willtensora
commited on
Training in progress, step 3, checkpoint
Browse files
last-checkpoint/adapter_config.json
CHANGED
@@ -10,21 +10,21 @@
|
|
10 |
"layers_pattern": null,
|
11 |
"layers_to_transform": null,
|
12 |
"loftq_config": {},
|
13 |
-
"lora_alpha":
|
14 |
-
"lora_dropout": 0.
|
15 |
"megatron_config": null,
|
16 |
"megatron_core": "megatron.core",
|
17 |
"modules_to_save": null,
|
18 |
"peft_type": "LORA",
|
19 |
-
"r":
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
|
|
23 |
"q_proj",
|
24 |
"gate_proj",
|
25 |
-
"up_proj",
|
26 |
"k_proj",
|
27 |
-
"down_proj",
|
28 |
"v_proj",
|
29 |
"o_proj"
|
30 |
],
|
|
|
10 |
"layers_pattern": null,
|
11 |
"layers_to_transform": null,
|
12 |
"loftq_config": {},
|
13 |
+
"lora_alpha": 16,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
"megatron_config": null,
|
16 |
"megatron_core": "megatron.core",
|
17 |
"modules_to_save": null,
|
18 |
"peft_type": "LORA",
|
19 |
+
"r": 8,
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"down_proj",
|
24 |
+
"up_proj",
|
25 |
"q_proj",
|
26 |
"gate_proj",
|
|
|
27 |
"k_proj",
|
|
|
28 |
"v_proj",
|
29 |
"o_proj"
|
30 |
],
|
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c599b75a981b0d9f0dc6a0e91aa387a26e70ef6d36d76cb04bce8ce82a092b48
|
3 |
+
size 14696
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a58ebf1b77ea2d04d0501506dc56060e091959c460d798517cb5ca27f6473af7
|
3 |
+
size 39398
|
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 sha256:464e6cdff3f8548ba79ace3859c72e6b06d1e045e69932eb75c584ad0e8918c8
|
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:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,34 +1,56 @@
|
|
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,
|
10 |
"log_history": [
|
11 |
{
|
12 |
-
"epoch": 0.
|
13 |
-
"grad_norm": 0.
|
14 |
-
"learning_rate":
|
15 |
-
"loss": 11.
|
16 |
"step": 1
|
17 |
},
|
18 |
{
|
19 |
-
"epoch": 0.
|
20 |
-
"eval_loss": 11.
|
21 |
-
"eval_runtime":
|
22 |
-
"eval_samples_per_second":
|
23 |
-
"eval_steps_per_second":
|
24 |
"step": 1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
25 |
}
|
26 |
],
|
27 |
"logging_steps": 1,
|
28 |
-
"max_steps":
|
29 |
"num_input_tokens_seen": 0,
|
30 |
"num_train_epochs": 1,
|
31 |
-
"save_steps":
|
32 |
"stateful_callbacks": {
|
33 |
"TrainerControl": {
|
34 |
"args": {
|
@@ -36,13 +58,13 @@
|
|
36 |
"should_evaluate": false,
|
37 |
"should_log": false,
|
38 |
"should_save": true,
|
39 |
-
"should_training_stop":
|
40 |
},
|
41 |
"attributes": {}
|
42 |
}
|
43 |
},
|
44 |
-
"total_flos":
|
45 |
-
"train_batch_size":
|
46 |
"trial_name": null,
|
47 |
"trial_params": null
|
48 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0016825574873808188,
|
5 |
+
"eval_steps": 3,
|
6 |
+
"global_step": 3,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"epoch": 0.0005608524957936063,
|
13 |
+
"grad_norm": 0.012027375400066376,
|
14 |
+
"learning_rate": 2e-05,
|
15 |
+
"loss": 11.9315,
|
16 |
"step": 1
|
17 |
},
|
18 |
{
|
19 |
+
"epoch": 0.0005608524957936063,
|
20 |
+
"eval_loss": 11.931306838989258,
|
21 |
+
"eval_runtime": 2.6701,
|
22 |
+
"eval_samples_per_second": 281.261,
|
23 |
+
"eval_steps_per_second": 140.818,
|
24 |
"step": 1
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.0011217049915872126,
|
28 |
+
"grad_norm": 0.008168625645339489,
|
29 |
+
"learning_rate": 4e-05,
|
30 |
+
"loss": 11.9304,
|
31 |
+
"step": 2
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 0.0016825574873808188,
|
35 |
+
"grad_norm": 0.014232893474400043,
|
36 |
+
"learning_rate": 6e-05,
|
37 |
+
"loss": 11.9319,
|
38 |
+
"step": 3
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.0016825574873808188,
|
42 |
+
"eval_loss": 11.931304931640625,
|
43 |
+
"eval_runtime": 2.7097,
|
44 |
+
"eval_samples_per_second": 277.154,
|
45 |
+
"eval_steps_per_second": 138.761,
|
46 |
+
"step": 3
|
47 |
}
|
48 |
],
|
49 |
"logging_steps": 1,
|
50 |
+
"max_steps": 10,
|
51 |
"num_input_tokens_seen": 0,
|
52 |
"num_train_epochs": 1,
|
53 |
+
"save_steps": 3,
|
54 |
"stateful_callbacks": {
|
55 |
"TrainerControl": {
|
56 |
"args": {
|
|
|
58 |
"should_evaluate": false,
|
59 |
"should_log": false,
|
60 |
"should_save": true,
|
61 |
+
"should_training_stop": false
|
62 |
},
|
63 |
"attributes": {}
|
64 |
}
|
65 |
},
|
66 |
+
"total_flos": 384024576.0,
|
67 |
+
"train_batch_size": 2,
|
68 |
"trial_name": null,
|
69 |
"trial_params": null
|
70 |
}
|
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:dae77c6881efffb1525ab27d15f41925709b4eb57600c98d05461f542cc3b806
|
3 |
size 6776
|