Training in progress, step 99, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db26a3a5e53c205f2d4bad20dce751ff2dfc9682295ec167967af50b2b707383
+oid sha256:0771b506c18a983f794d7e56c67b3ee20d1dc2550da032a4b20066daefefd817
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cded7f24df305c017db794fab5ac075a743c116d0ddb541ba3d8731b641edb06
+oid sha256:403532b0d20d332fa74f71935a4dcd99db3b7a276fc4daecfa27651df91f8538
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5051a0e31a9165b3b43ecaf91c64aba598ba8800af01edf71cd1ee48db7cb7f
+oid sha256:3f0195db21e9fddf5284f51a9c8408cef27c5c73fc46fcd57d4fff9429d9abe3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0569f9f06b6a114946825bdc699040cc55958cfef46aba8eb5fb625896d49025
+oid sha256:5b64833e2721bfb57dae2a544bde34ace02492c2f80bfbff48034c9946dc6b4a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04920049200492005,
+  "epoch": 0.05412054120541206,
   "eval_steps": 9,
-  "global_step": 90,
+  "global_step": 99,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -305,6 +305,35 @@
       "eval_samples_per_second": 7.22,
       "eval_steps_per_second": 0.905,
       "step": 90
+    },
+    {
+      "epoch": 0.05084050840508405,
+      "grad_norm": 0.16890203952789307,
+      "learning_rate": 7.426068431000882e-07,
+      "loss": 0.6217,
+      "step": 93
+    },
+    {
+      "epoch": 0.05248052480524805,
+      "grad_norm": 0.21651792526245117,
+      "learning_rate": 2.4329828146074095e-07,
+      "loss": 0.6589,
+      "step": 96
+    },
+    {
+      "epoch": 0.05412054120541206,
+      "grad_norm": 0.236527681350708,
+      "learning_rate": 1.522932452260595e-08,
+      "loss": 0.6654,
+      "step": 99
+    },
+    {
+      "epoch": 0.05412054120541206,
+      "eval_loss": 0.6207596063613892,
+      "eval_runtime": 426.6715,
+      "eval_samples_per_second": 7.221,
+      "eval_steps_per_second": 0.905,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.3568005266931712e+17,
+  "total_flos": 2.594794408771584e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null