Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f58410d96441928b8e84e5a035dd9daab11804184e66e72f4a9943f6f7543b9
+oid sha256:07fd2d883b3c30cc1093c7fda725e9c8a0ac574e394d22051406f9d03df9738c
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:521fb488372582689b64a4c4f59d3ebdeba63473ff33c9bc9ddfd307ad145452
+oid sha256:2dcd5775ffa55bf8a3d7381114bb17f05ce3d30c3a7506fbc53aa7b1049c40ff
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e25ec60ffe2fb5edbd0cfbdda0f17282b968644048575059d74da5532e8c1dcd
+oid sha256:3b0b45da7dc6845999a5dc9b182fd5e7b147bf10ea32f46a273a67dd81f951f6
 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": 0.005725821251605799,
+  "epoch": 0.007340796476417691,
   "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": 3.1426,
       "step": 35
+    },
+    {
+      "epoch": 0.005872637181134153,
+      "grad_norm": 1.596264123916626,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.793,
+      "step": 40
+    },
+    {
+      "epoch": 0.005872637181134153,
+      "eval_loss": 2.929900646209717,
+      "eval_runtime": 103.2968,
+      "eval_samples_per_second": 27.765,
+      "eval_steps_per_second": 13.882,
+      "step": 40
+    },
+    {
+      "epoch": 0.006606716828775922,
+      "grad_norm": 1.112859845161438,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.9454,
+      "step": 45
+    },
+    {
+      "epoch": 0.007340796476417691,
+      "grad_norm": 0.8456483483314514,
+      "learning_rate": 0.0,
+      "loss": 2.7399,
+      "step": 50
+    },
+    {
+      "epoch": 0.007340796476417691,
+      "eval_loss": 2.9293360710144043,
+      "eval_runtime": 102.8064,
+      "eval_samples_per_second": 27.897,
+      "eval_steps_per_second": 13.949,
+      "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": 489709900922880.0,
+  "total_flos": 601007605678080.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null