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:ff072f23281448819b95c770c0c8e697fe4c5e3883501e6ed1d35814d9918afe
+oid sha256:c7376767c79553edf9b8c35750fe5c52b7e87bfb7b4edcd1aca6eb928b840a89
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83c628c2905760c55ce8038f1b5f49fba49ecf261faa7c0d773361d663e055b0
+oid sha256:c299b5a90c1928811b5d54d3951638baed62ef54fd32a0112576293fbe19f9d4
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e929b74b092d250e864583ec73853e1cf0bc3ea16a30208b7acbc86e2ff2c44e
+oid sha256:d4f0ad7219323c6994e257a4040730f64ee21b45bdf338e935fca021e67c8081
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccc7e73cc5879da996ace4c3a10d9efe08a100111973e801d61997747e95e982
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02783229259589652,
+  "epoch": 0.03568242640499554,
   "eval_steps": 13,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -312,6 +312,83 @@
       "eval_samples_per_second": 22.858,
       "eval_steps_per_second": 11.429,
       "step": 39
+    },
+    {
+      "epoch": 0.028545941123996433,
+      "grad_norm": 0.6841302514076233,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.5095,
+      "step": 40
+    },
+    {
+      "epoch": 0.02925958965209634,
+      "grad_norm": 0.7829428315162659,
+      "learning_rate": 2.3959403439996907e-05,
+      "loss": 0.664,
+      "step": 41
+    },
+    {
+      "epoch": 0.029973238180196253,
+      "grad_norm": 0.6107116341590881,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.4047,
+      "step": 42
+    },
+    {
+      "epoch": 0.030686886708296165,
+      "grad_norm": 0.6358041167259216,
+      "learning_rate": 1.4735983564590783e-05,
+      "loss": 0.4236,
+      "step": 43
+    },
+    {
+      "epoch": 0.03140053523639608,
+      "grad_norm": 0.4066013991832733,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.238,
+      "step": 44
+    },
+    {
+      "epoch": 0.032114183764495985,
+      "grad_norm": 0.4986321032047272,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.3765,
+      "step": 45
+    },
+    {
+      "epoch": 0.03282783229259589,
+      "grad_norm": 0.5418090224266052,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 0.6273,
+      "step": 46
+    },
+    {
+      "epoch": 0.03354148082069581,
+      "grad_norm": 0.4689207673072815,
+      "learning_rate": 2.7630079602323442e-06,
+      "loss": 0.5362,
+      "step": 47
+    },
+    {
+      "epoch": 0.03425512934879572,
+      "grad_norm": 0.6380236744880676,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 0.5239,
+      "step": 48
+    },
+    {
+      "epoch": 0.03496877787689563,
+      "grad_norm": 0.5709643959999084,
+      "learning_rate": 3.0826662668720364e-07,
+      "loss": 0.5051,
+      "step": 49
+    },
+    {
+      "epoch": 0.03568242640499554,
+      "grad_norm": 0.7242156863212585,
+      "learning_rate": 0.0,
+      "loss": 0.4429,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -326,12 +403,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9077684227276800.0,
+  "total_flos": 1.17054349246464e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null