Training in progress, step 650, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d08b6d9b3a9d15d25aadb2cb24debe2d7cdca1e55bd48ea3702a43a94a2581af
+oid sha256:a3668fa34724afb7451663beb5c2888ddcb2b7ecddb13ed07d944025c27d8d3b
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b95e8afeb39ff0d445ff047308657bd1c41dd23bbe6bc9ee6297f75a79be822b
+oid sha256:03eb30e093c78829d55e5b35712320efbf2416ee2737745a276186c084bbdecb
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4171439eadb13b2843ff5c47858b0150e7075e96e555aee2539438f15e25168
+oid sha256:9f89037ac2abeb6171c1ce95a77a94c808e277b9f70abf8b11f093a79735219d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea258fcfaa803fc3574884ee61cef84bd44233621e9e6a5cc1b7b02d59d4cca3
+oid sha256:f40d91018758ada40c1cb9514ff9b9e8ed129fd32f51a6eaa9ac898e033c2d44
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8346813329019734,
+  "epoch": 0.8411517308314461,
   "eval_steps": 386,
-  "global_step": 645,
+  "global_step": 650,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4538,6 +4538,41 @@
       "learning_rate": 9.410213514796564e-05,
       "loss": 0.8242,
       "step": 645
+    },
+    {
+      "epoch": 0.835975412487868,
+      "grad_norm": 0.8321415185928345,
+      "learning_rate": 9.408269466472864e-05,
+      "loss": 0.9094,
+      "step": 646
+    },
+    {
+      "epoch": 0.8372694920737626,
+      "grad_norm": 0.7805325984954834,
+      "learning_rate": 9.406322420934123e-05,
+      "loss": 0.837,
+      "step": 647
+    },
+    {
+      "epoch": 0.8385635716596571,
+      "grad_norm": 0.8147938251495361,
+      "learning_rate": 9.404372379504151e-05,
+      "loss": 0.9177,
+      "step": 648
+    },
+    {
+      "epoch": 0.8398576512455516,
+      "grad_norm": 0.7518514394760132,
+      "learning_rate": 9.402419343508797e-05,
+      "loss": 0.7562,
+      "step": 649
+    },
+    {
+      "epoch": 0.8411517308314461,
+      "grad_norm": 0.7858056426048279,
+      "learning_rate": 9.400463314275943e-05,
+      "loss": 0.9865,
+      "step": 650
     }
   ],
   "logging_steps": 1,
@@ -4557,7 +4592,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.210694757423514e+17,
+  "total_flos": 7.266591616008192e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null