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:b2806de322ba6a9bc97cdfa319fbabbdeaf7b1b6097d1b304c01aaac57acc86e
+oid sha256:27846b98289a8d3c56bc8a578907502b3ccf12c7fd54a7e37cba9a0a673d63ec
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28e022f64db763f78f5d8cee11f359b33f23816fcb74a4e12d9be235f56d3d72
+oid sha256:2e1db746075fd956b1f7b90b1529f9020de8d0f80bd276bc19b78f1fb2f51da4
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a13307056da4bbb211ad48ade25632cd037a6f559d3df7d1e4eebdbef92276c
+oid sha256:894ae9e2dd56efcd745c69d81e84d269bfa54a0f8cbcf8e14a4428f929aae407
 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": 0.0001486942783680803,
+  "epoch": 0.00022304141755212045,
   "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": 27.143,
       "eval_steps_per_second": 13.571,
       "step": 6
+    },
+    {
+      "epoch": 0.00017347665809609367,
+      "grad_norm": 0.6194573044776917,
+      "learning_rate": 0.00014,
+      "loss": 1.0728,
+      "step": 7
+    },
+    {
+      "epoch": 0.00019825903782410705,
+      "grad_norm": 0.6491646766662598,
+      "learning_rate": 0.00016,
+      "loss": 0.9076,
+      "step": 8
+    },
+    {
+      "epoch": 0.00022304141755212045,
+      "grad_norm": 0.6161671876907349,
+      "learning_rate": 0.00018,
+      "loss": 0.7104,
+      "step": 9
+    },
+    {
+      "epoch": 0.00022304141755212045,
+      "eval_loss": 0.7862219214439392,
+      "eval_runtime": 625.4316,
+      "eval_samples_per_second": 27.165,
+      "eval_steps_per_second": 13.583,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1294694973702144.0,
+  "total_flos": 2034520672960512.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null