Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c5798691fceeef7587674007a21c62b7b7eb99d4deed37780c5a29fea43dcb8
+oid sha256:f81f06cd9f7de204cfda130b7d8f0d24efe15d738734a3ca2de2ecdabb7a70ac
 size 767856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:322aacf33dc28e0df8985460823e1a407a74d726f6da0c77ced6ea43e45417b4
+oid sha256:626eb631f3c2757311cd7a0c5f39685b0a21d12f31977fe73781374506e2a8d8
 size 1003002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8285489f68000ec4600333ccee281bca8dd48450423899eaa09a26dab85569a3
+oid sha256:27035ea1efd96357598ccd3bea9cecacd80035eaa6d3792153213c56e73abd54
 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": 0.028070175438596492,
+  "epoch": 0.042105263157894736,
   "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": 37.305,
       "eval_steps_per_second": 37.305,
       "step": 6
+    },
+    {
+      "epoch": 0.03274853801169591,
+      "grad_norm": 10.740998268127441,
+      "learning_rate": 0.00014,
+      "loss": 7.112,
+      "step": 7
+    },
+    {
+      "epoch": 0.03742690058479532,
+      "grad_norm": 9.38088607788086,
+      "learning_rate": 0.00016,
+      "loss": 7.3835,
+      "step": 8
+    },
+    {
+      "epoch": 0.042105263157894736,
+      "grad_norm": 9.658013343811035,
+      "learning_rate": 0.00018,
+      "loss": 6.7257,
+      "step": 9
+    },
+    {
+      "epoch": 0.042105263157894736,
+      "eval_loss": 6.872171401977539,
+      "eval_runtime": 1.2413,
+      "eval_samples_per_second": 36.252,
+      "eval_steps_per_second": 36.252,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1628971204608.0,
+  "total_flos": 2443456806912.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null