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:b23dea81b05d1e14ed8656fe853769f174f36b96783682fd64aee65fb2077b30
+oid sha256:db37ce5e679bd52fa7bd7bb5e96998e8d29003f10bdd3e4b831200ed8bbbfc76
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f084e1a9628dad4748afbba239e939549080032b5cc1d0b5dcbc6ebbce6487ac
+oid sha256:e7e0a174c8d512bc4b27aeaa3957718d8b1a6bc1411f385564dd3f2887e91085
 size 160172858

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e2355e43fd44f1d9860c59f45b4d1039afaad0a42f79d076c0667863cd27cb0
+oid sha256:73aa535a34327d8ff7e12fc9f716f24d876cbdb9f9fc9bc13d972c1b7c68dd32
 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": 0.008421052631578947,
+  "epoch": 0.016842105263157894,
   "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": 15.142,
       "eval_steps_per_second": 15.142,
       "step": 3
+    },
+    {
+      "epoch": 0.011228070175438596,
+      "grad_norm": 0.38444051146507263,
+      "learning_rate": 8e-05,
+      "loss": 2.2965,
+      "step": 4
+    },
+    {
+      "epoch": 0.014035087719298246,
+      "grad_norm": 0.3640546500682831,
+      "learning_rate": 0.0001,
+      "loss": 2.2651,
+      "step": 5
+    },
+    {
+      "epoch": 0.016842105263157894,
+      "grad_norm": 0.4015711545944214,
+      "learning_rate": 0.00012,
+      "loss": 2.3536,
+      "step": 6
+    },
+    {
+      "epoch": 0.016842105263157894,
+      "eval_loss": 2.4016966819763184,
+      "eval_runtime": 5.1087,
+      "eval_samples_per_second": 14.681,
+      "eval_steps_per_second": 14.681,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 488619940773888.0,
+  "total_flos": 977239881547776.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null