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:df28b50bab512ac645fa68fac1c86ef6662bf365874e22ee25c9d645056ac8f6
+oid sha256:0d63845ff87af5f49412554f7254c155efe08d31e72ebded0c77a008c3b550bf
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:872131ee30e3d9fe3b5a9a292cab1c251d35712d5e85653391ba19926212a4c1
+oid sha256:65d48a55604f6f2bc16a0c134bdb974fade303feeabd6a2e54d41f87ff4d9ce8
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b26e49241d5ac88dbc0f73e1077ee9e1101b4750f840d96d4e5dd2f12625c8b
+oid sha256:92d1c4a5d8ed6435fc8de2ba213ed5167ba25caa45caaa54976f6de932fd5350
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f93031ee92693951f7562964ce0be13246486809776db9a6a80c3650bbacf2b3
+oid sha256:b1356bfcc59da4f00dd18593893d4cbb0ff70ddc212c9ad462e4e728d43cfa7b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8cc2b70f581f63a0afc6a33ed22b923602cb936a6a87f4acd2611a2fd882f80
+oid sha256:02d8700df175605714b8637cebcf2ebccdfb3b8f3a32c3ff4877ed71c7ca0465
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a957aa4a2a763bbe311e785c1e2994b18689037f06db53306ce99c4d783656db
+oid sha256:e7ab071d9c76c98b4b92e6b8b5c1778fc500a77ed244fb8d485009350009d12c
 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": 0.6595218466611706,
+  "epoch": 1.3289365210222588,
   "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": 43.32,
       "eval_steps_per_second": 11.263,
       "step": 25
+    },
+    {
+      "epoch": 0.6859027205276175,
+      "grad_norm": 2.5826122760772705,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.6125,
+      "step": 26
+    },
+    {
+      "epoch": 0.7122835943940643,
+      "grad_norm": 3.505153179168701,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.6932,
+      "step": 27
+    },
+    {
+      "epoch": 0.7386644682605111,
+      "grad_norm": 2.812425136566162,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.6941,
+      "step": 28
+    },
+    {
+      "epoch": 0.765045342126958,
+      "grad_norm": 2.6993019580841064,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.5275,
+      "step": 29
+    },
+    {
+      "epoch": 0.7914262159934048,
+      "grad_norm": 1.6319504976272583,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.1855,
+      "step": 30
+    },
+    {
+      "epoch": 0.8178070898598516,
+      "grad_norm": 1.3986767530441284,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.1984,
+      "step": 31
+    },
+    {
+      "epoch": 0.8441879637262985,
+      "grad_norm": 1.2282105684280396,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.209,
+      "step": 32
+    },
+    {
+      "epoch": 0.8705688375927453,
+      "grad_norm": 0.9565277695655823,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.1846,
+      "step": 33
+    },
+    {
+      "epoch": 0.8969497114591921,
+      "grad_norm": 1.4811856746673584,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.2668,
+      "step": 34
+    },
+    {
+      "epoch": 0.9233305853256389,
+      "grad_norm": 1.6929315328598022,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.3288,
+      "step": 35
+    },
+    {
+      "epoch": 0.9497114591920858,
+      "grad_norm": 2.3932266235351562,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.4036,
+      "step": 36
+    },
+    {
+      "epoch": 0.9760923330585326,
+      "grad_norm": 3.5589423179626465,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.4499,
+      "step": 37
+    },
+    {
+      "epoch": 1.012366034624897,
+      "grad_norm": 2.737474203109741,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.4322,
+      "step": 38
+    },
+    {
+      "epoch": 1.0387469084913439,
+      "grad_norm": 1.1250501871109009,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.1337,
+      "step": 39
+    },
+    {
+      "epoch": 1.0651277823577905,
+      "grad_norm": 0.7960028052330017,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.085,
+      "step": 40
+    },
+    {
+      "epoch": 1.0915086562242373,
+      "grad_norm": 1.7320730686187744,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0977,
+      "step": 41
+    },
+    {
+      "epoch": 1.1178895300906841,
+      "grad_norm": 1.0344929695129395,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.083,
+      "step": 42
+    },
+    {
+      "epoch": 1.144270403957131,
+      "grad_norm": 1.1064660549163818,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.1348,
+      "step": 43
+    },
+    {
+      "epoch": 1.1706512778235778,
+      "grad_norm": 1.4996426105499268,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.1599,
+      "step": 44
+    },
+    {
+      "epoch": 1.1970321516900246,
+      "grad_norm": 1.5553085803985596,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.2289,
+      "step": 45
+    },
+    {
+      "epoch": 1.2234130255564715,
+      "grad_norm": 2.5401673316955566,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.3329,
+      "step": 46
+    },
+    {
+      "epoch": 1.2497938994229183,
+      "grad_norm": 2.7614471912384033,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.2996,
+      "step": 47
+    },
+    {
+      "epoch": 1.2761747732893651,
+      "grad_norm": 2.3601768016815186,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.1815,
+      "step": 48
+    },
+    {
+      "epoch": 1.302555647155812,
+      "grad_norm": 0.7562735080718994,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0601,
+      "step": 49
+    },
+    {
+      "epoch": 1.3289365210222588,
+      "grad_norm": 0.7278848886489868,
+      "learning_rate": 1e-05,
+      "loss": 0.0562,
+      "step": 50
+    },
+    {
+      "epoch": 1.3289365210222588,
+      "eval_loss": 0.14836329221725464,
+      "eval_runtime": 1.1577,
+      "eval_samples_per_second": 43.188,
+      "eval_steps_per_second": 11.229,
+      "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