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:c12ed770612486badba77b2ad00cf7ccddf0bd2e243e848432314448eca57035
+oid sha256:3ae52d7903c68e8a521585733e9937d74f1d0cd6fecfb6489f24ecfeef62824e
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4dd57f0105641466ad7829228c158440d79faea013e4377f11c67a5e6fae672
+oid sha256:b57abab64de78b6794cfdd556cc89b3c6cf7f150803fe25a3be9e4747d33274e
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:631dfb2aa9ae256eca5748a1b2ab04547dfc14e5e8346db748407ed5d049499d
+oid sha256:a68cd2a0196a6713af61a6a5ec57d388549ceab000d778970629ba70bc0f12ea
 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": 0.0008338544923910778,
+  "epoch": 0.0016677089847821555,
   "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": 32.18,
       "eval_steps_per_second": 16.1,
       "step": 3
+    },
+    {
+      "epoch": 0.0011118059898547704,
+      "grad_norm": 1.9711511135101318,
+      "learning_rate": 8e-05,
+      "loss": 3.4461,
+      "step": 4
+    },
+    {
+      "epoch": 0.0013897574873184629,
+      "grad_norm": 2.1288695335388184,
+      "learning_rate": 0.0001,
+      "loss": 4.0495,
+      "step": 5
+    },
+    {
+      "epoch": 0.0016677089847821555,
+      "grad_norm": 2.4953269958496094,
+      "learning_rate": 0.00012,
+      "loss": 3.8412,
+      "step": 6
+    },
+    {
+      "epoch": 0.0016677089847821555,
+      "eval_loss": 3.8704497814178467,
+      "eval_runtime": 47.1276,
+      "eval_samples_per_second": 32.147,
+      "eval_steps_per_second": 16.084,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 554869274443776.0,
+  "total_flos": 1109738548887552.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null