Training in progress, step 15000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:054ab94a66b126df267b052c3963349825d38029b9947a5eeef3e088fc94d5e3
+oid sha256:c8b87db48356f50aba644c7f62751e63e8a04ec2268f84e4eba37dd50c1a0411
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c700b2458cc3a7d705b174e5b082b75ff9b46e4556e47eb6bc98ed85f7b5b362
+oid sha256:85a117e1ecba729ee34a78722b6baa410d7ae44754ab32c14568e8bd85298764
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c9886b9061bb2e70af0da0a78b4bba065bbf4e416078705ff5fff6c95adfc84
+oid sha256:5cb981e2bdbf592329578c66e6b81722ec222bc355b0ddd3bdc9f7689a385e7a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6ce624ffb18558fd63335de21c66bfccbf585f56176b1bb9297748553d5fb95
+oid sha256:0054105d8fb5cdfddd8876e0968830f9a7aa658759cebb2ad97ea276facb582b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.0824647843837738,
-  "best_model_checkpoint": "./fine-tuned/checkpoint-12500",
-  "epoch": 1.16,
+  "best_metric": 0.08243728429079056,
+  "best_model_checkpoint": "./fine-tuned/checkpoint-15000",
+  "epoch": 1.2,
   "eval_steps": 500,
-  "global_step": 14500,
+  "global_step": 15000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2269,6 +2269,84 @@
       "eval_samples_per_second": 22.714,
       "eval_steps_per_second": 5.678,
       "step": 14500
+    },
+    {
+      "epoch": 1.164,
+      "grad_norm": 0.06833196431398392,
+      "learning_rate": 1.25436e-05,
+      "loss": 0.0586,
+      "step": 14550
+    },
+    {
+      "epoch": 1.168,
+      "grad_norm": 0.16051365435123444,
+      "learning_rate": 1.24836e-05,
+      "loss": 0.056,
+      "step": 14600
+    },
+    {
+      "epoch": 1.172,
+      "grad_norm": 0.18909616768360138,
+      "learning_rate": 1.24236e-05,
+      "loss": 0.057,
+      "step": 14650
+    },
+    {
+      "epoch": 1.176,
+      "grad_norm": 0.17333486676216125,
+      "learning_rate": 1.23636e-05,
+      "loss": 0.0562,
+      "step": 14700
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 0.0701974630355835,
+      "learning_rate": 1.23036e-05,
+      "loss": 0.0545,
+      "step": 14750
+    },
+    {
+      "epoch": 1.184,
+      "grad_norm": 0.1582074612379074,
+      "learning_rate": 1.2243599999999999e-05,
+      "loss": 0.06,
+      "step": 14800
+    },
+    {
+      "epoch": 1.188,
+      "grad_norm": 0.13948781788349152,
+      "learning_rate": 1.21836e-05,
+      "loss": 0.0529,
+      "step": 14850
+    },
+    {
+      "epoch": 1.192,
+      "grad_norm": 0.0946699008345604,
+      "learning_rate": 1.21236e-05,
+      "loss": 0.0668,
+      "step": 14900
+    },
+    {
+      "epoch": 1.196,
+      "grad_norm": 0.1089014783501625,
+      "learning_rate": 1.20636e-05,
+      "loss": 0.0562,
+      "step": 14950
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.09682592004537582,
+      "learning_rate": 1.20036e-05,
+      "loss": 0.0548,
+      "step": 15000
+    },
+    {
+      "epoch": 1.2,
+      "eval_loss": 0.08243728429079056,
+      "eval_runtime": 88.0302,
+      "eval_samples_per_second": 22.719,
+      "eval_steps_per_second": 5.68,
+      "step": 15000
     }
   ],
   "logging_steps": 50,
@@ -2288,7 +2366,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.531955765248e+16,
+  "total_flos": 3.65374734336e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null