Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d65b14ed36fe73406b9901f5675803ce359f0e8d04ee4bad34fa90ad92a8fd9
+oid sha256:49966ce8edde3ed93d28ee1ebca2349cb4c21e8143ecf758f6d49e35956361e4
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9de58c98e1b334c95481290a5158025e82a4b2e2ecb810895a4ff4ff5718ab00
+oid sha256:66e82ff93a3b5f4c0b7fcca7759cf25419dac506278ab1f1f86d13bc262cd0b2
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f005639ce0865eae9775065c9fed38932da15f22f9e96d8e1fc81a298bdf6ae
+oid sha256:88471f2b3b1e4c205d9505ad6de006cb23590a0562a633e21bbcb4ef69f0d7ee
 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": 0.0002771618625277162,
+  "epoch": 0.0005543237250554324,
   "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": 23.69,
       "eval_steps_per_second": 11.845,
       "step": 3
+    },
+    {
+      "epoch": 0.0003695491500369549,
+      "grad_norm": 1.3642616271972656,
+      "learning_rate": 8e-05,
+      "loss": 2.4042,
+      "step": 4
+    },
+    {
+      "epoch": 0.00046193643754619364,
+      "grad_norm": 2.06803822517395,
+      "learning_rate": 0.0001,
+      "loss": 2.9043,
+      "step": 5
+    },
+    {
+      "epoch": 0.0005543237250554324,
+      "grad_norm": 2.2044570446014404,
+      "learning_rate": 0.00012,
+      "loss": 2.7562,
+      "step": 6
+    },
+    {
+      "epoch": 0.0005543237250554324,
+      "eval_loss": 2.5870378017425537,
+      "eval_runtime": 192.5166,
+      "eval_samples_per_second": 23.676,
+      "eval_steps_per_second": 11.838,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 786064805462016.0,
+  "total_flos": 1664607823331328.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null