Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19b92fe1e1ff0eb3200ef50f54dcbc756c55b990b4560e8b0b793abdc00d8115
+oid sha256:ef67e1b23f53f1a274109b215801f62036dd76aabb1c81ad2ceaa1c0bec257bf
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ce59baac1f37170e2e85a5eca524fb632a6936ee18239f57602598b10637aca
+oid sha256:81c55f785264031c429e7c0ce688cc3aefce3c93c87d4392fb6e72d49e73b3d1
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95090da2d95a472f5c64af5c674e1d01adf3712de56ff370ce85b98c3feb8764
+oid sha256:e091a109b1d98c241cd35341a1a58393bcf5f6fb7f837866e41c8697200b8ffd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fd8212ec5ec3406d74a7f927b717dd30ea8a06115ee6582e14976f7b84b4b58
+oid sha256:b489c13e2d776471e9a48162938854a24466ce6713df9c0fb59abd9a09fb226b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.18744142455482662,
+  "epoch": 0.28116213683223995,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 10.757,
       "eval_steps_per_second": 5.402,
       "step": 100
+    },
+    {
+      "epoch": 0.20618556701030927,
+      "grad_norm": 0.5432748794555664,
+      "learning_rate": 8.79463319744677e-05,
+      "loss": 1.7362,
+      "step": 110
+    },
+    {
+      "epoch": 0.22492970946579194,
+      "grad_norm": 0.5037766695022583,
+      "learning_rate": 7.217825360835473e-05,
+      "loss": 1.6193,
+      "step": 120
+    },
+    {
+      "epoch": 0.2436738519212746,
+      "grad_norm": 0.5351141691207886,
+      "learning_rate": 5.713074385969457e-05,
+      "loss": 1.7659,
+      "step": 130
+    },
+    {
+      "epoch": 0.2624179943767573,
+      "grad_norm": 0.518492579460144,
+      "learning_rate": 4.3193525326884435e-05,
+      "loss": 1.7379,
+      "step": 140
+    },
+    {
+      "epoch": 0.28116213683223995,
+      "grad_norm": 0.6918880343437195,
+      "learning_rate": 3.072756464904006e-05,
+      "loss": 1.7342,
+      "step": 150
+    },
+    {
+      "epoch": 0.28116213683223995,
+      "eval_loss": NaN,
+      "eval_runtime": 20.9389,
+      "eval_samples_per_second": 10.746,
+      "eval_steps_per_second": 5.397,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.189931617583104e+16,
+  "total_flos": 9.308643967107072e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null