Training in progress, step 24, 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 604317736
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0de1721e2f523127df97f2c06d4e321159a4f1ad57b5d79d9595230d7374f945
|
3 |
size 604317736
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 41119636
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:126ed599f450a0e8d1966807394c42c685518fe534eaafea64bd9f775f3e0261
|
3 |
size 41119636
|
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 sha256:3f7fd14fcb32c3b176408d2e13cd1c94c1c766bd99cbc3b9a0b01659b2c1fb2b
|
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:b9fbbdb6036d2372f81987526c35ebf7be4064ed59a37e6c1ea765cbfb6cc373
|
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": 6,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -52,6 +52,29 @@
|
|
52 |
"learning_rate": 8.535533905932738e-05,
|
53 |
"loss": 0.0289,
|
54 |
"step": 15
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
55 |
}
|
56 |
],
|
57 |
"logging_steps": 5,
|
@@ -71,7 +94,7 @@
|
|
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": 0.8067226890756303,
|
5 |
"eval_steps": 6,
|
6 |
+
"global_step": 24,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
52 |
"learning_rate": 8.535533905932738e-05,
|
53 |
"loss": 0.0289,
|
54 |
"step": 15
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.6050420168067226,
|
58 |
+
"eval_loss": 0.001077459310181439,
|
59 |
+
"eval_runtime": 1.0113,
|
60 |
+
"eval_samples_per_second": 12.854,
|
61 |
+
"eval_steps_per_second": 6.921,
|
62 |
+
"step": 18
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.6722689075630253,
|
66 |
+
"grad_norm": 0.04066217690706253,
|
67 |
+
"learning_rate": 5e-05,
|
68 |
+
"loss": 0.0018,
|
69 |
+
"step": 20
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.8067226890756303,
|
73 |
+
"eval_loss": 0.0004625740693882108,
|
74 |
+
"eval_runtime": 0.9911,
|
75 |
+
"eval_samples_per_second": 13.117,
|
76 |
+
"eval_steps_per_second": 7.063,
|
77 |
+
"step": 24
|
78 |
}
|
79 |
],
|
80 |
"logging_steps": 5,
|
|
|
94 |
"attributes": {}
|
95 |
}
|
96 |
},
|
97 |
+
"total_flos": 3908961942110208.0,
|
98 |
"train_batch_size": 2,
|
99 |
"trial_name": null,
|
100 |
"trial_params": null
|