Training in progress, step 3000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 272123144
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f6aef3a65b706883648a40261c469821b28ad715e937813acd70959ef272f12
|
3 |
size 272123144
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 544259743
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:754050cd8531a1ec4be7c92439fadfa8bb9b0a1187abc0ab8979a2df096fbe8a
|
3 |
size 544259743
|
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 sha256:8d138cfe3a4adf21f048848ee35837c9a757a0a3616ff7adbb45b69aac247435
|
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 1000
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74ace5f16e09466618cf956d695538d60bba6bf21c0003f9e08e546fc6acbe93
|
3 |
size 1000
|
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": 1000,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -53,6 +53,29 @@
|
|
53 |
"eval_samples_per_second": 25.237,
|
54 |
"eval_steps_per_second": 0.535,
|
55 |
"step": 2000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
56 |
}
|
57 |
],
|
58 |
"logging_steps": 500,
|
@@ -72,7 +95,7 @@
|
|
72 |
"attributes": {}
|
73 |
}
|
74 |
},
|
75 |
-
"total_flos":
|
76 |
"train_batch_size": 24,
|
77 |
"trial_name": null,
|
78 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.7932310946589106,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 3000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
53 |
"eval_samples_per_second": 25.237,
|
54 |
"eval_steps_per_second": 0.535,
|
55 |
"step": 2000
|
56 |
+
},
|
57 |
+
{
|
58 |
+
"epoch": 0.6610259122157589,
|
59 |
+
"grad_norm": 1.4154396057128906,
|
60 |
+
"learning_rate": 8.206313191070773e-05,
|
61 |
+
"loss": 2.686,
|
62 |
+
"step": 2500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.7932310946589106,
|
66 |
+
"grad_norm": 1.821349024772644,
|
67 |
+
"learning_rate": 7.742312671390191e-05,
|
68 |
+
"loss": 2.607,
|
69 |
+
"step": 3000
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.7932310946589106,
|
73 |
+
"eval_accuracy": 0.5497897240925214,
|
74 |
+
"eval_loss": 2.657219886779785,
|
75 |
+
"eval_runtime": 73.4297,
|
76 |
+
"eval_samples_per_second": 25.058,
|
77 |
+
"eval_steps_per_second": 0.531,
|
78 |
+
"step": 3000
|
79 |
}
|
80 |
],
|
81 |
"logging_steps": 500,
|
|
|
95 |
"attributes": {}
|
96 |
}
|
97 |
},
|
98 |
+
"total_flos": 3.8445502169088e+16,
|
99 |
"train_batch_size": 24,
|
100 |
"trial_name": null,
|
101 |
"trial_params": null
|