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:ca4f5780da7479df03b31780ffd660f4126d9a41af235bd2c373ef8ab037d45c
+oid sha256:714deaca135bd52b0b9a0bb21dcdfbde57fbbbb5ee4a8b5d5a529180cdf5c1e7
 size 50365768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:919f7ec4c8c6e4d64e621460085a022d36082060758c1422f5c2f4080c424f74
+oid sha256:5a3ed12a2c16427f7ed9ca7d219f0519e9539a852409b8d0ef4323018c54624b
 size 25859156

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4daadbc8a0eb5eb3627f0a4012f1711d3d7a034e1da76dffaa7cff7352b14d0f
+oid sha256:f60f097760d01184e90b8291f5ef05a5c5cf847af7580ad2c71d67270d236bc2
 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": 0.020950846091861403,
+  "epoch": 0.026860059092130004,
   "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": 0.3137,
       "step": 35
+    },
+    {
+      "epoch": 0.021488047273704004,
+      "grad_norm": 0.5185353755950928,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.394,
+      "step": 40
+    },
+    {
+      "epoch": 0.021488047273704004,
+      "eval_loss": 0.0965627133846283,
+      "eval_runtime": 80.2685,
+      "eval_samples_per_second": 9.767,
+      "eval_steps_per_second": 4.884,
+      "step": 40
+    },
+    {
+      "epoch": 0.024174053182917002,
+      "grad_norm": 0.3682008981704712,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.3557,
+      "step": 45
+    },
+    {
+      "epoch": 0.026860059092130004,
+      "grad_norm": 0.5637223124504089,
+      "learning_rate": 0.0,
+      "loss": 0.4302,
+      "step": 50
+    },
+    {
+      "epoch": 0.026860059092130004,
+      "eval_loss": 0.09565096348524094,
+      "eval_runtime": 80.1864,
+      "eval_samples_per_second": 9.777,
+      "eval_steps_per_second": 4.889,
+      "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": 6861701498535936.0,
+  "total_flos": 8720557088440320.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null