Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4755120f810c742abecfb012865a2063adf6399f8f08c3ea827aea96457b71a7
+oid sha256:c32514e354b6d09fc79c674ee149cb36139ff7a0e4f49d81c13e17f27c9064d4
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50034867d33500fcbca5f263e64df4948cb0350e33b3094632dfba4eacd405fe
-size 2216
+oid sha256:5f35a23aa1a9990cc0a4971e7208c8803b940a85e13943c3d4bc8a4af22290b9
+size 168037178

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a60def06e8d16b47623b67a4aae8194c19582b3e85d8800ca2e3bc17092d1bb5
+oid sha256:ce8441b6f44f4e2fa1d2c030527340ac0218aae059aebad5b78181cb84cf26fe
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbbfd43de7fb2acc21f9de1871048cc58018d000e5907250651f158a613d62d3
+oid sha256:dc75c68691d11d10bcc57bd372463d3e0df9a0caca3bec2a2287a78f782bdcb7
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:219c62af0a99d0a3db4c57e4189ef3b142499e30571ad5cc800b8b67c9ce1583
+oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0017964071856287425,
+  "epoch": 0.003592814371257485,
   "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": 14.68,
       "eval_steps_per_second": 7.34,
       "step": 3
+    },
+    {
+      "epoch": 0.0023952095808383233,
+      "grad_norm": 9.167847633361816,
+      "learning_rate": 2e-05,
+      "loss": 11.4872,
+      "step": 4
+    },
+    {
+      "epoch": 0.0029940119760479044,
+      "grad_norm": 6.535604953765869,
+      "learning_rate": 4e-05,
+      "loss": 9.9558,
+      "step": 5
+    },
+    {
+      "epoch": 0.003592814371257485,
+      "grad_norm": 8.272323608398438,
+      "learning_rate": 6e-05,
+      "loss": 11.9577,
+      "step": 6
+    },
+    {
+      "epoch": 0.003592814371257485,
+      "eval_loss": 11.506834983825684,
+      "eval_runtime": 47.6191,
+      "eval_samples_per_second": 14.784,
+      "eval_steps_per_second": 7.392,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1109738548887552.0,
+  "total_flos": 2219477097775104.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null