Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f267bde378bec4eedadf0ace4ece596a4279f93b1cdfeed6d557b379ef219ea
+oid sha256:949dcbd30a0242483bafa481a73b675e0ffab3ce21b1088d2de31b5515edcf1a
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e336469d6e18da1d75f1bae792ce28a8e345a592f0f470fbb41ca82acb4af0d
+oid sha256:c4012013f86057d43e1df57d397d81757fbc568e61f475a73acf55a4fd5e1ec8
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc8903f8752042bd41db69607f72228eec71931f3045547a6843964f13d7daf8
+oid sha256:d2430845e2e629c04c5a5bb69918c8eff7e07a532b9e3c7f293731c4b9c0ba91
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ea7c84d40d261a2ee0c5f6cc5b08e6c0fd80637e5a76da45b0eff6d5f62a5ae
+oid sha256:b550957237b3f80459f4a2ddbdf18027a7a26706ad5d45faf3e75aeb28c53605
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4895d4c4fd99665cc2994b6a2790d84bd7cce3254bc10a707ab16b093b1de651
+oid sha256:9d1de7ee7d9c925c1bb272894ca5fb15749bc44d8774064354698a330b78da43
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.4311270125223614,
+  "epoch": 2.862254025044723,
   "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": 11.933,
       "eval_steps_per_second": 3.103,
       "step": 25
+    },
+    {
+      "epoch": 1.4883720930232558,
+      "grad_norm": NaN,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 1.5456171735241502,
+      "grad_norm": NaN,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 1.6028622540250446,
+      "grad_norm": NaN,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 1.6601073345259392,
+      "grad_norm": NaN,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 1.7173524150268338,
+      "grad_norm": NaN,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 1.7745974955277282,
+      "grad_norm": NaN,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 1.8318425760286225,
+      "grad_norm": NaN,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 1.889087656529517,
+      "grad_norm": NaN,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 1.9463327370304113,
+      "grad_norm": NaN,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 2.0035778175313057,
+      "grad_norm": NaN,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 2.0608228980322005,
+      "grad_norm": NaN,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 2.118067978533095,
+      "grad_norm": NaN,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 2.1753130590339893,
+      "grad_norm": NaN,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 2.2325581395348837,
+      "grad_norm": NaN,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 2.289803220035778,
+      "grad_norm": NaN,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 2.3470483005366725,
+      "grad_norm": NaN,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 2.404293381037567,
+      "grad_norm": NaN,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 2.4615384615384617,
+      "grad_norm": NaN,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 2.518783542039356,
+      "grad_norm": NaN,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 2.5760286225402504,
+      "grad_norm": NaN,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 2.633273703041145,
+      "grad_norm": NaN,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 2.690518783542039,
+      "grad_norm": NaN,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 2.747763864042934,
+      "grad_norm": NaN,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 2.8050089445438284,
+      "grad_norm": NaN,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 2.862254025044723,
+      "grad_norm": NaN,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 2.862254025044723,
+      "eval_loss": NaN,
+      "eval_runtime": 3.9994,
+      "eval_samples_per_second": 12.502,
+      "eval_steps_per_second": 3.251,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,12 +395,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.993581059871867e+17,
+  "total_flos": 5.998666393657016e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null