Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1aa85ff170fb699ecfdd0d6eaa7525a5546753f4afb56ac9c831722e3c7351ee
+oid sha256:7d32117ad81fb40aea95361956972570c66cbedf2abb07486c26274b7b1e7446
 size 216151256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8ce9e16b0c50248b29a69b050fc3ccdcb4a7d2188bc3a97a6d0e8cf5cab88e6
+oid sha256:172309f0b37ddc6ccacd683f7affa3c4966940af5e2e5af1fe9c7937e25c474f
 size 432640054

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39ed5f2f7efa7f3ea61e60b1a3a7affc14cc9414ca521f6b20a6e7c6e69f01a2
+oid sha256:dfacf77ecd66b65be26e3d3ce8a0aeb80f7593ac2c5782468632478c58ec8633
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0032512395350727465,
+  "epoch": 0.00487685930260912,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 7.453,
       "eval_steps_per_second": 3.728,
       "step": 20
+    },
+    {
+      "epoch": 0.003413801511826384,
+      "grad_norm": 2.110877275466919,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 2.2109,
+      "step": 21
+    },
+    {
+      "epoch": 0.003901487442087296,
+      "grad_norm": 2.2336580753326416,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 2.3767,
+      "step": 24
+    },
+    {
+      "epoch": 0.004064049418840933,
+      "eval_loss": 2.470907688140869,
+      "eval_runtime": 347.6491,
+      "eval_samples_per_second": 7.453,
+      "eval_steps_per_second": 3.728,
+      "step": 25
+    },
+    {
+      "epoch": 0.0043891733723482075,
+      "grad_norm": 1.6830624341964722,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 2.2971,
+      "step": 27
+    },
+    {
+      "epoch": 0.00487685930260912,
+      "grad_norm": 1.5091761350631714,
+      "learning_rate": 0.0,
+      "loss": 2.3314,
+      "step": 30
+    },
+    {
+      "epoch": 0.00487685930260912,
+      "eval_loss": 2.4591238498687744,
+      "eval_runtime": 347.6421,
+      "eval_samples_per_second": 7.453,
+      "eval_steps_per_second": 3.728,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -103,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8236125420257280.0,
+  "total_flos": 1.235418813038592e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null