Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d8c8d76d5eeec97b53c73368160dd4a09acadf0fe64cc3fb55d59114f678046
+oid sha256:82cbc1436555ae7d546ded72700bc32a0ea4eca4823e510642a48fa9b2766644
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e96ac018555abd8643471532a07ec6e5b2028428d8a482c5614f1cf5b7ab4e97
+oid sha256:46da027ff02668f6f300c9d14a64f3614bba23be3d05c730d85cacb5c12cc24f
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c06f86e44de31ecb1453df32bbadc8c4866d3d70bd372db2fae198d86855fc7
+oid sha256:9c6ae91960a2bccfecefc0e27290c8561809a1c526444b56ccd443b100dd64b2
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2252ab0e4fe8f04bd46b8664c8636928e5c03b30a76ab5eab3a9bcbab55378ed
+oid sha256:64f586f0550e82a82c3839adbb2fb3f0b3636a55499cc154cdc61b87155bafb3
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e13823a949711e5e865592629e2f86f19cb86d2f8f7a42b4077b4438f5aad2d1
+oid sha256:c42b913c4d58b9afb4de794178493a846d093eb75c73789219ce4ae749e20b43
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1e8adde84a6d04ae3af3f2ad37cc6db20a2f9042d4f75a6dcfdcc7777b334f1
+oid sha256:5d2f047b0f9672cd6699377192232b93f7fbb3bec87844d023fb40e31fe085ed
 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": 0.03415446356145669,
+  "epoch": 0.06830892712291338,
   "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": 14.339,
       "eval_steps_per_second": 3.728,
       "step": 25
+    },
+    {
+      "epoch": 0.03552064210391496,
+      "grad_norm": 1.5169587135314941,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 2.3497,
+      "step": 26
+    },
+    {
+      "epoch": 0.03688682064637322,
+      "grad_norm": 2.4556190967559814,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 2.9366,
+      "step": 27
+    },
+    {
+      "epoch": 0.03825299918883149,
+      "grad_norm": 2.6385529041290283,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 2.97,
+      "step": 28
+    },
+    {
+      "epoch": 0.039619177731289756,
+      "grad_norm": 2.0972061157226562,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 3.172,
+      "step": 29
+    },
+    {
+      "epoch": 0.040985356273748025,
+      "grad_norm": 1.6529752016067505,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 3.3134,
+      "step": 30
+    },
+    {
+      "epoch": 0.04235153481620629,
+      "grad_norm": 1.3257697820663452,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 3.3341,
+      "step": 31
+    },
+    {
+      "epoch": 0.04371771335866456,
+      "grad_norm": 1.5197049379348755,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 3.3917,
+      "step": 32
+    },
+    {
+      "epoch": 0.04508389190112283,
+      "grad_norm": 1.694000244140625,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 3.6008,
+      "step": 33
+    },
+    {
+      "epoch": 0.0464500704435811,
+      "grad_norm": 1.9344284534454346,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 3.4473,
+      "step": 34
+    },
+    {
+      "epoch": 0.04781624898603936,
+      "grad_norm": 2.178778648376465,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 3.5018,
+      "step": 35
+    },
+    {
+      "epoch": 0.04918242752849763,
+      "grad_norm": 2.6502668857574463,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 3.7114,
+      "step": 36
+    },
+    {
+      "epoch": 0.0505486060709559,
+      "grad_norm": 2.9071402549743652,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 4.0033,
+      "step": 37
+    },
+    {
+      "epoch": 0.051914784613414165,
+      "grad_norm": 0.6881694793701172,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 2.4487,
+      "step": 38
+    },
+    {
+      "epoch": 0.053280963155872434,
+      "grad_norm": 0.6594279408454895,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 2.6734,
+      "step": 39
+    },
+    {
+      "epoch": 0.0546471416983307,
+      "grad_norm": 0.7833492159843445,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 2.8635,
+      "step": 40
+    },
+    {
+      "epoch": 0.05601332024078897,
+      "grad_norm": 0.9415630102157593,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 3.1077,
+      "step": 41
+    },
+    {
+      "epoch": 0.05737949878324724,
+      "grad_norm": 0.9522256255149841,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 3.099,
+      "step": 42
+    },
+    {
+      "epoch": 0.0587456773257055,
+      "grad_norm": 0.9785342812538147,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 3.0967,
+      "step": 43
+    },
+    {
+      "epoch": 0.06011185586816377,
+      "grad_norm": 1.0899083614349365,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 3.2681,
+      "step": 44
+    },
+    {
+      "epoch": 0.06147803441062204,
+      "grad_norm": 1.2303138971328735,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 3.3943,
+      "step": 45
+    },
+    {
+      "epoch": 0.0628442129530803,
+      "grad_norm": 1.5075228214263916,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 3.438,
+      "step": 46
+    },
+    {
+      "epoch": 0.06421039149553857,
+      "grad_norm": 1.4767671823501587,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 3.6421,
+      "step": 47
+    },
+    {
+      "epoch": 0.06557657003799684,
+      "grad_norm": 1.618712306022644,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 3.5912,
+      "step": 48
+    },
+    {
+      "epoch": 0.06694274858045511,
+      "grad_norm": 1.9819996356964111,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 3.6884,
+      "step": 49
+    },
+    {
+      "epoch": 0.06830892712291338,
+      "grad_norm": 3.463073968887329,
+      "learning_rate": 1e-05,
+      "loss": 4.0977,
+      "step": 50
+    },
+    {
+      "epoch": 0.06830892712291338,
+      "eval_loss": 3.257638931274414,
+      "eval_runtime": 3.4994,
+      "eval_samples_per_second": 14.288,
+      "eval_steps_per_second": 3.715,
+      "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": 2.984974321220321e+17,
+  "total_flos": 5.969948642440643e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null