Training in progress, step 95, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c33b6f41ff4ceb62efc4638d195dfc5b077d4e62d14f715b777185cfd64bb8a
+oid sha256:61aece05d6fca5a9a455223f54d11788fb69baa3a1bb939dcd1217cf74f42a8c
 size 59827904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdea95794d41522f6b051e8432670ba48b0134b62bcbf42c14086457fcc86d03
+oid sha256:595168fc88acc93538dac96ad7075991c7f5e24a1f60aa1e44636d2f2ebc40fe
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d7e9b37fba6634a583fc8b1bf58a4648f316317630483e214e684618a5aa0cb
+oid sha256:14a47bb6c7de5708f6f2b75126905ee2455abe93376f11950e796f2aa144c3bf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfdc0543e9ce40f0d0b0ee9752d10d130598c759cc5a2bd973736f6096894d17
+oid sha256:3160dd3097641f3bf4d4036c0ddfd8673184925120f088b5ebecc6a1e5c953dd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04401247019988997,
+  "epoch": 0.04645760743321719,
   "eval_steps": 34,
-  "global_step": 90,
+  "global_step": 95,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -661,6 +661,41 @@
       "learning_rate": 0.00014457383557765386,
       "loss": 9.7034,
       "step": 90
+    },
+    {
+      "epoch": 0.044501497646555414,
+      "grad_norm": 1.0282610752728596e+19,
+      "learning_rate": 0.0001429120608772609,
+      "loss": 9.0363,
+      "step": 91
+    },
+    {
+      "epoch": 0.04499052509322086,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00014123563174739037,
+      "loss": 9.3536,
+      "step": 92
+    },
+    {
+      "epoch": 0.0454795525398863,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00013954512068705424,
+      "loss": 10.7834,
+      "step": 93
+    },
+    {
+      "epoch": 0.045968579986551746,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00013784110500423104,
+      "loss": 9.8873,
+      "step": 94
+    },
+    {
+      "epoch": 0.04645760743321719,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00013612416661871533,
+      "loss": 8.2064,
+      "step": 95
     }
   ],
   "logging_steps": 1,
@@ -680,7 +715,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.9840317083615232e+17,
+  "total_flos": 2.0942556921593856e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null