Training in progress, step 1000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53a641713a48fe2c2775fef9c54e774fea83ba96701599d9ea2cc9fc22d196f2
+oid sha256:ff8cae616e41b6eeadfd895301ce06f02907c037312d6d128cbc6789ddc9b7f8
 size 577789320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1bdda7358e270805a3339ad3586cfc53df99d948d4c7bd7eadc3d776a5a7bc6
+oid sha256:ec073b4caedc3cfb8350822a4965385a3c9d2c064db1caa88ca86be33b024ab7
 size 1155772233

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2014204079f4cf57723509002ee27c406cb9fda25b9864e76faa196ba0c2eaa1
+oid sha256:45cef88be00665fc8a314476e14e0a14878c0d750e849e6b98a7e57eddf92a77
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92e482854e4ff3c178dda878d03bf3633330934a775fc818e1843bd607d65d07
+oid sha256:6080dc3c4f31046c753abd07ed5f1a8449e11695e9772af37e8337628bc01d7f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.4584241807460785,
-  "best_model_checkpoint": "mikhail-panzo/ceb_b128_le5_s4000/checkpoint-500",
-  "epoch": 39.21568627450981,
+  "best_metric": 0.42202475666999817,
+  "best_model_checkpoint": "mikhail-panzo/ceb_b128_le5_s4000/checkpoint-1000",
+  "epoch": 78.43137254901961,
   "eval_steps": 500,
-  "global_step": 500,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -85,6 +85,84 @@
       "eval_samples_per_second": 28.171,
       "eval_steps_per_second": 3.6,
       "step": 500
+    },
+    {
+      "epoch": 43.13725490196079,
+      "grad_norm": 0.8968011736869812,
+      "learning_rate": 2.7450000000000004e-06,
+      "loss": 0.5121,
+      "step": 550
+    },
+    {
+      "epoch": 47.05882352941177,
+      "grad_norm": 1.1953343152999878,
+      "learning_rate": 2.995e-06,
+      "loss": 0.5047,
+      "step": 600
+    },
+    {
+      "epoch": 50.98039215686274,
+      "grad_norm": 0.8916338682174683,
+      "learning_rate": 3.2450000000000003e-06,
+      "loss": 0.5013,
+      "step": 650
+    },
+    {
+      "epoch": 54.90196078431372,
+      "grad_norm": 1.166737675666809,
+      "learning_rate": 3.495e-06,
+      "loss": 0.4847,
+      "step": 700
+    },
+    {
+      "epoch": 58.8235294117647,
+      "grad_norm": 0.9191999435424805,
+      "learning_rate": 3.745e-06,
+      "loss": 0.4849,
+      "step": 750
+    },
+    {
+      "epoch": 62.745098039215684,
+      "grad_norm": 1.0393210649490356,
+      "learning_rate": 3.995000000000001e-06,
+      "loss": 0.4827,
+      "step": 800
+    },
+    {
+      "epoch": 66.66666666666667,
+      "grad_norm": 0.764959454536438,
+      "learning_rate": 4.245e-06,
+      "loss": 0.483,
+      "step": 850
+    },
+    {
+      "epoch": 70.58823529411765,
+      "grad_norm": 1.0713616609573364,
+      "learning_rate": 4.495e-06,
+      "loss": 0.4762,
+      "step": 900
+    },
+    {
+      "epoch": 74.50980392156863,
+      "grad_norm": 0.8433477282524109,
+      "learning_rate": 4.745e-06,
+      "loss": 0.4702,
+      "step": 950
+    },
+    {
+      "epoch": 78.43137254901961,
+      "grad_norm": 0.6966288685798645,
+      "learning_rate": 4.9950000000000005e-06,
+      "loss": 0.4634,
+      "step": 1000
+    },
+    {
+      "epoch": 78.43137254901961,
+      "eval_loss": 0.42202475666999817,
+      "eval_runtime": 6.3604,
+      "eval_samples_per_second": 28.3,
+      "eval_steps_per_second": 3.616,
+      "step": 1000
     }
   ],
   "logging_steps": 50,
@@ -104,7 +182,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.088442385035588e+16,
+  "total_flos": 2.176673010094044e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null