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:ce24ef32980cb4a38e8ac9601175c211099b29d66040b199df1094baff32510f
+oid sha256:20aac304651b8077bd6f3d9063e810e85ca76022a78767a8b38cd39b92dce334
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dbc86d7fa1cd493fa9cd1fe03e7ce25df1032d43792ff97d49e9ca9c47a2fe5
+oid sha256:a0d04e2ce99dbe8d3d5f80004c74e70cd70c36d92c2389d0b082d385514d29ff
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5d7469bd8aa572b96a0bfe01d90717f4c785e8c4ce052fd1284233323b23176
+oid sha256:219cf31c0ed4058e09118b697ea7c842593a90f68e124ae6c57f70869ce8a065
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:841d566e1e32ab0815564250445c16c855e73ed3c3d007165979c78aae8c2f3f
+oid sha256:4223eb10d4f39330da65b0b0ad14b792d34183250eea4b5b28497e99831b925d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:324f07eeeff2ac8541f487dd67e3e97ecfd491adb9dda056be00d4eea9ce9a3d
+oid sha256:fdbee771b755aa09589fc8f0eb3995d811d09f983a090eee151a4b069a72713b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b74937e2ea9cbc03a86961eac4611abc815085f5ddeaf82b618fad3351905ea5
+oid sha256:e7a709e8615ae19440aaf1cda29a9f7ba2cf72c8e4cb1aabac13a75bba9f8bf9
 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": 0.6028636021100227,
+  "epoch": 1.2057272042200453,
   "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": 43.57,
       "eval_steps_per_second": 11.328,
       "step": 25
+    },
+    {
+      "epoch": 0.6269781461944235,
+      "grad_norm": 1.8943963050842285,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.7098,
+      "step": 26
+    },
+    {
+      "epoch": 0.6510926902788244,
+      "grad_norm": 1.3358711004257202,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.6979,
+      "step": 27
+    },
+    {
+      "epoch": 0.6752072343632253,
+      "grad_norm": 1.7418076992034912,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.718,
+      "step": 28
+    },
+    {
+      "epoch": 0.6993217784476262,
+      "grad_norm": 2.2980732917785645,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.7217,
+      "step": 29
+    },
+    {
+      "epoch": 0.7234363225320272,
+      "grad_norm": 2.3880324363708496,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.7251,
+      "step": 30
+    },
+    {
+      "epoch": 0.747550866616428,
+      "grad_norm": 2.4463062286376953,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.7254,
+      "step": 31
+    },
+    {
+      "epoch": 0.771665410700829,
+      "grad_norm": 1.9282697439193726,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.7128,
+      "step": 32
+    },
+    {
+      "epoch": 0.7957799547852299,
+      "grad_norm": 1.4290863275527954,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.6968,
+      "step": 33
+    },
+    {
+      "epoch": 0.8198944988696307,
+      "grad_norm": 1.8006930351257324,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.7076,
+      "step": 34
+    },
+    {
+      "epoch": 0.8440090429540317,
+      "grad_norm": 1.0373167991638184,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.7026,
+      "step": 35
+    },
+    {
+      "epoch": 0.8681235870384325,
+      "grad_norm": 0.7661415338516235,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.6926,
+      "step": 36
+    },
+    {
+      "epoch": 0.8922381311228335,
+      "grad_norm": 1.2040423154830933,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.701,
+      "step": 37
+    },
+    {
+      "epoch": 0.9163526752072344,
+      "grad_norm": 0.8971741199493408,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.7018,
+      "step": 38
+    },
+    {
+      "epoch": 0.9404672192916352,
+      "grad_norm": 0.7175334692001343,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.7001,
+      "step": 39
+    },
+    {
+      "epoch": 0.9645817633760362,
+      "grad_norm": 0.8451390862464905,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.6945,
+      "step": 40
+    },
+    {
+      "epoch": 0.9886963074604371,
+      "grad_norm": 1.954053282737732,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.7059,
+      "step": 41
+    },
+    {
+      "epoch": 1.012810851544838,
+      "grad_norm": 2.4371275901794434,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.076,
+      "step": 42
+    },
+    {
+      "epoch": 1.0369253956292388,
+      "grad_norm": 1.6779913902282715,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.6984,
+      "step": 43
+    },
+    {
+      "epoch": 1.0610399397136399,
+      "grad_norm": 1.369674563407898,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.6834,
+      "step": 44
+    },
+    {
+      "epoch": 1.0851544837980407,
+      "grad_norm": 1.0458629131317139,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.6891,
+      "step": 45
+    },
+    {
+      "epoch": 1.1092690278824415,
+      "grad_norm": 0.7835463285446167,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.6877,
+      "step": 46
+    },
+    {
+      "epoch": 1.1333835719668426,
+      "grad_norm": 1.0629692077636719,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.6778,
+      "step": 47
+    },
+    {
+      "epoch": 1.1574981160512434,
+      "grad_norm": 0.4367343485355377,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.6783,
+      "step": 48
+    },
+    {
+      "epoch": 1.1816126601356443,
+      "grad_norm": 0.9655264616012573,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.676,
+      "step": 49
+    },
+    {
+      "epoch": 1.2057272042200453,
+      "grad_norm": 0.7904195785522461,
+      "learning_rate": 1e-05,
+      "loss": 0.6994,
+      "step": 50
+    },
+    {
+      "epoch": 1.2057272042200453,
+      "eval_loss": 0.7077999711036682,
+      "eval_runtime": 1.1629,
+      "eval_samples_per_second": 42.995,
+      "eval_steps_per_second": 11.179,
+      "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": 5.29768176943104e+16,
+  "total_flos": 1.059536353886208e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null