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:e5be6903eb666b1994f410471b7093182bc8eea9fa7267c8831141e19f0cedb6
+oid sha256:c325d3e0ea8b1b321e62aa4a3b3294c3f9baa2ece4aea0ad99e77b3622fb9f5b
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69aa0ed74db62382cb9f03c125245610c3bf0c95bdf6d1bbbcd42ce79d5ecd14
+oid sha256:22cfed382d9aa0528fcbc11a43ae66f2532893d53753a336e94846ecac1d0ac0
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:553e1fb405e5a86730dc28a3317a872e5911817b713bc630846d7b7397c7144a
+oid sha256:c147b1c08477330d759087b3c2a05dc14fe388b2d52662d57f2867c2f564061b
 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": 0.0006911805363560963,
+  "epoch": 0.0013823610727121925,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,65 @@
       "eval_samples_per_second": 7.338,
       "eval_steps_per_second": 3.669,
       "step": 15
+    },
+    {
+      "epoch": 0.0008294166436273154,
+      "grad_norm": 1.062957763671875,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 5.2179,
+      "step": 18
+    },
+    {
+      "epoch": 0.0009215740484747949,
+      "eval_loss": 1.2275902032852173,
+      "eval_runtime": 1246.2045,
+      "eval_samples_per_second": 7.333,
+      "eval_steps_per_second": 3.666,
+      "step": 20
+    },
+    {
+      "epoch": 0.0009676527508985347,
+      "grad_norm": 0.8761299848556519,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 4.7563,
+      "step": 21
+    },
+    {
+      "epoch": 0.001105888858169754,
+      "grad_norm": 0.9032831192016602,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 4.4314,
+      "step": 24
+    },
+    {
+      "epoch": 0.0011519675605934938,
+      "eval_loss": 1.2096927165985107,
+      "eval_runtime": 1245.7257,
+      "eval_samples_per_second": 7.335,
+      "eval_steps_per_second": 3.668,
+      "step": 25
+    },
+    {
+      "epoch": 0.0012441249654409731,
+      "grad_norm": 1.0080879926681519,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 4.7194,
+      "step": 27
+    },
+    {
+      "epoch": 0.0013823610727121925,
+      "grad_norm": 0.8476549983024597,
+      "learning_rate": 0.0,
+      "loss": 5.2062,
+      "step": 30
+    },
+    {
+      "epoch": 0.0013823610727121925,
+      "eval_loss": 1.2064721584320068,
+      "eval_runtime": 1245.4272,
+      "eval_samples_per_second": 7.337,
+      "eval_steps_per_second": 3.669,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -88,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.079131093598208e+16,
+  "total_flos": 2.094783887572992e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null