Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e393efd366fba737b989885aac705a9c4a655cd225f75aff056c298418c3644
+oid sha256:68f3f3e37b829def4b3e89cb63af9d1b256b52e45b8f5dfa06e43061d83425c8
 size 66103768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:720a56b5dd6624fe09a926188791eeb518cb2137e21c3af2341bef682aed37e1
+oid sha256:a2155d68b3c7a0687cb22b37894f7fe72f3fa0f0ab26e5449924c6347fc7c5ba
 size 33939412

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9917d4a5f0c5b8851517cb0bf3f916dec078526028b49a7f7a76254573a6438
+oid sha256:0b3910328211d9b10a334cef210a94a471f7cf80543d1339c0b86a741316b70a
 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": 0.0027391006619493265,
+  "epoch": 0.00410865099292399,
   "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": 31.989,
       "eval_steps_per_second": 16.012,
       "step": 6
+    },
+    {
+      "epoch": 0.003195617438940881,
+      "grad_norm": 3.811544418334961,
+      "learning_rate": 0.00014,
+      "loss": 2.5571,
+      "step": 7
+    },
+    {
+      "epoch": 0.0036521342159324356,
+      "grad_norm": 5.701013565063477,
+      "learning_rate": 0.00016,
+      "loss": 2.3771,
+      "step": 8
+    },
+    {
+      "epoch": 0.00410865099292399,
+      "grad_norm": 4.322719573974609,
+      "learning_rate": 0.00018,
+      "loss": 1.28,
+      "step": 9
+    },
+    {
+      "epoch": 0.00410865099292399,
+      "eval_loss": 0.3839247226715088,
+      "eval_runtime": 28.854,
+      "eval_samples_per_second": 31.989,
+      "eval_steps_per_second": 16.012,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 864234241671168.0,
+  "total_flos": 1296351362506752.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null