Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f9d80f07040503af7e8a76440b6b77e83e5069cc12563724330a2a38641ef68
+oid sha256:0b31d5e1de5d40d5e236646cc9e14cf5910d035060732a0022c945ee30347c81
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2040675a80d6d72fa231f9698d7c7b82e93e5eebbb99e7ef1ae1ed9fdb7ca1ae
+oid sha256:d5ede2f8d9837198ddb692f6fa323fbef3bfdef7f0299c956679d31442d1782f
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a89b8ae8d44d011a5fcf9872a9ca7897e1346f7ae660734759b84961eb8955ef
+oid sha256:774fe8f35e4e402817b80fc88b66a4656857265fda208bde4a2db864b4822af9
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ad05ed5dbf7a269beba3fbaf24ed99f5f3ddac8e90a0e509314ab28cc57fc59
+oid sha256:a88d6ef830e9746aae803d87ee25ee2a80020a026bb9bc430627a53ba260752a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85f17c65642fb34e106ef98949c7ca56f090306fec944d02d58459432e8b36b6
+oid sha256:9036aaf9265d1bdcaf82e82926a26547465dfad5befa57d5bcad45ce8735ff95
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2d9eb834722d6feefbb4b68d884aa1b9e8c8e96f9d466a191be69b91c7b5d8f
+oid sha256:17d0da1ce7ef2369c5fda5d2532333c175ebbe2536731b3b912af3f4d93d2d3e
 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": 0.004573153303531617,
+  "epoch": 0.009146306607063235,
   "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": 14.329,
       "eval_steps_per_second": 3.726,
       "step": 25
+    },
+    {
+      "epoch": 0.004756079435672882,
+      "grad_norm": 1.7480310201644897,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 3.017,
+      "step": 26
+    },
+    {
+      "epoch": 0.004939005567814147,
+      "grad_norm": 1.3907936811447144,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 3.1465,
+      "step": 27
+    },
+    {
+      "epoch": 0.005121931699955412,
+      "grad_norm": 26.612220764160156,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 3.284,
+      "step": 28
+    },
+    {
+      "epoch": 0.005304857832096677,
+      "grad_norm": 1.115344762802124,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 3.3917,
+      "step": 29
+    },
+    {
+      "epoch": 0.005487783964237941,
+      "grad_norm": 1.0461210012435913,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 3.4146,
+      "step": 30
+    },
+    {
+      "epoch": 0.005670710096379206,
+      "grad_norm": 1.325683355331421,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 3.4329,
+      "step": 31
+    },
+    {
+      "epoch": 0.0058536362285204705,
+      "grad_norm": 1.1475805044174194,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 3.4794,
+      "step": 32
+    },
+    {
+      "epoch": 0.006036562360661735,
+      "grad_norm": 1.2684738636016846,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 3.5487,
+      "step": 33
+    },
+    {
+      "epoch": 0.006219488492803,
+      "grad_norm": 1.2360631227493286,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 3.6217,
+      "step": 34
+    },
+    {
+      "epoch": 0.006402414624944265,
+      "grad_norm": 1.497918725013733,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 3.5036,
+      "step": 35
+    },
+    {
+      "epoch": 0.006585340757085529,
+      "grad_norm": 1.5676883459091187,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 3.5703,
+      "step": 36
+    },
+    {
+      "epoch": 0.006768266889226794,
+      "grad_norm": 2.1435370445251465,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 3.6886,
+      "step": 37
+    },
+    {
+      "epoch": 0.006951193021368059,
+      "grad_norm": 1.654815435409546,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 3.0422,
+      "step": 38
+    },
+    {
+      "epoch": 0.007134119153509324,
+      "grad_norm": 1.5040534734725952,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 3.1364,
+      "step": 39
+    },
+    {
+      "epoch": 0.007317045285650589,
+      "grad_norm": 1.3657926321029663,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 3.1935,
+      "step": 40
+    },
+    {
+      "epoch": 0.007499971417791853,
+      "grad_norm": 1.264070987701416,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 3.4067,
+      "step": 41
+    },
+    {
+      "epoch": 0.0076828975499331174,
+      "grad_norm": 1.3875404596328735,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 3.2835,
+      "step": 42
+    },
+    {
+      "epoch": 0.007865823682074382,
+      "grad_norm": 1.2422032356262207,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 3.4278,
+      "step": 43
+    },
+    {
+      "epoch": 0.008048749814215647,
+      "grad_norm": 1.25910222530365,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 3.398,
+      "step": 44
+    },
+    {
+      "epoch": 0.008231675946356912,
+      "grad_norm": 1.284754753112793,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 3.5085,
+      "step": 45
+    },
+    {
+      "epoch": 0.008414602078498177,
+      "grad_norm": 1.3367297649383545,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 3.4191,
+      "step": 46
+    },
+    {
+      "epoch": 0.008597528210639442,
+      "grad_norm": 1.2780907154083252,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 3.3408,
+      "step": 47
+    },
+    {
+      "epoch": 0.008780454342780707,
+      "grad_norm": 1.462539553642273,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 3.653,
+      "step": 48
+    },
+    {
+      "epoch": 0.00896338047492197,
+      "grad_norm": 1.7677708864212036,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 3.4973,
+      "step": 49
+    },
+    {
+      "epoch": 0.009146306607063235,
+      "grad_norm": 3.7667927742004395,
+      "learning_rate": 1e-05,
+      "loss": 3.8798,
+      "step": 50
+    },
+    {
+      "epoch": 0.009146306607063235,
+      "eval_loss": 3.431530237197876,
+      "eval_runtime": 3.5348,
+      "eval_samples_per_second": 14.145,
+      "eval_steps_per_second": 3.678,
+      "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