Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e799224752b3dd521da98ef1a84eaa0eaf940cc5cebaf33d2064ebb7676681e
+oid sha256:19f3174feb372e0955d626bb8412d3f6f1087495ba985fcd5ff4df185c8bf461
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2865353aa8a59d16e061d20dceb742305497bf5eee86b3a1b97663e081c0efea
+oid sha256:9a35bb5162a07a8f2a678c11f289d341c5471bf578afd2fe46486e14852da2fd
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22a1b4fdd495985211dd600fcf7ec126057fcfa3033eee8cb48b64ba7475ce56
+oid sha256:9638bec4701ac209c7c25e3d20cbf5f45d8c700adb7f530190b33c30aaaaf3e9
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:370575635a1937a6dd994b07f8bd1e0dd852bb48f4512ebcc3923622c0e23043
+oid sha256:53a1f5368d68cf38bef371fc6ce80586987eb616a12e780461f29b978c3e4c5b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2fb5b17232b589d84ed3701e54d0808dce9297df7887cfcf7e7f4d90486cd03
+oid sha256:37ac7a64b7295554bb75b5ea37922360045c5248d2bf45c7d94ef425101fcfbc
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43712021e1414ca96338688c1b72edcc6147974df0b0636aa1aff4cc3a178a9b
+oid sha256:f22f9820cac8ef585e98a4f900badea7a6255a64eba3ec22da17a8cec74c6875
 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": 14.254,
       "eval_steps_per_second": 3.706,
       "step": 25
+    },
+    {
+      "epoch": 0.6859027205276175,
+      "grad_norm": 1.9853585958480835,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.2773,
+      "step": 26
+    },
+    {
+      "epoch": 0.7122835943940643,
+      "grad_norm": 1.9127581119537354,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.3066,
+      "step": 27
+    },
+    {
+      "epoch": 0.7386644682605111,
+      "grad_norm": 4.7101006507873535,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.4072,
+      "step": 28
+    },
+    {
+      "epoch": 0.765045342126958,
+      "grad_norm": 3.690385341644287,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.3013,
+      "step": 29
+    },
+    {
+      "epoch": 0.7914262159934048,
+      "grad_norm": 3.118375062942505,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.114,
+      "step": 30
+    },
+    {
+      "epoch": 0.8178070898598516,
+      "grad_norm": 2.6443421840667725,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.122,
+      "step": 31
+    },
+    {
+      "epoch": 0.8441879637262985,
+      "grad_norm": 1.4975119829177856,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.1105,
+      "step": 32
+    },
+    {
+      "epoch": 0.8705688375927453,
+      "grad_norm": 0.9905925989151001,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.0852,
+      "step": 33
+    },
+    {
+      "epoch": 0.8969497114591921,
+      "grad_norm": 2.3505523204803467,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.1168,
+      "step": 34
+    },
+    {
+      "epoch": 0.9233305853256389,
+      "grad_norm": 2.3073883056640625,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.2137,
+      "step": 35
+    },
+    {
+      "epoch": 0.9497114591920858,
+      "grad_norm": 2.3895084857940674,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.2163,
+      "step": 36
+    },
+    {
+      "epoch": 0.9760923330585326,
+      "grad_norm": 4.762124061584473,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.2559,
+      "step": 37
+    },
+    {
+      "epoch": 1.012366034624897,
+      "grad_norm": 2.988582134246826,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.2076,
+      "step": 38
+    },
+    {
+      "epoch": 1.0387469084913439,
+      "grad_norm": 0.7477741837501526,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0188,
+      "step": 39
+    },
+    {
+      "epoch": 1.0651277823577905,
+      "grad_norm": 0.26564833521842957,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0128,
+      "step": 40
+    },
+    {
+      "epoch": 1.0915086562242373,
+      "grad_norm": 0.3311631381511688,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0223,
+      "step": 41
+    },
+    {
+      "epoch": 1.1178895300906841,
+      "grad_norm": 0.9142094850540161,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0305,
+      "step": 42
+    },
+    {
+      "epoch": 1.144270403957131,
+      "grad_norm": 0.563532292842865,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0551,
+      "step": 43
+    },
+    {
+      "epoch": 1.1706512778235778,
+      "grad_norm": 0.9370564818382263,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0832,
+      "step": 44
+    },
+    {
+      "epoch": 1.1970321516900246,
+      "grad_norm": 1.3220709562301636,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.1321,
+      "step": 45
+    },
+    {
+      "epoch": 1.2234130255564715,
+      "grad_norm": 1.9462977647781372,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.1918,
+      "step": 46
+    },
+    {
+      "epoch": 1.2497938994229183,
+      "grad_norm": 1.4210519790649414,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.1166,
+      "step": 47
+    },
+    {
+      "epoch": 1.2761747732893651,
+      "grad_norm": 0.5465534329414368,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0366,
+      "step": 48
+    },
+    {
+      "epoch": 1.302555647155812,
+      "grad_norm": 0.24715368449687958,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0054,
+      "step": 49
+    },
+    {
+      "epoch": 1.3289365210222588,
+      "grad_norm": 0.39115121960639954,
+      "learning_rate": 1e-05,
+      "loss": 0.0234,
+      "step": 50
+    },
+    {
+      "epoch": 1.3289365210222588,
+      "eval_loss": 0.07087846100330353,
+      "eval_runtime": 3.4904,
+      "eval_samples_per_second": 14.325,
+      "eval_steps_per_second": 3.724,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null