Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0eb7aceec0625fe26f03c04ab20e2a7029176176cbf04ba60f1eedb6550c3870
+oid sha256:dd821372aa83947164a3f90984fd1e6d63e33d7eb0707eac39bd54295b720a90
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a3abdb658447a4bac398931ccdb0c013441495673febd54fe0b4698094a608e
+oid sha256:9ad8ac98b8b09f6f3c41eddce20f761f46a05399669c4cdd2e3f850d72868056
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d80af6fa073ce8d3a232f9b03646f8c6383dbb11dc57f0398deb1f5a0af1072
+oid sha256:d55b5146f7b584cbd79f12c99d54c69e6020e3eb66a5691014d6472cfae26416
 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": 0.06845798391237377,
+  "epoch": 0.10268697586856067,
   "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": 25.676,
       "eval_steps_per_second": 12.859,
       "step": 100
+    },
+    {
+      "epoch": 0.07530378230361116,
+      "grad_norm": 0.5051794052124023,
+      "learning_rate": 8.79463319744677e-05,
+      "loss": 0.7143,
+      "step": 110
+    },
+    {
+      "epoch": 0.08214958069484854,
+      "grad_norm": 0.620830237865448,
+      "learning_rate": 7.217825360835473e-05,
+      "loss": 0.6839,
+      "step": 120
+    },
+    {
+      "epoch": 0.08899537908608592,
+      "grad_norm": 0.5125678777694702,
+      "learning_rate": 5.713074385969457e-05,
+      "loss": 0.6344,
+      "step": 130
+    },
+    {
+      "epoch": 0.09584117747732329,
+      "grad_norm": 0.4516546428203583,
+      "learning_rate": 4.3193525326884435e-05,
+      "loss": 0.5826,
+      "step": 140
+    },
+    {
+      "epoch": 0.10268697586856067,
+      "grad_norm": 0.441818505525589,
+      "learning_rate": 3.072756464904006e-05,
+      "loss": 0.6178,
+      "step": 150
+    },
+    {
+      "epoch": 0.10268697586856067,
+      "eval_loss": 0.6720569133758545,
+      "eval_runtime": 23.9337,
+      "eval_samples_per_second": 25.696,
+      "eval_steps_per_second": 12.869,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.316579220802765e+16,
+  "total_flos": 3.426317769690317e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null