Training in progress, step 4000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ae955edc6f0f3d4522bd094fce5e3bd63e96d59ab8a37a589cb4270ab56e83d
+oid sha256:03d412e81a61d6d60043deb1f0cee257eb7b78051ac0f5df86eff142ee2f5736
 size 2216876959

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:415bb7f0400444aea370a4b4c7492037db38fd90f49e658525a2f3de1c53de78
+oid sha256:59a6b1471b3ef908655ec530f423c5206aac64f29eb05381e44ccf96ab8c46ae
 size 1112207913

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08caaceacca85ef32519a7581abfe5f23f29414206c4263faac6888a0071f567
+oid sha256:05787dac35dbdd37b3c745474cd2392f29710943747278ff59522a6996f89d5e
 size 14503

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:451f3ecd5c95243fdd2f69c7959fe4e80f342e2f1f787355e64d386bb5eb6461
+oid sha256:4e46694c7d98c5e4fefed63b336298efa60e63e823245b087b045057fdceba48
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:170a3af3f4139b4d5bab4b0c50be47bf25e44b89146714922596a6b635709b37
+oid sha256:ba4e799bc93ae8495865ed3fc239390cae62ebcc293d859b2256ac77ecd355e0
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.3640661938534278,
-  "global_step": 2000,
+  "epoch": 4.7281323877068555,
+  "global_step": 4000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,11 +144,149 @@
       "eval_samples_per_second": 5.087,
       "eval_steps_per_second": 0.318,
       "step": 2000
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 2.5342789598108745e-05,
+      "loss": 3.9868,
+      "step": 2100
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 2.4160756501182033e-05,
+      "loss": 3.9224,
+      "step": 2200
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 2.297872340425532e-05,
+      "loss": 3.8934,
+      "step": 2300
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 2.179669030732861e-05,
+      "loss": 3.8838,
+      "step": 2400
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 2.061465721040189e-05,
+      "loss": 3.8895,
+      "step": 2500
+    },
+    {
+      "epoch": 3.07,
+      "learning_rate": 1.9432624113475178e-05,
+      "loss": 3.8267,
+      "step": 2600
+    },
+    {
+      "epoch": 3.19,
+      "learning_rate": 1.8250591016548466e-05,
+      "loss": 3.8143,
+      "step": 2700
+    },
+    {
+      "epoch": 3.31,
+      "learning_rate": 1.706855791962175e-05,
+      "loss": 3.7788,
+      "step": 2800
+    },
+    {
+      "epoch": 3.43,
+      "learning_rate": 1.5886524822695038e-05,
+      "loss": 3.7714,
+      "step": 2900
+    },
+    {
+      "epoch": 3.55,
+      "learning_rate": 1.470449172576832e-05,
+      "loss": 3.752,
+      "step": 3000
+    },
+    {
+      "epoch": 3.55,
+      "eval_cer": 10.867020421289597,
+      "eval_loss": 7.850170612335205,
+      "eval_runtime": 147.6097,
+      "eval_samples_per_second": 5.088,
+      "eval_steps_per_second": 0.318,
+      "step": 3000
+    },
+    {
+      "epoch": 3.66,
+      "learning_rate": 1.3522458628841609e-05,
+      "loss": 3.7711,
+      "step": 3100
+    },
+    {
+      "epoch": 3.78,
+      "learning_rate": 1.2340425531914895e-05,
+      "loss": 3.7428,
+      "step": 3200
+    },
+    {
+      "epoch": 3.9,
+      "learning_rate": 1.115839243498818e-05,
+      "loss": 3.6924,
+      "step": 3300
+    },
+    {
+      "epoch": 4.02,
+      "learning_rate": 9.976359338061467e-06,
+      "loss": 3.6697,
+      "step": 3400
+    },
+    {
+      "epoch": 4.14,
+      "learning_rate": 8.794326241134753e-06,
+      "loss": 3.6303,
+      "step": 3500
+    },
+    {
+      "epoch": 4.26,
+      "learning_rate": 7.612293144208038e-06,
+      "loss": 3.641,
+      "step": 3600
+    },
+    {
+      "epoch": 4.37,
+      "learning_rate": 6.430260047281324e-06,
+      "loss": 3.6441,
+      "step": 3700
+    },
+    {
+      "epoch": 4.49,
+      "learning_rate": 5.24822695035461e-06,
+      "loss": 3.6077,
+      "step": 3800
+    },
+    {
+      "epoch": 4.61,
+      "learning_rate": 4.066193853427896e-06,
+      "loss": 3.5844,
+      "step": 3900
+    },
+    {
+      "epoch": 4.73,
+      "learning_rate": 2.884160756501182e-06,
+      "loss": 3.5919,
+      "step": 4000
+    },
+    {
+      "epoch": 4.73,
+      "eval_cer": 10.43849493487699,
+      "eval_loss": 8.424138069152832,
+      "eval_runtime": 147.3939,
+      "eval_samples_per_second": 5.095,
+      "eval_steps_per_second": 0.319,
+      "step": 4000
     }
   ],
   "max_steps": 4230,
   "num_train_epochs": 5,
-  "total_flos": 5.772747680264356e+18,
+  "total_flos": 1.1545495360528712e+19,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:415bb7f0400444aea370a4b4c7492037db38fd90f49e658525a2f3de1c53de78
+oid sha256:59a6b1471b3ef908655ec530f423c5206aac64f29eb05381e44ccf96ab8c46ae
 size 1112207913

runs/Apr27_08-37-21_cef3a7eee143/events.out.tfevents.1651048661.cef3a7eee143.38.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c7540e57ca7a9cf0701ba602feb467a95ffe73a22b30698d9d43f6644f8a3f0
-size 84979
+oid sha256:e71b8f231ee1e34cd0a1e0474e2f3172d0e6a3f9547cfc08c2c6ba86cbbcaf75
+size 88755