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:e21c051855834de24b7d05dca96044278fdd4117d6488171f499db891b12bef1
+oid sha256:66b162df84f3f0a324fece7539f70e8909c555ee174b6ef0b86796b0e5d060e6
 size 767856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b07965d457c2e6f69df56ae59a38e3ea73a9215a88e1e6ea1ce4f14b3dd1e51d
+oid sha256:fd2031a3819e2f50b95eb05436690c69cfd5245b1b7adac6fe61f0aab1073c3c
 size 1003002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c99d856f4b0fd798f0682438819be33ce60061bf9a2f48fb0c01c526e16fde06
+oid sha256:8285489f68000ec4600333ccee281bca8dd48450423899eaa09a26dab85569a3
 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": 1.2491074086642253e-05,
+  "epoch": 2.4982148173284507e-05,
   "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": 60.834,
       "eval_steps_per_second": 30.417,
       "step": 3
+    },
+    {
+      "epoch": 1.6654765448856338e-05,
+      "grad_norm": 3.113203525543213,
+      "learning_rate": 8e-05,
+      "loss": 10.4829,
+      "step": 4
+    },
+    {
+      "epoch": 2.0818456811070422e-05,
+      "grad_norm": 4.432548999786377,
+      "learning_rate": 0.0001,
+      "loss": 9.137,
+      "step": 5
+    },
+    {
+      "epoch": 2.4982148173284507e-05,
+      "grad_norm": 3.4199392795562744,
+      "learning_rate": 0.00012,
+      "loss": 10.2811,
+      "step": 6
+    },
+    {
+      "epoch": 2.4982148173284507e-05,
+      "eval_loss": 10.47288990020752,
+      "eval_runtime": 1677.5588,
+      "eval_samples_per_second": 60.281,
+      "eval_steps_per_second": 30.141,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1628971204608.0,
+  "total_flos": 3257942409216.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null