Training in progress, step 6, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba24f71fef4ba844ad4ce0629e5e4ddfaa7748255ae9c212fee4b96b2052d163
+oid sha256:5774fcec65aeefffc9ebf901ab3905edb4397fbad62b71cb4511103398716bea
 size 25986148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6c79eac4ea24e0b72d6cae8c543e67672af6db4329afa8f10cc25f5d34b82d0
+oid sha256:6528327458bcd7e55b7e0b059031e81ede3d777d380e97f7a6d34a21c2a9cbb7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bd587e06dfbbf1eea2dc6523ef961ffd113a64511cfdb083e2bacb0e949059b
+oid sha256:65ba7072965e63c16dd886610f000b2c1bbf5f86c93118932f3bcd940d942578
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0009555661729574773,
+  "epoch": 0.0019111323459149545,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 6.254,
       "eval_steps_per_second": 3.132,
       "step": 3
+    },
+    {
+      "epoch": 0.0012740882306099697,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0002,
+      "loss": 1.3516,
+      "step": 4
+    },
+    {
+      "epoch": 0.0015926102882624622,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00025,
+      "loss": 3.2038,
+      "step": 5
+    },
+    {
+      "epoch": 0.0019111323459149545,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0003,
+      "loss": 2.3316,
+      "step": 6
+    },
+    {
+      "epoch": 0.0019111323459149545,
+      "eval_loss": 2.888601303100586,
+      "eval_runtime": 105.848,
+      "eval_samples_per_second": 6.245,
+      "eval_steps_per_second": 3.127,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 308810631610368.0,
+  "total_flos": 617621263220736.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null