Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:252bd84efd492b265d1fa2e9c78d513de052bb8f2f52e097164f9c04d80c2720
+oid sha256:68a900917f6d4bafe315dc763112915451a4efc826e656d0da6dadaace0944b5
 size 59933632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38a02c5d5082300733fd6e7205a6d545bcaa1a48b3907d3a077ac2509df0350e
+oid sha256:382fabd5af44f73b13d6e178f8ac00a867d52ff6d85b2f26debbc9c272a91493
 size 31822948

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee2e23f42f75569f483277032425654e0721778ef8d3a29f479ea93a55c53392
+oid sha256:12a1532e02c68d02f341ecc227c530c47eac50b4facb0221f09a61f5511251bf
 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": 0.00010876707983050463,
+  "epoch": 0.00016315061974575695,
   "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": 29.079,
       "eval_steps_per_second": 14.54,
       "step": 6
+    },
+    {
+      "epoch": 0.00012689492646892207,
+      "grad_norm": 1.0239311456680298,
+      "learning_rate": 0.00014,
+      "loss": 2.1336,
+      "step": 7
+    },
+    {
+      "epoch": 0.0001450227731073395,
+      "grad_norm": 0.9778740406036377,
+      "learning_rate": 0.00016,
+      "loss": 2.3313,
+      "step": 8
+    },
+    {
+      "epoch": 0.00016315061974575695,
+      "grad_norm": 0.8723558187484741,
+      "learning_rate": 0.00018,
+      "loss": 2.0553,
+      "step": 9
+    },
+    {
+      "epoch": 0.00016315061974575695,
+      "eval_loss": 2.4100735187530518,
+      "eval_runtime": 782.4358,
+      "eval_samples_per_second": 29.686,
+      "eval_steps_per_second": 14.843,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 634186138386432.0,
+  "total_flos": 1028409954140160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null