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:ba95c27510b762341006743bfaba6d6e49f759e1629ba02a19985186f302a70a
+oid sha256:4dc42a847cf98740ffd621890c3a73449659e069b59980bafcc4b090be35c3cb
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94d7c57cae4893854c112b5be5a055687b4c346c08c3206bff23fc1a9703f4a7
+oid sha256:1431bd430241c6aa28bd4777b34d465141dd069ede3eb937f90610f3f5ac9bc9
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:031f5f3e551f43b0fe1df3cce9d694cc2ba837b1b8da6f30df85df88dcf3df05
+oid sha256:f90f55ec5c228872fbcec425c4d61211662fbc8ab8b311515500a73d50690cdb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef527702b4e2147a500c0b29beb26751d245ebb60338b3910b449b6549ac4d59
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00019938235776284133,
+  "epoch": 0.00039876471552568267,
   "eval_steps": 8,
-  "global_step": 15,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,57 @@
       "learning_rate": 0.0002,
       "loss": 1.8888,
       "step": 15
+    },
+    {
+      "epoch": 0.00021267451494703075,
+      "eval_loss": 1.7299827337265015,
+      "eval_runtime": 2067.6299,
+      "eval_samples_per_second": 11.49,
+      "eval_steps_per_second": 5.745,
+      "step": 16
+    },
+    {
+      "epoch": 0.0002392588293154096,
+      "grad_norm": 1.4860124588012695,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.7889,
+      "step": 18
+    },
+    {
+      "epoch": 0.00027913530086797785,
+      "grad_norm": 0.8257107138633728,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.7835,
+      "step": 21
+    },
+    {
+      "epoch": 0.00031901177242054616,
+      "grad_norm": 0.6575050950050354,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 1.5446,
+      "step": 24
+    },
+    {
+      "epoch": 0.00031901177242054616,
+      "eval_loss": 1.5880478620529175,
+      "eval_runtime": 2067.4112,
+      "eval_samples_per_second": 11.492,
+      "eval_steps_per_second": 5.746,
+      "step": 24
+    },
+    {
+      "epoch": 0.0003588882439731144,
+      "grad_norm": 0.6337928175926208,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.7106,
+      "step": 27
+    },
+    {
+      "epoch": 0.00039876471552568267,
+      "grad_norm": 0.7751510739326477,
+      "learning_rate": 0.0,
+      "loss": 1.5877,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -72,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3801291172085760.0,
+  "total_flos": 7519945579560960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null