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:d078e43505dfe4719a7b5b3d7872229a9e161bce7ee442e399fe2e11a81a4e66
+oid sha256:ae278b3e85383875f421ff36b4eee7e5005fe8d313b4f062df299d62b4a24a29
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37f73a026f03da663aecf168248b10a5a959fccc92f4d62375493dd9ebad3972
+oid sha256:24303179311cba1a348c5db8a5b04b807ea04ca8c092ba7b9e2def36d26550cc
 size 13685516

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": 0.2821869488536155,
+  "epoch": 0.42328042328042326,
   "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": 121.289,
       "eval_steps_per_second": 60.645,
       "step": 10
+    },
+    {
+      "epoch": 0.31040564373897706,
+      "grad_norm": 3.115682601928711,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 6.0316,
+      "step": 11
+    },
+    {
+      "epoch": 0.3386243386243386,
+      "grad_norm": 3.406926155090332,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 6.203,
+      "step": 12
+    },
+    {
+      "epoch": 0.36684303350970016,
+      "grad_norm": 3.4907941818237305,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 5.9364,
+      "step": 13
+    },
+    {
+      "epoch": 0.3950617283950617,
+      "grad_norm": 3.92707896232605,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 5.4231,
+      "step": 14
+    },
+    {
+      "epoch": 0.42328042328042326,
+      "grad_norm": 3.5260536670684814,
+      "learning_rate": 5e-05,
+      "loss": 5.4519,
+      "step": 15
+    },
+    {
+      "epoch": 0.42328042328042326,
+      "eval_loss": 4.813125133514404,
+      "eval_runtime": 0.5202,
+      "eval_samples_per_second": 115.351,
+      "eval_steps_per_second": 57.676,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1023167913000960.0,
+  "total_flos": 1534751869501440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null