Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54ebc1bc56647d16e2ba7a0521ea1caf5bdfbe306346caef694004ac0115b2cf
+oid sha256:221d037186431de434a1d4dc2457e06c75c536627aeba8864ab2ed82eba62489
 size 109009752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88da9b473d35427cb5db357a999680df67efb85e98750298ba28c16c41905764
+oid sha256:8136345dafc5434be5ad2acc33e84f5d9942c1f3239a090df4e5e2080352763f
 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 sha256:3fc7800513a1b4dd006c457152c700dd768bb49ee4ed8e4d9665a4e42095b054
+oid sha256:fd5d42bb0afda20ec4c83d38c6af1131541c335ecab229c74e7f418894f3c13b
 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": 23.756,
       "eval_steps_per_second": 11.884,
       "step": 100
+    },
+    {
+      "epoch": 0.02258379099727968,
+      "grad_norm": 0.6514111161231995,
+      "learning_rate": 9.174206545276677e-05,
+      "loss": 0.3086,
+      "step": 110
+    },
+    {
+      "epoch": 0.024636862906123286,
+      "grad_norm": 0.5423412322998047,
+      "learning_rate": 7.54514512859201e-05,
+      "loss": 0.2823,
+      "step": 120
+    },
+    {
+      "epoch": 0.026689934814966895,
+      "grad_norm": 0.43237441778182983,
+      "learning_rate": 5.983045753470308e-05,
+      "loss": 0.2855,
+      "step": 130
+    },
+    {
+      "epoch": 0.028743006723810503,
+      "grad_norm": 0.508624792098999,
+      "learning_rate": 4.530518418775733e-05,
+      "loss": 0.2724,
+      "step": 140
+    },
+    {
+      "epoch": 0.030796078632654107,
+      "grad_norm": 0.3984101712703705,
+      "learning_rate": 3.227184283742591e-05,
+      "loss": 0.2764,
+      "step": 150
+    },
+    {
+      "epoch": 0.030796078632654107,
+      "eval_loss": 0.28801968693733215,
+      "eval_runtime": 86.3387,
+      "eval_samples_per_second": 23.755,
+      "eval_steps_per_second": 11.883,
+      "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