Training in progress, step 5500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1e91e1bdef8cc188ea4d189cd5523f60cddadc3613fe79933294461a702e8a8
+oid sha256:43ca506b0183f9255cc6c3701ab3aee5b7772bf568964446510a6d0a144e6b33
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89290f193b6b7457d80f97bce6f0ec93a64c4a9bc3d593d8d12aeb4cde9c3c6d
+oid sha256:7c1038f81f76195378c96900b3959ec8f4c557986d1afd0f635616ff00bffc77
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ea7477084e9e4ebf5f677e60167e6c2deee97d19a5a21299c6eb4ed40d31928
+oid sha256:e7f92d67c89ccf30b9936f79f017a85d14b84762689e01f7c463f2d3a6a334a4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69f50b15ae17c7257c9fed364b38e68d62581d1ae697e8e4bb273e2e41cb49e9
+oid sha256:774dfffb03e2468097535f9b9aa538278b4485e6383bdbb24c5835c80721018e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.0860014408826828,
-  "best_model_checkpoint": "./fine-tuned/checkpoint-5000",
-  "epoch": 0.4,
+  "best_metric": 0.08539459854364395,
+  "best_model_checkpoint": "./fine-tuned/checkpoint-5500",
+  "epoch": 0.44,
   "eval_steps": 500,
-  "global_step": 5000,
+  "global_step": 5500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -787,6 +787,84 @@
       "eval_samples_per_second": 22.798,
       "eval_steps_per_second": 5.699,
       "step": 5000
+    },
+    {
+      "epoch": 0.404,
+      "grad_norm": 0.1547604650259018,
+      "learning_rate": 2.39424e-05,
+      "loss": 0.0691,
+      "step": 5050
+    },
+    {
+      "epoch": 0.408,
+      "grad_norm": 0.17712494730949402,
+      "learning_rate": 2.38824e-05,
+      "loss": 0.064,
+      "step": 5100
+    },
+    {
+      "epoch": 0.412,
+      "grad_norm": 0.16606800258159637,
+      "learning_rate": 2.38224e-05,
+      "loss": 0.0687,
+      "step": 5150
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 0.18862195312976837,
+      "learning_rate": 2.37624e-05,
+      "loss": 0.0662,
+      "step": 5200
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.1778397411108017,
+      "learning_rate": 2.3702400000000002e-05,
+      "loss": 0.0632,
+      "step": 5250
+    },
+    {
+      "epoch": 0.424,
+      "grad_norm": 0.15363118052482605,
+      "learning_rate": 2.36424e-05,
+      "loss": 0.0617,
+      "step": 5300
+    },
+    {
+      "epoch": 0.428,
+      "grad_norm": 0.1690954864025116,
+      "learning_rate": 2.35824e-05,
+      "loss": 0.0717,
+      "step": 5350
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 0.19384829699993134,
+      "learning_rate": 2.35224e-05,
+      "loss": 0.0669,
+      "step": 5400
+    },
+    {
+      "epoch": 0.436,
+      "grad_norm": 0.20759643614292145,
+      "learning_rate": 2.34624e-05,
+      "loss": 0.0662,
+      "step": 5450
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.16528765857219696,
+      "learning_rate": 2.34024e-05,
+      "loss": 0.0737,
+      "step": 5500
+    },
+    {
+      "epoch": 0.44,
+      "eval_loss": 0.08539459854364395,
+      "eval_runtime": 87.7109,
+      "eval_samples_per_second": 22.802,
+      "eval_steps_per_second": 5.701,
+      "step": 5500
     }
   ],
   "logging_steps": 50,
@@ -806,7 +884,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.21791578112e+16,
+  "total_flos": 1.339707359232e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null