Training in progress, step 4500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb20c01c6d0ed7412fdd53b3fd1d6b5664d0c4fe72256922bfcaa6f72fead983
+oid sha256:d6a0a45b5c73136651ea586a81a22e48be0c01723e388f5ecb20cadf32c2d146
 size 577789320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49a22853b7504b5d628e13034dcce42f3e37578207b02ac2cf906dcd5dd394a1
+oid sha256:0bfb144672a55867df598f92e30f306392e5627f25e7e988d31605510f3f6276
 size 1155772233

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:546eb67e9ac703715999e4a48906215e9d1d8502c3d871bfb0192cba37d95e1c
+oid sha256:23cfe734181a7e84ba3feae03eb5140aab76f01a3b8447c97bd8142d5e306dad
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c60ee6aac5ac8445ac5970aadfe2a044f6171da693a5ec664e210ea94daaf15
+oid sha256:9becdbdb0c73597ccfbdbc6b4341353e796af8282a1a374bd120ee6357f11761
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.39598318934440613,
   "best_model_checkpoint": "mikhail_panzo/ceb_b64_le4_s8000/checkpoint-3500",
-  "epoch": 158.41584158415841,
+  "epoch": 178.21782178217822,
   "eval_steps": 500,
-  "global_step": 4000,
+  "global_step": 4500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -631,6 +631,84 @@
       "eval_samples_per_second": 25.107,
       "eval_steps_per_second": 3.208,
       "step": 4000
+    },
+    {
+      "epoch": 160.3960396039604,
+      "grad_norm": 0.9373750686645508,
+      "learning_rate": 6.585e-05,
+      "loss": 0.3537,
+      "step": 4050
+    },
+    {
+      "epoch": 162.37623762376236,
+      "grad_norm": 1.3369851112365723,
+      "learning_rate": 6.501666666666667e-05,
+      "loss": 0.3585,
+      "step": 4100
+    },
+    {
+      "epoch": 164.35643564356437,
+      "grad_norm": 0.6891220211982727,
+      "learning_rate": 6.418333333333334e-05,
+      "loss": 0.3519,
+      "step": 4150
+    },
+    {
+      "epoch": 166.33663366336634,
+      "grad_norm": 0.8272483944892883,
+      "learning_rate": 6.335e-05,
+      "loss": 0.3542,
+      "step": 4200
+    },
+    {
+      "epoch": 168.31683168316832,
+      "grad_norm": 0.9853746891021729,
+      "learning_rate": 6.251666666666666e-05,
+      "loss": 0.3553,
+      "step": 4250
+    },
+    {
+      "epoch": 170.2970297029703,
+      "grad_norm": 1.0020989179611206,
+      "learning_rate": 6.168333333333333e-05,
+      "loss": 0.3558,
+      "step": 4300
+    },
+    {
+      "epoch": 172.27722772277227,
+      "grad_norm": 1.4780181646347046,
+      "learning_rate": 6.085000000000001e-05,
+      "loss": 0.3505,
+      "step": 4350
+    },
+    {
+      "epoch": 174.25742574257427,
+      "grad_norm": 0.9966872334480286,
+      "learning_rate": 6.0016666666666664e-05,
+      "loss": 0.3513,
+      "step": 4400
+    },
+    {
+      "epoch": 176.23762376237624,
+      "grad_norm": 1.2055169343948364,
+      "learning_rate": 5.918333333333333e-05,
+      "loss": 0.3509,
+      "step": 4450
+    },
+    {
+      "epoch": 178.21782178217822,
+      "grad_norm": 1.075426697731018,
+      "learning_rate": 5.835e-05,
+      "loss": 0.3545,
+      "step": 4500
+    },
+    {
+      "epoch": 178.21782178217822,
+      "eval_loss": 0.3981594443321228,
+      "eval_runtime": 6.8387,
+      "eval_samples_per_second": 26.321,
+      "eval_steps_per_second": 3.363,
+      "step": 4500
     }
   ],
   "logging_steps": 50,
@@ -650,7 +728,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.322114324975938e+16,
+  "total_flos": 4.862391888488112e+16,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null