Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4eefdd92b0c60936c9f3bdf2c8a6a1f03876bce7210bb35f89a8fe03907cd744
+oid sha256:95ea90ea2fd04d0bc27c09eb4255076048366f2c8b9f2bb8008c0c86e8e87e54
 size 39256456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfc899a583885876500290295cc9bc0c7b4168ffa45f853d63afe66f426ab094
+oid sha256:a0e0a76163509f784b8b1a1f5b6e35875cacd660f581ba32eb43f76ff42cdbdd
 size 20632826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d622c5fb7bd558d55cdd7ea3c956fd06a0d8788be259d61032675ae3fa69edd6
+oid sha256:d3b2ed62d3c3041d929f4689e56812b00363ecda2ba4abac93da71f834cdd0c0
 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": 0.00024234590839324662,
+  "epoch": 0.00048469181678649324,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 28.154,
       "eval_steps_per_second": 14.08,
       "step": 3
+    },
+    {
+      "epoch": 0.00032312787785766214,
+      "grad_norm": 13.849967956542969,
+      "learning_rate": 8e-05,
+      "loss": 6.0094,
+      "step": 4
+    },
+    {
+      "epoch": 0.0004039098473220777,
+      "grad_norm": 11.20494556427002,
+      "learning_rate": 0.0001,
+      "loss": 5.0195,
+      "step": 5
+    },
+    {
+      "epoch": 0.00048469181678649324,
+      "grad_norm": 10.72175407409668,
+      "learning_rate": 0.00012,
+      "loss": 4.6667,
+      "step": 6
+    },
+    {
+      "epoch": 0.00048469181678649324,
+      "eval_loss": 3.9255988597869873,
+      "eval_runtime": 186.96,
+      "eval_samples_per_second": 27.883,
+      "eval_steps_per_second": 13.944,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 146843338014720.0,
+  "total_flos": 293686676029440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null