Training in progress, step 400, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe3597c122a2e5567b331b531c1b0cf98c2606dfe5fc98bc664181d12b2b83cd
+oid sha256:12140b3527e8c387ab119cfaeb385ddf7ee08efb2029bcede8b49ffa881bc50e
 size 966995080

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5feb1207165a2472ed0fc4a2352d29febeb73effc6fad6dbd900bc416ac92d15
+oid sha256:69d8260db719def1ed71c3ac4aef34515c81b7554c540c6bf09b8c6ef1774fbf
 size 1925064044

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fd91acef56149d62ef60f134f6bef8f3143b1426e8731dcb1c5449312d3ea8c
+oid sha256:309d78c0cbac356af547d46b1e70776079ec1d34f37e987fe5340ad766fae6b9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f9b9e6716d4845c0461a67674925be51cb5bd879f6bddb03b17fa941754a7de
+oid sha256:09ff4109b85e31dcf014a99ae517a55071a006425bd4bf896b18ef8c2d279509
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 176.42124237382143,
-  "best_model_checkpoint": "./whisper-it/checkpoint-100",
-  "epoch": 0.19083969465648856,
+  "best_metric": 70.1955074875208,
+  "best_model_checkpoint": "./whisper-it/checkpoint-300",
+  "epoch": 0.7633587786259542,
   "eval_steps": 100,
-  "global_step": 100,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -40,6 +40,105 @@
       "eval_steps_per_second": 0.095,
       "eval_wer": 176.42124237382143,
       "step": 100
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 0.9794,
+      "step": 125
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 2.9e-06,
+      "loss": 0.8642,
+      "step": 150
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 3.4000000000000005e-06,
+      "loss": 0.8044,
+      "step": 175
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 3.88e-06,
+      "loss": 0.7389,
+      "step": 200
+    },
+    {
+      "epoch": 0.38,
+      "eval_loss": 0.8330782055854797,
+      "eval_runtime": 1755.11,
+      "eval_samples_per_second": 0.855,
+      "eval_steps_per_second": 0.107,
+      "eval_wer": 80.49084858569051,
+      "step": 200
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 4.38e-06,
+      "loss": 0.6293,
+      "step": 225
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 4.880000000000001e-06,
+      "loss": 0.5066,
+      "step": 250
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 5.380000000000001e-06,
+      "loss": 0.3526,
+      "step": 275
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 5.8800000000000005e-06,
+      "loss": 0.2951,
+      "step": 300
+    },
+    {
+      "epoch": 0.57,
+      "eval_loss": 0.4260523319244385,
+      "eval_runtime": 1708.1953,
+      "eval_samples_per_second": 0.878,
+      "eval_steps_per_second": 0.11,
+      "eval_wer": 70.1955074875208,
+      "step": 300
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.380000000000001e-06,
+      "loss": 0.2553,
+      "step": 325
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 6.88e-06,
+      "loss": 0.2744,
+      "step": 350
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 7.3800000000000005e-06,
+      "loss": 0.279,
+      "step": 375
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 7.88e-06,
+      "loss": 0.2703,
+      "step": 400
+    },
+    {
+      "epoch": 0.76,
+      "eval_loss": 0.40512609481811523,
+      "eval_runtime": 1849.1681,
+      "eval_samples_per_second": 0.811,
+      "eval_steps_per_second": 0.102,
+      "eval_wer": 101.62922906267333,
+      "step": 400
     }
   ],
   "logging_steps": 25,
@@ -47,7 +146,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 8,
   "save_steps": 100,
-  "total_flos": 9.23473281024e+17,
+  "total_flos": 3.693893124096e+18,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0deaaf9b4dc785b95bcfecba732d9f20738cd6d99cb5f2d674c46008c563ff98
-size 4856
+oid sha256:a6afd188b1bb5040b1e1647512623a4ea330124b3938572fb5350dd1ea4ab41d
+size 4792