Training in progress, step 200, checkpoint

last-checkpoint/config.json

@@ -43,7 +43,7 @@
     2
   ],
   "ctc_loss_reduction": "mean",
-  "ctc_zero_infinity": false,
+  "ctc_zero_infinity": true,
   "diversity_loss_weight": 0.1,
   "do_stable_layer_norm": true,
   "eos_token_id": 2,
@@ -64,7 +64,7 @@
   "mask_feature_length": 10,
   "mask_feature_min_masks": 0,
   "mask_feature_prob": 0.0,
-  "mask_time_length": 5,
+  "mask_time_length": 10,
   "mask_time_min_masks": 2,
   "mask_time_prob": 0.05,
   "model_type": "wav2vec2",

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9943c125d533def374c92e62764fa9d5f751012948f78a46b38bc79cfac2a0cf
+oid sha256:361df9cebcb1a2ffc9266959f7e68c97ed1b31f111697b77cb4c6fcb7aa4bb6e
 size 1261926380

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abff52a4cb221cb6fdea55294c6a7f2291f55946f6c1a5de2d334f55f16ba256
+oid sha256:14379549cbbd615e1afc0f55a72aeefce9e30a8d572d6881616daf914ac9f050
 size 2490397494

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15e9e40d7a10723b41ae89b32ea99392d168dfcbf7c21d9d393f955eea5a17df
+oid sha256:ae6d077d17ee0eb0d05a121413a9e8770985be4c4d32267b724795c0599d8873
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5771c0459252628d921b8efec8b44d18d11d0dd4c0120b974418319c20ad04e
+oid sha256:5fc54d329cf6de9dd761f8fb381d9d1d1cba79225575c60b10e5e232eb19099e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,36 +1,52 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.33783783783783783,
+  "epoch": 0.966183574879227,
   "eval_steps": 100,
-  "global_step": 100,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.34,
-      "grad_norm": NaN,
-      "learning_rate": 0.0001729,
-      "loss": 6.329,
+      "epoch": 0.48,
+      "grad_norm": 0.33149510622024536,
+      "learning_rate": 0.00018810000000000002,
+      "loss": 3.162,
       "step": 100
     },
     {
-      "epoch": 0.34,
-      "eval_loss": Infinity,
-      "eval_runtime": 77.9869,
-      "eval_samples_per_second": 15.015,
-      "eval_steps_per_second": 1.885,
+      "epoch": 0.48,
+      "eval_loss": 2.6494271755218506,
+      "eval_runtime": 61.8673,
+      "eval_samples_per_second": 13.125,
+      "eval_steps_per_second": 1.649,
       "eval_wer": 1.0,
       "step": 100
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": NaN,
+      "learning_rate": 0.00037620000000000004,
+      "loss": 2.8381,
+      "step": 200
+    },
+    {
+      "epoch": 0.97,
+      "eval_loss": 2.6534550189971924,
+      "eval_runtime": 62.5126,
+      "eval_samples_per_second": 12.989,
+      "eval_steps_per_second": 1.632,
+      "eval_wer": 1.0,
+      "step": 200
     }
   ],
   "logging_steps": 100,
-  "max_steps": 8880,
+  "max_steps": 6210,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 1.2267819282523704e+17,
+  "total_flos": 4.310189589213924e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2de0a87eb18a49a9f916c4d5d69b8a801be8a6fb5c6c876aa08d56068e5e5288
+oid sha256:662cb01d4e6609aa62cde1fb3cfa65348fbcf48196567d53cb73aabfde47c1ae
 size 4920