Training in progress, step 4500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:584cc7080503436fab808747265007ba22d5dc7f87081d3d2a92c2bc981b6189
+oid sha256:e0b208bca8c38b9a486fdd9848f4c1f128bf3a9e0dd7c14795016400d7b156f9
 size 577789320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b71388c82afb605fda221fa01e407f05f575aea43c2ecf94e4b641246ae83f53
+oid sha256:cac6a52c28a4ed955005016fab85cda9f346342c5c6edaf668270626ccece527
 size 1155772233

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8395728209749e45e061868d1ad95ae4d38a60f0620c734e90b671f9bd79d5fa
+oid sha256:5effaff3153159d29c8fd9780ecce06ed2dc4f38caf2bd0d61af35ad7d99b03a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c60ee6aac5ac8445ac5970aadfe2a044f6171da693a5ec664e210ea94daaf15
+oid sha256:9becdbdb0c73597ccfbdbc6b4341353e796af8282a1a374bd120ee6357f11761
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.4142945408821106,
   "best_model_checkpoint": "mikhail_panzo/fil_b64_le4_s8000/checkpoint-2500",
-  "epoch": 177.77777777777777,
+  "epoch": 200.0,
   "eval_steps": 500,
-  "global_step": 4000,
+  "global_step": 4500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -631,6 +631,84 @@
       "eval_samples_per_second": 18.296,
       "eval_steps_per_second": 2.301,
       "step": 4000
+    },
+    {
+      "epoch": 180.0,
+      "grad_norm": 2.798970937728882,
+      "learning_rate": 6.585e-05,
+      "loss": 0.3657,
+      "step": 4050
+    },
+    {
+      "epoch": 182.22222222222223,
+      "grad_norm": 1.2629871368408203,
+      "learning_rate": 6.501666666666667e-05,
+      "loss": 0.3666,
+      "step": 4100
+    },
+    {
+      "epoch": 184.44444444444446,
+      "grad_norm": 0.970268964767456,
+      "learning_rate": 6.418333333333334e-05,
+      "loss": 0.3668,
+      "step": 4150
+    },
+    {
+      "epoch": 186.66666666666666,
+      "grad_norm": 1.7865740060806274,
+      "learning_rate": 6.335e-05,
+      "loss": 0.364,
+      "step": 4200
+    },
+    {
+      "epoch": 188.88888888888889,
+      "grad_norm": 0.8204932808876038,
+      "learning_rate": 6.251666666666666e-05,
+      "loss": 0.3647,
+      "step": 4250
+    },
+    {
+      "epoch": 191.11111111111111,
+      "grad_norm": 0.910372257232666,
+      "learning_rate": 6.168333333333333e-05,
+      "loss": 0.3676,
+      "step": 4300
+    },
+    {
+      "epoch": 193.33333333333334,
+      "grad_norm": 1.2381336688995361,
+      "learning_rate": 6.085000000000001e-05,
+      "loss": 0.3632,
+      "step": 4350
+    },
+    {
+      "epoch": 195.55555555555554,
+      "grad_norm": 1.588180661201477,
+      "learning_rate": 6.0016666666666664e-05,
+      "loss": 0.3621,
+      "step": 4400
+    },
+    {
+      "epoch": 197.77777777777777,
+      "grad_norm": 1.093023419380188,
+      "learning_rate": 5.918333333333333e-05,
+      "loss": 0.3609,
+      "step": 4450
+    },
+    {
+      "epoch": 200.0,
+      "grad_norm": 1.071207046508789,
+      "learning_rate": 5.835e-05,
+      "loss": 0.362,
+      "step": 4500
+    },
+    {
+      "epoch": 200.0,
+      "eval_loss": 0.42145419120788574,
+      "eval_runtime": 7.8841,
+      "eval_samples_per_second": 20.167,
+      "eval_steps_per_second": 2.537,
+      "step": 4500
     }
   ],
   "logging_steps": 50,
@@ -650,7 +728,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.495380828098797e+16,
+  "total_flos": 6.180482295807811e+16,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null