Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b13dc2280d67714abd8f873ede5e607d50de59228b2814b12a46cd0b8ad10f17
+oid sha256:71b09cdeb18c34078e9491dd106900e84f1ddcddb6578902427a88407134e6dd
 size 209760536

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8de025b6a8b6ee19a01a69f179b6a667aec141736a4140ca906fa91fd04a1892
+oid sha256:ba9c29ec827360a3982e6f01cda37a2a0dc21319cdeb8c295c01dda2c1634d38
 size 419620666

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:426dd7c3d52534a781d2600dff8dc59ec80d8a1446190dc82ba661359f7ead62
+oid sha256:85e13fa025c9a824f965c7766c9716c9550812a29eb06c59107269912ce31e69
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00015941590014188016,
+  "epoch": 0.0003188318002837603,
   "eval_steps": 8,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "learning_rate": 9e-05,
       "loss": 7.0782,
       "step": 9
+    },
+    {
+      "epoch": 0.00019129908017025618,
+      "grad_norm": 0.8096962571144104,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 6.3456,
+      "step": 12
+    },
+    {
+      "epoch": 0.00023912385021282023,
+      "grad_norm": 0.9577824473381042,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 5.6146,
+      "step": 15
+    },
+    {
+      "epoch": 0.00025506544022700823,
+      "eval_loss": 1.4773930311203003,
+      "eval_runtime": 5097.0629,
+      "eval_samples_per_second": 5.182,
+      "eval_steps_per_second": 2.591,
+      "step": 16
+    },
+    {
+      "epoch": 0.00028694862025538425,
+      "grad_norm": 1.3272778987884521,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 5.7386,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6601911922851840.0,
+  "total_flos": 1.320382384570368e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null