Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c233f1c620c09bf19f826d1fa61facea592ff868c11502b37369601e02f8356
+oid sha256:dd6c993784037b3e75ce16102432c9ac7e63e2fe229aa51e5621e5e63b850751
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d552aa8a592378110f79c37c3fed8a2f487ef00c846e2d86597ff438816332e7
+oid sha256:d95d631398d4018e8b7334d8571b3d4fe4d26248811a5e9b12c0fe9092fdd789
 size 168149074

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a3b96852ea2a689adf8f1cc86874c6e93a130324b13ae84494c715e8376b0b4
+oid sha256:0e3b6581f6b33326bbcd8b468d20a59b8114d7b1b656c310a34922fb317e9432
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d605401690d7669ff16aeaca6820cbd8d0d605afe748c51045ce90888810a22
+oid sha256:040b95482c646935022d148ebc91f462fbf2195cfa3365adbbe3bd6ca1f35a74
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08762322015334063,
+  "epoch": 0.10952902519167579,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,49 @@
       "eval_samples_per_second": 9.406,
       "eval_steps_per_second": 4.752,
       "step": 20
+    },
+    {
+      "epoch": 0.09200438116100766,
+      "grad_norm": 0.1209622249007225,
+      "learning_rate": 0.00016494480483301836,
+      "loss": 0.0109,
+      "step": 21
+    },
+    {
+      "epoch": 0.0963855421686747,
+      "grad_norm": 0.04279917851090431,
+      "learning_rate": 0.00015877852522924732,
+      "loss": 0.0042,
+      "step": 22
+    },
+    {
+      "epoch": 0.10076670317634173,
+      "grad_norm": 0.11789191514253616,
+      "learning_rate": 0.0001522498564715949,
+      "loss": 0.0147,
+      "step": 23
+    },
+    {
+      "epoch": 0.10514786418400876,
+      "grad_norm": 0.28664666414260864,
+      "learning_rate": 0.00014539904997395468,
+      "loss": 0.0328,
+      "step": 24
+    },
+    {
+      "epoch": 0.10952902519167579,
+      "grad_norm": 0.10409914702177048,
+      "learning_rate": 0.000138268343236509,
+      "loss": 0.0087,
+      "step": 25
+    },
+    {
+      "epoch": 0.10952902519167579,
+      "eval_loss": 0.0160684771835804,
+      "eval_runtime": 10.3064,
+      "eval_samples_per_second": 9.412,
+      "eval_steps_per_second": 4.754,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -206,7 +249,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.479651398516736e+16,
+  "total_flos": 1.84956424814592e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null