Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92f2973f2b3ea009c79105bfb97972c8e367a350ae65fb1468979b3a9b5e50f3
+oid sha256:8ebf77821607f524109e3b0d90768515247f13665452765c00368a8737474d0f
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acd8096c1458359309615421eb614275d07684a3f1bf01595ba7066644304914
+oid sha256:129f48fe78f214a7326263da24c1fc4ff08d336be18ddb2e7d46441a641de5e4
 size 19859140

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": 0.11730205278592376,
+  "epoch": 0.17595307917888564,
   "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": 45.256,
       "eval_steps_per_second": 22.628,
       "step": 10
+    },
+    {
+      "epoch": 0.12903225806451613,
+      "grad_norm": 0.9128552675247192,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 2.3762,
+      "step": 11
+    },
+    {
+      "epoch": 0.14076246334310852,
+      "grad_norm": 0.6775148510932922,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 2.3551,
+      "step": 12
+    },
+    {
+      "epoch": 0.15249266862170088,
+      "grad_norm": 0.6293225288391113,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 2.3521,
+      "step": 13
+    },
+    {
+      "epoch": 0.16422287390029325,
+      "grad_norm": 0.6110206842422485,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 2.1611,
+      "step": 14
+    },
+    {
+      "epoch": 0.17595307917888564,
+      "grad_norm": 0.7426127195358276,
+      "learning_rate": 5e-05,
+      "loss": 2.254,
+      "step": 15
+    },
+    {
+      "epoch": 0.17595307917888564,
+      "eval_loss": 2.3244590759277344,
+      "eval_runtime": 3.1977,
+      "eval_samples_per_second": 45.032,
+      "eval_steps_per_second": 22.516,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1313407946981376.0,
+  "total_flos": 1962004464009216.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null