Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98e73bbb56ed33df02becfea3375596f6d64b44a1dbbf2432e64797751172d8e
+oid sha256:111764613685ffc037603e88edea7c8fa029974a28056f2a0b4441f6a62cd001
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1271ea4d6fa8467eced8f934f22c530c32f8468a964095e9dd5cc3ea3dcf8996
+oid sha256:94951bde0f3f2d33e885e6c14f4e1ab0c5117bce5c17dd7b8283d7d2a2c03889
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8532b81b442a52e7641152d52819f99f24bb427b98bc8d1a82e25a081ba985ff
+oid sha256:295f0a621346f38e97a347d06bb9927816fe04926f6efca6f6b2fe56f30407d9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eee81c5e75673c3b9060a012dcd6537b28a2cc9b4464a9db8908848717dda896
+oid sha256:361be27873b08d40e317526a465204192a8fb0defda2b993ddf9efe3fb3de7d7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02942258183155572,
+  "epoch": 0.036778227289444645,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,28 @@
       "eval_samples_per_second": 11.03,
       "eval_steps_per_second": 1.387,
       "step": 20
+    },
+    {
+      "epoch": 0.030893710923133505,
+      "grad_norm": 1.5845534801483154,
+      "learning_rate": 4.123620120825459e-05,
+      "loss": 8.3277,
+      "step": 21
+    },
+    {
+      "epoch": 0.035307098197866864,
+      "grad_norm": 1.4348173141479492,
+      "learning_rate": 3.634976249348867e-05,
+      "loss": 7.9879,
+      "step": 24
+    },
+    {
+      "epoch": 0.036778227289444645,
+      "eval_loss": 1.9180830717086792,
+      "eval_runtime": 103.7801,
+      "eval_samples_per_second": 11.033,
+      "eval_steps_per_second": 1.388,
+      "step": 25
     }
   ],
   "logging_steps": 3,
@@ -108,7 +130,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.613858577416192e+16,
+  "total_flos": 3.26732322177024e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null