Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22135f35813c0e588e00dde7ccd892bf4d72feebc02949f8ce4d790757e9bdb5
+oid sha256:88904c13d6749de54522b001ea3d40d9d8703630ac0a3f23ec34199ae820b686
 size 60599872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d53324317087bac37b6133fac5a4a752bb85f2bc962944f8a8d57ccf21389114
+oid sha256:1953201a421b9d499bdd1b08428af1a2edce8642a81cd66ab62ef1c1b86d384c
 size 121392706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c52de05fe5c8147f447e867613fc60128252d4b53397bb3cf97c5d546e9aee0
+oid sha256:d01bfb733e0148c89bf17b1dca4d00cb4a679f0c9c256e420819765acefceaea
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89958b120aa262622be62a652746c566e144488fddef8d9952ff0046e4d4ecec
+oid sha256:a10999a5ad22ecacdeb4fd9e17ec58338daec959c037dabe6e6d75930d82694b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02f85a447f83024c6b8f99dda5e8429c072e9f97c81c4f3e1760f162a4f086d9
+oid sha256:7de110759ec3b95513052f51650f5a97c49d2978a29830756ed8602e030a1cb4
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:446a914226d7d756238ae8c3c096ca3c93cd6e8913fe6e73cda4d227381563be
+oid sha256:d2a635c09151c0437925edc5fffc3710ccbe5620522af3a625a5410a84b9ba58
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.3621262458471761,
+  "epoch": 2.7242524916943522,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 67.551,
       "eval_steps_per_second": 17.563,
       "step": 25
+    },
+    {
+      "epoch": 1.415282392026578,
+      "grad_norm": 0.7274023294448853,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0638,
+      "step": 26
+    },
+    {
+      "epoch": 1.4684385382059801,
+      "grad_norm": 1.0477628707885742,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.1032,
+      "step": 27
+    },
+    {
+      "epoch": 1.521594684385382,
+      "grad_norm": 1.7702083587646484,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0773,
+      "step": 28
+    },
+    {
+      "epoch": 1.574750830564784,
+      "grad_norm": 0.9557569026947021,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.0616,
+      "step": 29
+    },
+    {
+      "epoch": 1.627906976744186,
+      "grad_norm": 1.0757166147232056,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.1396,
+      "step": 30
+    },
+    {
+      "epoch": 1.6810631229235882,
+      "grad_norm": 0.8739386796951294,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.0655,
+      "step": 31
+    },
+    {
+      "epoch": 1.73421926910299,
+      "grad_norm": 0.9457898736000061,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0842,
+      "step": 32
+    },
+    {
+      "epoch": 1.787375415282392,
+      "grad_norm": 0.5630450248718262,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.0476,
+      "step": 33
+    },
+    {
+      "epoch": 1.8405315614617939,
+      "grad_norm": 0.7644055485725403,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.1071,
+      "step": 34
+    },
+    {
+      "epoch": 1.893687707641196,
+      "grad_norm": 1.1439839601516724,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.1219,
+      "step": 35
+    },
+    {
+      "epoch": 1.946843853820598,
+      "grad_norm": 0.68359375,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.1116,
+      "step": 36
+    },
+    {
+      "epoch": 2.0332225913621262,
+      "grad_norm": 1.7485463619232178,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.1243,
+      "step": 37
+    },
+    {
+      "epoch": 2.086378737541528,
+      "grad_norm": 0.47398442029953003,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.0464,
+      "step": 38
+    },
+    {
+      "epoch": 2.13953488372093,
+      "grad_norm": 0.9993898272514343,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.082,
+      "step": 39
+    },
+    {
+      "epoch": 2.1926910299003324,
+      "grad_norm": 0.46211889386177063,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0404,
+      "step": 40
+    },
+    {
+      "epoch": 2.2458471760797343,
+      "grad_norm": 0.8578104972839355,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.1049,
+      "step": 41
+    },
+    {
+      "epoch": 2.299003322259136,
+      "grad_norm": 0.7607599496841431,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.086,
+      "step": 42
+    },
+    {
+      "epoch": 2.352159468438538,
+      "grad_norm": 0.46289491653442383,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0477,
+      "step": 43
+    },
+    {
+      "epoch": 2.4053156146179404,
+      "grad_norm": 0.8016815185546875,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0811,
+      "step": 44
+    },
+    {
+      "epoch": 2.4584717607973423,
+      "grad_norm": 0.43612438440322876,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0495,
+      "step": 45
+    },
+    {
+      "epoch": 2.511627906976744,
+      "grad_norm": 0.7244629263877869,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0904,
+      "step": 46
+    },
+    {
+      "epoch": 2.564784053156146,
+      "grad_norm": 0.526421844959259,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0517,
+      "step": 47
+    },
+    {
+      "epoch": 2.617940199335548,
+      "grad_norm": 0.7599980235099792,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0553,
+      "step": 48
+    },
+    {
+      "epoch": 2.6710963455149503,
+      "grad_norm": 0.7634601593017578,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0647,
+      "step": 49
+    },
+    {
+      "epoch": 2.7242524916943522,
+      "grad_norm": 0.7769803404808044,
+      "learning_rate": 1e-05,
+      "loss": 0.1012,
+      "step": 50
+    },
+    {
+      "epoch": 2.7242524916943522,
+      "eval_loss": 0.14976823329925537,
+      "eval_runtime": 0.725,
+      "eval_samples_per_second": 68.97,
+      "eval_steps_per_second": 17.932,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,12 +395,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.27222702669824e+16,
+  "total_flos": 2.54445405339648e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null