Training in progress, step 9, 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 17425352
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:84495954457b772247356bd832294de5642b1452ac7076e4fca047ef16a87484
|
| 3 |
size 17425352
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 10251668
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e9508200d7c2a2ae3ff1d4e556ddc11da4912b619b2bcdb9a401c049b743a56
|
| 3 |
size 10251668
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97b21c7f33e6dd1250e43a1885dcf2862e9a21f89ea7c79b66b9571be9c48ccc
|
| 3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 3,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -65,6 +65,35 @@
|
|
| 65 |
"eval_samples_per_second": 19.675,
|
| 66 |
"eval_steps_per_second": 9.853,
|
| 67 |
"step": 6
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 68 |
}
|
| 69 |
],
|
| 70 |
"logging_steps": 1,
|
|
@@ -84,7 +113,7 @@
|
|
| 84 |
"attributes": {}
|
| 85 |
}
|
| 86 |
},
|
| 87 |
-
"total_flos":
|
| 88 |
"train_batch_size": 2,
|
| 89 |
"trial_name": null,
|
| 90 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.005989020129762102,
|
| 5 |
"eval_steps": 3,
|
| 6 |
+
"global_step": 9,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 65 |
"eval_samples_per_second": 19.675,
|
| 66 |
"eval_steps_per_second": 9.853,
|
| 67 |
"step": 6
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 0.004658126767592747,
|
| 71 |
+
"grad_norm": 0.08330302685499191,
|
| 72 |
+
"learning_rate": 0.00014,
|
| 73 |
+
"loss": 1.8142,
|
| 74 |
+
"step": 7
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.005323573448677425,
|
| 78 |
+
"grad_norm": 0.07740814238786697,
|
| 79 |
+
"learning_rate": 0.00016,
|
| 80 |
+
"loss": 1.4322,
|
| 81 |
+
"step": 8
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.005989020129762102,
|
| 85 |
+
"grad_norm": 0.09462728351354599,
|
| 86 |
+
"learning_rate": 0.00018,
|
| 87 |
+
"loss": 1.4801,
|
| 88 |
+
"step": 9
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.005989020129762102,
|
| 92 |
+
"eval_loss": 1.6890851259231567,
|
| 93 |
+
"eval_runtime": 31.3841,
|
| 94 |
+
"eval_samples_per_second": 20.169,
|
| 95 |
+
"eval_steps_per_second": 10.101,
|
| 96 |
+
"step": 9
|
| 97 |
}
|
| 98 |
],
|
| 99 |
"logging_steps": 1,
|
|
|
|
| 113 |
"attributes": {}
|
| 114 |
}
|
| 115 |
},
|
| 116 |
+
"total_flos": 109748488765440.0,
|
| 117 |
"train_batch_size": 2,
|
| 118 |
"trial_name": null,
|
| 119 |
"trial_params": null
|