Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:518ef7c37a4492099b3b80f966b40b0fb2eab5bfcadf480c300ce889fc26f0ee
+oid sha256:c8f8a91182ccbda1fbc34a229d14cc255e09c50c5f046bc608de063ba2946e2d
 size 104902272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:410a81b2543437f266a92cb3f17e67a6d06a2192f1e034bd0737bcfd995ff14d
+oid sha256:19ee534d0019fb169a9e43d76044417ca12e89420e4493e1e0f8b3d29be76cb6
 size 53622996

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca3c0186b3a13958bb603ba3c5cd1a680924c7f463ca3b8c4723827c05c83c3f
+oid sha256:74f2e0e81975bb9790d426cf1e81631aed9cf6bad42c0428d645bae0c8dcc89d
 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": 0.003006012024048096,
+  "epoch": 0.006012024048096192,
   "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": 13.618,
       "eval_steps_per_second": 6.825,
       "step": 3
+    },
+    {
+      "epoch": 0.004008016032064128,
+      "grad_norm": 0.3600659966468811,
+      "learning_rate": 8e-05,
+      "loss": 4.7573,
+      "step": 4
+    },
+    {
+      "epoch": 0.00501002004008016,
+      "grad_norm": 0.43822160363197327,
+      "learning_rate": 0.0001,
+      "loss": 4.6953,
+      "step": 5
+    },
+    {
+      "epoch": 0.006012024048096192,
+      "grad_norm": 0.5357103943824768,
+      "learning_rate": 0.00012,
+      "loss": 4.6973,
+      "step": 6
+    },
+    {
+      "epoch": 0.006012024048096192,
+      "eval_loss": 1.2071658372879028,
+      "eval_runtime": 31.0044,
+      "eval_samples_per_second": 13.579,
+      "eval_steps_per_second": 6.805,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1882395078819840.0,
+  "total_flos": 3764790157639680.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null