Training in progress, step 99, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d252f39e4c118ba28df113c091d2f96041db6bd084560903c5bffdc30e80e2d5
+oid sha256:2469b7f1630992c57af81b05dad6de0c275f7da3ed2a6416eba9b2633cac25aa
 size 34793120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38364dc3bf6bcd8e454896ee392b1564151763b1b24574acdca4c63a1aa2edc2
+oid sha256:4fa3094ba801fb51dad8f008e37ec47ca7cd82a7bdfcca678780b805ea1272aa
 size 18132116

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f83e68cb6a4a890208b1eef3cbc3a679a0fd71015d7548509bdf4aed6690926d
+oid sha256:d5aab06f0a66985fccaabc6be66903c6da6e74a9f7a0beef6221d698a0e2eb49
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0569f9f06b6a114946825bdc699040cc55958cfef46aba8eb5fb625896d49025
+oid sha256:5b64833e2721bfb57dae2a544bde34ace02492c2f80bfbff48034c9946dc6b4a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.2720848056537102,
+  "epoch": 1.3992932862190812,
   "eval_steps": 9,
-  "global_step": 90,
+  "global_step": 99,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -305,6 +305,35 @@
       "eval_samples_per_second": 39.944,
       "eval_steps_per_second": 4.993,
       "step": 90
+    },
+    {
+      "epoch": 1.314487632508834,
+      "grad_norm": 0.06280746310949326,
+      "learning_rate": 7.426068431000882e-07,
+      "loss": 2.4519,
+      "step": 93
+    },
+    {
+      "epoch": 1.3568904593639575,
+      "grad_norm": 0.07523226737976074,
+      "learning_rate": 2.4329828146074095e-07,
+      "loss": 2.6474,
+      "step": 96
+    },
+    {
+      "epoch": 1.3992932862190812,
+      "grad_norm": 0.0763295441865921,
+      "learning_rate": 1.522932452260595e-08,
+      "loss": 2.5686,
+      "step": 99
+    },
+    {
+      "epoch": 1.3992932862190812,
+      "eval_loss": 2.3409645557403564,
+      "eval_runtime": 2.9989,
+      "eval_samples_per_second": 40.015,
+      "eval_steps_per_second": 5.002,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.14420684423168e+16,
+  "total_flos": 1.258627528654848e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null