Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52e0da0a197e5a6e225ab59b6a0c41edd1b32736ea7d2494b6a36a10c07064bc
+oid sha256:de8027f8fcd97fa51ad45557b67f8b9c58e8d4bc1ad1e1189c7e85d76bd2a3ef
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1be93a4b801b0d7108a58c2f240d76a35f3ab344637dac662a1c08a883d0bffd
+oid sha256:fc413951c1fba24899ee8e099794a7197b16c4341342c73a315a89300b539f28
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3287c736d0d207c2f0759d8872a823ca63756120377bf508b68df1a30f38000b
+oid sha256:b945839f62fba14f44ee64b3971d188e4a957f75b61288f4cb44c7f3a22430f4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.013472549680026945,
+  "epoch": 0.02694509936005389,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 4.914,
       "eval_steps_per_second": 2.465,
       "step": 10
+    },
+    {
+      "epoch": 0.016167059616032334,
+      "grad_norm": 0.3981638252735138,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.6151,
+      "step": 12
+    },
+    {
+      "epoch": 0.020208824520040417,
+      "grad_norm": 0.37302765250205994,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.574,
+      "step": 15
+    },
+    {
+      "epoch": 0.020208824520040417,
+      "eval_loss": 0.6328597068786621,
+      "eval_runtime": 63.7,
+      "eval_samples_per_second": 4.914,
+      "eval_steps_per_second": 2.465,
+      "step": 15
+    },
+    {
+      "epoch": 0.0242505894240485,
+      "grad_norm": 0.41704243421554565,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.6303,
+      "step": 18
+    },
+    {
+      "epoch": 0.02694509936005389,
+      "eval_loss": 0.6112756729125977,
+      "eval_runtime": 63.7255,
+      "eval_samples_per_second": 4.912,
+      "eval_steps_per_second": 2.464,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -71,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5842362358038528.0,
+  "total_flos": 1.1684724716077056e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null