Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a5ee48bc4774e595084532880248bfb7475fcc0bb0247db5055aab90db95e06
+oid sha256:4fa0ac5421769d5719178d5a3107fde5b044b10fb6c80c58eec6a9c6decd05f1
 size 59933632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa2a53340e738356ad853ed10039e887f156051ffdc694aa6652a50f867ccff0
+oid sha256:1b645069f9a659914796b2d7b0efd0b6a4ddca4744902a0add688904ed228e27
 size 31822948

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f683ddb734a49a81357cf94290689cd53aeaac91c3f07e9e55fa6eb78450c109
+oid sha256:6872307f4470a047155c6b916b2c9040d688e2f96562192a9d5c5fb6108984b7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.400999639628348e-05,
+  "epoch": 0.00018801999279256695,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -36,6 +36,35 @@
       "eval_samples_per_second": 14.806,
       "eval_steps_per_second": 7.404,
       "step": 3
+    },
+    {
+      "epoch": 0.0001253466618617113,
+      "grad_norm": 5.215977668762207,
+      "learning_rate": 8e-05,
+      "loss": 2.4588,
+      "step": 4
+    },
+    {
+      "epoch": 0.00015668332732713913,
+      "grad_norm": 4.574519157409668,
+      "learning_rate": 0.0001,
+      "loss": 2.3348,
+      "step": 5
+    },
+    {
+      "epoch": 0.00018801999279256695,
+      "grad_norm": 3.121293544769287,
+      "learning_rate": 0.00012,
+      "loss": 2.2783,
+      "step": 6
+    },
+    {
+      "epoch": 0.00018801999279256695,
+      "eval_loss": 1.8826760053634644,
+      "eval_runtime": 919.8555,
+      "eval_samples_per_second": 14.608,
+      "eval_steps_per_second": 7.304,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -55,7 +84,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 205681990828032.0,
+  "total_flos": 411363981656064.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null