End of training

README.md

@@ -38,12 +38,12 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
 - train_batch_size: 32
-- eval_batch_size: 32
+- eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: constant_with_warmup
-- lr_scheduler_warmup_steps: 50
-- training_steps: 1
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- training_steps: 3
 - mixed_precision_training: Native AMP
 
 ### Training results

config.json

@@ -25,20 +25,7 @@
   "encoder_layerdrop": 0.0,
   "encoder_layers": 4,
   "eos_token_id": 50257,
-  "forced_decoder_ids": [
-    [
-      1,
-      50259
-    ],
-    [
-      2,
-      50359
-    ],
-    [
-      3,
-      50363
-    ]
-  ],
+  "forced_decoder_ids": null,
   "init_std": 0.02,
   "is_encoder_decoder": true,
   "mask_feature_length": 10,
@@ -56,99 +43,10 @@
   "num_mel_bins": 80,
   "pad_token_id": 50257,
   "scale_embedding": false,
-  "suppress_tokens": [
-    1,
-    2,
-    7,
-    8,
-    9,
-    10,
-    14,
-    25,
-    26,
-    27,
-    28,
-    29,
-    31,
-    58,
-    59,
-    60,
-    61,
-    62,
-    63,
-    90,
-    91,
-    92,
-    93,
-    359,
-    503,
-    522,
-    542,
-    873,
-    893,
-    902,
-    918,
-    922,
-    931,
-    1350,
-    1853,
-    1982,
-    2460,
-    2627,
-    3246,
-    3253,
-    3268,
-    3536,
-    3846,
-    3961,
-    4183,
-    4667,
-    6585,
-    6647,
-    7273,
-    9061,
-    9383,
-    10428,
-    10929,
-    11938,
-    12033,
-    12331,
-    12562,
-    13793,
-    14157,
-    14635,
-    15265,
-    15618,
-    16553,
-    16604,
-    18362,
-    18956,
-    20075,
-    21675,
-    22520,
-    26130,
-    26161,
-    26435,
-    28279,
-    29464,
-    31650,
-    32302,
-    32470,
-    36865,
-    42863,
-    47425,
-    49870,
-    50254,
-    50258,
-    50358,
-    50359,
-    50360,
-    50361,
-    50362
-  ],
+  "suppress_tokens": [],
   "torch_dtype": "float32",
   "transformers_version": "4.35.2",
-  "use_cache": false,
+  "use_cache": true,
   "use_weighted_layer_sum": false,
   "vocab_size": 51865
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:709f21504ce794231c93972d3b5f83ff3b78b75bdb3f0309f7e3f45d977f8489
+oid sha256:2ea9d5b670a7f8f43e9d9c2038a4e26784a9b71188f8dcdfce63eb4f87b70c84
 size 151061672

runs/Nov27_11-13-54_icdcub-03/events.out.tfevents.1701083652.icdcub-03

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abb70362dae1a5836a16fd1c4c05f5d2aa193407bae491e6b479eda76a5b61fc
+size 9928

runs/Nov27_11-15-45_icdcub-03/events.out.tfevents.1701083747.icdcub-03

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0bf24e8826464c5c5666c1eec8ba9a5d28a7791b3a714b2c34eb1906a8a7106
+size 4984

runs/Nov27_11-17-02_icdcub-03/events.out.tfevents.1701083825.icdcub-03

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd0f0353fd6544f8583f4689e5948c05a68270769a280fe622833872e8a9938c
+size 4984

runs/Nov27_11-19-46_icdcub-03/events.out.tfevents.1701083988.icdcub-03

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7065480b3b9959eac2c838067cc731acbe52d3c763aa1e0dae24befb2e30a888
+size 4984

runs/Nov27_11-23-56_icdcub-03/events.out.tfevents.1701084238.icdcub-03

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55631932587db6acf6b56c526b283fc21bf134f4f6ce25483d8e31d53333a0c1
+size 4984

runs/Nov27_11-38-13_icdcub-03/events.out.tfevents.1701085095.icdcub-03

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6eaea35ec8e0b174d794d0d33efbcd32be6a063680b9b243654b5bbe5f34e3db
+size 9928

runs/Nov27_12-01-04_icdcub-03/events.out.tfevents.1701086466.icdcub-03

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99970e85c4afb787b7474c48106a2b858d8ceceabe6b17c0b6248a31c899497b
+size 4984

runs/Nov27_12-06-08_icdcub-03/events.out.tfevents.1701086770.icdcub-03

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f5da58dc123b30f9f9492be7b25e83dd1fd4c18833ed93a70aba8e5a2aed434
+size 5332

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f442d6a71b4265e615d0b6aeca32f9951b8fc8f39a153ef7804d63ba73c48d64
+oid sha256:cbb5036d00f0361d3086e8a8a32b898c56ca0393e4123619dde7a205aae63347
 size 4283