Training in progress, step 8000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d78442b4e54c305874c81e5bbdf0ba83af286871119ec98549317a5f4613ce1e
+oid sha256:14347b694edbac48f71cf8408ac46afe84e4750316570c1ed940bf72283d84fe
 size 577789320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ddfa344f1d95e08566566e266a49ffbeb8411a7a9f2ace99274a0aaeec28e86
+oid sha256:424e6a391353585b51b6aa2f3d9a51faefe01f643f861e61d4f4255d4be74b1e
 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:ba9826396d1061aee6fdf7293fd789e47f8a5ac9db78d8396f43ecdcae9b12a2
+oid sha256:f11095f13a6bb8e73004d74d741982d584b499e9ac31a59ea1de9965f3fec76b
 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": 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": 20.184,
       "eval_steps_per_second": 2.579,
       "step": 7500
+    },
+    {
+      "epoch": 149.5049504950495,
+      "grad_norm": 1.1068042516708374,
+      "learning_rate": 7.566666666666667e-07,
+      "loss": 0.4029,
+      "step": 7550
+    },
+    {
+      "epoch": 150.4950495049505,
+      "grad_norm": 1.2785730361938477,
+      "learning_rate": 6.733333333333334e-07,
+      "loss": 0.4001,
+      "step": 7600
+    },
+    {
+      "epoch": 151.4851485148515,
+      "grad_norm": 1.0063281059265137,
+      "learning_rate": 5.900000000000001e-07,
+      "loss": 0.3977,
+      "step": 7650
+    },
+    {
+      "epoch": 152.47524752475246,
+      "grad_norm": 1.1545789241790771,
+      "learning_rate": 5.066666666666667e-07,
+      "loss": 0.4015,
+      "step": 7700
+    },
+    {
+      "epoch": 153.46534653465346,
+      "grad_norm": 1.0624966621398926,
+      "learning_rate": 4.233333333333334e-07,
+      "loss": 0.4044,
+      "step": 7750
+    },
+    {
+      "epoch": 154.45544554455446,
+      "grad_norm": 1.3898247480392456,
+      "learning_rate": 3.4000000000000003e-07,
+      "loss": 0.4005,
+      "step": 7800
+    },
+    {
+      "epoch": 155.44554455445544,
+      "grad_norm": 1.2618342638015747,
+      "learning_rate": 2.566666666666667e-07,
+      "loss": 0.4025,
+      "step": 7850
+    },
+    {
+      "epoch": 156.43564356435644,
+      "grad_norm": 1.0798155069351196,
+      "learning_rate": 1.7333333333333335e-07,
+      "loss": 0.4015,
+      "step": 7900
+    },
+    {
+      "epoch": 157.4257425742574,
+      "grad_norm": 1.0550168752670288,
+      "learning_rate": 9e-08,
+      "loss": 0.3952,
+      "step": 7950
+    },
+    {
+      "epoch": 158.41584158415841,
+      "grad_norm": 1.0714497566223145,
+      "learning_rate": 6.666666666666667e-09,
+      "loss": 0.3989,
+      "step": 8000
+    },
+    {
+      "epoch": 158.41584158415841,
+      "eval_loss": 0.39282524585723877,
+      "eval_runtime": 8.2483,
+      "eval_samples_per_second": 21.823,
+      "eval_steps_per_second": 2.788,
+      "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