Training in progress, step 3500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c11f704b1b4aa8bc3af8188283a5921d8394ced6d379868e0222fce729a62f3
+oid sha256:c40c6de7444148be371ad64018106aad8e6968c48ad4f1a5ba76c5bbb3457825
 size 577789320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddccfc72ff5eb6b1be097bb2e77e7140dfb67b555437c64a78d573e0f9c95559
+oid sha256:cde8fb2c9d2fad7abe888cd8eebf39657d7017c06365654c14e57548a415a268
 size 1155772233

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee653f7383e3e0a38bcdb44f8cb7eeb17acb240c4b99ac1103433495e7d56368
+oid sha256:2c9bf8a55d2767cc2209da3cec6b29014b65c97cebef0df143ce81d06133a59d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad1b29a2638e1b447334a358eec29a8b7ed7b3b45a0cb1bd7d41f21fb38e93d2
+oid sha256:3b37e9ef30e383e795affd2915d5979e774d36e929b105a379fff9b722cf9675
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.3979886472225189,
-  "best_model_checkpoint": "mikhail_panzo/ceb_b32_le5_s4000/checkpoint-3000",
-  "epoch": 59.40594059405941,
+  "best_metric": 0.3965218663215637,
+  "best_model_checkpoint": "mikhail_panzo/ceb_b32_le5_s4000/checkpoint-3500",
+  "epoch": 69.3069306930693,
   "eval_steps": 500,
-  "global_step": 3000,
+  "global_step": 3500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -475,6 +475,84 @@
       "eval_samples_per_second": 25.821,
       "eval_steps_per_second": 3.299,
       "step": 3000
+    },
+    {
+      "epoch": 60.396039603960396,
+      "grad_norm": 1.2070516347885132,
+      "learning_rate": 4.755e-06,
+      "loss": 0.4339,
+      "step": 3050
+    },
+    {
+      "epoch": 61.386138613861384,
+      "grad_norm": 1.050790548324585,
+      "learning_rate": 4.505e-06,
+      "loss": 0.4223,
+      "step": 3100
+    },
+    {
+      "epoch": 62.37623762376238,
+      "grad_norm": 1.0747731924057007,
+      "learning_rate": 4.255e-06,
+      "loss": 0.4277,
+      "step": 3150
+    },
+    {
+      "epoch": 63.366336633663366,
+      "grad_norm": 1.7592554092407227,
+      "learning_rate": 4.005000000000001e-06,
+      "loss": 0.4234,
+      "step": 3200
+    },
+    {
+      "epoch": 64.35643564356435,
+      "grad_norm": 0.9947736263275146,
+      "learning_rate": 3.7550000000000005e-06,
+      "loss": 0.4297,
+      "step": 3250
+    },
+    {
+      "epoch": 65.34653465346534,
+      "grad_norm": 1.4066519737243652,
+      "learning_rate": 3.505e-06,
+      "loss": 0.4228,
+      "step": 3300
+    },
+    {
+      "epoch": 66.33663366336634,
+      "grad_norm": 1.2692670822143555,
+      "learning_rate": 3.255e-06,
+      "loss": 0.4216,
+      "step": 3350
+    },
+    {
+      "epoch": 67.32673267326733,
+      "grad_norm": 1.1489667892456055,
+      "learning_rate": 3.005e-06,
+      "loss": 0.4207,
+      "step": 3400
+    },
+    {
+      "epoch": 68.31683168316832,
+      "grad_norm": 1.1599435806274414,
+      "learning_rate": 2.7550000000000003e-06,
+      "loss": 0.4225,
+      "step": 3450
+    },
+    {
+      "epoch": 69.3069306930693,
+      "grad_norm": 1.3135476112365723,
+      "learning_rate": 2.505e-06,
+      "loss": 0.4228,
+      "step": 3500
+    },
+    {
+      "epoch": 69.3069306930693,
+      "eval_loss": 0.3965218663215637,
+      "eval_runtime": 7.2483,
+      "eval_samples_per_second": 24.833,
+      "eval_steps_per_second": 3.173,
+      "step": 3500
     }
   ],
   "logging_steps": 50,
@@ -494,7 +572,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6206373863449352e+16,
+  "total_flos": 1.89071129766222e+16,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null