Training in progress, step 8000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99876fe6bd351f75a02b3a9808186d1b448bd2491ee23ee0a8aeb43bc170fbd6
+oid sha256:1bd35714ae6834e3a058bdc15b7498341f12549cbde8d04ed3efab8547ebadad
 size 577789320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a96075133b42f651d7fd0d56298216a77015a7ef39f1a5b980259ccf9be9b410
+oid sha256:6abb4c00a59e74b942e5f9da52770fc7e6fb415772ab74e2af1e568a7cc45b67
 size 1155772233

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7aca6dd3493fbba1f0e04ce463672e9c6637c7fdcee4f2b30e09ee0d653c8045
+oid sha256:e65d5e866573e78443e1465c9b9c0413095bd120b3384ac5fdd2285abe38197f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5cdfe5ed4f14bdadfee62402701e9c3c91a7e1b8246c7c7f0be536b67574fb3
+oid sha256:797161cb36b8434a2e9b424b1551b1d663e1ac4112ca3f634c3c132aead6996b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.39791539311408997,
   "best_model_checkpoint": "mikhail-panzo/ceb_b32_le4_s8000/checkpoint-4500",
-  "epoch": 148.5148514851485,
+  "epoch": 158.41584158415841,
   "eval_steps": 500,
-  "global_step": 7500,
+  "global_step": 8000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1177,6 +1177,84 @@
       "eval_samples_per_second": 22.161,
       "eval_steps_per_second": 2.832,
       "step": 7500
+    },
+    {
+      "epoch": 149.5049504950495,
+      "grad_norm": 0.6580781936645508,
+      "learning_rate": 7.55e-06,
+      "loss": 0.345,
+      "step": 7550
+    },
+    {
+      "epoch": 150.4950495049505,
+      "grad_norm": 1.1213836669921875,
+      "learning_rate": 6.716666666666667e-06,
+      "loss": 0.3411,
+      "step": 7600
+    },
+    {
+      "epoch": 151.4851485148515,
+      "grad_norm": 0.6676567792892456,
+      "learning_rate": 5.8833333333333335e-06,
+      "loss": 0.3387,
+      "step": 7650
+    },
+    {
+      "epoch": 152.47524752475246,
+      "grad_norm": 0.6813247799873352,
+      "learning_rate": 5.050000000000001e-06,
+      "loss": 0.3416,
+      "step": 7700
+    },
+    {
+      "epoch": 153.46534653465346,
+      "grad_norm": 1.187516212463379,
+      "learning_rate": 4.216666666666666e-06,
+      "loss": 0.3448,
+      "step": 7750
+    },
+    {
+      "epoch": 154.45544554455446,
+      "grad_norm": 0.8873435854911804,
+      "learning_rate": 3.3833333333333337e-06,
+      "loss": 0.3413,
+      "step": 7800
+    },
+    {
+      "epoch": 155.44554455445544,
+      "grad_norm": 0.7723808288574219,
+      "learning_rate": 2.55e-06,
+      "loss": 0.3431,
+      "step": 7850
+    },
+    {
+      "epoch": 156.43564356435644,
+      "grad_norm": 1.762637734413147,
+      "learning_rate": 1.7166666666666668e-06,
+      "loss": 0.3424,
+      "step": 7900
+    },
+    {
+      "epoch": 157.4257425742574,
+      "grad_norm": 0.5451408624649048,
+      "learning_rate": 8.833333333333334e-07,
+      "loss": 0.3369,
+      "step": 7950
+    },
+    {
+      "epoch": 158.41584158415841,
+      "grad_norm": 0.7317779660224915,
+      "learning_rate": 5.0000000000000004e-08,
+      "loss": 0.34,
+      "step": 8000
+    },
+    {
+      "epoch": 158.41584158415841,
+      "eval_loss": 0.3990664780139923,
+      "eval_runtime": 7.7498,
+      "eval_samples_per_second": 23.226,
+      "eval_steps_per_second": 2.968,
+      "step": 8000
     }
   ],
   "logging_steps": 50,
@@ -1191,12 +1269,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.051916995267073e+16,
+  "total_flos": 4.322114324975938e+16,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null