Model save
Browse files- README.md +1 -1
- all_results.json +18 -0
- eval_results.json +13 -0
- model.safetensors +1 -1
- train_results.json +8 -0
- trainer_state.json +72 -0
- training_args.bin +1 -1
README.md
CHANGED
@@ -37,7 +37,7 @@ The following hyperparameters were used during training:
|
|
37 |
- seed: 42
|
38 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
39 |
- lr_scheduler_type: linear
|
40 |
-
- num_epochs:
|
41 |
|
42 |
### Training results
|
43 |
|
|
|
37 |
- seed: 42
|
38 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
39 |
- lr_scheduler_type: linear
|
40 |
+
- num_epochs: 3.0
|
41 |
|
42 |
### Training results
|
43 |
|
all_results.json
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"eval_gen_len": 78.04093919325707,
|
4 |
+
"eval_loss": 1.0967354774475098,
|
5 |
+
"eval_rouge1": 9.6103,
|
6 |
+
"eval_rouge2": 3.2602,
|
7 |
+
"eval_rougeL": 9.4833,
|
8 |
+
"eval_rougeLsum": 9.5204,
|
9 |
+
"eval_runtime": 305.3578,
|
10 |
+
"eval_samples": 1661,
|
11 |
+
"eval_samples_per_second": 5.44,
|
12 |
+
"eval_steps_per_second": 1.362,
|
13 |
+
"train_loss": 1.3809210790793738,
|
14 |
+
"train_runtime": 2386.364,
|
15 |
+
"train_samples": 14964,
|
16 |
+
"train_samples_per_second": 6.271,
|
17 |
+
"train_steps_per_second": 1.568
|
18 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"eval_gen_len": 78.04093919325707,
|
4 |
+
"eval_loss": 1.0967354774475098,
|
5 |
+
"eval_rouge1": 9.6103,
|
6 |
+
"eval_rouge2": 3.2602,
|
7 |
+
"eval_rougeL": 9.4833,
|
8 |
+
"eval_rougeLsum": 9.5204,
|
9 |
+
"eval_runtime": 305.3578,
|
10 |
+
"eval_samples": 1661,
|
11 |
+
"eval_samples_per_second": 5.44,
|
12 |
+
"eval_steps_per_second": 1.362
|
13 |
+
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2444578688
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:37846d11c8151954bf5997b55c431a0d3e59a1f8018b9c208ebb8eed603b171c
|
3 |
size 2444578688
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"train_loss": 1.3809210790793738,
|
4 |
+
"train_runtime": 2386.364,
|
5 |
+
"train_samples": 14964,
|
6 |
+
"train_samples_per_second": 6.271,
|
7 |
+
"train_steps_per_second": 1.568
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 3741,
|
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,
|
13 |
+
"learning_rate": 4.331729484095162e-05,
|
14 |
+
"loss": 1.7279,
|
15 |
+
"step": 500
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.27,
|
19 |
+
"learning_rate": 3.663458968190324e-05,
|
20 |
+
"loss": 1.5155,
|
21 |
+
"step": 1000
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.4,
|
25 |
+
"learning_rate": 2.995188452285485e-05,
|
26 |
+
"loss": 1.4301,
|
27 |
+
"step": 1500
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.53,
|
31 |
+
"learning_rate": 2.326917936380647e-05,
|
32 |
+
"loss": 1.3448,
|
33 |
+
"step": 2000
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.67,
|
37 |
+
"learning_rate": 1.658647420475809e-05,
|
38 |
+
"loss": 1.2982,
|
39 |
+
"step": 2500
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.8,
|
43 |
+
"learning_rate": 9.903769045709705e-06,
|
44 |
+
"loss": 1.2323,
|
45 |
+
"step": 3000
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.94,
|
49 |
+
"learning_rate": 3.2210638866613206e-06,
|
50 |
+
"loss": 1.2036,
|
51 |
+
"step": 3500
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 1.0,
|
55 |
+
"step": 3741,
|
56 |
+
"total_flos": 1.70456184471552e+16,
|
57 |
+
"train_loss": 1.3809210790793738,
|
58 |
+
"train_runtime": 2386.364,
|
59 |
+
"train_samples_per_second": 6.271,
|
60 |
+
"train_steps_per_second": 1.568
|
61 |
+
}
|
62 |
+
],
|
63 |
+
"logging_steps": 500,
|
64 |
+
"max_steps": 3741,
|
65 |
+
"num_input_tokens_seen": 0,
|
66 |
+
"num_train_epochs": 1,
|
67 |
+
"save_steps": 500,
|
68 |
+
"total_flos": 1.70456184471552e+16,
|
69 |
+
"train_batch_size": 4,
|
70 |
+
"trial_name": null,
|
71 |
+
"trial_params": null
|
72 |
+
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5048
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9fea473a216aa9aa4b033031c9e8f1485df505e03a5b11e6cee03b585b064ee7
|
3 |
size 5048
|