Training in progress, step 22500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cf00b77a940691d2a87a25214434a0d48f9864c65fc3b0b19e53bccdbef0226
+oid sha256:e0f4dd5c7f06f434e4d8cbac5754e2c65f64bd46ac822a7e90462688dcf30e65
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2faa9161687d4c30fe8c5c851dcaf7629e9d07b563b4b1ca8c6d9fe9490b63c8
+oid sha256:a565ab0875e5f8e974ebb52445ef3770a07896c54aaad2beab4684116687c64d
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92097f0b98245def4fd493d6f93f0c40c3a4e7e4f11939d1bbd3057b8f076619
+oid sha256:e4371c359f3f61a0b206a73cb497201135751765261ece06b66d5005fa4a3d9e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a00533389a4678d5ecaa8f25d54446914041611d7541f6bf05750bdc13a462b
+oid sha256:4c6c8e99b80f348613f137bd980faaac34ec4fa21cbf485269f4beb839740a21
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.4666666666666668,
+  "epoch": 1.5,
   "eval_steps": 500,
-  "global_step": 22000,
+  "global_step": 22500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1555,6 +1555,41 @@
       "learning_rate": 1.0225333333333334e-05,
       "loss": 0.0624,
       "step": 22000
+    },
+    {
+      "epoch": 1.4733333333333334,
+      "grad_norm": 0.2268645465373993,
+      "learning_rate": 1.0180888888888889e-05,
+      "loss": 0.0504,
+      "step": 22100
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.1687782257795334,
+      "learning_rate": 1.0136444444444444e-05,
+      "loss": 0.05,
+      "step": 22200
+    },
+    {
+      "epoch": 1.4866666666666668,
+      "grad_norm": 0.3606027364730835,
+      "learning_rate": 1.0092000000000001e-05,
+      "loss": 0.0558,
+      "step": 22300
+    },
+    {
+      "epoch": 1.4933333333333334,
+      "grad_norm": 0.18675172328948975,
+      "learning_rate": 1.0047555555555558e-05,
+      "loss": 0.058,
+      "step": 22400
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.29337164759635925,
+      "learning_rate": 1.0003111111111113e-05,
+      "loss": 0.0564,
+      "step": 22500
     }
   ],
   "logging_steps": 100,
@@ -1574,7 +1609,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.358829436928e+16,
+  "total_flos": 5.48062101504e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null