Training in progress, step 2000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7c9c6832d9b9ae653131500755efe8459dc2939032a1a72e8b52c63f0712a9c
+oid sha256:1e5aa83ea314da30a6ec0a6ec269ff5cf39237d3466631877f4ba4181db862d3
 size 471641972

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:261006764b961cb77ecaa2b21e3d80eafad77c93a3fcd0f268ba14b40110edb0
+oid sha256:26cba81b64fd91075b5245eb0f07f97e602bdf0fb2c89db319fba234803a644a
 size 943408715

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ed2b6db1ec60a90525d794c2133b0b06d86cdbb9449fa71c4bc4c94c91b3cb8
+oid sha256:47b49161b40289a196f0b323f09234647ca94a52a813ac8389a3c26b9e4065b1
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce8670e31cae653a7a564e9213a3ea8b6e626fad48fd45659de57f0263ddc216
+oid sha256:07aeb2ac6edabf9bd17bc37036b0bfcddb1f3b70b32195f555982e9c1e0b8fec
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": Infinity,
   "best_model_checkpoint": null,
-  "epoch": 0.12690355329949238,
+  "epoch": 0.25380710659898476,
   "eval_steps": 1000,
-  "global_step": 1000,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -93,6 +93,84 @@
       "eval_samples_per_second": 332.374,
       "eval_steps_per_second": 41.547,
       "step": 1000
+    },
+    {
+      "epoch": 0.13959390862944163,
+      "grad_norm": 8.010664939880371,
+      "learning_rate": 9.792278920651884e-05,
+      "loss": 3.4147,
+      "step": 1100
+    },
+    {
+      "epoch": 0.15228426395939088,
+      "grad_norm": 8.114327430725098,
+      "learning_rate": 9.725487576810046e-05,
+      "loss": 3.2962,
+      "step": 1200
+    },
+    {
+      "epoch": 0.1649746192893401,
+      "grad_norm": 7.225535869598389,
+      "learning_rate": 9.658696232968207e-05,
+      "loss": 3.1452,
+      "step": 1300
+    },
+    {
+      "epoch": 0.17766497461928935,
+      "grad_norm": 7.01926326751709,
+      "learning_rate": 9.591904889126369e-05,
+      "loss": 3.0837,
+      "step": 1400
+    },
+    {
+      "epoch": 0.19035532994923857,
+      "grad_norm": 8.998798370361328,
+      "learning_rate": 9.525113545284532e-05,
+      "loss": 3.011,
+      "step": 1500
+    },
+    {
+      "epoch": 0.20304568527918782,
+      "grad_norm": 9.184762954711914,
+      "learning_rate": 9.458322201442693e-05,
+      "loss": 2.9722,
+      "step": 1600
+    },
+    {
+      "epoch": 0.21573604060913706,
+      "grad_norm": 7.888009071350098,
+      "learning_rate": 9.391530857600855e-05,
+      "loss": 2.9282,
+      "step": 1700
+    },
+    {
+      "epoch": 0.22842639593908629,
+      "grad_norm": 8.22140884399414,
+      "learning_rate": 9.324739513759018e-05,
+      "loss": 2.8396,
+      "step": 1800
+    },
+    {
+      "epoch": 0.24111675126903553,
+      "grad_norm": 6.9004950523376465,
+      "learning_rate": 9.257948169917178e-05,
+      "loss": 2.7948,
+      "step": 1900
+    },
+    {
+      "epoch": 0.25380710659898476,
+      "grad_norm": 8.627703666687012,
+      "learning_rate": 9.191156826075342e-05,
+      "loss": 2.7533,
+      "step": 2000
+    },
+    {
+      "epoch": 0.25380710659898476,
+      "eval_loss": NaN,
+      "eval_runtime": 631.0573,
+      "eval_samples_per_second": 399.629,
+      "eval_steps_per_second": 49.954,
+      "step": 2000
     }
   ],
   "logging_steps": 100,
@@ -107,7 +185,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -121,7 +199,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 542189854973952.0,
+  "total_flos": 1087545149735424.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null