Training in progress, step 6000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43ca506b0183f9255cc6c3701ab3aee5b7772bf568964446510a6d0a144e6b33
+oid sha256:095aeb5c44cb9a72ed1a0f1b80ff171de934de9ed141a1a2063927e0ba663d9e
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c1038f81f76195378c96900b3959ec8f4c557986d1afd0f635616ff00bffc77
+oid sha256:50e33fe817fc94e5049b80c11e32eacd950298cccd79b079b276bb66599beb80
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7f92d67c89ccf30b9936f79f017a85d14b84762689e01f7c463f2d3a6a334a4
+oid sha256:fd399035d6d61703194945de98fdae7ea399ca55d89cd8d7f88b8fcde8480235
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:774dfffb03e2468097535f9b9aa538278b4485e6383bdbb24c5835c80721018e
+oid sha256:4409b78a0c49863ad1dc85e7b70a0947c6e5044950cda1ebb0cfe114c7f86bca
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.08539459854364395,
   "best_model_checkpoint": "./fine-tuned/checkpoint-5500",
-  "epoch": 0.44,
+  "epoch": 0.48,
   "eval_steps": 500,
-  "global_step": 5500,
+  "global_step": 6000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -865,6 +865,84 @@
       "eval_samples_per_second": 22.802,
       "eval_steps_per_second": 5.701,
       "step": 5500
+    },
+    {
+      "epoch": 0.444,
+      "grad_norm": 0.09632231295108795,
+      "learning_rate": 2.3342400000000002e-05,
+      "loss": 0.0621,
+      "step": 5550
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 0.15080232918262482,
+      "learning_rate": 2.32824e-05,
+      "loss": 0.0674,
+      "step": 5600
+    },
+    {
+      "epoch": 0.452,
+      "grad_norm": 0.14794333279132843,
+      "learning_rate": 2.32224e-05,
+      "loss": 0.0662,
+      "step": 5650
+    },
+    {
+      "epoch": 0.456,
+      "grad_norm": 0.15014077723026276,
+      "learning_rate": 2.31624e-05,
+      "loss": 0.0574,
+      "step": 5700
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.10953331738710403,
+      "learning_rate": 2.31024e-05,
+      "loss": 0.0684,
+      "step": 5750
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 0.17434537410736084,
+      "learning_rate": 2.30424e-05,
+      "loss": 0.0687,
+      "step": 5800
+    },
+    {
+      "epoch": 0.468,
+      "grad_norm": 0.12245655059814453,
+      "learning_rate": 2.29824e-05,
+      "loss": 0.0689,
+      "step": 5850
+    },
+    {
+      "epoch": 0.472,
+      "grad_norm": 0.10118559747934341,
+      "learning_rate": 2.29224e-05,
+      "loss": 0.0609,
+      "step": 5900
+    },
+    {
+      "epoch": 0.476,
+      "grad_norm": 0.14768172800540924,
+      "learning_rate": 2.28624e-05,
+      "loss": 0.0717,
+      "step": 5950
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.18510164320468903,
+      "learning_rate": 2.28024e-05,
+      "loss": 0.0716,
+      "step": 6000
+    },
+    {
+      "epoch": 0.48,
+      "eval_loss": 0.08568704128265381,
+      "eval_runtime": 87.7082,
+      "eval_samples_per_second": 22.803,
+      "eval_steps_per_second": 5.701,
+      "step": 6000
     }
   ],
   "logging_steps": 50,
@@ -884,7 +962,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.339707359232e+16,
+  "total_flos": 1.461498937344e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null