Training in progress, step 27, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a3543f4e5bd078beba570d5745a45a246a1e951429b417e8359cf2821362796
+oid sha256:82b6c062750989e13cc6c31f673eb28ae7f34054528935e3efb54a06b33e193f
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7755f2da965022367da7226127267c47838725c2b28082989bc01d3528bff76b
+oid sha256:0d6b498b711ec5f0e8abf6d80fe36e5c89263ba6a857852931649201f8325b09
 size 1342555602

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bac162d0d465793ae018f840b2d4ec5d89408f3aa97a4569adf5e87ec7ffc48
+oid sha256:09a2b4355f0adc64fc321dace50424cb5a3dd3e04ef257930c533b857151ab4c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4b679dfcad285902b67d18379c2cc1ca0aebfc7646cb33fa82a3fb8ed15c820
+oid sha256:f1f9e237c4e244cd6a21b3069d52ab1ce3e784c965dcb77abb8266616185916c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.15254237288135594,
+  "epoch": 0.2288135593220339,
   "eval_steps": 9,
-  "global_step": 18,
+  "global_step": 27,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,28 @@
       "eval_samples_per_second": 18.902,
       "eval_steps_per_second": 2.385,
       "step": 18
+    },
+    {
+      "epoch": 0.1694915254237288,
+      "grad_norm": 0.8838627338409424,
+      "learning_rate": 0.00015,
+      "loss": 0.9562,
+      "step": 20
+    },
+    {
+      "epoch": 0.211864406779661,
+      "grad_norm": 0.6448015570640564,
+      "learning_rate": 0.00014855889603024227,
+      "loss": 0.884,
+      "step": 25
+    },
+    {
+      "epoch": 0.2288135593220339,
+      "eval_loss": 0.9067414999008179,
+      "eval_runtime": 22.2329,
+      "eval_samples_per_second": 18.891,
+      "eval_steps_per_second": 2.384,
+      "step": 27
     }
   ],
   "logging_steps": 5,
@@ -71,7 +93,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.7907501206798336e+16,
+  "total_flos": 4.18612518101975e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null