Training in progress, step 4500

checkpoint-4500/config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "openai/whisper-small",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": null,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "max_length": 448,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "model_type": "whisper",
+  "num_hidden_layers": 12,
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "suppress_tokens": [],
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.0",
+  "use_cache": false,
+  "vocab_size": 51865
+}

checkpoint-4500/generation_config.json

@@ -0,0 +1,113 @@
+{
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": [
+    [
+      1,
+      null
+    ],
+    [
+      2,
+      50359
+    ]
+  ],
+  "max_length": 448,
+  "pad_token_id": 50257,
+  "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
+  ],
+  "transformers_version": "4.26.0",
+  "use_cache": false
+}

checkpoint-4500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa822a93aba214478e26258877e8e2c2efb08aa752695bc79f74e0350dbe657b
+size 1934158597

checkpoint-4500/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f290febfcc9410ad10956bd3e2b7eb46a42d73582ab6680937d50a283802601
+size 967099139

checkpoint-4500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa6e527ec7398fa3dff73f812f7a9d0ebec2f26279eaf1c8170bae697478d3a8
+size 14503

checkpoint-4500/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50190a136ed9c06499e0f150b24c3f76b70b4ea8055ecf3500caefc7bf973aeb
+size 559

checkpoint-4500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:756568293eb6558e73569c129eb15a4b49eb76b5477b663f4731fe076bb57df6
+size 623

checkpoint-4500/trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.966702470461869,
+  "global_step": 4500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.11,
+      "learning_rate": 6.10123648e-05,
+      "loss": 1.2324,
+      "step": 500
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 5.472524835555556e-05,
+      "loss": 0.7401,
+      "step": 1000
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.789142613333333e-05,
+      "loss": 0.6104,
+      "step": 1500
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 4.105760391111111e-05,
+      "loss": 0.5478,
+      "step": 2000
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 3.4223781688888885e-05,
+      "loss": 0.4784,
+      "step": 2500
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 2.7389959466666668e-05,
+      "loss": 0.4348,
+      "step": 3000
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 2.0556137244444445e-05,
+      "loss": 0.3875,
+      "step": 3500
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.3722315022222223e-05,
+      "loss": 0.3587,
+      "step": 4000
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 6.8884928e-06,
+      "loss": 0.3241,
+      "step": 4500
+    }
+  ],
+  "max_steps": 5000,
+  "num_train_epochs": 2,
+  "total_flos": 2.077814882304e+19,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-4500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23a1c75d84d87e3d0838d46de30a891bf97e78786468d38612fc1413d5ee7b22
+size 3695

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0a9e5660209cf04f005cd8d18275e76572f9e375d8426a9b7d36f3c3a87ac88
+oid sha256:0f290febfcc9410ad10956bd3e2b7eb46a42d73582ab6680937d50a283802601
 size 967099139

runs/Sep21_06-58-08_instance-20230918-233817/events.out.tfevents.1695279506.instance-20230918-233817

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f633cf741e5dad7e4393d4a5c5773abc4f342b6def6a04adfffe8aeff9b0bf43
-size 5486
+oid sha256:76957660ce8b5020e3ca7176457a05ae98ba4f90fc9ac6269611e012e5acb4e2
+size 5643