Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81ca70464c6891920e1f1c6fe83db22bc0a91f7c7af8769d6b2121524c5f10b7
+oid sha256:62cad1900e5ab5f9cf7a434864d5e34e9e15b6ba1d7f44608590b27fc1d902e2
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:051d2b675f138dbfb7f1bacb7a389b85aedf2fb7a36e0e277db4b2e4320710ee
+oid sha256:030d09393d6feba96439d5f7a7ebf9d2c003756aefa441ba9bd045d6616b6af9
 size 79968772

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:caa173be0daf3b70291aa54f3fc172b70d25960de7e9a07e7f57c5f27ae513c9
+oid sha256:28cb1b5e093b2599d8fa1806646d1f09bc9ce7ac92f9796c6863470342508537
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fd8212ec5ec3406d74a7f927b717dd30ea8a06115ee6582e14976f7b84b4b58
+oid sha256:b489c13e2d776471e9a48162938854a24466ce6713df9c0fb59abd9a09fb226b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.13183915622940012,
+  "epoch": 0.19775873434410018,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 36.654,
       "eval_steps_per_second": 18.327,
       "step": 100
+    },
+    {
+      "epoch": 0.14502307185234015,
+      "grad_norm": 1.9904274940490723,
+      "learning_rate": 8.79463319744677e-05,
+      "loss": 1.1787,
+      "step": 110
+    },
+    {
+      "epoch": 0.15820698747528017,
+      "grad_norm": 1.6863394975662231,
+      "learning_rate": 7.217825360835473e-05,
+      "loss": 1.2355,
+      "step": 120
+    },
+    {
+      "epoch": 0.17139090309822017,
+      "grad_norm": 1.930191993713379,
+      "learning_rate": 5.713074385969457e-05,
+      "loss": 1.1418,
+      "step": 130
+    },
+    {
+      "epoch": 0.1845748187211602,
+      "grad_norm": 1.7425230741500854,
+      "learning_rate": 4.3193525326884435e-05,
+      "loss": 1.1267,
+      "step": 140
+    },
+    {
+      "epoch": 0.19775873434410018,
+      "grad_norm": 1.7823681831359863,
+      "learning_rate": 3.072756464904006e-05,
+      "loss": 1.2661,
+      "step": 150
+    },
+    {
+      "epoch": 0.19775873434410018,
+      "eval_loss": 1.1526826620101929,
+      "eval_runtime": 4.3671,
+      "eval_samples_per_second": 36.638,
+      "eval_steps_per_second": 18.319,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4967074313011200.0,
+  "total_flos": 7450611469516800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null