Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98b756dcfbebdd4514f5d127e35262efe4156d546ea77dd9256c161ca2b556ec
+oid sha256:64da054c93a16fb6e1ef0847fe0d797ab54982efa19f47494e0b5ae3f2839369
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5ce9b24f3719a554d62ece4c61312f5afcbb47d740e6a2fca29ece9192f8533
+oid sha256:601b0830993c2ca49af0f1ab3b15f9686870e2555ad211a46250284c590a2b7e
 size 3633466

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6011dbc1beaf916a24aa0692a7ad3787fe62f4d3127d9859b27643438838594d
+oid sha256:ff5440c0314dadc3defe4b4803f353543d71edfcba882e67961bec9458fb6240
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:ff2736979009751c0c6b0ddcc5f6544d6f723aa752b4798eab0b70fb76cf0083
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01710863986313088,
+  "epoch": 0.02566295979469632,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 201.021,
       "eval_steps_per_second": 100.613,
       "step": 10
+    },
+    {
+      "epoch": 0.018819503849443968,
+      "grad_norm": 1.2083159685134888,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.7023,
+      "step": 11
+    },
+    {
+      "epoch": 0.020530367835757058,
+      "grad_norm": 1.0155587196350098,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.6187,
+      "step": 12
+    },
+    {
+      "epoch": 0.022241231822070145,
+      "grad_norm": 1.0483033657073975,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.7,
+      "step": 13
+    },
+    {
+      "epoch": 0.023952095808383235,
+      "grad_norm": 0.8496240973472595,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.5521,
+      "step": 14
+    },
+    {
+      "epoch": 0.02566295979469632,
+      "grad_norm": 1.384743571281433,
+      "learning_rate": 5e-05,
+      "loss": 0.7186,
+      "step": 15
+    },
+    {
+      "epoch": 0.02566295979469632,
+      "eval_loss": 0.7239178419113159,
+      "eval_runtime": 4.9498,
+      "eval_samples_per_second": 198.999,
+      "eval_steps_per_second": 99.6,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 203183954067456.0,
+  "total_flos": 304347272970240.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null