Training in progress, step 117, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d15e4509d78b338702add67e1a0342d20cea1e62d70828144cdd82d7e225f61c
+oid sha256:df9b95bc471cc3fea848c45abf3ec644b179a80655080267108d364c7410a07b
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a134a8407784819add1857aa0a3a9ee8c24a75e636b885a04bed46b9e8d507c
+oid sha256:9bd86cd5aaff0df3defda957eee1d5e98476a0bed9dff47a67adde018538ba72
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11f555bc649def2d5f222c82b81fe7588d9710c829bc5246c9b7c7e93cf60c40
+oid sha256:a9dfcfa634c3d602fbb32d8617cc1f5299a65b972221d7081152805a0ea9f6b3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c89b61481eb2980a04190d12a0165f95c9fc0a4db20ad8cc3d895835eac42f68
+oid sha256:49a9f08177ba433a82ec0fa599b737a453ff55e83dd9d31c6fddaf5bc4b0a0b3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.028800886181113265,
+  "epoch": 0.032400996953752426,
   "eval_steps": 13,
-  "global_step": 104,
+  "global_step": 117,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -317,6 +317,49 @@
       "eval_samples_per_second": 13.199,
       "eval_steps_per_second": 1.651,
       "step": 104
+    },
+    {
+      "epoch": 0.029077817779008586,
+      "grad_norm": 2.075512647628784,
+      "learning_rate": 2.3398396174233178e-05,
+      "loss": 1.4585,
+      "step": 105
+    },
+    {
+      "epoch": 0.029908612572694546,
+      "grad_norm": 2.6266424655914307,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.4344,
+      "step": 108
+    },
+    {
+      "epoch": 0.030739407366380506,
+      "grad_norm": 1.5184435844421387,
+      "learning_rate": 1.7956219300748793e-05,
+      "loss": 1.387,
+      "step": 111
+    },
+    {
+      "epoch": 0.031570202160066466,
+      "grad_norm": 2.3101930618286133,
+      "learning_rate": 1.544686755065677e-05,
+      "loss": 1.3772,
+      "step": 114
+    },
+    {
+      "epoch": 0.032400996953752426,
+      "grad_norm": 2.4926693439483643,
+      "learning_rate": 1.3094050125632972e-05,
+      "loss": 1.339,
+      "step": 117
+    },
+    {
+      "epoch": 0.032400996953752426,
+      "eval_loss": 0.3452422320842743,
+      "eval_runtime": 460.5584,
+      "eval_samples_per_second": 13.206,
+      "eval_steps_per_second": 1.652,
+      "step": 117
     }
   ],
   "logging_steps": 3,
@@ -336,7 +379,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.689729633311785e+17,
+  "total_flos": 1.9026089571935846e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null