Training in progress, step 32, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12643d73306d913bb59b9fef8ebce83ff830057d2ff5d47969f3e4d61fdebd0c
+oid sha256:20c8eb8325ee56887bcac39c7154198c4c29da0906f5c3ea537f9c33b12522a7
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e3f5b4eec3e66d80a2fd8c3c6b19d5807558d664d02d881def3beb6b46979ab
+oid sha256:c50dbc656fd8436361ad2967fe1a74152d58ec2100319552b81b9e758a442b69
 size 400361770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5c166beb56023c475d0a1e4488772a1479f599ca29e77e7106a93caafb4ed00
+oid sha256:fd7a7ac14760662453a208d3a2065875c8aad63732e589bcd3c513e8d0acfc26
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff994fffd2fb6fe21545e6fbc55baa2a1474438a89b2d40605678f7de701427c
+oid sha256:06c69db2db6de56f38ba12b474a491d20087e27dc2893a95d6ac7716476ca645
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007537519348542971,
+  "epoch": 0.008614307826906252,
   "eval_steps": 4,
-  "global_step": 28,
+  "global_step": 32,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -267,6 +267,42 @@
       "eval_samples_per_second": 8.363,
       "eval_steps_per_second": 4.184,
       "step": 28
+    },
+    {
+      "epoch": 0.007806716468133791,
+      "grad_norm": 2.46905255317688,
+      "learning_rate": 0.0001078459095727845,
+      "loss": 4.1957,
+      "step": 29
+    },
+    {
+      "epoch": 0.00807591358772461,
+      "grad_norm": 2.6972992420196533,
+      "learning_rate": 0.0001,
+      "loss": 3.7234,
+      "step": 30
+    },
+    {
+      "epoch": 0.008345110707315431,
+      "grad_norm": 2.946199655532837,
+      "learning_rate": 9.215409042721552e-05,
+      "loss": 3.8905,
+      "step": 31
+    },
+    {
+      "epoch": 0.008614307826906252,
+      "grad_norm": 2.631840944290161,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 3.8763,
+      "step": 32
+    },
+    {
+      "epoch": 0.008614307826906252,
+      "eval_loss": 3.9116568565368652,
+      "eval_runtime": 187.6034,
+      "eval_samples_per_second": 8.342,
+      "eval_steps_per_second": 4.174,
+      "step": 32
     }
   ],
   "logging_steps": 1,
@@ -286,7 +322,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.147304212319437e+16,
+  "total_flos": 2.454061956936499e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null