Training in progress, step 7500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bf207505ea0770e992b10321cf92842a01b7db9b1ba86d3f01074f365bd4ae7
+oid sha256:d78442b4e54c305874c81e5bbdf0ba83af286871119ec98549317a5f4613ce1e
 size 577789320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a89e9b7bd3a572819055db2b92d6c96066357d4810b359c18fbacd1f6df90fcc
+oid sha256:0ddfa344f1d95e08566566e266a49ffbeb8411a7a9f2ace99274a0aaeec28e86
 size 1155772233

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fd469b706d373ddaaa5e043595342540cb7b58eeea80694856200a502dbfc77
+oid sha256:7aca6dd3493fbba1f0e04ce463672e9c6637c7fdcee4f2b30e09ee0d653c8045
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79faef7859961c2a638e4312a796703fd0c86e5877b740a2ce8b47db225af025
+oid sha256:ba9826396d1061aee6fdf7293fd789e47f8a5ac9db78d8396f43ecdcae9b12a2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.3917270302772522,
   "best_model_checkpoint": "mikhail-panzo/ceb_b32_le5_s8000/checkpoint-6500",
-  "epoch": 138.6138613861386,
+  "epoch": 148.5148514851485,
   "eval_steps": 500,
-  "global_step": 7000,
+  "global_step": 7500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1099,6 +1099,84 @@
       "eval_samples_per_second": 23.822,
       "eval_steps_per_second": 3.044,
       "step": 7000
+    },
+    {
+      "epoch": 139.6039603960396,
+      "grad_norm": 1.1762559413909912,
+      "learning_rate": 1.5900000000000002e-06,
+      "loss": 0.4117,
+      "step": 7050
+    },
+    {
+      "epoch": 140.59405940594058,
+      "grad_norm": 1.515325665473938,
+      "learning_rate": 1.506666666666667e-06,
+      "loss": 0.4014,
+      "step": 7100
+    },
+    {
+      "epoch": 141.58415841584159,
+      "grad_norm": 1.0724811553955078,
+      "learning_rate": 1.4233333333333336e-06,
+      "loss": 0.4028,
+      "step": 7150
+    },
+    {
+      "epoch": 142.5742574257426,
+      "grad_norm": 1.0034635066986084,
+      "learning_rate": 1.34e-06,
+      "loss": 0.3977,
+      "step": 7200
+    },
+    {
+      "epoch": 143.56435643564356,
+      "grad_norm": 1.1974977254867554,
+      "learning_rate": 1.2566666666666668e-06,
+      "loss": 0.4013,
+      "step": 7250
+    },
+    {
+      "epoch": 144.55445544554456,
+      "grad_norm": 1.167351484298706,
+      "learning_rate": 1.1733333333333335e-06,
+      "loss": 0.3992,
+      "step": 7300
+    },
+    {
+      "epoch": 145.54455445544554,
+      "grad_norm": 1.1566020250320435,
+      "learning_rate": 1.0900000000000002e-06,
+      "loss": 0.4,
+      "step": 7350
+    },
+    {
+      "epoch": 146.53465346534654,
+      "grad_norm": 0.8720223307609558,
+      "learning_rate": 1.0066666666666668e-06,
+      "loss": 0.4006,
+      "step": 7400
+    },
+    {
+      "epoch": 147.52475247524754,
+      "grad_norm": 1.1982648372650146,
+      "learning_rate": 9.233333333333334e-07,
+      "loss": 0.3999,
+      "step": 7450
+    },
+    {
+      "epoch": 148.5148514851485,
+      "grad_norm": 1.1742349863052368,
+      "learning_rate": 8.400000000000001e-07,
+      "loss": 0.3989,
+      "step": 7500
+    },
+    {
+      "epoch": 148.5148514851485,
+      "eval_loss": 0.3927270770072937,
+      "eval_runtime": 8.9179,
+      "eval_samples_per_second": 20.184,
+      "eval_steps_per_second": 2.579,
+      "step": 7500
     }
   ],
   "logging_steps": 50,
@@ -1118,7 +1196,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.78207684271391e+16,
+  "total_flos": 4.051916995267073e+16,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null