Training in progress, step 34, 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:b49200427e73a3bc3abff5b78ed757a13a25a3209083b694551b70fc897db305
|
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 sha256:6d8a46ad28492fa3a3dac917306bfe6321f479df576296982d15ae5872fc4f49
|
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 sha256:75cd7a9059f676bac12f4d36b37f2c0d98ddcad78e7f3f7fcee4fb71208e9876
|
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 sha256:1fe247b8abd9f098bbbafb55011dbe010f2fe145118845b911d1500aa9422fe0
|
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":
|
5 |
"eval_steps": 7,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -53,6 +53,21 @@
|
|
53 |
"eval_samples_per_second": 19.017,
|
54 |
"eval_steps_per_second": 2.44,
|
55 |
"step": 21
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
56 |
}
|
57 |
],
|
58 |
"logging_steps": 10,
|
@@ -67,12 +82,12 @@
|
|
67 |
"should_evaluate": false,
|
68 |
"should_log": false,
|
69 |
"should_save": true,
|
70 |
-
"should_training_stop":
|
71 |
},
|
72 |
"attributes": {}
|
73 |
}
|
74 |
},
|
75 |
-
"total_flos":
|
76 |
"train_batch_size": 8,
|
77 |
"trial_name": null,
|
78 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0205607476635514,
|
5 |
"eval_steps": 7,
|
6 |
+
"global_step": 34,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
53 |
"eval_samples_per_second": 19.017,
|
54 |
"eval_steps_per_second": 2.44,
|
55 |
"step": 21
|
56 |
+
},
|
57 |
+
{
|
58 |
+
"epoch": 0.8373831775700935,
|
59 |
+
"eval_loss": 3.368011675775051e-06,
|
60 |
+
"eval_runtime": 11.9911,
|
61 |
+
"eval_samples_per_second": 18.847,
|
62 |
+
"eval_steps_per_second": 2.418,
|
63 |
+
"step": 28
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.897196261682243,
|
67 |
+
"grad_norm": 0.006284361705183983,
|
68 |
+
"learning_rate": 3.8060233744356633e-06,
|
69 |
+
"loss": 0.0001,
|
70 |
+
"step": 30
|
71 |
}
|
72 |
],
|
73 |
"logging_steps": 10,
|
|
|
82 |
"should_evaluate": false,
|
83 |
"should_log": false,
|
84 |
"should_save": true,
|
85 |
+
"should_training_stop": true
|
86 |
},
|
87 |
"attributes": {}
|
88 |
}
|
89 |
},
|
90 |
+
"total_flos": 9.53452363555799e+16,
|
91 |
"train_batch_size": 8,
|
92 |
"trial_name": null,
|
93 |
"trial_params": null
|