Training in progress, step 39, 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 83945296
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e34fa58de8d74f26fcaad3fceb0b0eb8ca3d390168887ba2db39f922b1fb2ff
|
3 |
size 83945296
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 43122580
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b05cec2adb0cd5684d91f388bab50378e2a4fd0f3253c749813de384cd85a0b2
|
3 |
size 43122580
|
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:d8f44d2d86b9b1930bd4e09c6d32e310e74530c2b9bb36d40d5b3060d71d8503
|
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 sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
|
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": 10,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -66,6 +66,28 @@
|
|
66 |
"learning_rate": 6.91341716182545e-05,
|
67 |
"loss": 4.8792,
|
68 |
"step": 25
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
69 |
}
|
70 |
],
|
71 |
"logging_steps": 5,
|
@@ -85,7 +107,7 @@
|
|
85 |
"attributes": {}
|
86 |
}
|
87 |
},
|
88 |
-
"total_flos":
|
89 |
"train_batch_size": 2,
|
90 |
"trial_name": null,
|
91 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0936374549819928,
|
5 |
"eval_steps": 10,
|
6 |
+
"global_step": 39,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
66 |
"learning_rate": 6.91341716182545e-05,
|
67 |
"loss": 4.8792,
|
68 |
"step": 25
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.07202881152460984,
|
72 |
+
"grad_norm": 8.490561485290527,
|
73 |
+
"learning_rate": 5e-05,
|
74 |
+
"loss": 5.1044,
|
75 |
+
"step": 30
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.07202881152460984,
|
79 |
+
"eval_loss": 1.2332581281661987,
|
80 |
+
"eval_runtime": 13.8173,
|
81 |
+
"eval_samples_per_second": 12.738,
|
82 |
+
"eval_steps_per_second": 6.369,
|
83 |
+
"step": 30
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 0.08403361344537816,
|
87 |
+
"grad_norm": 7.227184772491455,
|
88 |
+
"learning_rate": 3.086582838174551e-05,
|
89 |
+
"loss": 4.9676,
|
90 |
+
"step": 35
|
91 |
}
|
92 |
],
|
93 |
"logging_steps": 5,
|
|
|
107 |
"attributes": {}
|
108 |
}
|
109 |
},
|
110 |
+
"total_flos": 8675725406109696.0,
|
111 |
"train_batch_size": 2,
|
112 |
"trial_name": null,
|
113 |
"trial_params": null
|