Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:952697146b9ad5747ca6b92cc603112bb01a1a9766d72f75de97eb993b73139f
+oid sha256:6beef2575683cce18664edacbfa195e48578b7c53004d4083fc154cf0b772522
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b2b65bc813b3eb278d61c2ebee7e565a3412a9ab6b4d19a956d49d2cbcb6289
+oid sha256:344220da850a408c75846910a972fd7513b40e722ae9ec55faaf9d2eefb62fdc
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a68cd2a0196a6713af61a6a5ec57d388549ceab000d778970629ba70bc0f12ea
+oid sha256:b90a19943f8ef28f7f3c1abafd8de7b24ff68c3eda11dffdc748b1a1d989fcb2
 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": 0.005348785379986628,
+  "epoch": 0.008023178069979943,
   "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": 32.9,
       "eval_steps_per_second": 16.485,
       "step": 6
+    },
+    {
+      "epoch": 0.0062402496099844,
+      "grad_norm": 3.1466526985168457,
+      "learning_rate": 0.00014,
+      "loss": 2.517,
+      "step": 7
+    },
+    {
+      "epoch": 0.007131713839982171,
+      "grad_norm": 2.911224365234375,
+      "learning_rate": 0.00016,
+      "loss": 2.2118,
+      "step": 8
+    },
+    {
+      "epoch": 0.008023178069979943,
+      "grad_norm": 3.6586551666259766,
+      "learning_rate": 0.00018,
+      "loss": 2.3297,
+      "step": 9
+    },
+    {
+      "epoch": 0.008023178069979943,
+      "eval_loss": 2.15604567527771,
+      "eval_runtime": 14.3547,
+      "eval_samples_per_second": 32.951,
+      "eval_steps_per_second": 16.51,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1109738548887552.0,
+  "total_flos": 1664607823331328.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null