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:ae306ef2b68d63c1e6831432699753d77d12f2609aac63b7cd1a77e871c4a74b
+oid sha256:a9ad89b4b2289fa84c3c402b9ef361af34634a3db2b16e62745169761c36d7ed
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:261aa96ba3735f869bd8d5ff28c42006713b99b33296c2d6149369af16856e7b
+oid sha256:364b47ba0126d53df12c77e0528bf968e9d4b4d940a9c41f7d879fd5a56080e2
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85b0ae6c3bd2ac4ea01467a5edbc086cdc303e1ace1b12b41ab97be3e932f8c7
+oid sha256:ab4032206871f76f267774b23b5210fddd18559968f207e84376a2a9e45c5846
 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": 0.027303754266211604,
+  "epoch": 0.040955631399317405,
   "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": 54.648,
       "eval_steps_per_second": 27.618,
       "step": 6
+    },
+    {
+      "epoch": 0.03185437997724687,
+      "grad_norm": 71.99066162109375,
+      "learning_rate": 0.00014,
+      "loss": 3.9438,
+      "step": 7
+    },
+    {
+      "epoch": 0.03640500568828214,
+      "grad_norm": 20.329301834106445,
+      "learning_rate": 0.00016,
+      "loss": 3.8839,
+      "step": 8
+    },
+    {
+      "epoch": 0.040955631399317405,
+      "grad_norm": 17.403549194335938,
+      "learning_rate": 0.00018,
+      "loss": 3.3409,
+      "step": 9
+    },
+    {
+      "epoch": 0.040955631399317405,
+      "eval_loss": 2.8907394409179688,
+      "eval_runtime": 1.7017,
+      "eval_samples_per_second": 54.652,
+      "eval_steps_per_second": 27.62,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 153475186950144.0,
+  "total_flos": 230212780425216.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null