Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99209c00b01259212a75bcd1ee90724ff886337dbfd2a72d9069b71c06923ac6
+oid sha256:b588f1f9770ee4137e875d99407268649d970d7df4baaafc3076267ed0c5c560
 size 94412008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b73ab48107f63a9f65afdb0a2a086aadb6577b0b55d4f55874f7e4918c7ce92
+oid sha256:d71603b163c54de6d5e598247bdda1657b711b76baada55855b4dad7a225ca04
 size 48260756

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:241143b21cc924d430c26337fe782eca95bd4e2597092f90ee9241ee7d7a4b6c
+oid sha256:f59726f487b5ed348f0ab0883dc9cc88111fc1bbf85690706ad84a62e4544e63
 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": 0.0970752955818295,
+  "epoch": 0.12445550715619166,
   "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": 2.7865,
       "step": 35
+    },
+    {
+      "epoch": 0.09956440572495333,
+      "grad_norm": 1.5695966482162476,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.0397,
+      "step": 40
+    },
+    {
+      "epoch": 0.09956440572495333,
+      "eval_loss": 0.7450600862503052,
+      "eval_runtime": 49.9519,
+      "eval_samples_per_second": 3.403,
+      "eval_steps_per_second": 1.702,
+      "step": 40
+    },
+    {
+      "epoch": 0.11200995644057249,
+      "grad_norm": 1.4493436813354492,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.1448,
+      "step": 45
+    },
+    {
+      "epoch": 0.12445550715619166,
+      "grad_norm": 1.4496955871582031,
+      "learning_rate": 0.0,
+      "loss": 3.0665,
+      "step": 50
+    },
+    {
+      "epoch": 0.12445550715619166,
+      "eval_loss": 0.7428323030471802,
+      "eval_runtime": 50.1265,
+      "eval_samples_per_second": 3.391,
+      "eval_steps_per_second": 1.696,
+      "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": 2.225188179542016e+16,
+  "total_flos": 2.8528053583872e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null