Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d8bb98cc079647c8595486d7ec4c6c1dbfeab5c9d69b725689294cc7970fea7
+oid sha256:07d04bc45df4b3cba486cc45e2063279e0846f0c8df938b6f995b5dc99706092
 size 109009752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c45325f5b31a2e0c27b39dfa70d3fa45e24543d4239b3ca7c2adb32ea06e4cba
+oid sha256:366ee91d89db94a05da45409deef2ace46f614a21262ad65fe818248ddf64abe
 size 56088148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:356b548ab3e5c18278417ebb5318355e9481c8992b11479d08e62a1cb33f7930
+oid sha256:895bc9637d2006530369fffe00fd60c01471aa1822b76fe15317578b06a982b9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fd8212ec5ec3406d74a7f927b717dd30ea8a06115ee6582e14976f7b84b4b58
+oid sha256:b489c13e2d776471e9a48162938854a24466ce6713df9c0fb59abd9a09fb226b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.020530719088436074,
+  "epoch": 0.030796078632654107,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 23.761,
       "eval_steps_per_second": 11.886,
       "step": 100
+    },
+    {
+      "epoch": 0.02258379099727968,
+      "grad_norm": 0.619922399520874,
+      "learning_rate": 8.79463319744677e-05,
+      "loss": 0.308,
+      "step": 110
+    },
+    {
+      "epoch": 0.024636862906123286,
+      "grad_norm": 0.47642096877098083,
+      "learning_rate": 7.217825360835473e-05,
+      "loss": 0.2825,
+      "step": 120
+    },
+    {
+      "epoch": 0.026689934814966895,
+      "grad_norm": 0.38181358575820923,
+      "learning_rate": 5.713074385969457e-05,
+      "loss": 0.2863,
+      "step": 130
+    },
+    {
+      "epoch": 0.028743006723810503,
+      "grad_norm": 0.5245420336723328,
+      "learning_rate": 4.3193525326884435e-05,
+      "loss": 0.2711,
+      "step": 140
+    },
+    {
+      "epoch": 0.030796078632654107,
+      "grad_norm": 0.40633440017700195,
+      "learning_rate": 3.072756464904006e-05,
+      "loss": 0.2751,
+      "step": 150
+    },
+    {
+      "epoch": 0.030796078632654107,
+      "eval_loss": 0.2869807481765747,
+      "eval_runtime": 86.1617,
+      "eval_samples_per_second": 23.804,
+      "eval_steps_per_second": 11.908,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.254755040591872e+16,
+  "total_flos": 3.384772789272576e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null