Training in progress, step 6, 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 767856
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d5321f96fff7dc277f6021cfba941e0f2367ebbf677ce9310414e036cb8c9a84
|
3 |
size 767856
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1003002
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:14ee3b6e2c337ec21fa9ac0d302626cdd02b11a41d3bd1b4f4c475b75f127484
|
3 |
size 1003002
|
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:ae596888a63c03586377673bda3da0862fda255f512ebfa49851277059dd39e1
|
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 sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
|
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,
|
@@ -44,6 +44,35 @@
|
|
44 |
"eval_samples_per_second": 36.876,
|
45 |
"eval_steps_per_second": 18.848,
|
46 |
"step": 3
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
47 |
}
|
48 |
],
|
49 |
"logging_steps": 1,
|
@@ -63,7 +92,7 @@
|
|
63 |
"attributes": {}
|
64 |
}
|
65 |
},
|
66 |
-
"total_flos":
|
67 |
"train_batch_size": 2,
|
68 |
"trial_name": null,
|
69 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.056074766355140186,
|
5 |
"eval_steps": 3,
|
6 |
+
"global_step": 6,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
44 |
"eval_samples_per_second": 36.876,
|
45 |
"eval_steps_per_second": 18.848,
|
46 |
"step": 3
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 0.037383177570093455,
|
50 |
+
"grad_norm": 11.376309394836426,
|
51 |
+
"learning_rate": 8e-05,
|
52 |
+
"loss": 7.6639,
|
53 |
+
"step": 4
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 0.04672897196261682,
|
57 |
+
"grad_norm": 11.1522855758667,
|
58 |
+
"learning_rate": 0.0001,
|
59 |
+
"loss": 7.3003,
|
60 |
+
"step": 5
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 0.056074766355140186,
|
64 |
+
"grad_norm": 8.25159740447998,
|
65 |
+
"learning_rate": 0.00012,
|
66 |
+
"loss": 6.9106,
|
67 |
+
"step": 6
|
68 |
+
},
|
69 |
+
{
|
70 |
+
"epoch": 0.056074766355140186,
|
71 |
+
"eval_loss": 7.386815071105957,
|
72 |
+
"eval_runtime": 1.279,
|
73 |
+
"eval_samples_per_second": 35.184,
|
74 |
+
"eval_steps_per_second": 17.983,
|
75 |
+
"step": 6
|
76 |
}
|
77 |
],
|
78 |
"logging_steps": 1,
|
|
|
92 |
"attributes": {}
|
93 |
}
|
94 |
},
|
95 |
+
"total_flos": 3257942409216.0,
|
96 |
"train_batch_size": 2,
|
97 |
"trial_name": null,
|
98 |
"trial_params": null
|