Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b2405aa05cf83ea8899ee9104bc5bcfd395a9efe761117075f7d3f82bd68971
+oid sha256:74939770c5f4de6c54954b66d8697524ed067843d0c95c76c7d913998ec9ba71
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63a09141c4e7eaed8bd7e881b825afdc01aa9dd868cf7a3e380d6ac2a2be4dae
+oid sha256:69acaf30f6b4a693b7c92bea7bf6b09ab80971083780d77ef435884e19dd5f4a
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:142d5945d68c654b4ca2ebf57c1bd75b6d495dcf2e00e4e5f6f5123c0dd3fb8b
+oid sha256:9cd5c3a48a3559ff7695d92e037ac134c01ff7aac9031f8f4de3ac26834c34fd
 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": 0.00267946857206654,
+  "epoch": 0.00401920285809981,
   "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": 22.457,
       "eval_steps_per_second": 11.241,
       "step": 6
+    },
+    {
+      "epoch": 0.0031260466674109637,
+      "grad_norm": 1.458383321762085,
+      "learning_rate": 0.00014,
+      "loss": 9.5776,
+      "step": 7
+    },
+    {
+      "epoch": 0.003572624762755387,
+      "grad_norm": 1.346551537513733,
+      "learning_rate": 0.00016,
+      "loss": 9.4983,
+      "step": 8
+    },
+    {
+      "epoch": 0.00401920285809981,
+      "grad_norm": 1.525188684463501,
+      "learning_rate": 0.00018,
+      "loss": 8.969,
+      "step": 9
+    },
+    {
+      "epoch": 0.00401920285809981,
+      "eval_loss": 2.1105306148529053,
+      "eval_runtime": 42.0209,
+      "eval_samples_per_second": 22.441,
+      "eval_steps_per_second": 11.233,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1180843200479232.0,
+  "total_flos": 1750905435193344.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null