Training in progress, step 63, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe6d4f42001a866807fabf39f7009f5ed64636eca8752ecce8831a62c918e49d
+oid sha256:fa7c45e2674891e2b68f653b16da5e4dfdb0197d3cfb98a1efac6929e8f572bb
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03669da72977c22ca754bf8ea8c9fbd85fd8b749e54c7aded5c5fa7231419406
+oid sha256:f82887d90453ef2587f1e78ec6b1ef1dd2d711ce1dd8a87fdb07bb2950a5dddf
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c9b98a522023efb72d5ea76453db813b341022ab0b021338e401600719c6645
+oid sha256:1a92831aa364b46aee711e5985b1abd369151fe3337010ec9c2766ed3ad59cf4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f449418676ee143dc49fe68c0605204371c150076b291ef62a6b7b955efd8f73
+oid sha256:03b2d2818ab3151c9ed744a4cb682fe1730b800005846a54cc3da941ac8ce20d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.032258064516129,
+  "epoch": 1.2043010752688172,
   "eval_steps": 9,
-  "global_step": 54,
+  "global_step": 63,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,6 +189,35 @@
       "eval_samples_per_second": 8.961,
       "eval_steps_per_second": 4.506,
       "step": 54
+    },
+    {
+      "epoch": 1.0896057347670252,
+      "grad_norm": 1.0551518201828003,
+      "learning_rate": 0.00011175373974578378,
+      "loss": 1.4021,
+      "step": 57
+    },
+    {
+      "epoch": 1.146953405017921,
+      "grad_norm": 1.3845959901809692,
+      "learning_rate": 0.0001,
+      "loss": 1.3838,
+      "step": 60
+    },
+    {
+      "epoch": 1.2043010752688172,
+      "grad_norm": 1.4633151292800903,
+      "learning_rate": 8.824626025421626e-05,
+      "loss": 1.4003,
+      "step": 63
+    },
+    {
+      "epoch": 1.2043010752688172,
+      "eval_loss": 1.873085856437683,
+      "eval_runtime": 19.7425,
+      "eval_samples_per_second": 8.965,
+      "eval_steps_per_second": 4.508,
+      "step": 63
     }
   ],
   "logging_steps": 3,
@@ -208,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.2227651533511066e+17,
+  "total_flos": 3.759892678909624e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null