Training in progress, step 150

adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "inception-mbzuai/jais-13b-chat",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": {
+    "lm_head": "Linear4bit",
+    "transformer.h.31.attn.c_attn": "Linear4bit",
+    "transformer.h.31.attn.c_proj": "Linear4bit",
+    "transformer.h.31.mlp.c_fc": "Linear4bit",
+    "transformer.h.31.mlp.c_fc2": "Linear4bit",
+    "transformer.h.31.mlp.c_proj": "Linear4bit",
+    "transformer.h.39.attn.c_attn": "Linear4bit",
+    "transformer.h.39.attn.c_proj": "Linear4bit",
+    "transformer.h.39.mlp.c_fc": "Linear4bit",
+    "transformer.h.39.mlp.c_fc2": "Linear4bit",
+    "transformer.h.39.mlp.c_proj": "Linear4bit"
+  },
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0f6cc85e16701c65edac4081267d7ece98445988732192e66727701078b7c5b
+size 1757547392

runs/May08_13-17-02_1a4355fd49c6/events.out.tfevents.1715174223.1a4355fd49c6.293.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87d3dfc02d9cc544c860fa83ce3f59b8c9186c975dad0b9763766118c625e1cd
+size 4184

runs/May08_13-22-43_1a4355fd49c6/events.out.tfevents.1715174564.1a4355fd49c6.3824.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:279986aa30287f7e0379268f63fe4d4510b1b089574831085158b38041805545
+size 4184

runs/May08_13-28-31_1a4355fd49c6/events.out.tfevents.1715174912.1a4355fd49c6.5658.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6d7fa38e3ecf8353424eccd7da6d5563d8998f053e42fcdc68aaa6aa72197d2
+size 5889

runs/May08_13-35-45_1a4355fd49c6/events.out.tfevents.1715175346.1a4355fd49c6.7870.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dbb91e2aea1d7dde724489da1e2f4ab5c2c5676455293ec1d64745bd48bf0ba
+size 4184

runs/May08_13-40-58_1a4355fd49c6/events.out.tfevents.1715175659.1a4355fd49c6.9554.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:082733d2b9c1cabcc61a7d194618b935a88c0e081acac943b2b4e3b0c2463ee5
+size 4184

runs/May08_13-46-55_1a4355fd49c6/events.out.tfevents.1715176016.1a4355fd49c6.11417.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c47cce71751256784a5d57d2db121a6e2dc728ee5bdd5bdd531b4b45d37a95c
+size 7135

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c25bf010f4f17c937c7fb28de8a18b3f440859d36dba17b52fd16e60a245b4fd
+size 4984