Training in progress, step 25000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a24784d7d4d1fc3fbb8fc67b836bb1c712f3f7b0c64c99ff1439b5fe2a051a5b
+oid sha256:e5271a77ad1e021749695ce7d0b16c4d3727b85c97d485c7bb3129da662dddf6
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:970bf634ac4ebe2edc929d89a76708d0db104aba94f7c07086ba7355e47fc214
+oid sha256:00b65ea8887464da7fcfa35adec6122142ff8b2f23f27b66874391d481d4ab50
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21c4e82da06fbd2a474e3defc7564dd624a46c9abb731c268ce51609d77b1972
+oid sha256:88a612cd3882628c0e5813e2d93583f2975d34afc744ee2ddc650af9cf2374f6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81a72d6c77b06746b972f475e80b7808db62786b79e89637fe4fa97684c444ab
+oid sha256:c12f3d0d653641cfe7f85f17f77b9ba95d2a97d1ea4e5bfd08bc3a80818a1f85
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.08147666603326797,
-  "best_model_checkpoint": "./fine-tuned/checkpoint-24500",
-  "epoch": 1.96,
+  "best_metric": 0.08146847784519196,
+  "best_model_checkpoint": "./fine-tuned/checkpoint-25000",
+  "epoch": 2.0,
   "eval_steps": 500,
-  "global_step": 24500,
+  "global_step": 25000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3829,6 +3829,84 @@
       "eval_samples_per_second": 22.712,
       "eval_steps_per_second": 5.678,
       "step": 24500
+    },
+    {
+      "epoch": 1.964,
+      "grad_norm": 0.1472010761499405,
+      "learning_rate": 5.496e-07,
+      "loss": 0.0485,
+      "step": 24550
+    },
+    {
+      "epoch": 1.968,
+      "grad_norm": 0.14501795172691345,
+      "learning_rate": 4.896e-07,
+      "loss": 0.0554,
+      "step": 24600
+    },
+    {
+      "epoch": 1.972,
+      "grad_norm": 0.09672766178846359,
+      "learning_rate": 4.296e-07,
+      "loss": 0.0534,
+      "step": 24650
+    },
+    {
+      "epoch": 1.976,
+      "grad_norm": 0.1332007199525833,
+      "learning_rate": 3.696e-07,
+      "loss": 0.0513,
+      "step": 24700
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 0.0856068879365921,
+      "learning_rate": 3.0959999999999997e-07,
+      "loss": 0.0531,
+      "step": 24750
+    },
+    {
+      "epoch": 1.984,
+      "grad_norm": 0.07875853031873703,
+      "learning_rate": 2.4959999999999996e-07,
+      "loss": 0.0511,
+      "step": 24800
+    },
+    {
+      "epoch": 1.988,
+      "grad_norm": 0.1319677084684372,
+      "learning_rate": 1.896e-07,
+      "loss": 0.0493,
+      "step": 24850
+    },
+    {
+      "epoch": 1.992,
+      "grad_norm": 0.20934289693832397,
+      "learning_rate": 1.296e-07,
+      "loss": 0.0559,
+      "step": 24900
+    },
+    {
+      "epoch": 1.996,
+      "grad_norm": 0.12190008908510208,
+      "learning_rate": 6.96e-08,
+      "loss": 0.0589,
+      "step": 24950
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.2332906574010849,
+      "learning_rate": 9.600000000000002e-09,
+      "loss": 0.0557,
+      "step": 25000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.08146847784519196,
+      "eval_runtime": 88.0931,
+      "eval_samples_per_second": 22.703,
+      "eval_steps_per_second": 5.676,
+      "step": 25000
     }
   ],
   "logging_steps": 50,
@@ -3843,12 +3921,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.967787327488e+16,
+  "total_flos": 6.0895789056e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null