Training in progress, step 2000, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1635ff493aa519c5f30369636e8878234b655a0814e69ae4d8564d50dcdeda5
+oid sha256:993ebd29d60cf74d729607be7535ff900f1686ae6540c14b5448b141c17c89bd
 size 1001436090

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cadba7cba1c5a5048705cb26b34fbce7d0efdc1f379d462a37db7987df19fcd
+oid sha256:f752d463e725c61a26b667909ecce1aa465b98909bf3944f71ea3f1f1f9164ef
 size 500704602

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1701f11bae0225927f0a15fe016a503fb5442618ce4f6adfa514bb6b69ae591
+oid sha256:8b68988526a415dcb3130161d19be0023ecfa7543158f651622c931e2d744176
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecc42a44c7d848601d80219f0d1eb00781589042cb6b9acb00e933718b0d9adb
+oid sha256:1679676eae92a38677246489e338d905f8ad588bd072400ef5910115fa41db57
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.9305019305019306,
+  "epoch": 3.861003861003861,
   "eval_steps": 100,
-  "global_step": 1000,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -147,13 +147,153 @@
       "eval_samples_per_second": 184.369,
       "eval_steps_per_second": 11.543,
       "step": 1000
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 9.15057915057915e-05,
+      "loss": 2.5298,
+      "step": 1100
+    },
+    {
+      "epoch": 2.12,
+      "eval_loss": 2.9245471954345703,
+      "eval_runtime": 15.8964,
+      "eval_samples_per_second": 183.878,
+      "eval_steps_per_second": 11.512,
+      "step": 1100
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 9.073359073359073e-05,
+      "loss": 2.4042,
+      "step": 1200
+    },
+    {
+      "epoch": 2.32,
+      "eval_loss": 2.9138386249542236,
+      "eval_runtime": 15.8757,
+      "eval_samples_per_second": 184.117,
+      "eval_steps_per_second": 11.527,
+      "step": 1200
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 8.996138996138996e-05,
+      "loss": 2.454,
+      "step": 1300
+    },
+    {
+      "epoch": 2.51,
+      "eval_loss": 2.910158157348633,
+      "eval_runtime": 15.8495,
+      "eval_samples_per_second": 184.422,
+      "eval_steps_per_second": 11.546,
+      "step": 1300
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 8.918918918918919e-05,
+      "loss": 2.4826,
+      "step": 1400
+    },
+    {
+      "epoch": 2.7,
+      "eval_loss": 2.8909964561462402,
+      "eval_runtime": 15.8725,
+      "eval_samples_per_second": 184.155,
+      "eval_steps_per_second": 11.529,
+      "step": 1400
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 8.841698841698842e-05,
+      "loss": 2.4967,
+      "step": 1500
+    },
+    {
+      "epoch": 2.9,
+      "eval_loss": 2.899423122406006,
+      "eval_runtime": 15.8786,
+      "eval_samples_per_second": 184.084,
+      "eval_steps_per_second": 11.525,
+      "step": 1500
+    },
+    {
+      "epoch": 3.09,
+      "learning_rate": 8.764478764478765e-05,
+      "loss": 2.3621,
+      "step": 1600
+    },
+    {
+      "epoch": 3.09,
+      "eval_loss": 2.966057538986206,
+      "eval_runtime": 15.8621,
+      "eval_samples_per_second": 184.276,
+      "eval_steps_per_second": 11.537,
+      "step": 1600
+    },
+    {
+      "epoch": 3.28,
+      "learning_rate": 8.687258687258688e-05,
+      "loss": 2.1633,
+      "step": 1700
+    },
+    {
+      "epoch": 3.28,
+      "eval_loss": 2.950388193130493,
+      "eval_runtime": 15.8876,
+      "eval_samples_per_second": 183.98,
+      "eval_steps_per_second": 11.518,
+      "step": 1700
+    },
+    {
+      "epoch": 3.47,
+      "learning_rate": 8.61003861003861e-05,
+      "loss": 2.2039,
+      "step": 1800
+    },
+    {
+      "epoch": 3.47,
+      "eval_loss": 2.9389660358428955,
+      "eval_runtime": 15.8602,
+      "eval_samples_per_second": 184.298,
+      "eval_steps_per_second": 11.538,
+      "step": 1800
+    },
+    {
+      "epoch": 3.67,
+      "learning_rate": 8.532818532818533e-05,
+      "loss": 2.2382,
+      "step": 1900
+    },
+    {
+      "epoch": 3.67,
+      "eval_loss": 2.94706392288208,
+      "eval_runtime": 15.8638,
+      "eval_samples_per_second": 184.256,
+      "eval_steps_per_second": 11.536,
+      "step": 1900
+    },
+    {
+      "epoch": 3.86,
+      "learning_rate": 8.455598455598456e-05,
+      "loss": 2.2235,
+      "step": 2000
+    },
+    {
+      "epoch": 3.86,
+      "eval_loss": 2.9332854747772217,
+      "eval_runtime": 15.8506,
+      "eval_samples_per_second": 184.409,
+      "eval_steps_per_second": 11.545,
+      "step": 2000
     }
   ],
   "logging_steps": 100,
   "max_steps": 12950,
   "num_train_epochs": 25,
   "save_steps": 1000,
-  "total_flos": 5004154253952000.0,
+  "total_flos": 1.0018169220096e+16,
   "trial_name": null,
   "trial_params": null
 }