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:f402162cf1f182618f2bb66d5f03306a2f211dda9ea863eb6f0b1ff3a4243d2b
+oid sha256:58f16b70d5c7ea66f5bcf93feb1af9bcb07f4092e71922f8a07ab16b615c422d
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5be2af21e0063e8c563c3cb0d3dd4fecd421b3b35ad6664c24abffeb06dd05a
+oid sha256:1120b9579c643a9ffcec130356e2691b013a0442bab57947464d952a0cb557da
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d3302d3866a6a17fd98f0f985156ca47a13f812a796abc8e9f9d979fbd082b0
+oid sha256:7b463883609ea29a433544401e2cca59a163be1d6a17f6d6e25dc877b7bef91b
 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": 0.000507292327203551,
+  "epoch": 0.001014584654407102,
   "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": 34.014,
       "eval_steps_per_second": 17.007,
       "step": 3
+    },
+    {
+      "epoch": 0.0006763897696047348,
+      "grad_norm": 0.4584774076938629,
+      "learning_rate": 8e-05,
+      "loss": 0.8486,
+      "step": 4
+    },
+    {
+      "epoch": 0.0008454872120059184,
+      "grad_norm": 0.5321890711784363,
+      "learning_rate": 0.0001,
+      "loss": 0.6456,
+      "step": 5
+    },
+    {
+      "epoch": 0.001014584654407102,
+      "grad_norm": 0.4280243217945099,
+      "learning_rate": 0.00012,
+      "loss": 0.7778,
+      "step": 6
+    },
+    {
+      "epoch": 0.001014584654407102,
+      "eval_loss": 0.720082700252533,
+      "eval_runtime": 75.8775,
+      "eval_samples_per_second": 32.816,
+      "eval_steps_per_second": 16.408,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 51196944187392.0,
+  "total_flos": 102393888374784.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null