Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:947592abceaee94e3b3649532162aa930652dd816d55d57387a0e55cfe39d4e6
+oid sha256:1ff2245776dd849758f0c657c4db797c1f8d64b316c9a87dcccb65a3628a0346
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7c6775b743b6e50d19681b49eb990663409152b4672b2c60ca0e5589cad641e
+oid sha256:a6a9c80ecc8e4fbbf906f73af16366ab25329d182d4e255df82a1da164a659c2
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:290db72453c0549da48ac2c903de9d8ef739ca7e660c6a1235dab2d77509f626
+oid sha256:df96fa4ee210cc5b5c9dd9bcfee8a141cd26a15e203e80cf0a98ad5ed22dd249
 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": 0.01251303441084463,
+  "epoch": 0.018769551616266946,
   "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": 31.875,
       "eval_steps_per_second": 15.937,
       "step": 6
+    },
+    {
+      "epoch": 0.014598540145985401,
+      "grad_norm": 0.8114572763442993,
+      "learning_rate": 0.00014,
+      "loss": 1.7647,
+      "step": 7
+    },
+    {
+      "epoch": 0.016684045881126174,
+      "grad_norm": 0.6929518580436707,
+      "learning_rate": 0.00016,
+      "loss": 1.4965,
+      "step": 8
+    },
+    {
+      "epoch": 0.018769551616266946,
+      "grad_norm": 0.7459466457366943,
+      "learning_rate": 0.00018,
+      "loss": 1.8414,
+      "step": 9
+    },
+    {
+      "epoch": 0.018769551616266946,
+      "eval_loss": 1.9566819667816162,
+      "eval_runtime": 6.3571,
+      "eval_samples_per_second": 31.775,
+      "eval_steps_per_second": 15.888,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 300058398425088.0,
+  "total_flos": 487594897440768.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null