Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae06b15227ce783a9cc8aeb7ec79148602a98831e07f322ae9002d75fa688194
+oid sha256:0a0a44dd525d72fa0a552ed385e6959f8939d7a3f99103d7693a0282bb2a27e6
 size 295765866

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cad1d24fd8dec1f2c767e0d0bed75d4e67073680bb8c17c47c0b697dfa1fc4c2
+oid sha256:a50f388098c6562fca4757115dfb689e1ba33131d7e3e2d3f996e9d37b582574
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3f6891a2dad4098258cacbb534eda6cb23344f32c27a937c7da2508a5fd6662
+oid sha256:ef593f391c66ba3ea6e8dea3b2aa8e19ae1f574e3c6a18c96ee14293016120aa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007064641469445425,
+  "epoch": 0.01412928293889085,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 16.392,
       "eval_steps_per_second": 8.196,
       "step": 25
+    },
+    {
+      "epoch": 0.007347227128223242,
+      "grad_norm": NaN,
+      "learning_rate": 3.84324902086706e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.0076298127870010595,
+      "grad_norm": NaN,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.007912398445778877,
+      "grad_norm": NaN,
+      "learning_rate": 3.654371533087586e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.008194984104556694,
+      "grad_norm": NaN,
+      "learning_rate": 3.556545654351749e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.008477569763334511,
+      "grad_norm": NaN,
+      "learning_rate": 3.456708580912725e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.008760155422112328,
+      "grad_norm": NaN,
+      "learning_rate": 3.355050358314172e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.009042741080890145,
+      "grad_norm": NaN,
+      "learning_rate": 3.251764498760683e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.009325326739667962,
+      "grad_norm": NaN,
+      "learning_rate": 3.147047612756302e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.00960791239844578,
+      "grad_norm": NaN,
+      "learning_rate": 3.0410990348452573e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.009890498057223597,
+      "grad_norm": NaN,
+      "learning_rate": 2.9341204441673266e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.010173083716001412,
+      "grad_norm": NaN,
+      "learning_rate": 2.8263154805501297e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.01045566937477923,
+      "grad_norm": NaN,
+      "learning_rate": 2.717889356869146e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.010738255033557046,
+      "grad_norm": NaN,
+      "learning_rate": 2.6090484684133404e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.011020840692334864,
+      "grad_norm": NaN,
+      "learning_rate": 2.5e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.01130342635111268,
+      "grad_norm": NaN,
+      "learning_rate": 2.3909515315866605e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.011586012009890498,
+      "grad_norm": NaN,
+      "learning_rate": 2.2821106431308544e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.011868597668668315,
+      "grad_norm": NaN,
+      "learning_rate": 2.173684519449872e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.012151183327446132,
+      "grad_norm": NaN,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.01243376898622395,
+      "grad_norm": NaN,
+      "learning_rate": 1.958900965154743e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.012716354645001766,
+      "grad_norm": NaN,
+      "learning_rate": 1.852952387243698e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.012998940303779584,
+      "grad_norm": NaN,
+      "learning_rate": 1.7482355012393177e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.0132815259625574,
+      "grad_norm": NaN,
+      "learning_rate": 1.6449496416858284e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.013564111621335218,
+      "grad_norm": NaN,
+      "learning_rate": 1.5432914190872757e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.013846697280113035,
+      "grad_norm": NaN,
+      "learning_rate": 1.443454345648252e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.01412928293889085,
+      "grad_norm": NaN,
+      "learning_rate": 1.3456284669124158e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.01412928293889085,
+      "eval_loss": NaN,
+      "eval_runtime": 90.3579,
+      "eval_samples_per_second": 16.49,
+      "eval_steps_per_second": 8.245,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5761228924256256.0,
+  "total_flos": 9072280030150656.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null