Training in progress, step 7000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6285fa313f0947673eec5233d58debefd79860b88f1e8817dbce58e3f753178
+oid sha256:2c5f184b1d46adf06c909c07ec09ec73f59fa0356e2bb6d27bf1d629195e514e
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dbee5bdfb983c0e941bb4bb09b7db4d65254e5039bb314ca888b9a074cade77
+oid sha256:9d751b2339dd99faad4d27209d8ea82d6e6756bf23742c7710a4679bed5de6ad
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7da8bfa9479088a603d5d711484f1c342c030cc789c3b380976c39f9fdee1630
+oid sha256:d2abd40401eddc2bd3c6c44fde55af2f1f3f33fa474fa02d7522b22eefad8987
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e8c3d9b9adef7fe2e8d44bfba6c38d304f6dc2baa719635d5abe8206c21dc4c
+oid sha256:52ad8d98ce7fdace8246d70df783ac4b591617302d583209f66506bee9bb36f7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.08497656136751175,
   "best_model_checkpoint": "./fine-tuned/checkpoint-6500",
-  "epoch": 0.52,
+  "epoch": 0.56,
   "eval_steps": 500,
-  "global_step": 6500,
+  "global_step": 7000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1021,6 +1021,84 @@
       "eval_samples_per_second": 22.813,
       "eval_steps_per_second": 5.703,
       "step": 6500
+    },
+    {
+      "epoch": 0.524,
+      "grad_norm": 0.24468739330768585,
+      "learning_rate": 2.21424e-05,
+      "loss": 0.0688,
+      "step": 6550
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 0.17887485027313232,
+      "learning_rate": 2.20824e-05,
+      "loss": 0.0645,
+      "step": 6600
+    },
+    {
+      "epoch": 0.532,
+      "grad_norm": 0.12986980378627777,
+      "learning_rate": 2.2022399999999998e-05,
+      "loss": 0.0609,
+      "step": 6650
+    },
+    {
+      "epoch": 0.536,
+      "grad_norm": 0.25361281633377075,
+      "learning_rate": 2.1962399999999998e-05,
+      "loss": 0.0603,
+      "step": 6700
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.1815791130065918,
+      "learning_rate": 2.19024e-05,
+      "loss": 0.0659,
+      "step": 6750
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 0.12782719731330872,
+      "learning_rate": 2.18424e-05,
+      "loss": 0.0641,
+      "step": 6800
+    },
+    {
+      "epoch": 0.548,
+      "grad_norm": 0.1801528036594391,
+      "learning_rate": 2.17824e-05,
+      "loss": 0.0666,
+      "step": 6850
+    },
+    {
+      "epoch": 0.552,
+      "grad_norm": 0.1247314065694809,
+      "learning_rate": 2.17224e-05,
+      "loss": 0.0592,
+      "step": 6900
+    },
+    {
+      "epoch": 0.556,
+      "grad_norm": 0.19411933422088623,
+      "learning_rate": 2.16624e-05,
+      "loss": 0.0688,
+      "step": 6950
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.11316727846860886,
+      "learning_rate": 2.1602400000000002e-05,
+      "loss": 0.0635,
+      "step": 7000
+    },
+    {
+      "epoch": 0.56,
+      "eval_loss": 0.08500248938798904,
+      "eval_runtime": 87.7238,
+      "eval_samples_per_second": 22.799,
+      "eval_steps_per_second": 5.7,
+      "step": 7000
     }
   ],
   "logging_steps": 50,
@@ -1040,7 +1118,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.583290515456e+16,
+  "total_flos": 1.705082093568e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null