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:a6754bc6cff75e0ac50d352b965bc2ef7bd8c75733fca18adab3895f48f37aa7
+oid sha256:e4de0075cc9eee808e24fedb4d483a7123502417322e537ba5c534c5331dec9a
 size 109009752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:397948b1508678ae115a21146646de3f868be5c337a66c0b351e8032e292b44b
+oid sha256:8dd9ebd38dd4d1498e9d16ffee93b91ef29d2633bffc83bd9325d3a0048a1c9b
 size 56088148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38c142131baef1355b873a2c67e4c735b6209235a2e80b579d174b88c74e83cc
+oid sha256:b2ab72f23bd8fe5041f7f2dc5f0bc1b45c4d1c803eb0aaf73f1fe5ef6de41a81
 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": 23.763,
       "eval_steps_per_second": 11.887,
       "step": 100
+    },
+    {
+      "epoch": 0.02258379099727968,
+      "grad_norm": 0.6141920685768127,
+      "learning_rate": 8.79463319744677e-05,
+      "loss": 0.3081,
+      "step": 110
+    },
+    {
+      "epoch": 0.024636862906123286,
+      "grad_norm": 0.5217195749282837,
+      "learning_rate": 7.217825360835473e-05,
+      "loss": 0.2823,
+      "step": 120
+    },
+    {
+      "epoch": 0.026689934814966895,
+      "grad_norm": 0.4080885350704193,
+      "learning_rate": 5.713074385969457e-05,
+      "loss": 0.2858,
+      "step": 130
+    },
+    {
+      "epoch": 0.028743006723810503,
+      "grad_norm": 0.6725149750709534,
+      "learning_rate": 4.3193525326884435e-05,
+      "loss": 0.2708,
+      "step": 140
+    },
+    {
+      "epoch": 0.030796078632654107,
+      "grad_norm": 0.5834973454475403,
+      "learning_rate": 3.072756464904006e-05,
+      "loss": 0.2758,
+      "step": 150
+    },
+    {
+      "epoch": 0.030796078632654107,
+      "eval_loss": 0.28681352734565735,
+      "eval_runtime": 86.1917,
+      "eval_samples_per_second": 23.796,
+      "eval_steps_per_second": 11.904,
+      "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