Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e4f5ccef9c64928842c58941e68d2c9942d85366ca3ffcc3e88a9f8fbf87dac
+oid sha256:9bc9e81363084991114af7e7059f99c25c341905df9fff4c16bbe92da6313109
 size 39256456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfded22273ed6dd7475014d98f12bb30fa7e5113856b7347337bb151dfce2831
+oid sha256:2273e9428947fbb8f752eec0ee6edfca96678774550bc64026373f5462a77a56
 size 20632826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:896ce3df835bc8812a5e1e71a5700a53a32d1137a73fc2ff1348157152fcbe6b
+oid sha256:4f62bf5dc3982cb724ba2d66b6ebf6a8ca8dd5328c3bcb309df49a4d1148029b
 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": 0.0004929548535513289,
+  "epoch": 0.0009859097071026578,
   "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": 13.249,
       "eval_steps_per_second": 6.627,
       "step": 3
+    },
+    {
+      "epoch": 0.0006572731380684385,
+      "grad_norm": 1.109828233718872,
+      "learning_rate": 8e-05,
+      "loss": 1.645,
+      "step": 4
+    },
+    {
+      "epoch": 0.0008215914225855482,
+      "grad_norm": 1.2177774906158447,
+      "learning_rate": 0.0001,
+      "loss": 1.7819,
+      "step": 5
+    },
+    {
+      "epoch": 0.0009859097071026578,
+      "grad_norm": 1.7350780963897705,
+      "learning_rate": 0.00012,
+      "loss": 1.7212,
+      "step": 6
+    },
+    {
+      "epoch": 0.0009859097071026578,
+      "eval_loss": 1.7177189588546753,
+      "eval_runtime": 194.4652,
+      "eval_samples_per_second": 13.18,
+      "eval_steps_per_second": 6.592,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 232501951856640.0,
+  "total_flos": 501714738216960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null