Training in progress, step 300000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86d436dc49f5f51ea77f6836f11593647aadd3d2d015e3b7016978a45cdea4be
+oid sha256:e419578f524e1611c3d5902d97ccf8efc92603d3b33f13949516891bb5476e00
 size 893441530

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d30e23f392129c2b6012431f5749433f649dc915f8d436528a227eb4caa64cc8
+oid sha256:3926e99c54fb7c961027b62d11498ced043c43266a692f441538601c7a5f10f7
 size 454197066

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2d397fa0d192b129facc18c0551253ed4f60480e5eab4c8aacf636029150284
-size 14244
+oid sha256:c42cb907bbd858ffd2b5bae4767d672ae3b753bd7ac85cb51990a0992d4df69a
+size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e51ba9fab0cc2d23119085e21856e86faf00d221719139ebcc44bc3aa4c220a
+oid sha256:08b25c62270eb67709cff9418808f83a4a7710e7ce508a964ce593dde6417e23
 size 1064

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.29,
-  "global_step": 290000,
+  "epoch": 0.3,
+  "global_step": 300000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2152,11 +2152,85 @@
       "eval_samples_per_second": 103.835,
       "eval_steps_per_second": 12.979,
       "step": 290000
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.7432579625275767e-05,
+      "loss": 0.3557,
+      "step": 291000
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.7422214882158484e-05,
+      "loss": 0.3569,
+      "step": 292000
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.7411816815187455e-05,
+      "loss": 0.3564,
+      "step": 293000
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.7401385538074276e-05,
+      "loss": 0.3574,
+      "step": 294000
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.7390921164893724e-05,
+      "loss": 0.3573,
+      "step": 295000
+    },
+    {
+      "epoch": 0.29,
+      "eval_runtime": 3244.7523,
+      "eval_samples_per_second": 104.677,
+      "eval_steps_per_second": 13.085,
+      "step": 295000
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.7380423810082507e-05,
+      "loss": 0.353,
+      "step": 296000
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.7369893588438012e-05,
+      "loss": 0.3568,
+      "step": 297000
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.7359330615117058e-05,
+      "loss": 0.3537,
+      "step": 298000
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.734873500563463e-05,
+      "loss": 0.3576,
+      "step": 299000
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.7338106875862617e-05,
+      "loss": 0.3575,
+      "step": 300000
+    },
+    {
+      "epoch": 0.3,
+      "eval_runtime": 3130.8127,
+      "eval_samples_per_second": 108.487,
+      "eval_steps_per_second": 13.561,
+      "step": 300000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 9223372036854775807,
-  "total_flos": 2.56783695023702e+21,
+  "total_flos": 2.656383051969331e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d30e23f392129c2b6012431f5749433f649dc915f8d436528a227eb4caa64cc8
+oid sha256:3926e99c54fb7c961027b62d11498ced043c43266a692f441538601c7a5f10f7
 size 454197066