873001,
|
| 4129 |
"num_tokens": 19155980.0,
|
| 4130 |
"step": 4110
|
| 4131 |
+
},
|
| 4132 |
+
{
|
| 4133 |
+
"entropy": 1.0650635436177254,
|
| 4134 |
+
"epoch": 0.8789333333333333,
|
| 4135 |
+
"grad_norm": 0.22809672355651855,
|
| 4136 |
+
"learning_rate": 6.23157722113219e-05,
|
| 4137 |
+
"loss": 1.208934211730957,
|
| 4138 |
+
"mean_token_accuracy": 0.7424666874110699,
|
| 4139 |
+
"num_tokens": 19206121.0,
|
| 4140 |
+
"step": 4120
|
| 4141 |
}
|
| 4142 |
],
|
| 4143 |
"logging_steps": 10,
|
|
|
|
| 4157 |
"attributes": {}
|
| 4158 |
}
|
| 4159 |
},
|
| 4160 |
+
"total_flos": 9.08747825015808e+16,
|
| 4161 |
"train_batch_size": 4,
|
| 4162 |
"trial_name": null,
|
| 4163 |
"trial_params": null
|