Training in progress, step 5500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5e8f8ee6350b5bf599e72c4ed95c5ed225294745782627a48eb47afcd60198a
+oid sha256:faa8d265400b8791cf4a64562e9e11c979135179f68220ef5ea4d9c6d3c03a42
 size 577789320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3e98f457664f710d43650233769483b6f02ab91fe63bc5195ec194110b01ada
+oid sha256:53cf28f4d98aad829ae5bdc1a8c4046f73443537482fbc16a8e07a413da66020
 size 1155772233

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73ecc1efc440dd76fa6474f280ad4ef4dfdd6e209fee029d2373c73ccc111e83
+oid sha256:bbcf3cde1491bc0510b355c8e8cc9d1b437a18e9740ee673986de59df4b2ff6f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b02450bf90416881debf85ba0d776babdc9d2efe4751382ccfff0b7db595003
+oid sha256:5b353b67d3c68734cb4cbcb55694f7eeeb40f54128ba041a6736d420b09008b6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.3931240439414978,
   "best_model_checkpoint": "mikhail-panzo/ceb_b64_le5_s8000/checkpoint-5000",
-  "epoch": 196.07843137254903,
+  "epoch": 215.68627450980392,
   "eval_steps": 500,
-  "global_step": 5000,
+  "global_step": 5500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -787,6 +787,84 @@
       "eval_samples_per_second": 27.936,
       "eval_steps_per_second": 3.57,
       "step": 5000
+    },
+    {
+      "epoch": 198.0392156862745,
+      "grad_norm": 0.9328787922859192,
+      "learning_rate": 4.92e-06,
+      "loss": 0.405,
+      "step": 5050
+    },
+    {
+      "epoch": 200.0,
+      "grad_norm": 1.2074756622314453,
+      "learning_rate": 4.836666666666667e-06,
+      "loss": 0.3996,
+      "step": 5100
+    },
+    {
+      "epoch": 201.9607843137255,
+      "grad_norm": 0.7930981516838074,
+      "learning_rate": 4.753333333333333e-06,
+      "loss": 0.3994,
+      "step": 5150
+    },
+    {
+      "epoch": 203.92156862745097,
+      "grad_norm": 0.8685852885246277,
+      "learning_rate": 4.670000000000001e-06,
+      "loss": 0.3983,
+      "step": 5200
+    },
+    {
+      "epoch": 205.88235294117646,
+      "grad_norm": 0.8023931980133057,
+      "learning_rate": 4.586666666666667e-06,
+      "loss": 0.4041,
+      "step": 5250
+    },
+    {
+      "epoch": 207.84313725490196,
+      "grad_norm": 0.7825555801391602,
+      "learning_rate": 4.503333333333333e-06,
+      "loss": 0.4012,
+      "step": 5300
+    },
+    {
+      "epoch": 209.80392156862746,
+      "grad_norm": 1.1338242292404175,
+      "learning_rate": 4.42e-06,
+      "loss": 0.3996,
+      "step": 5350
+    },
+    {
+      "epoch": 211.76470588235293,
+      "grad_norm": 1.3594533205032349,
+      "learning_rate": 4.336666666666667e-06,
+      "loss": 0.4022,
+      "step": 5400
+    },
+    {
+      "epoch": 213.72549019607843,
+      "grad_norm": 1.0148471593856812,
+      "learning_rate": 4.253333333333334e-06,
+      "loss": 0.4003,
+      "step": 5450
+    },
+    {
+      "epoch": 215.68627450980392,
+      "grad_norm": 0.932323157787323,
+      "learning_rate": 4.17e-06,
+      "loss": 0.4055,
+      "step": 5500
+    },
+    {
+      "epoch": 215.68627450980392,
+      "eval_loss": 0.3945559561252594,
+      "eval_runtime": 6.6419,
+      "eval_samples_per_second": 27.101,
+      "eval_steps_per_second": 3.463,
+      "step": 5500
     }
   ],
   "logging_steps": 50,
@@ -806,7 +884,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.440105584628308e+16,
+  "total_flos": 5.984476827927444e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null