Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cca461e07d8975da8e2ae147ab95611a24a85744128c9071bcfa8e6eb2ec330
+oid sha256:be7ba107b10de658bb695f91b1d8c421ad94b477f00c22af3b4c08ea55bc2611
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88d985dd0d64ed929cd47581ca510a971ddf71db7d5f67d0f21326bd59c5f8b7
+oid sha256:1966e44ecd240e944b100d0134a05488f2a992beb1659da8b49cfcb516ce74d5
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88d894e21213c07cbd0cec0014f57efd5c4063573964a7d259b2cdbd9a265b45
+oid sha256:5c39023ce1b62d2335c9de84427aaee446300d6e23bcdbb10b1fa8f6bdbb1d3a
 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": 0.000786072409362324,
+  "epoch": 0.0010077851402081077,
   "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": 1.3362,
       "step": 35
+    },
+    {
+      "epoch": 0.0008062281121664861,
+      "grad_norm": 1.378598690032959,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.8891,
+      "step": 40
+    },
+    {
+      "epoch": 0.0008062281121664861,
+      "eval_loss": 1.10456383228302,
+      "eval_runtime": 1915.9106,
+      "eval_samples_per_second": 10.903,
+      "eval_steps_per_second": 5.452,
+      "step": 40
+    },
+    {
+      "epoch": 0.0009070066261872969,
+      "grad_norm": 0.817628026008606,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.1041,
+      "step": 45
+    },
+    {
+      "epoch": 0.0010077851402081077,
+      "grad_norm": 1.2205736637115479,
+      "learning_rate": 0.0,
+      "loss": 1.131,
+      "step": 50
+    },
+    {
+      "epoch": 0.0010077851402081077,
+      "eval_loss": 1.10031259059906,
+      "eval_runtime": 1922.4649,
+      "eval_samples_per_second": 10.866,
+      "eval_steps_per_second": 5.433,
+      "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": 9941407833784320.0,
+  "total_flos": 1.2761993312206848e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null