Training in progress, step 4000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e88bcddd088e858a9bb66970598a4a31f3a99fa875613237e38373a495920782
+oid sha256:fb20c01c6d0ed7412fdd53b3fd1d6b5664d0c4fe72256922bfcaa6f72fead983
 size 577789320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:438c0b912e69bdcffb4b36884a45fded87e651b5552ce3d28f7d81aadd80e521
+oid sha256:49a22853b7504b5d628e13034dcce42f3e37578207b02ac2cf906dcd5dd394a1
 size 1155772233

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bf2e8e416936cf8f439e26111c4885ea7eb78961a1138cdb6b5117961ec9a25
+oid sha256:546eb67e9ac703715999e4a48906215e9d1d8502c3d871bfb0192cba37d95e1c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29698bcd3e83b59e82799f82508a0c896d6666ff11032f6f0bdfe1ebc23e6468
+oid sha256:9c60ee6aac5ac8445ac5970aadfe2a044f6171da693a5ec664e210ea94daaf15
 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": 138.6138613861386,
+  "epoch": 158.41584158415841,
   "eval_steps": 500,
-  "global_step": 3500,
+  "global_step": 4000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -553,6 +553,84 @@
       "eval_samples_per_second": 23.582,
       "eval_steps_per_second": 3.013,
       "step": 3500
+    },
+    {
+      "epoch": 140.59405940594058,
+      "grad_norm": 2.1505396366119385,
+      "learning_rate": 7.418333333333334e-05,
+      "loss": 0.367,
+      "step": 3550
+    },
+    {
+      "epoch": 142.5742574257426,
+      "grad_norm": 1.6036536693572998,
+      "learning_rate": 7.335000000000001e-05,
+      "loss": 0.3622,
+      "step": 3600
+    },
+    {
+      "epoch": 144.55445544554456,
+      "grad_norm": 1.1357529163360596,
+      "learning_rate": 7.251666666666666e-05,
+      "loss": 0.3589,
+      "step": 3650
+    },
+    {
+      "epoch": 146.53465346534654,
+      "grad_norm": 1.5478957891464233,
+      "learning_rate": 7.168333333333333e-05,
+      "loss": 0.3577,
+      "step": 3700
+    },
+    {
+      "epoch": 148.5148514851485,
+      "grad_norm": 1.0070338249206543,
+      "learning_rate": 7.085e-05,
+      "loss": 0.3582,
+      "step": 3750
+    },
+    {
+      "epoch": 150.4950495049505,
+      "grad_norm": 0.9300253987312317,
+      "learning_rate": 7.001666666666667e-05,
+      "loss": 0.3563,
+      "step": 3800
+    },
+    {
+      "epoch": 152.47524752475246,
+      "grad_norm": 0.9197555184364319,
+      "learning_rate": 6.918333333333334e-05,
+      "loss": 0.3514,
+      "step": 3850
+    },
+    {
+      "epoch": 154.45544554455446,
+      "grad_norm": 0.6059859991073608,
+      "learning_rate": 6.835000000000001e-05,
+      "loss": 0.3575,
+      "step": 3900
+    },
+    {
+      "epoch": 156.43564356435644,
+      "grad_norm": 0.7884564399719238,
+      "learning_rate": 6.751666666666668e-05,
+      "loss": 0.3613,
+      "step": 3950
+    },
+    {
+      "epoch": 158.41584158415841,
+      "grad_norm": 0.7471904754638672,
+      "learning_rate": 6.668333333333333e-05,
+      "loss": 0.3525,
+      "step": 4000
+    },
+    {
+      "epoch": 158.41584158415841,
+      "eval_loss": 0.39685142040252686,
+      "eval_runtime": 7.1693,
+      "eval_samples_per_second": 25.107,
+      "eval_steps_per_second": 3.208,
+      "step": 4000
     }
   ],
   "logging_steps": 50,
@@ -572,7 +650,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.78207684271391e+16,
+  "total_flos": 4.322114324975938e+16,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null