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:dc14fe8f7507e90d322ffb5b6ce95e1fca2360025e87ca8462c6368248e75484
+oid sha256:5e49e2229fc4600dc2c513dc55e8658a823a9566dafa9e3b3a07d6076a6414c3
 size 66103768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4986c8429abbde5e0a51913bcfbb060d5c038e026dc2c893867a3b7097946c02
+oid sha256:4459a5353de16eece081ca00b1c74a65ec56cc030e9e35582cec56684d78bc90
 size 33939412

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9293b15c6b91c5eb6e21b46891f3471558c8d935f612fac13696ddde48813452
+oid sha256:3d73de7e08e2b63c7f7a17b4df18d956fc7a4ba53bd037e44237f16e13577905
 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": 0.01253616200578592,
+  "epoch": 0.016072002571520413,
   "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": 8.0253,
       "step": 35
+    },
+    {
+      "epoch": 0.01285760205721633,
+      "grad_norm": 4.0796122550964355,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 8.0616,
+      "step": 40
+    },
+    {
+      "epoch": 0.01285760205721633,
+      "eval_loss": 1.911198377609253,
+      "eval_runtime": 129.339,
+      "eval_samples_per_second": 10.128,
+      "eval_steps_per_second": 5.064,
+      "step": 40
+    },
+    {
+      "epoch": 0.01446480231436837,
+      "grad_norm": 3.8582828044891357,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 7.7004,
+      "step": 45
+    },
+    {
+      "epoch": 0.016072002571520413,
+      "grad_norm": 3.681159496307373,
+      "learning_rate": 0.0,
+      "loss": 7.3475,
+      "step": 50
+    },
+    {
+      "epoch": 0.016072002571520413,
+      "eval_loss": 1.904124140739441,
+      "eval_runtime": 129.1904,
+      "eval_samples_per_second": 10.14,
+      "eval_steps_per_second": 5.07,
+      "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": 8246235055945728.0,
+  "total_flos": 1.0586869460471808e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null