Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a84ec866e8b3f097ace2aad1584fa2f6343b8e4dcc4039995334e090da90366d
+oid sha256:5515a2c5cf836fa097c14ec7e52df4e90e83389ac02072e5bcfbd7c4ec164361
 size 47235968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:516aee7c860197304bbe8ef3352cdaadb03eb4484286228ca8010113ca84abdc
+oid sha256:af3b5747e34831d3dc378b4806065236eb2dc4747edde869294cd73da184f54e
 size 24410836

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:975b8cdec9db6491693b955e7ce00a77fecb1e446b0b009f1ae26af34c449975
+oid sha256:433eb544b6f54648556b9de0e6e72a20c544038c1e6b74cbcf887924dd4b0660
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.049586776859504134,
+  "epoch": 0.0743801652892562,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 31.408,
       "eval_steps_per_second": 16.012,
       "step": 6
+    },
+    {
+      "epoch": 0.05785123966942149,
+      "grad_norm": 2.208061456680298,
+      "learning_rate": 0.00014,
+      "loss": 2.2149,
+      "step": 7
+    },
+    {
+      "epoch": 0.06611570247933884,
+      "grad_norm": 2.9599900245666504,
+      "learning_rate": 0.00016,
+      "loss": 2.592,
+      "step": 8
+    },
+    {
+      "epoch": 0.0743801652892562,
+      "grad_norm": 2.5015549659729004,
+      "learning_rate": 0.00018,
+      "loss": 2.028,
+      "step": 9
+    },
+    {
+      "epoch": 0.0743801652892562,
+      "eval_loss": 5.103657245635986,
+      "eval_runtime": 1.6215,
+      "eval_samples_per_second": 31.452,
+      "eval_steps_per_second": 16.034,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 572094205132800.0,
+  "total_flos": 866314082058240.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null