Training in progress, step 5, 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:d00083665f391c20d599d53015ddafe1b05e46e52a2b962c7acae49d0ebe7f8f
|
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 sha256:7b14b1388af0284f1f37a5fc92476989b3b4a836f11a2d91d5532d3f2d263b81
|
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 sha256:21b5aab58187fa1ac46dd81962d006723fcefa76854b0df6079ac40be4238f82
|
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 sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
|
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,
|
@@ -51,6 +51,13 @@
|
|
51 |
"learning_rate": 4e-05,
|
52 |
"loss": 2.5524,
|
53 |
"step": 4
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
54 |
}
|
55 |
],
|
56 |
"logging_steps": 1,
|
@@ -65,12 +72,12 @@
|
|
65 |
"should_evaluate": false,
|
66 |
"should_log": false,
|
67 |
"should_save": true,
|
68 |
-
"should_training_stop":
|
69 |
},
|
70 |
"attributes": {}
|
71 |
}
|
72 |
},
|
73 |
-
"total_flos":
|
74 |
"train_batch_size": 1,
|
75 |
"trial_name": null,
|
76 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0005868157178590029,
|
5 |
"eval_steps": 3,
|
6 |
+
"global_step": 5,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
51 |
"learning_rate": 4e-05,
|
52 |
"loss": 2.5524,
|
53 |
"step": 4
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 0.0005868157178590029,
|
57 |
+
"grad_norm": 1.2470061779022217,
|
58 |
+
"learning_rate": 5e-05,
|
59 |
+
"loss": 2.2495,
|
60 |
+
"step": 5
|
61 |
}
|
62 |
],
|
63 |
"logging_steps": 1,
|
|
|
72 |
"should_evaluate": false,
|
73 |
"should_log": false,
|
74 |
"should_save": true,
|
75 |
+
"should_training_stop": true
|
76 |
},
|
77 |
"attributes": {}
|
78 |
}
|
79 |
},
|
80 |
+
"total_flos": 1872683801247744.0,
|
81 |
"train_batch_size": 1,
|
82 |
"trial_name": null,
|
83 |
"trial_params": null
|