Training in progress, step 1500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f36e5a0b6d5e742c466322d76efee0b73370b5485024c67c77eac11f086f754
+oid sha256:9d7652a9232339d6e1ccab695f9ba6075718fdf1dba2b8c3ef19b0f3a6ee730a
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ab2d96aa7c14ac25f979268944fa39d11946c62f201537bea6172cdd553e3a3
+oid sha256:985478ebfc1a47c88f3e1ac69469cffbbf30686a65738f52bcb40a45462289c1
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2b52d82f73e570b1698336d070d85ea4c32ca359687f3058f1f92bb220326cb
+oid sha256:67614312c1d6bdffeb060b44c3dda6a1d76fa4797cd7f644d2f81b287adb0cdc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b12b10cf3f340469d3096b69b56bd466b59c9a88eb55d010a305dd7220038dd5
+oid sha256:3c11535f68e6db49da07158fe11fecce1c2974b2e1c50f93ec69532ea7b0bd8a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.41562759767248547,
+  "epoch": 0.6234413965087282,
   "eval_steps": 500,
-  "global_step": 1000,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -21,6 +21,13 @@
       "learning_rate": 1.834081463009144e-05,
       "loss": 0.4895,
       "step": 1000
+    },
+    {
+      "epoch": 0.6234413965087282,
+      "grad_norm": 0.4806763529777527,
+      "learning_rate": 1.7509559434746467e-05,
+      "loss": 0.4473,
+      "step": 1500
     }
   ],
   "logging_steps": 500,
@@ -40,7 +47,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2435831562240000.0,
+  "total_flos": 3653747343360000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null