Training in progress, step 6, checkpoint
Browse files
last-checkpoint/adapter_config.json
CHANGED
@@ -20,12 +20,12 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"k_proj",
|
24 |
-
"down_proj",
|
25 |
-
"v_proj",
|
26 |
"up_proj",
|
27 |
-
"gate_proj",
|
28 |
"q_proj",
|
|
|
|
|
|
|
|
|
29 |
"o_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
|
|
|
|
23 |
"up_proj",
|
|
|
24 |
"q_proj",
|
25 |
+
"v_proj",
|
26 |
+
"k_proj",
|
27 |
+
"gate_proj",
|
28 |
+
"down_proj",
|
29 |
"o_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 78480072
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77b761d0893717fa5d685720cb4b787328dd2f1eeb9741af187d11cc0a34e089
|
3 |
size 78480072
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 40131268
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23d28cf7dab918f8a0d8107852e53d06bb0b47b75122a81305705f6b2fe6dd2f
|
3 |
size 40131268
|
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:d85c5e3e589dfdf3eb8679de9d5cf33e0165cd6aeb13a8f2940235bf86350900
|
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:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
|
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,
|
@@ -18,32 +18,61 @@
|
|
18 |
{
|
19 |
"epoch": 0.0007328691828508611,
|
20 |
"eval_loss": 12.304828643798828,
|
21 |
-
"eval_runtime":
|
22 |
-
"eval_samples_per_second": 5.
|
23 |
-
"eval_steps_per_second": 5.
|
24 |
"step": 1
|
25 |
},
|
26 |
{
|
27 |
"epoch": 0.0014657383657017222,
|
28 |
-
"grad_norm":
|
29 |
"learning_rate": 2e-05,
|
30 |
"loss": 10.6283,
|
31 |
"step": 2
|
32 |
},
|
33 |
{
|
34 |
"epoch": 0.0021986075485525836,
|
35 |
-
"grad_norm":
|
36 |
"learning_rate": 4e-05,
|
37 |
"loss": 11.3833,
|
38 |
"step": 3
|
39 |
},
|
40 |
{
|
41 |
"epoch": 0.0021986075485525836,
|
42 |
-
"eval_loss": 12.
|
43 |
-
"eval_runtime": 56.
|
44 |
-
"eval_samples_per_second": 5.
|
45 |
-
"eval_steps_per_second": 5.
|
46 |
"step": 3
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
47 |
}
|
48 |
],
|
49 |
"logging_steps": 1,
|
@@ -63,7 +92,7 @@
|
|
63 |
"attributes": {}
|
64 |
}
|
65 |
},
|
66 |
-
"total_flos":
|
67 |
"train_batch_size": 1,
|
68 |
"trial_name": null,
|
69 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.004397215097105167,
|
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,
|
|
|
18 |
{
|
19 |
"epoch": 0.0007328691828508611,
|
20 |
"eval_loss": 12.304828643798828,
|
21 |
+
"eval_runtime": 56.9499,
|
22 |
+
"eval_samples_per_second": 5.057,
|
23 |
+
"eval_steps_per_second": 5.057,
|
24 |
"step": 1
|
25 |
},
|
26 |
{
|
27 |
"epoch": 0.0014657383657017222,
|
28 |
+
"grad_norm": 42.04989242553711,
|
29 |
"learning_rate": 2e-05,
|
30 |
"loss": 10.6283,
|
31 |
"step": 2
|
32 |
},
|
33 |
{
|
34 |
"epoch": 0.0021986075485525836,
|
35 |
+
"grad_norm": 37.467315673828125,
|
36 |
"learning_rate": 4e-05,
|
37 |
"loss": 11.3833,
|
38 |
"step": 3
|
39 |
},
|
40 |
{
|
41 |
"epoch": 0.0021986075485525836,
|
42 |
+
"eval_loss": 12.051217079162598,
|
43 |
+
"eval_runtime": 56.814,
|
44 |
+
"eval_samples_per_second": 5.069,
|
45 |
+
"eval_steps_per_second": 5.069,
|
46 |
"step": 3
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 0.0029314767314034445,
|
50 |
+
"grad_norm": 44.678558349609375,
|
51 |
+
"learning_rate": 6e-05,
|
52 |
+
"loss": 9.6695,
|
53 |
+
"step": 4
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 0.003664345914254306,
|
57 |
+
"grad_norm": 48.171749114990234,
|
58 |
+
"learning_rate": 8e-05,
|
59 |
+
"loss": 14.795,
|
60 |
+
"step": 5
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 0.004397215097105167,
|
64 |
+
"grad_norm": 32.893001556396484,
|
65 |
+
"learning_rate": 0.0001,
|
66 |
+
"loss": 7.3908,
|
67 |
+
"step": 6
|
68 |
+
},
|
69 |
+
{
|
70 |
+
"epoch": 0.004397215097105167,
|
71 |
+
"eval_loss": 9.441511154174805,
|
72 |
+
"eval_runtime": 56.7951,
|
73 |
+
"eval_samples_per_second": 5.071,
|
74 |
+
"eval_steps_per_second": 5.071,
|
75 |
+
"step": 6
|
76 |
}
|
77 |
],
|
78 |
"logging_steps": 1,
|
|
|
92 |
"attributes": {}
|
93 |
}
|
94 |
},
|
95 |
+
"total_flos": 1180530414452736.0,
|
96 |
"train_batch_size": 1,
|
97 |
"trial_name": null,
|
98 |
"trial_params": null
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6712
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:722f3b82bb852127c4404471dd8bb057b70f4e0cb5a02b713538b276ca5a19c9
|
3 |
size 6712
|