Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f222fd3b1ef2f31b291f66119f93c38e5ce06c4f481136272b6d0e3c7ea4bc5
+oid sha256:94400bfdb540e84961f8f55eeb6ba6a3d5e74bc78e85d9834dd52457f6bb9738
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4451735e6a31dbe3b9eeac3f41d0479ae3cbae387ea09f56d619294b2e7fc408
+oid sha256:73be4c0d6c416751c8f0bcdb396cd4b0d9ec27d19fbdbe5de04effca7b68a910
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8fd9ed02254558172e0c1adf5c8f86e2a18c8ac4fa8869ed49936c433ecbe81
+oid sha256:75457ff9047a61e3f41ba81a128623afe5b1ae5c7463bc37a9196ea84fd005fc
 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": 0.0021329920546045967,
+  "epoch": 0.003199488081906895,
   "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": 15.903,
       "eval_steps_per_second": 7.952,
       "step": 100
+    },
+    {
+      "epoch": 0.002346291260065056,
+      "grad_norm": 1.0272051095962524,
+      "learning_rate": 8.79463319744677e-05,
+      "loss": 1.2709,
+      "step": 110
+    },
+    {
+      "epoch": 0.0025595904655255157,
+      "grad_norm": 1.6282625198364258,
+      "learning_rate": 7.217825360835473e-05,
+      "loss": 1.1521,
+      "step": 120
+    },
+    {
+      "epoch": 0.0027728896709859757,
+      "grad_norm": 0.982958197593689,
+      "learning_rate": 5.713074385969457e-05,
+      "loss": 1.1276,
+      "step": 130
+    },
+    {
+      "epoch": 0.0029861888764464353,
+      "grad_norm": 1.0101426839828491,
+      "learning_rate": 4.3193525326884435e-05,
+      "loss": 1.0648,
+      "step": 140
+    },
+    {
+      "epoch": 0.003199488081906895,
+      "grad_norm": 1.2995356321334839,
+      "learning_rate": 3.072756464904006e-05,
+      "loss": 1.1229,
+      "step": 150
+    },
+    {
+      "epoch": 0.003199488081906895,
+      "eval_loss": 0.2859799861907959,
+      "eval_runtime": 1241.8568,
+      "eval_samples_per_second": 15.896,
+      "eval_steps_per_second": 7.948,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.649073511923712e+16,
+  "total_flos": 5.5408925343744e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null