Training in progress, step 5000

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a3bb33a0c4878b032aec2026e3879865fa62989d9939826a716eb3580fa34cd
+oid sha256:658b9b2dec5afef11956f93a69d1e5899dfaf7ec45314dbb9a4f4fe9a8d341ef
 size 500897101

{checkpoint-4600 → checkpoint-4900/adapter_model}/adapter_config.json

@@ -14,13 +14,13 @@
   "r": 32,
   "revision": null,
   "target_modules": [
+    "k_proj",
+    "o_proj",
+    "down_proj",
     "gate_proj",
     "v_proj",
-    "k_proj",
     "q_proj",
-    "up_proj",
-    "o_proj",
-    "down_proj"
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

{checkpoint-4600 → checkpoint-4900/adapter_model}/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68baca464c45ad2c5da146b800b15dadf06eb685f6905c3cba44f31d2963c595
+oid sha256:2a3bb33a0c4878b032aec2026e3879865fa62989d9939826a716eb3580fa34cd
 size 500897101

{checkpoint-4600/adapter_model → checkpoint-5000}/adapter_config.json

@@ -14,13 +14,13 @@
   "r": 32,
   "revision": null,
   "target_modules": [
+    "k_proj",
+    "o_proj",
+    "down_proj",
     "gate_proj",
     "v_proj",
-    "k_proj",
     "q_proj",
-    "up_proj",
-    "o_proj",
-    "down_proj"
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

{checkpoint-4600/adapter_model → checkpoint-5000}/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68baca464c45ad2c5da146b800b15dadf06eb685f6905c3cba44f31d2963c595
+oid sha256:658b9b2dec5afef11956f93a69d1e5899dfaf7ec45314dbb9a4f4fe9a8d341ef
 size 500897101

{checkpoint-4600 → checkpoint-5000}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fce4744c6f9f99ebf88811d26dadf3b80e0f50d32d46161fc773f1754ac501b
+oid sha256:41a19364f98039f3de4a4fce0e0896ae1c403fab5b0de5a6478b8b3154215366
 size 1001752701

{checkpoint-4600 → checkpoint-5000}/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87cf73a108581136c28003995848a3469b34884b54056edbd96d9426b19286d4
+oid sha256:c3591569acf36220e21cfa3f00c334d4afa5214c3fa0f7f20b6081190208a2ce
 size 27772

{checkpoint-4600 → checkpoint-5000}/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ed08fdd87a9eb079576d2d2e79f82d8d181e81e5ea1aaaea16afb65f918ed37
+oid sha256:8a3d8da1aa54796771be8e0f102c1ba0e9bce209cd7f83f5e4242dbd0a2bfb18
 size 27772

{checkpoint-4600 → checkpoint-5000}/rng_state_10.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5231e38f102d1b091797b4cb63ddc5adec05d33a2851436dd68077cbb0064d28
+oid sha256:263b9c81bf6b52324cce079cb862bf0c4c6c076726306fe430175760cf77ce1d
 size 27789

{checkpoint-4600 → checkpoint-5000}/rng_state_11.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69f01b3fcb68dbb72dd1357f58bcfac99842616b87f82438c24f947602cd918b
+oid sha256:bfd9622dd9c9e0f101a3891d78b76d8a750232389d97fff8a48e4ab0113e3bf0
 size 27789

{checkpoint-4600 → checkpoint-5000}/rng_state_12.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f2bd26cbc1398ca2ebd540399d0c4d6338ed464d548af7c1038f852ca6219db
+oid sha256:8b52b3225a4c307e1e07d040be377b2268078fb40662cf123cf14c9225dfc3d2
 size 27789

{checkpoint-4600 → checkpoint-5000}/rng_state_13.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:858e20e80f50042ced11348b07f992a32041d7732ed58a017be4527ed0a13118
+oid sha256:a7022a9a5c490e593972113d5eec0a181e018cdd0b74c023342974a3d2a43471
 size 27789

{checkpoint-4600 → checkpoint-5000}/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d968dcc8ca9c991c99a196e8d92215f20f736625130c876c9b64041bce288b6d
+oid sha256:7ea427538851652ebb74224ead7e27e9853d1a0254ab5742c7f4e6a75f1a155b
 size 27772

{checkpoint-4600 → checkpoint-5000}/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9350788e0e90e8024f2d9ed4e04b572e4fb0c1a913ae77e1c4e4f233867609d0
+oid sha256:84c0d3bf83700c5dcf78d4bca3c01d4661af97db85b1e1021458aa4ebf191dc3
 size 27772

