Training in progress, step 1500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ce54e79e12252bae59725175488c3040706f1f2b3d873b46e5f7b8b4f2a94b7
+oid sha256:dfdb7a77d08b547c9c6992da199c063102f2b6c903aeaded67a582185a7a9a63
 size 577789320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:daa35d4afe619e77f5e075540ee2f825ce0dd6443ebafffcbfc84cbf09c27f5f
+oid sha256:a2648dbe15b2f12a7a27e77dc5a033f32672097c1fa4da3c801f2f4394e3a081
 size 1155772233

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eead311c135878827beadbd3c4b2cc7fba012f606f4bb99598cadd7e7cbf63b8
+oid sha256:50c476b54e3f06971186d630174c9829d4b9b06eb8eab96946ff7745f50fcfcc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8210f8e2249c280ac4965b4cc059199e79e619c33beb58bb250012029c0aaadf
+oid sha256:1a94e74103068a5fb8b31be8524087df4f57bd43f07d1db2b9d36084882fdbb5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.39941468834877014,
   "best_model_checkpoint": "mikhail_panzo/ceb_b64_le4_s8000/checkpoint-1000",
-  "epoch": 39.603960396039604,
+  "epoch": 59.40594059405941,
   "eval_steps": 500,
-  "global_step": 1000,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -163,6 +163,84 @@
       "eval_samples_per_second": 24.123,
       "eval_steps_per_second": 3.082,
       "step": 1000
+    },
+    {
+      "epoch": 41.584158415841586,
+      "grad_norm": 2.8653476238250732,
+      "learning_rate": 5.245e-05,
+      "loss": 0.4268,
+      "step": 1050
+    },
+    {
+      "epoch": 43.56435643564357,
+      "grad_norm": 1.5550223588943481,
+      "learning_rate": 5.495e-05,
+      "loss": 0.4265,
+      "step": 1100
+    },
+    {
+      "epoch": 45.54455445544554,
+      "grad_norm": 1.804150104522705,
+      "learning_rate": 5.745e-05,
+      "loss": 0.4192,
+      "step": 1150
+    },
+    {
+      "epoch": 47.524752475247524,
+      "grad_norm": 1.9916889667510986,
+      "learning_rate": 5.995000000000001e-05,
+      "loss": 0.4149,
+      "step": 1200
+    },
+    {
+      "epoch": 49.504950495049506,
+      "grad_norm": 2.1027019023895264,
+      "learning_rate": 6.245000000000001e-05,
+      "loss": 0.4203,
+      "step": 1250
+    },
+    {
+      "epoch": 51.48514851485149,
+      "grad_norm": 1.1542466878890991,
+      "learning_rate": 6.494999999999999e-05,
+      "loss": 0.4127,
+      "step": 1300
+    },
+    {
+      "epoch": 53.46534653465346,
+      "grad_norm": 1.8733513355255127,
+      "learning_rate": 6.745e-05,
+      "loss": 0.4165,
+      "step": 1350
+    },
+    {
+      "epoch": 55.445544554455445,
+      "grad_norm": 2.544435739517212,
+      "learning_rate": 6.995e-05,
+      "loss": 0.4156,
+      "step": 1400
+    },
+    {
+      "epoch": 57.42574257425743,
+      "grad_norm": 2.9764773845672607,
+      "learning_rate": 7.245000000000001e-05,
+      "loss": 0.4045,
+      "step": 1450
+    },
+    {
+      "epoch": 59.40594059405941,
+      "grad_norm": 1.334035038948059,
+      "learning_rate": 7.495e-05,
+      "loss": 0.4075,
+      "step": 1500
+    },
+    {
+      "epoch": 59.40594059405941,
+      "eval_loss": 0.40177610516548157,
+      "eval_runtime": 6.8721,
+      "eval_samples_per_second": 26.193,
+      "eval_steps_per_second": 3.347,
+      "step": 1500
     }
   ],
   "logging_steps": 50,
@@ -182,7 +260,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0803690034289064e+16,
+  "total_flos": 1.6206373863449352e+16,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null