Training in progress, step 32000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b61d5a5a0f5b7ace55f8bc3cfcc9327599d34056cf4715c1510e9c33291ed41
+oid sha256:d9a244e9cb55adf7cda56ccb82e1a9bee92d342f231471fb5502ab29003b5e6b
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31972f8c5588889908297685ea316a6c5603a5c6d49476ca372f9024aae59d33
+oid sha256:f2fb02fb3109cf50329151281ddbb10cbbd67d7bcacbec12c415183618e7c8c4
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d03e6c49a145ce2e51d87480bb76687cc7b5c7b56e94d2991de3e2ab67bd210
+oid sha256:ba3afeb76c9729f93ec4d0e7011fb72d06e1cea76b77b26bfd4a5e76df22f8c2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c724d2349acf4c39c5d4d83bc11668bbfaa5c5543e4339570ed104ddf6da9c9e
+oid sha256:89d99968826ce47bd88d7b05d470f4fb17f0bcc9ac13362244060de99696b592
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.1,
+  "epoch": 2.1333333333333333,
   "eval_steps": 500,
-  "global_step": 31500,
+  "global_step": 32000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2228,6 +2228,41 @@
       "learning_rate": 6.004888888888889e-06,
       "loss": 0.053,
       "step": 31500
+    },
+    {
+      "epoch": 2.1066666666666665,
+      "grad_norm": 0.18772698938846588,
+      "learning_rate": 5.960444444444445e-06,
+      "loss": 0.0483,
+      "step": 31600
+    },
+    {
+      "epoch": 2.1133333333333333,
+      "grad_norm": 0.18564331531524658,
+      "learning_rate": 5.916000000000001e-06,
+      "loss": 0.0493,
+      "step": 31700
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 0.14556245505809784,
+      "learning_rate": 5.871555555555556e-06,
+      "loss": 0.049,
+      "step": 31800
+    },
+    {
+      "epoch": 2.1266666666666665,
+      "grad_norm": 0.14260981976985931,
+      "learning_rate": 5.827111111111111e-06,
+      "loss": 0.0509,
+      "step": 31900
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 0.08872347325086594,
+      "learning_rate": 5.782666666666667e-06,
+      "loss": 0.0466,
+      "step": 32000
     }
   ],
   "logging_steps": 100,
@@ -2247,7 +2282,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.672869421056e+16,
+  "total_flos": 7.794660999168e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null