Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93a0e04e57b5482afe550df17a38da6ad82647c5bff03bef4e420bd6c83f9dec
+oid sha256:ac600afd017bf30efb895876b7b20a3e2b330b37f517343a971ec3345196a3c7
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f53a9d2505013e2cef2ddf0f0876cb79fc334bebf08f4b47dd48282df2fe7a0
+oid sha256:a348907cc4a0c012b94d54324124e77686c569e71ab8161c0511ff15f1fe94e0
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b15ef482adfa505ee3364d705bde5e2125f6e7d36e0d43bb6a6219adbcc213cb
+oid sha256:5109ddc5c3c73e6d26539cc868ed6f239041a0fd7060c2d4a82d83b474e40c57
 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": 0.0023492206912130113,
+  "epoch": 0.00301182139899104,
   "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": 1.3196,
       "step": 35
+    },
+    {
+      "epoch": 0.0024094571191928317,
+      "grad_norm": 25.286365509033203,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.4148,
+      "step": 40
+    },
+    {
+      "epoch": 0.0024094571191928317,
+      "eval_loss": 0.2982780337333679,
+      "eval_runtime": 692.0766,
+      "eval_samples_per_second": 10.1,
+      "eval_steps_per_second": 5.05,
+      "step": 40
+    },
+    {
+      "epoch": 0.0027106392590919358,
+      "grad_norm": 17.550260543823242,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.2314,
+      "step": 45
+    },
+    {
+      "epoch": 0.00301182139899104,
+      "grad_norm": 20.98444175720215,
+      "learning_rate": 0.0,
+      "loss": 1.1832,
+      "step": 50
+    },
+    {
+      "epoch": 0.00301182139899104,
+      "eval_loss": 0.2857048511505127,
+      "eval_runtime": 689.9907,
+      "eval_samples_per_second": 10.131,
+      "eval_steps_per_second": 5.065,
+      "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": 1.1348536864014336e+16,
+  "total_flos": 1.445952573407232e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null