Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc9b4a3a0507bd48a42176710db70e63abca7ae12318c250bbdcf9df9aea84c7
+oid sha256:58f2ce4ae7af57b60f7578d767277d756cd4a2659717dfeae882c0417ebe7919
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9907d0bfdc52ceb7a5bae96bf4206ed5d61858124566a3cbce3c036e8ed80ca2
+oid sha256:6136fccae05899c5770ba60d4ac50df69804114f951aa1f1c8d286c9262aa4c3
 size 37965300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3a8bc69c6dd53b491a232b40fd3a0df74d8a4eeef8cc7aedf11d65012e22031
+oid sha256:38d98de3804c2db040b85e337427c43f61d74444b1ae81f8d1f76948acd21257
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bec84b33191b76a1f66109f05ca2863b65ba9c0ae66be6a4921ad95ad9f1a38e
+oid sha256:0569f9f06b6a114946825bdc699040cc55958cfef46aba8eb5fb625896d49025
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.4086956521739131,
+  "epoch": 1.5652173913043477,
   "eval_steps": 9,
-  "global_step": 81,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -276,6 +276,35 @@
       "eval_samples_per_second": 36.316,
       "eval_steps_per_second": 4.867,
       "step": 81
+    },
+    {
+      "epoch": 1.4608695652173913,
+      "grad_norm": 0.48886847496032715,
+      "learning_rate": 3.798797596089351e-06,
+      "loss": 0.968,
+      "step": 84
+    },
+    {
+      "epoch": 1.5130434782608697,
+      "grad_norm": 0.44092217087745667,
+      "learning_rate": 2.5301488425208296e-06,
+      "loss": 1.467,
+      "step": 87
+    },
+    {
+      "epoch": 1.5652173913043477,
+      "grad_norm": 0.426158607006073,
+      "learning_rate": 1.5076844803522922e-06,
+      "loss": 1.3827,
+      "step": 90
+    },
+    {
+      "epoch": 1.5652173913043477,
+      "eval_loss": 0.9642850756645203,
+      "eval_runtime": 2.6781,
+      "eval_samples_per_second": 36.22,
+      "eval_steps_per_second": 4.854,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.128401785998541e+16,
+  "total_flos": 2.363530176626688e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null