{checkpoint-4600 → checkpoint-5000}/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e65ae4aaa3c776537f2bf5c5785311caf3d273bfe047df490befdca5b8e26247
+oid sha256:88b40363540e71d8f1d1cd8dbf6a880e5a85fe8c36554f2c6a6e6bf87eeee7ef
 size 27772

{checkpoint-4600 → checkpoint-5000}/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22bdddfd4edfea8b430f652448271c5f5d87f3505a772758c6417e8ff98655c4
+oid sha256:f452a098fe1f3d5946e80ca1866e99d8de678f832a877b5bd605c904adccd168
 size 27772

{checkpoint-4600 → checkpoint-5000}/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a2c49429dcbfeca1faa7a663803a0fdae88ad305b95d23e46226445395b9946
+oid sha256:d6329d34fc46a440591bbc38dc3e735aa628275c46bc5f5d67ea60d2ac817c9f
 size 27772

{checkpoint-4600 → checkpoint-5000}/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9c7570bf926e320eb7895bf959a53e1980cb414ed8bc39b4eda9b9478584053
+oid sha256:abc478444408d585c8510980bf6c3724dbd04c62fe3f44191f641810f4f2b408
 size 27772

{checkpoint-4600 → checkpoint-5000}/rng_state_8.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb6fa0fe38db2df9eb256d09e9da98351346be62c7aab5a72c2a011d6913561a
+oid sha256:43a4f27fdaf452bec4190380281039b2452b0cc819d9babdb1883bb6338b79df
 size 27772

{checkpoint-4600 → checkpoint-5000}/rng_state_9.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ed3fe525bbbbe135513154ac6a01e1c556fe2d6d16f9ab7210f0476687c9b5e
+oid sha256:bd492bc5d4f48c5532176ee3ad99275b5bfcd315a528c245cfa8d46477f6b13e
 size 27772

{checkpoint-4600 → checkpoint-5000}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdc6ea8a6b4cf0316e8365ff2c59039288c5d56c6df930ea3adced9242e298fc
+oid sha256:091fab5b44662db384d56b3c50422b403065ff0f62fb64f68c521ac3c38ad752
 size 627

{checkpoint-4600 → checkpoint-5000}/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.7836370686312524,
-  "global_step": 4600,
+  "epoch": 1.9387359441644048,
+  "global_step": 5000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1118,11 +1118,115 @@
       "learning_rate": 7.089008200684197e-05,
       "loss": 0.7982,
       "step": 4600
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 6.991918777418928e-05,
+      "loss": 0.7916,
+      "step": 4625
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 6.895140127495455e-05,
+      "loss": 0.7919,
+      "step": 4650
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 6.798682249388631e-05,
+      "loss": 0.7863,
+      "step": 4675
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 6.702555108433461e-05,
+      "loss": 0.789,
+      "step": 4700
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 6.606768635795574e-05,
+      "loss": 0.7902,
+      "step": 4725
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 6.511332727445191e-05,
+      "loss": 0.7924,
+      "step": 4750
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 6.416257243134747e-05,
+      "loss": 0.7957,
+      "step": 4775
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 6.321552005380256e-05,
+      "loss": 0.7916,
+      "step": 4800
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 6.22722679844652e-05,
+      "loss": 0.7867,
+      "step": 4825
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 6.133291367336284e-05,
+      "loss": 0.7944,
+      "step": 4850
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 6.039755416783457e-05,
+      "loss": 0.7982,
+      "step": 4875
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 5.946628610250484e-05,
+      "loss": 0.7918,
+      "step": 4900
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 5.853920568929996e-05,
+      "loss": 0.7921,
+      "step": 4925
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 5.761640870750799e-05,
+      "loss": 0.7878,
+      "step": 4950
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 5.669799049388375e-05,
+      "loss": 0.7901,
+      "step": 4975
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 5.578404593279911e-05,
+      "loss": 0.7858,
+      "step": 5000
+    },
+    {
+      "epoch": 1.94,
+      "eval_loss": 0.807844877243042,
+      "eval_runtime": 59.586,
+      "eval_samples_per_second": 12.251,
+      "eval_steps_per_second": 0.889,
+      "step": 5000
     }
   ],
   "max_steps": 7737,
   "num_train_epochs": 3,
-  "total_flos": 1.980912103157924e+19,
+  "total_flos": 2.1532695573582316e+19,
   "trial_name": null,
   "trial_params": null
 }

{checkpoint-4600 → checkpoint-5000}/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4458bf553277b063d908ed9668b95abc04892c52d8d793f6b007433394d06f17
+oid sha256:354c4769acaf21317d8ab58ba2dd133763f3bee1aec7488fb334e45f3e80ebc3
 size 4027