Training in progress, step 8, checkpoint
Browse files
last-checkpoint/adapter_config.json
CHANGED
@@ -20,13 +20,13 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"gate_proj",
|
24 |
"up_proj",
|
25 |
-
"o_proj",
|
26 |
-
"k_proj",
|
27 |
"v_proj",
|
|
|
|
|
28 |
"q_proj",
|
29 |
-
"down_proj"
|
|
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
23 |
"up_proj",
|
|
|
|
|
24 |
"v_proj",
|
25 |
+
"o_proj",
|
26 |
+
"gate_proj",
|
27 |
"q_proj",
|
28 |
+
"down_proj",
|
29 |
+
"k_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
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:e18c3f75ed3fe1a5ced3c209b9481e663fc622e68c85077a2ed711b452580839
|
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:b3c7e355eb230ce6f1da15a35043efd9a0b0158c1b10fe4b6f2e8ed815d1dab3
|
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:c46e88b4c6d353657e53552d7e0de44c36fe47ff4c4a5c23dafe2255812f99e9
|
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 sha256:6a3d18e607a27cfab9cec7cfaa7384cdb877a2330c4bcd4e1efcae25be9908cb
|
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 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -11,17 +11,32 @@
|
|
11 |
{
|
12 |
"epoch": 0.03361344537815126,
|
13 |
"eval_loss": 0.4333963394165039,
|
14 |
-
"eval_runtime": 0.
|
15 |
-
"eval_samples_per_second": 13.
|
16 |
-
"eval_steps_per_second": 7.
|
17 |
"step": 1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
18 |
}
|
19 |
],
|
20 |
"logging_steps": 5,
|
21 |
-
"max_steps":
|
22 |
"num_input_tokens_seen": 0,
|
23 |
-
"num_train_epochs":
|
24 |
-
"save_steps":
|
25 |
"stateful_callbacks": {
|
26 |
"TrainerControl": {
|
27 |
"args": {
|
@@ -29,12 +44,12 @@
|
|
29 |
"should_evaluate": false,
|
30 |
"should_log": false,
|
31 |
"should_save": true,
|
32 |
-
"should_training_stop":
|
33 |
},
|
34 |
"attributes": {}
|
35 |
}
|
36 |
},
|
37 |
-
"total_flos":
|
38 |
"train_batch_size": 2,
|
39 |
"trial_name": null,
|
40 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.2689075630252101,
|
5 |
+
"eval_steps": 6,
|
6 |
+
"global_step": 8,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
11 |
{
|
12 |
"epoch": 0.03361344537815126,
|
13 |
"eval_loss": 0.4333963394165039,
|
14 |
+
"eval_runtime": 0.9506,
|
15 |
+
"eval_samples_per_second": 13.675,
|
16 |
+
"eval_steps_per_second": 7.364,
|
17 |
"step": 1
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 0.16806722689075632,
|
21 |
+
"grad_norm": 0.773507297039032,
|
22 |
+
"learning_rate": 5e-05,
|
23 |
+
"loss": 0.4071,
|
24 |
+
"step": 5
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.20168067226890757,
|
28 |
+
"eval_loss": 0.3601323664188385,
|
29 |
+
"eval_runtime": 0.9296,
|
30 |
+
"eval_samples_per_second": 13.984,
|
31 |
+
"eval_steps_per_second": 7.53,
|
32 |
+
"step": 6
|
33 |
}
|
34 |
],
|
35 |
"logging_steps": 5,
|
36 |
+
"max_steps": 30,
|
37 |
"num_input_tokens_seen": 0,
|
38 |
+
"num_train_epochs": 2,
|
39 |
+
"save_steps": 8,
|
40 |
"stateful_callbacks": {
|
41 |
"TrainerControl": {
|
42 |
"args": {
|
|
|
44 |
"should_evaluate": false,
|
45 |
"should_log": false,
|
46 |
"should_save": true,
|
47 |
+
"should_training_stop": false
|
48 |
},
|
49 |
"attributes": {}
|
50 |
}
|
51 |
},
|
52 |
+
"total_flos": 1302987314036736.0,
|
53 |
"train_batch_size": 2,
|
54 |
"trial_name": null,
|
55 |
"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 6776
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:466ad16b8953a36cce55575e1feac72d6f4c79f779a748588701d487f553738f
|
3 |
size 6776
|