Training in progress, step 1500

checkpoint-1500/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-1500/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-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92d979e6826ad9009b93c7a4ee21cbf1cf8a9b6d2825d98fafcaf81bbef42f12
+size 1934158597

checkpoint-1500/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08d1daaf0146402ccd1f5c5b64758caa3bb2306d71e5cce84fc6ad5e7948461c
+size 967099139

checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2004f1b1db49ce90ad079a4c563df1294d7f019e7baf2366d84692ba5fbab003
+size 14503

checkpoint-1500/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17d2032ba24d7276de602270d41351f419f2013ffe9d6df2aefc3d831191f534
+size 559

checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d5fb1331262ff6b9bcbe9f71d57c821dc935d5bfce93dfed1c0b628f3903131
+size 623

checkpoint-1500/trainer_state.json

@@ -0,0 +1,34 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.322234156820623,
+  "global_step": 1500,
+  "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
+    }
+  ],
+  "max_steps": 5000,
+  "num_train_epochs": 2,
+  "total_flos": 6.92604960768e+18,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1500/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 sha256:711e3aec22525fee00645548162bcbbd868c97695b05ba807e369d0ee796e11d
+oid sha256:08d1daaf0146402ccd1f5c5b64758caa3bb2306d71e5cce84fc6ad5e7948461c
 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 sha256:6c3e7eb942c47cdec753b7fd0e75c111d30865add3cbfe264d4d41959538d1c4
-size 4701
+oid sha256:4de6d7ec393a4d9a37fcc9dde77d737043b13b1e9824d590db14bc837fc06055
+size 4858