Training in progress, step 4000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9e45fd838445085c38479903a62f6a446ac21368c6ea0eee96b18976cdf1100
+oid sha256:d18172f59d8cdf13648e208a2c9ed68e2c35f57395062ef667619c24cf24b102
 size 577789320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c0444821e06045c29f274919e49fff065deb13d65ad3fa51f76eb6cb00e2087
+oid sha256:af71716effd1caa22736d3a7d131f24e94f7344597d19702a29f27b880db0d3d
 size 1155772233

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d4282cda397df08dd845515457d155ad917a58fea1e7c7925c8b77caccfc2db
+oid sha256:6b7465f2e8b9bae857f76ec186b635aab5838dc4b5b3ef7b6cfb473e08afcb86
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ccd61c3eccb4c4508bcc2fc4d263b434bb910fdf4295c867e005e4b128c82ef
+oid sha256:0bd01f1a543bd9ecb58737837f10f865ac053c6c89fa1a7cdbd04da0c2caf558
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.41326722502708435,
   "best_model_checkpoint": "mikhail-panzo/fil_b64_le5_s8000/checkpoint-3500",
-  "epoch": 152.17391304347825,
+  "epoch": 173.91304347826087,
   "eval_steps": 500,
-  "global_step": 3500,
+  "global_step": 4000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -553,6 +553,84 @@
       "eval_samples_per_second": 24.518,
       "eval_steps_per_second": 3.084,
       "step": 3500
+    },
+    {
+      "epoch": 154.34782608695653,
+      "grad_norm": 2.30401611328125,
+      "learning_rate": 7.421666666666667e-06,
+      "loss": 0.4248,
+      "step": 3550
+    },
+    {
+      "epoch": 156.52173913043478,
+      "grad_norm": 0.9738525152206421,
+      "learning_rate": 7.338333333333334e-06,
+      "loss": 0.4354,
+      "step": 3600
+    },
+    {
+      "epoch": 158.69565217391303,
+      "grad_norm": 2.276857376098633,
+      "learning_rate": 7.255000000000001e-06,
+      "loss": 0.4345,
+      "step": 3650
+    },
+    {
+      "epoch": 160.8695652173913,
+      "grad_norm": 1.118604063987732,
+      "learning_rate": 7.171666666666667e-06,
+      "loss": 0.4243,
+      "step": 3700
+    },
+    {
+      "epoch": 163.04347826086956,
+      "grad_norm": 1.1995043754577637,
+      "learning_rate": 7.088333333333334e-06,
+      "loss": 0.4229,
+      "step": 3750
+    },
+    {
+      "epoch": 165.2173913043478,
+      "grad_norm": 1.1676712036132812,
+      "learning_rate": 7.005000000000001e-06,
+      "loss": 0.4225,
+      "step": 3800
+    },
+    {
+      "epoch": 167.3913043478261,
+      "grad_norm": 1.7886515855789185,
+      "learning_rate": 6.921666666666668e-06,
+      "loss": 0.4243,
+      "step": 3850
+    },
+    {
+      "epoch": 169.56521739130434,
+      "grad_norm": 1.0336685180664062,
+      "learning_rate": 6.838333333333334e-06,
+      "loss": 0.4288,
+      "step": 3900
+    },
+    {
+      "epoch": 171.7391304347826,
+      "grad_norm": 3.572209596633911,
+      "learning_rate": 6.7550000000000005e-06,
+      "loss": 0.4262,
+      "step": 3950
+    },
+    {
+      "epoch": 173.91304347826087,
+      "grad_norm": 3.631232261657715,
+      "learning_rate": 6.6716666666666674e-06,
+      "loss": 0.4264,
+      "step": 4000
+    },
+    {
+      "epoch": 173.91304347826087,
+      "eval_loss": 0.4149872660636902,
+      "eval_runtime": 6.8222,
+      "eval_samples_per_second": 23.306,
+      "eval_steps_per_second": 2.932,
+      "step": 4000
     }
   ],
   "logging_steps": 50,
@@ -572,7 +650,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.194546896348691e+16,
+  "total_flos": 5.937591783240058e+16,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null