Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82b654e51628ff3912882b096c131cef3fdaea4385100e33df765f023a351ba3
+oid sha256:d15c69df656052a8042e2c9eafd81f0bf030b591791944af5128196dfb7b334d
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80c46f702229600b1957feea090b0a822a75cc8e47634d94853cc93e10a7ff85
+oid sha256:f57dae0e4c70c2557518e17bd4c470f1a407fabd157de98687fa5736061dbf27
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ca82a561ff77829be4f53f199829857bccfb693ef73aa2d0668f096c355cee4
+oid sha256:7824cda9b09088755df9c1fad3a0258c249f3861ebeb526074259caef60b1595
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc78163c347c258a17d5fa38a4e22e79b63c35d2cfce0e026e30c38b9ae55f80
+oid sha256:92b4cf85d7ba7a497f88ff799bf4dec5af7dd95be6e00f78bf46ba5deb56bbf8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00027986216788231794,
+  "epoch": 0.0005597243357646359,
   "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": 33.481,
       "eval_steps_per_second": 16.741,
       "step": 3
+    },
+    {
+      "epoch": 0.00037314955717642395,
+      "grad_norm": 2.396655797958374,
+      "learning_rate": 4e-05,
+      "loss": 4.6442,
+      "step": 4
+    },
+    {
+      "epoch": 0.0004664369464705299,
+      "grad_norm": 3.150291681289673,
+      "learning_rate": 5e-05,
+      "loss": 6.5308,
+      "step": 5
+    },
+    {
+      "epoch": 0.0005597243357646359,
+      "grad_norm": 2.6992385387420654,
+      "learning_rate": 6e-05,
+      "loss": 6.1804,
+      "step": 6
+    },
+    {
+      "epoch": 0.0005597243357646359,
+      "eval_loss": 5.969189167022705,
+      "eval_runtime": 539.4806,
+      "eval_samples_per_second": 33.467,
+      "eval_steps_per_second": 16.735,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2918915377201152.0,
+  "total_flos": 5968528457859072.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null