Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:232bcc9858ce0d5c28e9aa298360eed5c7cf48195fa14f61cbf351cd02e615fe
+oid sha256:458d38fb0a6aae54b2a8c29bbe75a18fbe266a586e31ec7af154eb1d0d985b12
 size 104902272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b5f1a00c2c51f65d8628c1656aaae70ebd16e629157f10e5672ebcc305be65c
+oid sha256:93e3e91588ca755bc2d1120cf86f7e4bf41402ce28d7d70e29b3be4249f331ae
 size 53622996

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74f2e0e81975bb9790d426cf1e81631aed9cf6bad42c0428d645bae0c8dcc89d
+oid sha256:45e4abb5d8f838d7298d0da53d751603c0e159cddd8e50398726666cfef25317
 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": 0.006880733944954129,
+  "epoch": 0.010321100917431193,
   "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": 13.774,
       "eval_steps_per_second": 6.887,
       "step": 6
+    },
+    {
+      "epoch": 0.008027522935779817,
+      "grad_norm": 0.4998139441013336,
+      "learning_rate": 0.00014,
+      "loss": 7.1038,
+      "step": 7
+    },
+    {
+      "epoch": 0.009174311926605505,
+      "grad_norm": 0.8987786173820496,
+      "learning_rate": 0.00016,
+      "loss": 6.2242,
+      "step": 8
+    },
+    {
+      "epoch": 0.010321100917431193,
+      "grad_norm": 1.180274248123169,
+      "learning_rate": 0.00018,
+      "loss": 7.2237,
+      "step": 9
+    },
+    {
+      "epoch": 0.010321100917431193,
+      "eval_loss": 1.7290107011795044,
+      "eval_runtime": 26.7285,
+      "eval_samples_per_second": 13.768,
+      "eval_steps_per_second": 6.884,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3764790157639680.0,
+  "total_flos": 5647185236459520.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null