Training in progress, step 20, 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 39428606
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd874b11027d81450d3c8139a4c08c0666835afc6022318dfa6012d6ebda8ef2
|
| 3 |
size 39428606
|
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:e8a08161a62603d61d03a15b8540b57ba870af500e3a9c7784cab02da4f04080
|
| 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:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
|
| 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": 5,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -52,6 +52,43 @@
|
|
| 52 |
"eval_samples_per_second": 30.111,
|
| 53 |
"eval_steps_per_second": 15.056,
|
| 54 |
"step": 10
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
}
|
| 56 |
],
|
| 57 |
"logging_steps": 3,
|
|
@@ -71,7 +108,7 @@
|
|
| 71 |
"attributes": {}
|
| 72 |
}
|
| 73 |
},
|
| 74 |
-
"total_flos":
|
| 75 |
"train_batch_size": 2,
|
| 76 |
"trial_name": null,
|
| 77 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.05689900426742532,
|
| 5 |
"eval_steps": 5,
|
| 6 |
+
"global_step": 20,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 52 |
"eval_samples_per_second": 30.111,
|
| 53 |
"eval_steps_per_second": 15.056,
|
| 54 |
"step": 10
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.034139402560455195,
|
| 58 |
+
"grad_norm": NaN,
|
| 59 |
+
"learning_rate": 0.00019510565162951537,
|
| 60 |
+
"loss": 0.0,
|
| 61 |
+
"step": 12
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.04267425320056899,
|
| 65 |
+
"grad_norm": NaN,
|
| 66 |
+
"learning_rate": 0.00017071067811865476,
|
| 67 |
+
"loss": 0.0,
|
| 68 |
+
"step": 15
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.04267425320056899,
|
| 72 |
+
"eval_loss": NaN,
|
| 73 |
+
"eval_runtime": 4.9092,
|
| 74 |
+
"eval_samples_per_second": 30.148,
|
| 75 |
+
"eval_steps_per_second": 15.074,
|
| 76 |
+
"step": 15
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.051209103840682786,
|
| 80 |
+
"grad_norm": NaN,
|
| 81 |
+
"learning_rate": 0.00013090169943749476,
|
| 82 |
+
"loss": 0.0,
|
| 83 |
+
"step": 18
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.05689900426742532,
|
| 87 |
+
"eval_loss": NaN,
|
| 88 |
+
"eval_runtime": 4.9157,
|
| 89 |
+
"eval_samples_per_second": 30.107,
|
| 90 |
+
"eval_steps_per_second": 15.054,
|
| 91 |
+
"step": 20
|
| 92 |
}
|
| 93 |
],
|
| 94 |
"logging_steps": 3,
|
|
|
|
| 108 |
"attributes": {}
|
| 109 |
}
|
| 110 |
},
|
| 111 |
+
"total_flos": 148790292774912.0,
|
| 112 |
"train_batch_size": 2,
|
| 113 |
"trial_name": null,
|
| 114 |
"trial_params": null
|