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:c12eec3d9555b262a7a1435cfafc62807f8cbebc1dc3693eef87cf3c48a6bbe3
+oid sha256:e86fb750a11e3920161d2c12478f32d3cb703c03420e25ff266f54027ad7ec6a
 size 28348936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34c8afce54830e372f0c500c0f16ea0f923554f21caf1730b459cd6f071dd4ca
+oid sha256:b592ff2534fbb8d8fca8fa35d74a1b199438e1af0af5112c8b5cd595ee765a20
 size 14714004

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": 0.0037942564443074296,
+  "epoch": 0.005691384666461145,
   "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": 38.863,
       "eval_steps_per_second": 19.436,
       "step": 10
+    },
+    {
+      "epoch": 0.004173682088738173,
+      "grad_norm": 1.3251705169677734,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 4.0423,
+      "step": 11
+    },
+    {
+      "epoch": 0.004553107733168915,
+      "grad_norm": 1.281868815422058,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 3.6271,
+      "step": 12
+    },
+    {
+      "epoch": 0.004932533377599658,
+      "grad_norm": 1.4134122133255005,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 3.7919,
+      "step": 13
+    },
+    {
+      "epoch": 0.005311959022030402,
+      "grad_norm": 1.4654074907302856,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 3.6354,
+      "step": 14
+    },
+    {
+      "epoch": 0.005691384666461145,
+      "grad_norm": 1.5566564798355103,
+      "learning_rate": 5e-05,
+      "loss": 3.4872,
+      "step": 15
+    },
+    {
+      "epoch": 0.005691384666461145,
+      "eval_loss": 3.444849729537964,
+      "eval_runtime": 114.2907,
+      "eval_samples_per_second": 38.84,
+      "eval_steps_per_second": 19.424,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1298095480504320.0,
+  "total_flos": 1947143220756480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null