Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78e965f8a6390205972f53c9273588c19457c6759b764c5ca0f1fe62c45d1080
+oid sha256:251c3b9093844066151de4ac2118356d8317997372ae9878e7ebe2aac9ae3f43
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4055c9a5a8c092ddc7343a6df05131a34a767e5a7a220836aa4b69f8cc814e91
+oid sha256:4c91ce781038e9fb6e4498ccc9a9f5facdcd66cf94cb28f3847f8b9a5624d6e6
 size 42545748

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db05f4be4bfd57c6db9f1684109ea8219cb794f0abafbe3b2696e0554a780ed9
+oid sha256:8d6306c7ebebc1ba61010c16f5f72bbe4229c8a68ab9af106d32f4e58acec2ce
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85ee19ea163e868f40d9ecdcecd226ea53d13afff03ee0a58dfaa5fb6cd5af1e
+oid sha256:fc3b0b845800bdf47f080936f1270a73604b86e0e0e3193c1562e20ca31b9318
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.012,
+  "epoch": 0.016,
   "eval_steps": 1000,
-  "global_step": 30,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,13 +187,73 @@
       "learning_rate": 0.00014736842105263158,
       "loss": 1.6827,
       "step": 30
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00014526315789473686,
+      "loss": 1.8042,
+      "step": 31
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0001431578947368421,
+      "loss": 1.5183,
+      "step": 32
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00014105263157894736,
+      "loss": 2.3209,
+      "step": 33
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00013894736842105264,
+      "loss": 1.7139,
+      "step": 34
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0001368421052631579,
+      "loss": 1.9278,
+      "step": 35
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00013473684210526317,
+      "loss": 1.6632,
+      "step": 36
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00013263157894736842,
+      "loss": 1.6254,
+      "step": 37
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0001305263157894737,
+      "loss": 1.726,
+      "step": 38
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00012842105263157895,
+      "loss": 2.3053,
+      "step": 39
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0001263157894736842,
+      "loss": 1.509,
+      "step": 40
     }
   ],
   "logging_steps": 1,
   "max_steps": 100,
   "num_train_epochs": 1,
   "save_steps": 10,
-  "total_flos": 2104744175566848.0,
+  "total_flos": 2434139976646656.0,
   "trial_name": null,
   "trial_params": null
 }