Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9af965a03f4a1b4d0726aed83ed0af56fa7803d27d50f4de8cf215bf6004e4b5
+oid sha256:db87586bc7bb49254a6bc25bdcecb51e41905ce54d62e17d2d9ad15b48094712
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a5e4942af8d3c6ac4b1ca5ab46ef98b6bc73bbb49efd7fa2f5a5d3ef8415201
+oid sha256:61a6bb15e7f886af5f6763f319b9a7f161beb3bf0c7c2d212e1ebdfcd2bc702e
 size 160284754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c325a5b88aa7600e783ee566917eff9758a4ec707c33c129463258bf687aee2
+oid sha256:318d5daa1e33a35543249e590b5fd9b28d4e2137de5e81940e98782aeff96166
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:842484d97bbf42f9f92b7e7c8dcf4fda5e0b0607fec45e60ed168e6d3a7f3132
+oid sha256:4677d15317405bcdd600dfdae9d04715d81517a0dbc7789a073149e371184d8c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04186289900575615,
+  "epoch": 0.052328623757195186,
   "eval_steps": 3,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -203,6 +203,57 @@
       "learning_rate": 1.4644660940672627e-05,
       "loss": 2.3639,
       "step": 20
+    },
+    {
+      "epoch": 0.04395604395604396,
+      "grad_norm": 2.7575583457946777,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.8185,
+      "step": 21
+    },
+    {
+      "epoch": 0.04395604395604396,
+      "eval_loss": 0.4724537432193756,
+      "eval_runtime": 28.7756,
+      "eval_samples_per_second": 7.02,
+      "eval_steps_per_second": 3.51,
+      "step": 21
+    },
+    {
+      "epoch": 0.046049188906331764,
+      "grad_norm": 2.319027900695801,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 1.7463,
+      "step": 22
+    },
+    {
+      "epoch": 0.04814233385661957,
+      "grad_norm": 3.020266056060791,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.9595,
+      "step": 23
+    },
+    {
+      "epoch": 0.05023547880690738,
+      "grad_norm": 2.4685897827148438,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 1.7662,
+      "step": 24
+    },
+    {
+      "epoch": 0.05023547880690738,
+      "eval_loss": 0.4614010155200958,
+      "eval_runtime": 28.736,
+      "eval_samples_per_second": 7.03,
+      "eval_steps_per_second": 3.515,
+      "step": 24
+    },
+    {
+      "epoch": 0.052328623757195186,
+      "grad_norm": 4.819024085998535,
+      "learning_rate": 0.0,
+      "loss": 2.0695,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -217,12 +268,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6514996968161280.0,
+  "total_flos": 8143746210201600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null