Training in progress, step 7500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3afee2b89c55d138018b573e9a914e6a07453c7de2e6deccf508c92105811902
+oid sha256:b57bafe229ddc9d396d70b73c5d3f1551beb944434118874bbd2db99ccfa0758
 size 4785762744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15bb57db9f3fbc5a6c418e8722464684cda94ed4f1003b4b9db8675541297f5d
+oid sha256:d4815fbb30c93a76d04b86b348cb01ba704d445bd57e754c90d9516cc171859c
 size 3497859804

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acc2d65074a2fcc8399dba6d3c0a62d0568496e8b5831e17319a7dcd95d56dc4
+oid sha256:56ada7a9076e894e38e63b2e547d8bfe564d09412403a53a9fd4f37e79358b8d
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc6c5d761a120c0c95ac7582051fc67375b77e8e7cc8898f714b41f2b1ba2779
+oid sha256:cd9a25d06c35d5d5739e33f68c959f00eb5b9e3a183683d69b110de9c2694ca6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.833515881708653,
+  "epoch": 4.1073384446878425,
   "eval_steps": 500,
-  "global_step": 7000,
+  "global_step": 7500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -497,6 +497,41 @@
       "learning_rate": 1.5683283458260718e-05,
       "loss": 0.2968,
       "step": 7000
+    },
+    {
+      "epoch": 3.888280394304491,
+      "grad_norm": 1.968000054359436,
+      "learning_rate": 1.4318389436742962e-05,
+      "loss": 0.2907,
+      "step": 7100
+    },
+    {
+      "epoch": 3.9430449069003286,
+      "grad_norm": 1.5500705242156982,
+      "learning_rate": 1.3005646664605165e-05,
+      "loss": 0.2922,
+      "step": 7200
+    },
+    {
+      "epoch": 3.9978094194961664,
+      "grad_norm": 1.7522929906845093,
+      "learning_rate": 1.1746973810164147e-05,
+      "loss": 0.2815,
+      "step": 7300
+    },
+    {
+      "epoch": 4.052573932092004,
+      "grad_norm": 0.8427908420562744,
+      "learning_rate": 1.0544210514649233e-05,
+      "loss": 0.1758,
+      "step": 7400
+    },
+    {
+      "epoch": 4.1073384446878425,
+      "grad_norm": 0.8239675760269165,
+      "learning_rate": 9.399114703433688e-06,
+      "loss": 0.17,
+      "step": 7500
     }
   ],
   "logging_steps": 100,
@@ -516,7 +551,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.3642526441134e+18,
+  "total_flos": 3.605124734318199e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null