huyquoctrinh
commited on
Commit
•
645530d
1
Parent(s):
b3acec6
Training in progress, step 4
Browse files- adapter_config.json +11 -11
- adapter_model.safetensors +1 -1
- all_results.json +9 -0
- runs/Nov10_19-01-02_bdaa6bed38f5/events.out.tfevents.1731265343.bdaa6bed38f5.578166.0 +3 -0
- train_results.json +9 -0
- trainer_state.json +98 -0
- training_args.bin +1 -1
adapter_config.json
CHANGED
@@ -23,22 +23,22 @@
|
|
23 |
"rank_pattern": {},
|
24 |
"revision": null,
|
25 |
"target_modules": [
|
26 |
-
"
|
27 |
"embed_tokens.1",
|
28 |
-
"enc_to_dec_proj",
|
29 |
-
"lm_heads.3",
|
30 |
"lm_heads.0",
|
31 |
-
"embed_tokens.3",
|
32 |
-
"fc2",
|
33 |
-
"embed_tokens.0",
|
34 |
-
"lm_heads.2",
|
35 |
"lm_heads.1",
|
36 |
-
"out_proj",
|
37 |
-
"embed_tokens.2",
|
38 |
"fc1",
|
39 |
-
"
|
|
|
40 |
"k_proj",
|
41 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
42 |
],
|
43 |
"task_type": null,
|
44 |
"use_dora": false,
|
|
|
23 |
"rank_pattern": {},
|
24 |
"revision": null,
|
25 |
"target_modules": [
|
26 |
+
"embed_tokens.3",
|
27 |
"embed_tokens.1",
|
|
|
|
|
28 |
"lm_heads.0",
|
|
|
|
|
|
|
|
|
29 |
"lm_heads.1",
|
|
|
|
|
30 |
"fc1",
|
31 |
+
"embed_tokens.2",
|
32 |
+
"lm_heads.2",
|
33 |
"k_proj",
|
34 |
+
"audio_enc_to_dec_proj",
|
35 |
+
"q_proj",
|
36 |
+
"fc2",
|
37 |
+
"enc_to_dec_proj",
|
38 |
+
"v_proj",
|
39 |
+
"embed_tokens.0",
|
40 |
+
"lm_heads.3",
|
41 |
+
"out_proj"
|
42 |
],
|
43 |
"task_type": null,
|
44 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 87103456
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c8f4b1a0e0ee0b428a920b1c3841d09e9d88759aac174509f80a57e7f4a0917
|
3 |
size 87103456
|
all_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.764705882352941,
|
3 |
+
"total_flos": 3464493556500.0,
|
4 |
+
"train_loss": 8.955702781677246,
|
5 |
+
"train_runtime": 51.5041,
|
6 |
+
"train_samples": 33,
|
7 |
+
"train_samples_per_second": 2.563,
|
8 |
+
"train_steps_per_second": 0.155
|
9 |
+
}
|
runs/Nov10_19-01-02_bdaa6bed38f5/events.out.tfevents.1731265343.bdaa6bed38f5.578166.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3da1b41b50118c307873fac21b3d40e63672d3988a22835df67087dd2f8c9798
|
3 |
+
size 13797
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.764705882352941,
|
3 |
+
"total_flos": 3464493556500.0,
|
4 |
+
"train_loss": 8.955702781677246,
|
5 |
+
"train_runtime": 51.5041,
|
6 |
+
"train_samples": 33,
|
7 |
+
"train_samples_per_second": 2.563,
|
8 |
+
"train_steps_per_second": 0.155
|
9 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,98 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.764705882352941,
|
5 |
+
"eval_steps": 25,
|
6 |
+
"global_step": 8,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.47058823529411764,
|
13 |
+
"grad_norm": 9.738798141479492,
|
14 |
+
"learning_rate": 0.000175,
|
15 |
+
"loss": 9.5576,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.9411764705882353,
|
20 |
+
"grad_norm": 9.771041870117188,
|
21 |
+
"learning_rate": 0.00015000000000000001,
|
22 |
+
"loss": 9.4171,
|
23 |
+
"step": 2
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 1.4117647058823528,
|
27 |
+
"grad_norm": 9.270547866821289,
|
28 |
+
"learning_rate": 0.000125,
|
29 |
+
"loss": 9.2248,
|
30 |
+
"step": 3
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 1.8823529411764706,
|
34 |
+
"grad_norm": 10.51770305633545,
|
35 |
+
"learning_rate": 0.0001,
|
36 |
+
"loss": 8.9946,
|
37 |
+
"step": 4
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 2.3529411764705883,
|
41 |
+
"grad_norm": 13.01863956451416,
|
42 |
+
"learning_rate": 7.500000000000001e-05,
|
43 |
+
"loss": 8.8172,
|
44 |
+
"step": 5
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 2.8235294117647056,
|
48 |
+
"grad_norm": 14.001367568969727,
|
49 |
+
"learning_rate": 5e-05,
|
50 |
+
"loss": 8.702,
|
51 |
+
"step": 6
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 3.2941176470588234,
|
55 |
+
"grad_norm": 17.041738510131836,
|
56 |
+
"learning_rate": 2.5e-05,
|
57 |
+
"loss": 8.5038,
|
58 |
+
"step": 7
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 3.764705882352941,
|
62 |
+
"grad_norm": 17.74396514892578,
|
63 |
+
"learning_rate": 0.0,
|
64 |
+
"loss": 8.4284,
|
65 |
+
"step": 8
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 3.764705882352941,
|
69 |
+
"step": 8,
|
70 |
+
"total_flos": 3464493556500.0,
|
71 |
+
"train_loss": 8.955702781677246,
|
72 |
+
"train_runtime": 51.5041,
|
73 |
+
"train_samples_per_second": 2.563,
|
74 |
+
"train_steps_per_second": 0.155
|
75 |
+
}
|
76 |
+
],
|
77 |
+
"logging_steps": 1.0,
|
78 |
+
"max_steps": 8,
|
79 |
+
"num_input_tokens_seen": 0,
|
80 |
+
"num_train_epochs": 4,
|
81 |
+
"save_steps": 500,
|
82 |
+
"stateful_callbacks": {
|
83 |
+
"TrainerControl": {
|
84 |
+
"args": {
|
85 |
+
"should_epoch_stop": false,
|
86 |
+
"should_evaluate": false,
|
87 |
+
"should_log": false,
|
88 |
+
"should_save": true,
|
89 |
+
"should_training_stop": true
|
90 |
+
},
|
91 |
+
"attributes": {}
|
92 |
+
}
|
93 |
+
},
|
94 |
+
"total_flos": 3464493556500.0,
|
95 |
+
"train_batch_size": 2,
|
96 |
+
"trial_name": null,
|
97 |
+
"trial_params": null
|
98 |
+
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5496
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bea38050c21d5e39b7e7bcf9888e96db4bb3a8d28f5be7e63662536bbc76096c
|
3 |
size 5496
|