Training in progress, step 600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eeb743d2fa9bf331d379631b7ef0b8c68e7774e97a71b38840d8975b5d99fc4a
+oid sha256:a94fac9e323c5fbebfe886066a1743f12550b20b593b0fca7b99a7ea370dd990
 size 119597408

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e07fbe7b1b0f4cd92cbd073a4e31b6a5e3a92d3e33cecc19de5d91d7616d06d3
+oid sha256:512cf826ff85e68fffbcaa4e5178926ef6fafa0892b557e9f00ceaa6914d5726
 size 60387220

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d9b92fa45e44153a07435b55d5d3d71bf302bfd9a3b3f027d29977fda525192
+oid sha256:01d248dd4a61bc85f685999c311d599535fb345e57d98e4ccefd0735e695f9bd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efef9367937c87bc0bc848b4e2adc863b119783b8c6fd51e9157e257a682f5a9
+oid sha256:92364bde4f303f913bfd963d4c88c3c3a056f83b75924575f2b397f85dd5b7b0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03374440149702436,
+  "epoch": 0.03681207436039021,
   "eval_steps": 20,
-  "global_step": 550,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -412,6 +412,51 @@
       "eval_samples_per_second": 5.069,
       "eval_steps_per_second": 0.659,
       "step": 540
+    },
+    {
+      "epoch": 0.034357936069697524,
+      "grad_norm": 0.623745322227478,
+      "learning_rate": 0.00019772968992882274,
+      "loss": 1.5216,
+      "step": 560
+    },
+    {
+      "epoch": 0.034357936069697524,
+      "eval_loss": 1.3708571195602417,
+      "eval_runtime": 19.6215,
+      "eval_samples_per_second": 5.096,
+      "eval_steps_per_second": 0.663,
+      "step": 560
+    },
+    {
+      "epoch": 0.03558500521504387,
+      "grad_norm": 0.7613083124160767,
+      "learning_rate": 0.0001976478769532848,
+      "loss": 1.4677,
+      "step": 580
+    },
+    {
+      "epoch": 0.03558500521504387,
+      "eval_loss": 1.3612563610076904,
+      "eval_runtime": 19.7315,
+      "eval_samples_per_second": 5.068,
+      "eval_steps_per_second": 0.659,
+      "step": 580
+    },
+    {
+      "epoch": 0.03681207436039021,
+      "grad_norm": 0.6662244200706482,
+      "learning_rate": 0.00019756606397774689,
+      "loss": 1.4336,
+      "step": 600
+    },
+    {
+      "epoch": 0.03681207436039021,
+      "eval_loss": 1.3519067764282227,
+      "eval_runtime": 19.6923,
+      "eval_samples_per_second": 5.078,
+      "eval_steps_per_second": 0.66,
+      "step": 600
     }
   ],
   "logging_steps": 20,
@@ -419,7 +464,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 50,
-  "total_flos": 3.5324564332032e+16,
+  "total_flos": 3.892256129028096e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null