Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17ec00aa75361d1fd9a70101d9749e9376b1d7253f0544581c53b893b6d40c0a
+oid sha256:cecb9e1afd8934e0b1fe5909c4043ae3d0ec5889ce94695eb56744e9bcc4e6dc
 size 39256456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a64d78c0026a40b40feb604099e69aca3982e19b31b23d0db5d6d285c8c92b4e
+oid sha256:c11bacbb148416ea423d68261d2732f806e9eb1ff020d78c5bfb3194d29ebf4a
 size 20632826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3b2ed62d3c3041d929f4689e56812b00363ecda2ba4abac93da71f834cdd0c0
+oid sha256:b74e3c925ceec40baf5d508fc3d6ea8a468f31ee20a14f9330a7ee79c304b1d4
 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": 0.00014203872922683586,
+  "epoch": 0.00021305809384025378,
   "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": 53.374,
       "eval_steps_per_second": 26.688,
       "step": 6
+    },
+    {
+      "epoch": 0.0001657118507646418,
+      "grad_norm": 5.301882266998291,
+      "learning_rate": 0.00014,
+      "loss": 4.0845,
+      "step": 7
+    },
+    {
+      "epoch": 0.0001893849723024478,
+      "grad_norm": 5.137835502624512,
+      "learning_rate": 0.00016,
+      "loss": 4.0146,
+      "step": 8
+    },
+    {
+      "epoch": 0.00021305809384025378,
+      "grad_norm": 6.15079402923584,
+      "learning_rate": 0.00018,
+      "loss": 3.206,
+      "step": 9
+    },
+    {
+      "epoch": 0.00021305809384025378,
+      "eval_loss": 3.147989511489868,
+      "eval_runtime": 332.2808,
+      "eval_samples_per_second": 53.53,
+      "eval_steps_per_second": 26.767,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 293686676029440.0,
+  "total_flos": 440530014044160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null