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:c640c19b6621a27a8559690f37f56e1069ecbfc7092edb099ba0f383bbbbe23b
+oid sha256:42d99688ad17beffa73f79600415fb531d9229560c19892544968ad2792d2eb1
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7b75caf1d55c3b0638ecfc56003ae16adb1a1c9d5571c97fb1f22d4ba2f6f34
+oid sha256:e1f8907e2922164b1495f36ce5351518f266472ac33af87e4d1a2db1eb67635f
 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": 0.00046669907632474475,
+  "epoch": 0.0007000486144871172,
   "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": 32.996,
       "eval_steps_per_second": 16.498,
       "step": 6
+    },
+    {
+      "epoch": 0.0005444822557122023,
+      "grad_norm": 2.643089532852173,
+      "learning_rate": 0.00014,
+      "loss": 3.4304,
+      "step": 7
+    },
+    {
+      "epoch": 0.0006222654350996597,
+      "grad_norm": 2.6849687099456787,
+      "learning_rate": 0.00016,
+      "loss": 3.1282,
+      "step": 8
+    },
+    {
+      "epoch": 0.0007000486144871172,
+      "grad_norm": 3.3133139610290527,
+      "learning_rate": 0.00018,
+      "loss": 2.8319,
+      "step": 9
+    },
+    {
+      "epoch": 0.0007000486144871172,
+      "eval_loss": 2.61970591545105,
+      "eval_runtime": 164.1071,
+      "eval_samples_per_second": 32.991,
+      "eval_steps_per_second": 16.495,
+      "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