Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72264c2dd14c74fa9e70bc3f30e3f408eb772e3b31d440e766e8cb94cf499941
+oid sha256:987e4b63e12de213a09c8e74c81dada907bb17c64ace19c12e9842ec1ee6c605
 size 59933632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a760ece99505e7fcdcb1d4266cd957fafac17a52b5314f6dd33611679bab49b
+oid sha256:2a9b5d3810e8d35d8a179b0333760149ef732208387f500318bdf6d9ea8ec583
 size 31822948

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ea20ba7a13cf55be50c10b12ac6334e4f25253657ee7c4e1fb558b55ba1ab7b
+oid sha256:666d398dab05582426b55689121e6cb5a01ecefc7c7d556daadbabcbdc805fde
 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": 0.01199169805519256,
+  "epoch": 0.015373971865631485,
   "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": 2.5771,
       "step": 35
+    },
+    {
+      "epoch": 0.012299177492505189,
+      "grad_norm": 3.426758050918579,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.0909,
+      "step": 40
+    },
+    {
+      "epoch": 0.012299177492505189,
+      "eval_loss": 2.3121838569641113,
+      "eval_runtime": 68.5853,
+      "eval_samples_per_second": 19.975,
+      "eval_steps_per_second": 9.988,
+      "step": 40
+    },
+    {
+      "epoch": 0.013836574679068337,
+      "grad_norm": 4.541368007659912,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.0835,
+      "step": 45
+    },
+    {
+      "epoch": 0.015373971865631485,
+      "grad_norm": 4.1236491203308105,
+      "learning_rate": 0.0,
+      "loss": 2.1409,
+      "step": 50
+    },
+    {
+      "epoch": 0.015373971865631485,
+      "eval_loss": 2.292968511581421,
+      "eval_runtime": 68.3112,
+      "eval_samples_per_second": 20.055,
+      "eval_steps_per_second": 10.028,
+      "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": 2828127373885440.0,
+  "total_flos": 3599434839490560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null