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:d3e8021aa433b10da6c7a532abb262fc8afd1ea4a3ff82361e5db6b44ded3397
+oid sha256:9b75248e872f03c1488b6a757f0894e5f3d3d00f7332d6ade210dbd3f5683494
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f4f659f3b4f7efd062e5392579ad6ce2f40e39d2150898b35ace46ee7446fcb
+oid sha256:77aa0085bf57cf5725aa9536bbca4a8045b564a543c41d88e622b55bb1545c76
 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": 42.475,
       "eval_steps_per_second": 11.044,
       "step": 25
+    },
+    {
+      "epoch": 0.6269781461944235,
+      "grad_norm": 2.149623155593872,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.7159,
+      "step": 26
+    },
+    {
+      "epoch": 0.6510926902788244,
+      "grad_norm": 1.6069267988204956,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.7016,
+      "step": 27
+    },
+    {
+      "epoch": 0.6752072343632253,
+      "grad_norm": 1.8428833484649658,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.7185,
+      "step": 28
+    },
+    {
+      "epoch": 0.6993217784476262,
+      "grad_norm": 2.2342772483825684,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.7152,
+      "step": 29
+    },
+    {
+      "epoch": 0.7234363225320272,
+      "grad_norm": 2.2674312591552734,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.7215,
+      "step": 30
+    },
+    {
+      "epoch": 0.747550866616428,
+      "grad_norm": 2.4576127529144287,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.7263,
+      "step": 31
+    },
+    {
+      "epoch": 0.771665410700829,
+      "grad_norm": 1.9661893844604492,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.7121,
+      "step": 32
+    },
+    {
+      "epoch": 0.7957799547852299,
+      "grad_norm": 1.5866667032241821,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.6985,
+      "step": 33
+    },
+    {
+      "epoch": 0.8198944988696307,
+      "grad_norm": 1.9591314792633057,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.7061,
+      "step": 34
+    },
+    {
+      "epoch": 0.8440090429540317,
+      "grad_norm": 1.0886839628219604,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.702,
+      "step": 35
+    },
+    {
+      "epoch": 0.8681235870384325,
+      "grad_norm": 0.9035281538963318,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.6946,
+      "step": 36
+    },
+    {
+      "epoch": 0.8922381311228335,
+      "grad_norm": 1.2744226455688477,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.7007,
+      "step": 37
+    },
+    {
+      "epoch": 0.9163526752072344,
+      "grad_norm": 0.9525231122970581,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.7026,
+      "step": 38
+    },
+    {
+      "epoch": 0.9404672192916352,
+      "grad_norm": 0.6737602353096008,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.6995,
+      "step": 39
+    },
+    {
+      "epoch": 0.9645817633760362,
+      "grad_norm": 0.9529001116752625,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.692,
+      "step": 40
+    },
+    {
+      "epoch": 0.9886963074604371,
+      "grad_norm": 2.1047470569610596,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.707,
+      "step": 41
+    },
+    {
+      "epoch": 1.012810851544838,
+      "grad_norm": 2.6895995140075684,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.075,
+      "step": 42
+    },
+    {
+      "epoch": 1.0369253956292388,
+      "grad_norm": 1.840681552886963,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.7008,
+      "step": 43
+    },
+    {
+      "epoch": 1.0610399397136399,
+      "grad_norm": 1.435666561126709,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.6875,
+      "step": 44
+    },
+    {
+      "epoch": 1.0851544837980407,
+      "grad_norm": 1.2137730121612549,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.6951,
+      "step": 45
+    },
+    {
+      "epoch": 1.1092690278824415,
+      "grad_norm": 0.7718119621276855,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.69,
+      "step": 46
+    },
+    {
+      "epoch": 1.1333835719668426,
+      "grad_norm": 0.9619392156600952,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.6785,
+      "step": 47
+    },
+    {
+      "epoch": 1.1574981160512434,
+      "grad_norm": 0.41596081852912903,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.6781,
+      "step": 48
+    },
+    {
+      "epoch": 1.1816126601356443,
+      "grad_norm": 0.9458053112030029,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.6787,
+      "step": 49
+    },
+    {
+      "epoch": 1.2057272042200453,
+      "grad_norm": 0.9001806974411011,
+      "learning_rate": 1e-05,
+      "loss": 0.6987,
+      "step": 50
+    },
+    {
+      "epoch": 1.2057272042200453,
+      "eval_loss": 0.7060160040855408,
+      "eval_runtime": 1.1649,
+      "eval_samples_per_second": 42.923,
+      "eval_steps_per_second": 11.16,
+      "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