Training in progress, step 85, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b06d6095f86341e631c31dfe5c014ab0c7bdd8dd50ae9b2f22748fb787b26c43
+oid sha256:be4a3e12ace7db54eb920b934f6c0ee05cc4f4a8c194adf5d5df9e3b0cdd68c9
 size 34793120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6d475747d9aed2705bc7b24c14fe90c153254ec151ddecd24eebe44d949f462
+oid sha256:7bedc55c1f8f18184593c54334179fa1f18a4e48f30fc591992b4c57dd36d69e
 size 18132116

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bb1f6ba326b8488be4e2327d96e736f1996da096cf4aab9ac45520a7cbbf382
+oid sha256:c81be7588d13c4d18f0badc374dddf114640e4f47aaffe28b0dd04921466a3ad
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40aaba2d15c70d89033b94214bc8306c06d04f2fbceef0fdedf952808109d707
+oid sha256:24510621ac929102038dbb9557bac0e17f0ed52c36608ebab8e700d1b1464f1d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.37517241379310345,
+  "epoch": 0.4689655172413793,
   "eval_steps": 17,
-  "global_step": 68,
+  "global_step": 85,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -201,6 +201,56 @@
       "eval_samples_per_second": 68.1,
       "eval_steps_per_second": 8.708,
       "step": 68
+    },
+    {
+      "epoch": 0.38068965517241377,
+      "grad_norm": 0.45721158385276794,
+      "learning_rate": 7.803575286758364e-05,
+      "loss": 2.1911,
+      "step": 69
+    },
+    {
+      "epoch": 0.3972413793103448,
+      "grad_norm": 0.5159802436828613,
+      "learning_rate": 7.594847868906076e-05,
+      "loss": 2.249,
+      "step": 72
+    },
+    {
+      "epoch": 0.41379310344827586,
+      "grad_norm": 0.4334803819656372,
+      "learning_rate": 7.379736965185368e-05,
+      "loss": 2.0298,
+      "step": 75
+    },
+    {
+      "epoch": 0.4303448275862069,
+      "grad_norm": 0.4824793338775635,
+      "learning_rate": 7.158771761692464e-05,
+      "loss": 2.1161,
+      "step": 78
+    },
+    {
+      "epoch": 0.44689655172413795,
+      "grad_norm": 0.507147490978241,
+      "learning_rate": 6.932495846462261e-05,
+      "loss": 2.1276,
+      "step": 81
+    },
+    {
+      "epoch": 0.463448275862069,
+      "grad_norm": 0.5079874396324158,
+      "learning_rate": 6.701465872208216e-05,
+      "loss": 2.3072,
+      "step": 84
+    },
+    {
+      "epoch": 0.4689655172413793,
+      "eval_loss": 2.1795969009399414,
+      "eval_runtime": 4.4446,
+      "eval_samples_per_second": 68.623,
+      "eval_steps_per_second": 8.775,
+      "step": 85
     }
   ],
   "logging_steps": 3,
@@ -220,7 +270,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4322559189319680.0,
+  "total_flos": 5403198986649600.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null