Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1847ab286a68a4d02b246ca18b5e7f5f063317ba7a7c85a17095ef94a16c04e
+oid sha256:efa7cacf388d42a0c46904a529ef46a23bc7ceeb8c62a808138636f1683c70a9
 size 15182728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ec683cdd27f5cd33b0d7c31ff1b9d174186c8138cd44d534883c6da0985e195
+oid sha256:71a0788a676c2113ef8062b3c1ec89acd97278d4b4b943daa8dc5874a73164ce
 size 8075796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57c3e567c74affae7478911fb166aed9b97f670988a0accdc6e7382bc1b315cf
+oid sha256:19c3a950b1db5e5a53ee1807fed513e1459650c81b28057a7dd9e7f6eb2c4dc2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.045494313210848646,
+  "epoch": 0.058326042578011085,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 3.439,
       "step": 35
+    },
+    {
+      "epoch": 0.04666083406240887,
+      "grad_norm": 2.644707679748535,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.8175,
+      "step": 40
+    },
+    {
+      "epoch": 0.04666083406240887,
+      "eval_loss": 3.5340569019317627,
+      "eval_runtime": 11.7924,
+      "eval_samples_per_second": 30.613,
+      "eval_steps_per_second": 15.349,
+      "step": 40
+    },
+    {
+      "epoch": 0.05249343832020997,
+      "grad_norm": 2.2937591075897217,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.6726,
+      "step": 45
+    },
+    {
+      "epoch": 0.058326042578011085,
+      "grad_norm": 2.1144652366638184,
+      "learning_rate": 0.0,
+      "loss": 3.0375,
+      "step": 50
+    },
+    {
+      "epoch": 0.058326042578011085,
+      "eval_loss": 3.520244836807251,
+      "eval_runtime": 11.618,
+      "eval_samples_per_second": 31.073,
+      "eval_steps_per_second": 15.579,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 299222830153728.0,
+  "total_flos": 383619013017600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null