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:c997ed667987f264c85a540726050690cb195101db9b9b986394c553fc887566
+oid sha256:b3be8adad683e14181523c84c06648d17193c9042de9e2a38676127a439c6d4f
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2aabf53556cd8865c418351dadd85c275ab43289121847e8f330a9dd8662c89d
+oid sha256:0ddb576e6d56d5e80e05c28f7e8eb5d3e742bcf6f5d13d2cf3013478c6d7bd3d
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9cf1558e0d6b4a48a39593121f2f836680d1dde71cf105a5e913425dc4ad8ac
+oid sha256:89becb00dfe197da4b326b0e6b72683a9138572945875800aafb42add5203181
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f7e91af1a79d7676619e959cc4b5dde54a9e2ec825d24c1c34fe5387a27894f
+oid sha256:d914dc409ae93ac75985631a9974025ebaa397f621307eef226e7d6e1076a1f6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0022089928097284045,
+  "epoch": 0.004417985619456809,
   "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": 2.908,
       "eval_steps_per_second": 1.454,
       "step": 25
+    },
+    {
+      "epoch": 0.0022973525221175405,
+      "grad_norm": 8.621397018432617,
+      "learning_rate": 0.0001537299608346824,
+      "loss": 8.2647,
+      "step": 26
+    },
+    {
+      "epoch": 0.0023857122345066766,
+      "grad_norm": 7.926273345947266,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 6.7474,
+      "step": 27
+    },
+    {
+      "epoch": 0.002474071946895813,
+      "grad_norm": 15.168147087097168,
+      "learning_rate": 0.00014617486132350343,
+      "loss": 8.1838,
+      "step": 28
+    },
+    {
+      "epoch": 0.002562431659284949,
+      "grad_norm": 8.807183265686035,
+      "learning_rate": 0.00014226182617406996,
+      "loss": 8.526,
+      "step": 29
+    },
+    {
+      "epoch": 0.002650791371674085,
+      "grad_norm": 9.189704895019531,
+      "learning_rate": 0.000138268343236509,
+      "loss": 7.7897,
+      "step": 30
+    },
+    {
+      "epoch": 0.0027391510840632212,
+      "grad_norm": 6.538626194000244,
+      "learning_rate": 0.00013420201433256689,
+      "loss": 7.312,
+      "step": 31
+    },
+    {
+      "epoch": 0.0028275107964523577,
+      "grad_norm": 5.638582706451416,
+      "learning_rate": 0.00013007057995042732,
+      "loss": 6.1696,
+      "step": 32
+    },
+    {
+      "epoch": 0.0029158705088414938,
+      "grad_norm": 7.880610942840576,
+      "learning_rate": 0.00012588190451025207,
+      "loss": 8.8579,
+      "step": 33
+    },
+    {
+      "epoch": 0.00300423022123063,
+      "grad_norm": 13.92683219909668,
+      "learning_rate": 0.00012164396139381029,
+      "loss": 6.6829,
+      "step": 34
+    },
+    {
+      "epoch": 0.003092589933619766,
+      "grad_norm": 7.7009596824646,
+      "learning_rate": 0.00011736481776669306,
+      "loss": 6.8181,
+      "step": 35
+    },
+    {
+      "epoch": 0.0031809496460089024,
+      "grad_norm": 11.020742416381836,
+      "learning_rate": 0.00011305261922200519,
+      "loss": 7.513,
+      "step": 36
+    },
+    {
+      "epoch": 0.0032693093583980384,
+      "grad_norm": 9.45319652557373,
+      "learning_rate": 0.00010871557427476583,
+      "loss": 8.3329,
+      "step": 37
+    },
+    {
+      "epoch": 0.0033576690707871745,
+      "grad_norm": 8.341961860656738,
+      "learning_rate": 0.00010436193873653361,
+      "loss": 6.6867,
+      "step": 38
+    },
+    {
+      "epoch": 0.0034460287831763105,
+      "grad_norm": 9.635961532592773,
+      "learning_rate": 0.0001,
+      "loss": 7.9651,
+      "step": 39
+    },
+    {
+      "epoch": 0.003534388495565447,
+      "grad_norm": 9.390765190124512,
+      "learning_rate": 9.563806126346642e-05,
+      "loss": 6.406,
+      "step": 40
+    },
+    {
+      "epoch": 0.003622748207954583,
+      "grad_norm": 6.492102146148682,
+      "learning_rate": 9.128442572523417e-05,
+      "loss": 7.1606,
+      "step": 41
+    },
+    {
+      "epoch": 0.003711107920343719,
+      "grad_norm": 12.913923263549805,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 8.1131,
+      "step": 42
+    },
+    {
+      "epoch": 0.0037994676327328556,
+      "grad_norm": 9.559767723083496,
+      "learning_rate": 8.263518223330697e-05,
+      "loss": 7.4009,
+      "step": 43
+    },
+    {
+      "epoch": 0.0038878273451219917,
+      "grad_norm": 10.509035110473633,
+      "learning_rate": 7.835603860618972e-05,
+      "loss": 5.1785,
+      "step": 44
+    },
+    {
+      "epoch": 0.003976187057511128,
+      "grad_norm": 5.890124320983887,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 5.0357,
+      "step": 45
+    },
+    {
+      "epoch": 0.004064546769900264,
+      "grad_norm": 13.03221321105957,
+      "learning_rate": 6.992942004957271e-05,
+      "loss": 8.2949,
+      "step": 46
+    },
+    {
+      "epoch": 0.0041529064822894,
+      "grad_norm": 6.9972453117370605,
+      "learning_rate": 6.579798566743314e-05,
+      "loss": 6.611,
+      "step": 47
+    },
+    {
+      "epoch": 0.004241266194678536,
+      "grad_norm": 18.20701026916504,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 7.0064,
+      "step": 48
+    },
+    {
+      "epoch": 0.004329625907067673,
+      "grad_norm": 9.751326560974121,
+      "learning_rate": 5.773817382593008e-05,
+      "loss": 6.5294,
+      "step": 49
+    },
+    {
+      "epoch": 0.004417985619456809,
+      "grad_norm": 7.42352294921875,
+      "learning_rate": 5.382513867649663e-05,
+      "loss": 5.4843,
+      "step": 50
+    },
+    {
+      "epoch": 0.004417985619456809,
+      "eval_loss": 0.9495617747306824,
+      "eval_runtime": 3283.7601,
+      "eval_samples_per_second": 2.902,
+      "eval_steps_per_second": 1.451,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.347789697024e+16,
+  "total_flos": 1.2695579394048e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null