Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57e8dc4e1092fa9772e7a9e5ccbac3870fabd213c8d05dc818e58aaefbc22fb3
+oid sha256:591b15f58df77048c268678e1aad964856d8edf0e4221633a7d3e7c88f36016a
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d4bb1d9b89bfabe09bb0ef2798b5517aebdac4a321322329dae8b4725dba9e4
+oid sha256:e19705360c15e7a15042e9517d40130eb8e2e7766fb7fecb631fb07c703d1582
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff5440c0314dadc3defe4b4803f353543d71edfcba882e67961bec9458fb6240
+oid sha256:9ea24ba22f005ab5531315a7c25fe17ce3b0d82d32e4d057cd4a8d9beeaa0eb4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff2736979009751c0c6b0ddcc5f6544d6f723aa752b4798eab0b70fb76cf0083
+oid sha256:532138a5ca880d8da393ae449e5715b2766def36b8838785ca08d07228b119b7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02738475581926061,
+  "epoch": 0.03651300775901415,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 40.864,
       "eval_steps_per_second": 20.454,
       "step": 15
+    },
+    {
+      "epoch": 0.02921040620721132,
+      "grad_norm": 3.7022249698638916,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 2.1359,
+      "step": 16
+    },
+    {
+      "epoch": 0.031036056595162027,
+      "grad_norm": 4.289546966552734,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.943,
+      "step": 17
+    },
+    {
+      "epoch": 0.032861706983112735,
+      "grad_norm": 3.9869320392608643,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.2934,
+      "step": 18
+    },
+    {
+      "epoch": 0.03468735737106344,
+      "grad_norm": 3.7422683238983154,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.9922,
+      "step": 19
+    },
+    {
+      "epoch": 0.03651300775901415,
+      "grad_norm": 3.6595163345336914,
+      "learning_rate": 0.0,
+      "loss": 1.9538,
+      "step": 20
+    },
+    {
+      "epoch": 0.03651300775901415,
+      "eval_loss": 2.249903440475464,
+      "eval_runtime": 25.2417,
+      "eval_samples_per_second": 36.566,
+      "eval_steps_per_second": 18.303,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.109738548887552e+16,
+  "total_flos": 1.479651398516736e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null