Training in progress, step 9, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5774fcec65aeefffc9ebf901ab3905edb4397fbad62b71cb4511103398716bea
+oid sha256:57799aaf1aab16b8eb569779e7dcc5cd1abdc466429f48ad317bbe8f288947db
 size 25986148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6528327458bcd7e55b7e0b059031e81ede3d777d380e97f7a6d34a21c2a9cbb7
+oid sha256:200d8a86ef41acdf01eea96fef00c6f1766f4a479628e82d083c05b86f6ea4b9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65ba7072965e63c16dd886610f000b2c1bbf5f86c93118932f3bcd940d942578
+oid sha256:180fb2930efffe03d2da3c10543b777c65c99574dc1268b92ac9f51b0f1b7030
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0019111323459149545,
+  "epoch": 0.002866698518872432,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 6.245,
       "eval_steps_per_second": 3.127,
       "step": 6
+    },
+    {
+      "epoch": 0.002229654403567447,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00035,
+      "loss": 2.3754,
+      "step": 7
+    },
+    {
+      "epoch": 0.0025481764612199395,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0004,
+      "loss": 3.8853,
+      "step": 8
+    },
+    {
+      "epoch": 0.002866698518872432,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00045000000000000004,
+      "loss": 1.8824,
+      "step": 9
+    },
+    {
+      "epoch": 0.002866698518872432,
+      "eval_loss": 2.888601303100586,
+      "eval_runtime": 105.7148,
+      "eval_samples_per_second": 6.253,
+      "eval_steps_per_second": 3.131,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 617621263220736.0,
+  "total_flos": 926431894831104.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null