Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4603ed702189eefe4a454a39f73d268f6b34d7b62d25f3a82564a5a6d2a6bf46
+oid sha256:320203ad35f22828ad32ed678d0a03efdda7f32454df09ceb270bb08a506e325
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0b8eb766891c00b0224f6039238261328735737cfa6c81e7ede585150b623fd
+oid sha256:e00991b61e085e6fca8d37974078572010442df839a6fa0572665332f0a40752
 size 166439638

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58ed156a7fd848f1f7fc3cd09fe962a41e3fcfc536d855dffc5cb2d42590de4c
+oid sha256:1f0149a2a0d195c125a1b0809c8c7d92e69186b35ae6cd37d3ee167aaa478e73
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:1e2ed9259304616a8ecebc61c5d000777b2978635f7a705b8d7081c480ce0bde
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.016645859342488557,
+  "epoch": 0.033291718684977115,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 12.242,
       "eval_steps_per_second": 6.145,
       "step": 10
+    },
+    {
+      "epoch": 0.019975031210986267,
+      "grad_norm": 0.6611196398735046,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.2296,
+      "step": 12
+    },
+    {
+      "epoch": 0.024968789013732832,
+      "grad_norm": 0.5405768752098083,
+      "learning_rate": 0.0001,
+      "loss": 1.0945,
+      "step": 15
+    },
+    {
+      "epoch": 0.024968789013732832,
+      "eval_loss": 1.1015284061431885,
+      "eval_runtime": 20.7034,
+      "eval_samples_per_second": 12.22,
+      "eval_steps_per_second": 6.134,
+      "step": 15
+    },
+    {
+      "epoch": 0.0299625468164794,
+      "grad_norm": 0.6583252549171448,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.0174,
+      "step": 18
+    },
+    {
+      "epoch": 0.033291718684977115,
+      "eval_loss": 1.0726263523101807,
+      "eval_runtime": 20.6899,
+      "eval_samples_per_second": 12.228,
+      "eval_steps_per_second": 6.138,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -66,12 +103,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2010596581048320.0,
+  "total_flos": 4021193162096640.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null