Training in progress, step 16, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e016c9f561a6d588d9c9525067440715fea17b7514126b99146d4d396da2ba1
+oid sha256:3a56b3bb97fbbf8130fca78041d9213b8f19c9b4c4bda5c8e0676b5f6084c49a
 size 26008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98802883d37c9021230cfeb0370c6693609dac587e299467c04eb68b3075358c
+oid sha256:d9b2dd13a3198675b727210c336be6f4edc89e64fef47be25e22e587ffa315f6
 size 61926

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:105f96f979368944b59d27d1e74fc1fa8227279f7d5146ad57761b7d32f1a2d9
+oid sha256:c6eeca6fec2d74dc35412cee25843a6e2b45b715cb98314d10ac41fc41a4cabc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a3d18e607a27cfab9cec7cfaa7384cdb877a2330c4bcd4e1efcae25be9908cb
+oid sha256:e3233603be2c007aac019155f1cd5d754e2eeb600f6ca413bd2048966230a2e8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06180589087397392,
+  "epoch": 0.12361178174794785,
   "eval_steps": 8,
-  "global_step": 8,
+  "global_step": 16,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -79,6 +79,70 @@
       "eval_samples_per_second": 203.416,
       "eval_steps_per_second": 102.172,
       "step": 8
+    },
+    {
+      "epoch": 0.06953162723322066,
+      "grad_norm": 0.09723018854856491,
+      "learning_rate": 9e-05,
+      "loss": 11.9271,
+      "step": 9
+    },
+    {
+      "epoch": 0.0772573635924674,
+      "grad_norm": 0.06599853187799454,
+      "learning_rate": 0.0001,
+      "loss": 11.9294,
+      "step": 10
+    },
+    {
+      "epoch": 0.08498309995171414,
+      "grad_norm": 0.08143449574708939,
+      "learning_rate": 9.938441702975689e-05,
+      "loss": 11.9204,
+      "step": 11
+    },
+    {
+      "epoch": 0.09270883631096088,
+      "grad_norm": 0.06527712196111679,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 11.9218,
+      "step": 12
+    },
+    {
+      "epoch": 0.10043457267020763,
+      "grad_norm": 0.04510502144694328,
+      "learning_rate": 9.45503262094184e-05,
+      "loss": 11.932,
+      "step": 13
+    },
+    {
+      "epoch": 0.10816030902945437,
+      "grad_norm": 0.0751844048500061,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 11.9265,
+      "step": 14
+    },
+    {
+      "epoch": 0.1158860453887011,
+      "grad_norm": 0.05361689627170563,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 11.9278,
+      "step": 15
+    },
+    {
+      "epoch": 0.12361178174794785,
+      "grad_norm": 0.09501861780881882,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 11.9095,
+      "step": 16
+    },
+    {
+      "epoch": 0.12361178174794785,
+      "eval_loss": 11.927022933959961,
+      "eval_runtime": 1.0762,
+      "eval_samples_per_second": 203.491,
+      "eval_steps_per_second": 102.21,
+      "step": 16
     }
   ],
   "logging_steps": 1,
@@ -98,7 +162,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 47966060544.0,
+  "total_flos": 95932121088.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null