Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8726001b2559c5210d471b05bcd3ca9efd93187345c0b8c9eb8b8b05e4bbcc2f
+oid sha256:d249afbf5da3a161992f04af672ca9ebcae6e24e9ff928eb07c55f2a01621135
 size 59933632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55b2d4f7d323e10fc0c261d487824f64a50c3ff877043918adb091d0562dd13c
+oid sha256:9ef12219da0a717b155f073b87dcf7216b1ede9e7613439c7467ba252eefe666
 size 31822948

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3dc19fb608bbec0317a2814f2248a2b3971a089b405d5983bf531bf20b49b87
+oid sha256:d21a9b0e7e989e91c7bce6b82ce964e13898ea3b95ad3b6be6d33020dc0abf1c
 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": 0.006594800253646164,
+  "epoch": 0.008454872120059184,
   "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": 0.581,
       "step": 35
+    },
+    {
+      "epoch": 0.006763897696047347,
+      "grad_norm": 2.075490713119507,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.3814,
+      "step": 40
+    },
+    {
+      "epoch": 0.006763897696047347,
+      "eval_loss": 0.35606133937835693,
+      "eval_runtime": 198.9773,
+      "eval_samples_per_second": 12.514,
+      "eval_steps_per_second": 6.257,
+      "step": 40
+    },
+    {
+      "epoch": 0.007609384908053266,
+      "grad_norm": 1.5487943887710571,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.285,
+      "step": 45
+    },
+    {
+      "epoch": 0.008454872120059184,
+      "grad_norm": 2.912466526031494,
+      "learning_rate": 0.0,
+      "loss": 0.3002,
+      "step": 50
+    },
+    {
+      "epoch": 0.008454872120059184,
+      "eval_loss": 0.3085382878780365,
+      "eval_runtime": 198.8114,
+      "eval_samples_per_second": 12.524,
+      "eval_steps_per_second": 6.262,
+      "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": 4833526784458752.0,
+  "total_flos": 6101899061231616.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null